No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Artificial Intelligence, Radiomics, and Computational Modeling in Skull Base Surgery
Abstract
This chapter explores current artificial intelligence (AI), radiomics, and computational modeling applications in skull base surgery. AI advancements are providing opportunities to improve diagnostic accuracy, surgical planning, and postoperative care. Currently, computational models can assist in diagnosis, simulate surgical scenarios, and improve safety during surgical procedures by identifying critical structures. AI-powered technologies, such as liquid biopsy, machine learning, radiomic analysis, computer vision, and label-free optical imaging, aim to revolutionize skull base surgery. AI-driven advancements promise safer, more precise, and effective surgeries, improving patient outcomes and preoperative assessment.
ResearchGate has not been able to resolve any citations for this publication.
Purpose
Pituitary adenoma surgery is a complex procedure due to critical adjacent neurovascular structures, variations in size and extensions of the lesions, and potential hormonal imbalances. The integration of artificial intelligence (AI) and machine learning (ML) has demonstrated considerable potential in assisting neurosurgeons in decision-making, optimizing surgical outcomes, and providing real-time feedback. This scoping review comprehensively summarizes the current status of AI/ML technologies in pituitary adenoma surgery, highlighting their strengths and limitations.
Methods
PubMed, Embase, Web of Science, and Scopus were searched following the PRISMA-ScR guidelines. Studies discussing the use of AI/ML in pituitary adenoma surgery were included. Eligible studies were grouped to analyze the different outcomes of interest of current AI/ML technologies.
Results
Among the 2438 identified articles, 44 studies met the inclusion criteria, with a total of seventeen different algorithms utilized across all studies. Studies were divided into two groups based on their input type: clinicopathological and imaging input. The four main outcome variables evaluated in the studies included: outcome (remission, recurrence or progression, gross-total resection, vision improvement, and hormonal recovery), complications (CSF leak, readmission, hyponatremia, and hypopituitarism), cost, and adenoma-related factors (aggressiveness, consistency, and Ki-67 labeling) prediction. Three studies focusing on workflow analysis and real-time navigation were discussed separately.
Conclusion
AI/ML modeling holds promise for improving pituitary adenoma surgery by enhancing preoperative planning and optimizing surgical strategies. However, addressing challenges such as algorithm selection, performance evaluation, data heterogeneity, and ethics is essential to establish robust and reliable ML models that can revolutionize neurosurgical practice and benefit patients.
Purpose
Assessment of pituitary adenoma (PA) volume and extent of resection (EOR) through manual segmentation is time-consuming and likely suffers from poor interrater agreement, especially postoperatively. Automated tumor segmentation and volumetry by use of deep learning techniques may provide more objective and quick volumetry.
Methods
We developed an automated volumetry pipeline for pituitary adenoma. Preoperative and three-month postoperative T1-weighted, contrast-enhanced magnetic resonance imaging (MRI) with manual segmentations were used for model training. After adequate preprocessing, an ensemble of convolutional neural networks (CNNs) was trained and validated for preoperative and postoperative automated segmentation of tumor tissue. Generalization was evaluated on a separate holdout set.
Results
In total, 193 image sets were used for training and 20 were held out for validation. At validation using the holdout set, our models (preoperative / postoperative) demonstrated a median Dice score of 0.71 (0.27) / 0 (0), a mean Jaccard score of 0.53 ± 0.21/0.030 ± 0.085 and a mean 95th percentile Hausdorff distance of 3.89 ± 1.96./12.199 ± 6.684. Pearson’s correlation coefficient for volume correlation was 0.85 / 0.22 and −0.14 for extent of resection. Gross total resection was detected with a sensitivity of 66.67% and specificity of 36.36%.
Conclusions
Our volumetry pipeline demonstrated its ability to accurately segment pituitary adenomas. This is highly valuable for lesion detection and evaluation of progression of pituitary incidentalomas. Postoperatively, however, objective and precise detection of residual tumor remains less successful. Larger datasets, more diverse data, and more elaborate modeling could potentially improve performance.
Simple Summary
Radiomics involves the extraction of quantitative features from medical images, which can provide more detailed and objective information about the features of a tumor compared to visual inspection alone. By analyzing the extensive range of features obtained through radiomics, machine-learning techniques can enhance tumor diagnosis, assess treatment response, and predict patient prognosis. This review highlights the mutual impact between the tumor and its microenvironment (habitat), in which tumor cells can modify the microenvironment to promote their growth and survival. At the same time, the habitat can also influence the behavior of tumor cells. Encouragingly, radiomics and machine learning have shown promising potential in diagnosing brain tumors and predicting prognosis. However, several limitations still need to be improved for their practical application in clinical settings. Further research is required to optimize radiomic feature extraction, standardize imaging protocols, validate models on larger datasets, and integrate diverse data to facilitate a more comprehensive analysis.
Abstract
Radiomics is a rapidly evolving field that involves extracting and analysing quantitative features from medical images, such as computed tomography or magnetic resonance images. Radiomics has shown promise in brain tumor diagnosis and patient-prognosis prediction by providing more detailed and objective information about tumors’ features than can be obtained from the visual inspection of the images alone. Radiomics data can be analyzed to determine their correlation with a tumor’s genetic status and grade, as well as in the assessment of its recurrence vs. therapeutic response, among other features. In consideration of the multi-parametric and high-dimensional space of features extracted by radiomics, machine learning can further improve tumor diagnosis, treatment response, and patients’ prognoses. There is a growing recognition that tumors and their microenvironments (habitats) mutually influence each other—tumor cells can alter the microenvironment to increase their growth and survival. At the same time, habitats can also influence the behavior of tumor cells. In this systematic review, we investigate the current limitations and future developments in radiomics and machine learning in analysing brain tumors and their habitats.
Purpose:
Tracking the 3D motion of the surgical tool and the patient anatomy is a fundamental requirement for computer-assisted skull-base surgery. The estimated motion can be used both for intra-operative guidance and for downstream skill analysis. Recovering such motion solely from surgical videos is desirable, as it is compliant with current clinical workflows and instrumentation.
Methods:
We present Tracker of Anatomy and Tool (TAToo). TAToo jointly tracks the rigid 3D motion of the patient skull and surgical drill from stereo microscopic videos. TAToo estimates motion via an iterative optimization process in an end-to-end differentiable form. For robust tracking performance, TAToo adopts a probabilistic formulation and enforces geometric constraints on the object level.
Results:
We validate TAToo on both simulation data, where ground truth motion is available, as well as on anthropomorphic phantom data, where optical tracking provides a strong baseline. We report sub-millimeter and millimeter inter-frame tracking accuracy for skull and drill, respectively, with rotation errors below [Formula: see text]. We further illustrate how TAToo may be used in a surgical navigation setting.
Conclusions:
We present TAToo, which simultaneously tracks the surgical tool and the patient anatomy in skull-base surgery. TAToo directly predicts the motion from surgical videos, without the need of any markers. Our results show that the performance of TAToo compares favorably to competing approaches. Future work will include fine-tuning of our depth network to reach a 1 mm clinical accuracy goal desired for surgical applications in the skull base.
Purpose:
Digital twins are virtual replicas of real-world objects and processes, and they have potential applications in the field of surgical procedures, such as enhancing situational awareness. We introduce Twin-S, a digital twin framework designed specifically for skull base surgeries.
Methods:
Twin-S is a novel framework that combines high-precision optical tracking and real-time simulation, making it possible to integrate it into image-guided interventions. To guarantee accurate representation, Twin-S employs calibration routines to ensure that the virtual model precisely reflects all real-world processes. Twin-S models and tracks key elements of skull base surgery, including surgical tools, patient anatomy, and surgical cameras. Importantly, Twin-S mirrors real-world drilling and updates the virtual model at frame rate of 28.
Results:
Our evaluation of Twin-S demonstrates its accuracy, with an average error of 1.39 mm during the drilling process. Our study also highlights the benefits of Twin-S, such as its ability to provide augmented surgical views derived from the continuously updated virtual model, thus offering additional situational awareness to the surgeon.
Conclusion:
We present Twin-S, a digital twin environment for skull base surgery. Twin-S captures the real-world surgical progresses and updates the virtual model in real time through the use of modern tracking technologies. Future research that integrates vision-based techniques could further increase the accuracy of Twin-S.
Background:
Interposition nerve grafting is an indispensable technique for facial nerve reconstruction in head and neck, and skull base surgery. The prognostic factors are inconclusive, partly due to limited objective assessment systems for facial nerve function. This study aimed to apply an artificial intelligence (AI)-based facial asymmetry measurement system to assess facial nerve grafting outcomes.
Methods:
We retrospectively reviewed data of 23 patients who underwent facial nerve grafting between 2011 and 2020. Oral asymmetry and synkinesis severity were measured using AI.
Results:
Oral movement recovered at 12-18 months postoperatively. Postoperative radiotherapy and a larger number of anastomosed distal stumps were significantly associated with poor and good final oral symmetry, respectively. Synkinesis severity was weakly correlated with the degree of oral movement recovery.
Conclusions:
Oral function recovered without a strong correlation with synkinesis. Caution should be exercised in facial nerve grafting for cases with postoperative radiotherapy.
Background
Recently, it was defined that the sellar barrier entity could be identified as a predictor of cerebrospinal fluid (CSF) intraoperative leakage. The aim of this study is to validate the application of the sellar barrier concept for predicting intraoperative CSF leak in endoscopic endonasal surgery for pituitary adenomas with a machine learning approach.
Methods
We conducted a prospective cohort study, from June 2019 to September 2020: data from 155 patients with pituitary subdiaphragmatic adenoma operated through endoscopic approach at the Division of Neurosurgery, Università degli Studi di Napoli “Federico II,” were included. Preoperative magnetic resonance images (MRI) and intraoperative findings were analyzed. After processing patient data, the experiment was conducted as a novelty detection problem, splitting outliers (i.e., patients with intraoperative fistula, n = 11/155) and inliers into separate datasets, the latter further separated into training ( n = 115/144) and inlier test ( n = 29/144) datasets. The machine learning analysis was performed using different novelty detection algorithms [isolation forest, local outlier factor, one-class support vector machine (oSVM)], whose performance was assessed separately and as an ensemble on the inlier and outlier test sets.
Results
According to the type of sellar barrier, patients were classified into two groups, i.e., strong and weak barrier; a third category of mixed barrier was defined when a case was neither weak nor strong. Significant differences between the three datasets were found for Knosp classification score ( p = 0.0015), MRI barrier: strong ( p = 1.405 × 10 ⁻⁶ ), MRI barrier: weak ( p = 4.487 × 10 ⁻⁸ ), intraoperative barrier: strong ( p = 2.788 × 10 ⁻⁷ ), and intraoperative barrier: weak ( p = 2.191 × 10 ⁻¹⁰ ). We recorded 11 cases of intraoperative leakage that occurred in the majority of patients presenting a weak sellar barrier ( p = 4.487 × 10 ⁻⁸ ) at preoperative MRI. Accuracy, sensitivity, and specificity for outlier detection were 0.70, 0.64, and 0.72 for IF; 0.85, 0.45, and 1.00 for LOF; 0.83, 0.64, and 0.90 for oSVM; and 0.83, 0.55, and 0.93 for the ensemble, respectively.
Conclusions
There is a true correlation between the type of sellar barrier at MRI and its in vivo features as observed during endoscopic endonasal surgery. The novelty detection models highlighted differences between patients who developed an intraoperative CSF leak and those who did not.
Background
Patients with pituitary lesions experience decrements in quality of life (QoL) and treatment aims to arrest or improve QoL decline.
Objective
To detect associations with QoL in trans-nasal endoscopic skull base surgery patients and train supervised learning classifiers to predict QoL improvement at 12 months.
Methods
A supervised learning analysis of a prospective multi-institutional dataset (451 patients) was conducted. QoL was measured using the anterior skull base surgery questionnaire (ASBS). Factors associated with QoL at baseline and at 12-month follow-up were identified using multivariate logistic regression. Multiple supervised learning models were trained to predict postoperative QoL improvement with five-fold cross-validation.
Results
ASBS at 12-month follow-up was significantly higher (132.19,SD = 24.87) than preoperative ASBS (121.87,SD = 25.72,p<0.05). High preoperative scores were significantly associated with institution, diabetes and lesions at the planum sphenoidale / tuberculum sella site. Patients with diabetes were five times less likely to report high preoperative QoL. Low preoperative QoL was significantly associated with female gender, a vision-related presentation, diabetes, secreting adenoma and the cavernous sinus site. Top quartile change in postoperative QoL at 12-month follow-up was negatively associated with baseline hypercholesterolemia, acromegaly and intraoperative CSF leak. Positive associations were detected for lesions at the sphenoid sinus site and deficient preoperative endocrine function. AdaBoost, logistic regression and neural network classifiers yielded the strongest predictive performance.
Conclusion
It was possible to predict postoperative positive change in QoL at 12-month follow-up using perioperative data. Further development and implementation of these models may facilitate improvements in informed consent, treatment decision-making and patient QoL.
Chordoma and chondrosarcoma share common radiographic characteristics yet are distinct clinically. A radiomic machine learning model differentiating these tumors preoperatively would help plan surgery. MR images were acquired from 57 consecutive patients with chordoma (N = 32) or chondrosarcoma (N = 25) treated at the University of Tokyo Hospital between September 2012 and February 2020. Preoperative T1-weighted images with gadolinium enhancement (GdT1) and T2-weighted images were analyzed. Datasets from the first 47 cases were used for model creation, and those from the subsequent 10 cases were used for validation. Feature extraction was performed semi-automatically, and 2438 features were obtained per image sequence. Machine learning models with logistic regression and a support vector machine were created. The model with the highest accuracy incorporated seven features extracted from GdT1 in the logistic regression. The average area under the curve was 0.93 ± 0.06, and accuracy was 0.90 (9/10) in the validation dataset. The same validation dataset was assessed by 20 board-certified neurosurgeons. Diagnostic accuracy ranged from 0.50 to 0.80 (median 0.60, 95% confidence interval 0.60 ± 0.06%), which was inferior to that of the machine learning model (p = 0.03), although there are some limitations, such as the risk of overfitting and the lack of an extramural cohort for truly independent final validation. In summary, we created a novel MRI-based machine learning model to differentiate skull base chordoma and chondrosarcoma from multiparametric signatures.
Purpose
To develop automated vestibular schwannoma measurements on contrast-enhanced T1- and T2-weighted MRI scans.
Materials and Methods
MRI data from 214 patients in 37 different centers were retrospectively analyzed between 2020 and 2021. Patients with hearing loss (134 positive for vestibular schwannoma [mean age ± SD, 54 years ± 12;64 men] and 80 negative for vestibular schwannoma) were randomly assigned to a training and validation set and to an independent test set. A convolutional neural network (CNN) was trained using fivefold cross-validation for two models (T1 and T2). Quantitative analysis, including Dice index, Hausdorff distance, surface-to-surface distance (S2S), and relative volume error, was used to compare the computer and the human delineations. An observer study was performed in which two experienced physicians evaluated both delineations.
Results
The T1-weighted model showed state-of-the-art performance, with a mean S2S distance of less than 0.6 mm for the whole tumor and the intrameatal and extrameatal tumor parts. The whole tumor Dice index and Hausdorff distance were 0.92 and 2.1 mm in the independent test set, respectively. T2-weighted images had a mean S2S distance less than 0.6 mm for the whole tumor and the intrameatal and extrameatal tumor parts. The whole tumor Dice index and Hausdorff distance were 0.87 and 1.5 mm in the independent test set. The observer study indicated that the tool was similar to human delineations in 85%–92% of cases.
Conclusion
The CNN model detected and delineated vestibular schwannomas accurately on contrast-enhanced T1- and T2-weighted MRI scans and distinguished the clinically relevant difference between intrameatal and extrameatal tumor parts.
Keywords: MRI, Ear, Nose, and Throat, Skull Base, Segmentation, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms
Major vascular injury resulting in uncontrolled bleeding is a catastrophic and often fatal complication of minimally invasive surgery. At the outset of these events, surgeons do not know how much blood will be lost or whether they will successfully control the hemorrhage (achieve hemostasis). We evaluate the ability of a deep learning neural network (DNN) to predict hemostasis control ability using the first minute of surgical video and compare model performance with human experts viewing the same video. The publicly available SOCAL dataset contains 147 videos of attending and resident surgeons managing hemorrhage in a validated, high-fidelity cadaveric simulator. Videos are labeled with outcome and blood loss (mL). The first minute of 20 videos was shown to four, blinded, fellowship trained skull-base neurosurgery instructors, and to SOCALNet (a DNN trained on SOCAL videos). SOCALNet architecture included a convolutional network (ResNet) identifying spatial features and a recurrent network identifying temporal features (LSTM). Experts independently assessed surgeon skill, predicted outcome and blood loss (mL). Outcome and blood loss predictions were compared with SOCALNet. Expert inter-rater reliability was 0.95. Experts correctly predicted 14/20 trials (Sensitivity: 82%, Specificity: 55%, Positive Predictive Value (PPV): 69%, Negative Predictive Value (NPV): 71%). SOCALNet correctly predicted 17/20 trials (Sensitivity 100%, Specificity 66%, PPV 79%, NPV 100%) and correctly identified all successful attempts. Expert predictions of the highest and lowest skill surgeons and expert predictions reported with maximum confidence were more accurate. Experts systematically underestimated blood loss (mean error − 131 mL, RMSE 350 mL, R ² 0.70) and fewer than half of expert predictions identified blood loss > 500 mL (47.5%, 19/40). SOCALNet had superior performance (mean error − 57 mL, RMSE 295 mL, R ² 0.74) and detected most episodes of blood loss > 500 mL (80%, 8/10). In validation experiments, SOCALNet evaluation of a critical on-screen surgical maneuver and high/low-skill composite videos were concordant with expert evaluation. Using only the first minute of video, experts and SOCALNet can predict outcome and blood loss during surgical hemorrhage. Experts systematically underestimated blood loss, and SOCALNet had no false negatives. DNNs can provide accurate, meaningful assessments of surgical video. We call for the creation of datasets of surgical adverse events for quality improvement research.
Objectives
A subset of non-functioning pituitary macroadenomas (NFMAs) may exhibit early progression/recurrence (P/R) after tumor resection. The purpose of this study was to apply deep learning (DL) algorithms for prediction of P/R in NFMAs.
Methods
From June 2009 to December 2019, 78 patients diagnosed with pathologically confirmed NFMAs, and who had undergone complete preoperative MRI and postoperative MRI follow-up for more than one year, were included. DL classifiers including multi-layer perceptron (MLP) and convolutional neural network (CNN) were used to build predictive models. Categorical and continuous clinical data were fed into the MLP model, and images of preoperative MRI (T2WI and contrast enhanced T1WI) were analyzed by the CNN model. MLP, CNN and multimodal CNN-MLP architectures were performed to predict P/R in NFMAs.
Results
Forty-two (42/78, 53.8%) patients exhibited P/R after surgery. The median follow-up time was 42 months, and the median time to P/R was 25 months. As compared with CNN using MRI (accuracy 83%, precision 87%, and AUC 0.84) or MLP using clinical data (accuracy 73%, precision 73%, and AUC 0.73) alone, the multimodal CNN-MLP model using both clinical and MRI features showed the best performance for prediction of P/R in NFMAs, with accuracy 83%, precision 90%, and AUC 0.85.
Conclusions
DL architecture incorporating clinical and MRI features performs well to predict P/R in NFMAs. Pending more studies to support the findings, the results of this study may provide valuable information for NFMAs treatment planning.
Objective
To develop machine learning (ML) models that predict postoperative remission, remission at last visit, and resistance to somatostatin receptor ligands (SRL) in patients with acromegaly and to determine the clinical features associated with the prognosis.
Methods
We studied outcomes using the area under the receiver operating characteristics (AUROC) values, which were reported as the performance metric. To determine the importance of each feature and easy interpretation, Shapley Additive explanations (SHAP) values, which help explain the outputs of ML models, are used.
Results
One-hundred fifty-two patients with acromegaly were included in the final analysis. The mean AUROC values resulting from 100 independent replications were 0.728 for postoperative 3 months remission status classification, 0.879 for remission at last visit classification, and 0.753 for SRL resistance status classification. Extreme gradient boosting model demonstrated that preoperative growth hormone (GH) level, age at operation, and preoperative tumor size were the most important predictors for early remission; resistance to SRL and preoperative tumor size represented the most important predictors of remission at last visit, and postoperative 3-month insulin-like growth factor 1 (IGF1) and GH levels (random and nadir) together with the sparsely granulated somatotroph adenoma subtype served as the most important predictors of SRL resistance.
Conclusions
ML models may serve as valuable tools in the prediction of remission and SRL resistance.
Anatomical cross‐sectional imaging methods such as contrast‐enhanced MRI and CT are the standard for the delineation, treatment planning, and follow‐up of patients with meningioma. Besides, advanced neuroimaging is increasingly used to non‐invasively provide detailed insights into the molecular and metabolic features of meningiomas. These techniques are usually based on MRI, e.g., perfusion‐weighted imaging, diffusion‐weighted imaging, MR spectroscopy, and positron emission tomography. Furthermore, artificial intelligence methods such as radiomics offer the potential to extract quantitative imaging features from routinely acquired anatomical MRI and CT scans and advanced imaging techniques. This allows the linking of imaging phenotypes to meningioma characteristics, e.g., the molecular‐genetic profile. Here, we review several diagnostic applications and future directions of these advanced neuroimaging techniques, including radiomics in preclinical models and patients with meningioma. Anatomical cross‐sectional imaging methods such as contrast‐enhanced MRI and CT are the standard for the delineation, treatment planning, and follow‐up of patients with meningioma. Besides, advanced neuroimaging is increasingly used to non‐invasively provide detailed insights into the molecular and metabolic features of meningiomas. These techniques are usually based on MRI, e.g., perfusion‐weighted imaging, diffusion‐weighted imaging, MR spectroscopy, and positron emission tomography. Furthermore, artificial intelligence methods such as radiomics offer the potential to extract quantitative imaging features from routinely acquired anatomical MRI and CT scans and advanced imaging techniques. This allows the linking of imaging phenotypes to meningioma characteristics, e.g., the molecular‐genetic profile. Here, we review several diagnostic applications and future directions of these advanced neuroimaging techniques, including radiomics in preclinical models and patients with meningioma.
Background
DNA methylation abnormalities are pervasive in pituitary neuroendocrine tumors (PitNETs). The feasibility to detect methylome alterations in circulating cell-free DNA (cfDNA) has been reported for several central nervous system tumors but not across PitNETs. The aim of the study was to use the liquid biopsy approach to detect PitNET-specific methylation signatures to differentiate these tumors from other sellar diseases.
Method
We profiled the cfDNA methylome (EPIC array) of 59 serum and 41 plasma liquid biopsy specimens from patients with PitNETs and other CNS diseases (sellar tumors and other pituitary non-neoplastic diseases, lower-grade gliomas and skull base meningiomas) or nontumor conditions, grouped as non-PitNET.
Results
Our results indicated that, despite quantitative and qualitative differences between serum and plasma cfDNA composition, both sources of liquid biopsy showed that patients with PitNETs presented a distinct methylome landscape compared to non-PitNETs. In addition, liquid biopsy methylomes captured epigenetic features reported in PitNET tissue and provided information about cell type composition. Using liquid biopsy-derived PitNETs-specific signatures as input to develop machine-learning predictive models, we generated scores which distinguished PitNETs from non-PitNETs conditions, including sellar tumor and non-neoplastic pituitary diseases, with accuracies above ~93% in independent cohort sets.
Conclusions
Our results underpin the potential application of methylation-based liquid biopsy profiling as a noninvasive approach to identify clinically relevant epigenetic markers to diagnose and potentially impact the prognostication and management of patients with PitNETs.
Introduction:
This study aims to develop a machine learning-based model integrating clinical and ophthalmic features to predict visual outcomes after transsphenoidal resection of sellar region tumors.
Methods:
Adult patients with optic chiasm compression by a sellar region tumor were examined to develop a model, and an independent retrospective cohort and a prospective cohort were used to validate our model. Predictors included demographic information, and ophthalmic and laboratory test results. We defined "recovery" as more than 5% for a p-value in mean deviation compared with the general population in the follow-up. Seven machine learning classifiers were employed, and the best-performing algorithm was selected. A decision curve analysis was used to assess the clinical usefulness of our model by estimating net benefit. We developed a nomogram based on essential features ranked by the SHAP score.
Results:
We included 159 patients (57.2% male), and the mean age was 42.3 years old. Among them, 96 patients were craniopharyngiomas and 63 patients were pituitary adenomas. Larger tumors (3.3 cm vs. 2.8 cm in tumor height) and craniopharyngiomas (73.6%) were associated with a worse prognosis (p < 0.001). Eyes with better outcomes were those with better visual field and thicker ganglion cell layer before operation. The ensemble model yielded the highest AUC of 0.911 [95% CI, 0.885-0.938], and the corresponding accuracy was 84.3%, with 0.863 in sensitivity and 0.820 in specificity. The model yielded AUCs of 0.861 and 0.843 in the two validation cohorts. Our model provided greater net benefit than the competing extremes of intervening in all or no patients in the decision curve analysis. A model explanation using SHAP score demonstrated that visual field, ganglion cell layer, tumor height, total thyroxine, and diagnosis were the most important features in predicting visual outcome.
Conclusion:
SHAP score can be a valuable resource for healthcare professionals in identifying patients with a higher risk of persistent visual deficit. The large-scale and prospective application of the proposed model would strengthen its clinical utility and universal applicability in practice.
For the tumors located in the anterior skull base, germinoma and craniopharyngioma (CP) are unusual types with similar clinical manifestations and imaging features. The difference in treatment strategies and outcomes of patients highlights the importance of making an accurate preoperative diagnosis. This retrospective study enrolled 107 patients diagnosed with germinoma (n = 44) and CP (n = 63). The region of interest (ROI) was drawn independently by two researchers. Radiomic features were extracted from contrast-enhanced T1WI and T2WI sequences. Here, we established the diagnosis models with a combination of three selection methods, as well as three classifiers. After training the models, their performances were evaluated on the independent validation cohort and compared based on the index of the area under the receiver operating characteristic curve (AUC) in the validation cohort. Nine models were established and compared to find the optimal one defined with the highest AUC in the validation cohort. For the models applied in the contrast-enhanced T1WI images, RFS + RFC and LASSO + LDA were observed to be the optimal models with AUCs of 0.91. For the models applied in the T2WI images, DC + LDA and LASSO + LDA were observed to be the optimal models with AUCs of 0.88. The evidence of this study indicated that radiomics-based machine learning could be potentially considered as the radiological method in the presurgical differential diagnosis of germinoma and CP with a reliable diagnostic performance.
Objective: To investigate the ability of a MRI-based radiomics-clinicopathological model to predict pituitary macroadenoma (PMA) recurrence within 5 years.
Materials and Methods: We recruited 74 recurrent and 94 non-recurrent subjects, following first surgery with 5-year follow-up data. Univariate and multivariate analyses were conducted to identify independent clinicopathological risk factors. Two independent and blinded neuroradiologists used 3D-Slicer software to manually delineate whole tumors using preoperative axial contrast-enhanced T1WI (CE-T1WI) images. 3D-Slicer was then used to extract radiomics features from segmented tumors. Dimensionality reduction was carried out by the least absolute shrinkage and selection operator (LASSO). Two multilayer perceptron (MLP) models were established, including independent clinicopathological risk factors (Model 1) and a combination of screened radiomics features and independent clinicopathological markers (Model 2). The predictive performance of these models was evaluated by receiver operator characteristic (ROC) curve analysis.
Results: In total, 1,130 features were identified, and 4 of these were selected by LASSO. In the test set, the area under the curve (AUC) of Model 2 was superior to Model 1 {0.783, [95% confidence interval (CI): 0.718—.860] vs. 0.739, (95% CI: 0.665–0.818)}. Model 2 also yielded the higher accuracy (0.808 vs. 0.692), sensitivity (0.826 vs. 0.652), and specificity (0.793 vs. 0.724) than Model 1.
Conclusions: The integrated classifier was superior to a clinical classifier and may facilitate the prediction of individualized prognosis and therapy.
PurposeTo systematically review the literature regarding the application of machine learning (ML) of magnetic resonance imaging (MRI) radiomics in common sellar tumors. To identify future directions for application of ML in sellar tumor MRI.Methods
PubMed, Medline, Embase, Google Scholar, Scopus, ArxIV, and bioRxiv were searched to identify relevant studies published between 2010 and September 2021. Studies were included if they specifically involved ML of MRI radiomics in the analysis of sellar masses. Risk of bias assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) Tool.ResultsFifty-eight articles were identified for review. All papers utilized retrospective data, and a quantitative systematic review was performed for thirty-one studies utilizing a public dataset which compared pituitary adenomas, meningiomas, and gliomas. One of the analyzed architectures yielded the highest classification accuracy of 0.996. The remaining twenty-seven articles were qualitatively reviewed and showed promising findings in predicting specific tumor characteristics such as tumor consistency, Ki-67 proliferative index, and post-surgical recurrence.Conclusion
This review highlights the potential clinical application of ML using MRI radiomic data of the sellar region in diagnosis and predicting treatment outcomes. We describe future directions for practical application in the clinical care of patients with pituitary neuroendocrine and other sellar tumors.
Purpose
Biochemical remission (BR), gross total resection (GTR), and intraoperative cerebrospinal fluid (CSF) leaks are important metrics in transsphenoidal surgery for acromegaly, and prediction of their likelihood using machine learning would be clinically advantageous. We aim to develop and externally validate clinical prediction models for outcomes after transsphenoidal surgery for acromegaly.
Methods
Using data from two registries, we develop and externally validate machine learning models for GTR, BR, and CSF leaks after endoscopic transsphenoidal surgery in acromegalic patients. For the model development a registry from Bologna, Italy was used. External validation was then performed using data from Zurich, Switzerland. Gender, age, prior surgery, as well as Hardy and Knosp classification were used as input features. Discrimination and calibration metrics were assessed.
Results
The derivation cohort consisted of 307 patients (43.3% male; mean [SD] age, 47.2 [12.7] years). GTR was achieved in 226 (73.6%) and BR in 245 (79.8%) patients. In the external validation cohort with 46 patients, 31 (75.6%) achieved GTR and 31 (77.5%) achieved BR. Area under the curve (AUC) at external validation was 0.75 (95% confidence interval: 0.59–0.88) for GTR, 0.63 (0.40–0.82) for BR, as well as 0.77 (0.62–0.91) for intraoperative CSF leaks. While prior surgery was the most important variable for prediction of GTR, age, and Hardy grading contributed most to the predictions of BR and CSF leaks, respectively.
Conclusions
Gross total resection, biochemical remission, and CSF leaks remain hard to predict, but machine learning offers potential in helping to tailor surgical therapy. We demonstrate the feasibility of developing and externally validating clinical prediction models for these outcomes after surgery for acromegaly and lay the groundwork for development of a multicenter model with more robust generalization.
Objective
No accurate predictive models were identified for hormonal prognosis in non-functioning pituitary adenoma (NFPA). This study aimed to develop machine learning (ML) models to facilitate the prognostic assessment of pituitary hormonal outcomes after surgery.
Methods
A total of 215 male patients with NFPA, who underwent surgery in four medical centers from 2015 to 2021, were retrospectively reviewed. The data were pooled after heterogeneity assessment, and they were randomly divided into training and testing sets (172:43). Six ML models and logistic regression models were developed using six anterior pituitary hormones.
Results
Only thyroid-stimulating hormone (p < 0.001), follicle-stimulating hormone (p < 0.001), and prolactin (PRL; p < 0.001) decreased significantly following surgery, whereas growth hormone (GH) (p < 0.001) increased significantly. The postoperative GH (p = 0.07) levels were slightly higher in patients with gross total resection, but the PRL (p = 0.03) level was significantly lower than that in patients with subtotal resection. The optimal model achieved area-under-the-receiver-operating-characteristic-curve values of 0.82, 0.74, and 0.85 in predicting hormonal hypofunction, new deficiency, and hormonal recovery following surgery, respectively. According to feature importance analyses, the preoperative levels of the same type and other hormones were all important in predicting postoperative individual hormonal hypofunction.
Conclusion
Fluctuation in anterior pituitary hormones varies with increases and decreases because of transsphenoidal surgery. The ML models could accurately predict postoperative pituitary outcomes based on preoperative anterior pituitary hormones in NFPA.
Preoperative prediction of visual recovery after pituitary adenoma surgery remains a challenge. We aimed to investigate the value of MRI-based radiomics of the optic chiasm in predicting postoperative visual field outcome using machine learning technology. A total of 131 pituitary adenoma patients were retrospectively enrolled and divided into the recovery group (N = 79) and the non-recovery group (N = 52) according to visual field outcome following surgical chiasmal decompression. Radiomic features were extracted from the optic chiasm on preoperative coronal T2-weighted imaging. Least absolute shrinkage and selection operator regression were first used to select optimal features. Then, three machine learning algorithms were employed to develop radiomic models to predict visual recovery, including support vector machine (SVM), random forest and linear discriminant analysis. The prognostic performances of models were evaluated via five-fold cross-validation. The results showed that radiomic models using different machine learning algorithms all achieved area under the curve (AUC) over 0.750. The SVM-based model represented the best predictive performance for visual field recovery, with the highest AUC of 0.824. In conclusion, machine learning-based radiomics of the optic chiasm on routine MR imaging could potentially serve as a novel approach to preoperatively predict visual recovery and allow personalized counseling for individual pituitary adenoma patients.
Neurosurgeons receive extensive and lengthy training to equip themselves with various technical skills, and neurosurgery require a great deal of pre-, intra- and postoperative clinical data collection, decision making, care and recovery. The last decade has seen a significant increase in the importance of artificial intelligence (AI) in neurosurgery. AI can provide a great promise in neurosurgery by complementing neurosurgeons' skills to provide the best possible interventional and noninterventional care for patients by enhancing diagnostic and prognostic outcomes in clinical treatment and help neurosurgeons with decision making during surgical interventions to improve patient outcomes. Furthermore, AI is playing a pivotal role in the production, processing and storage of clinical and experimental data. AI usage in neurosurgery can also reduce the costs associated with surgical care and provide high-quality healthcare to a broader population. Additionally, AI and neurosurgery can build a symbiotic relationship where AI helps to push the boundaries of neurosurgery, and neurosurgery can help AI to develop better and more robust algorithms. This review explores the role of AI in interventional and noninterventional aspects of neurosurgery during pre-, intra- and postoperative care, such as diagnosis, clinical decision making, surgical operation, prognosis, data acquisition, and research within the neurosurgical arena.
Background
There are no established accurate models that use machine learning (ML) methods to preoperatively predict immediate remission after transsphenoidal surgery (TSS) in patients diagnosed with histology-positive Cushing’s disease (CD).
Purpose
Our current study aims to devise and assess an ML-based model to preoperatively predict immediate remission after TSS in patients with CD.
Methods
A total of 1,045 participants with CD who received TSS at Peking Union Medical College Hospital in a 20-year period (between February 2000 and September 2019) were enrolled in the present study. In total nine ML classifiers were applied to construct models for the preoperative prediction of immediate remission with preoperative factors. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate the performance of the models. The performance of each ML-based model was evaluated in terms of AUC.
Results
The overall immediate remission rate was 73.3% (766/1045). First operation (p<0.001), cavernous sinus invasion on preoperative MRI(p<0.001), tumour size (p<0.001), preoperative ACTH (p=0.008), and disease duration (p=0.010) were significantly related to immediate remission on logistic univariate analysis. The AUCs of the models ranged between 0.664 and 0.743. The highest AUC, i.e., the best performance, was 0.743, which was achieved by stacking ensemble method with four factors: first operation, cavernous sinus invasion on preoperative MRI, tumour size and preoperative ACTH.
Conclusion
We developed a readily available ML-based model for the preoperative prediction of immediate remission in patients with CD.
PurposeFunctional pituitary adenomas (FPAs) cause severe neuro-endocrinopathies including Cushing’s disease (CD) and acromegaly. While many are effectively cured following FPA resection, some encounter disease recurrence/progression or hormonal non-remission requiring adjuvant treatment. Identification of risk factors for suboptimal postoperative outcomes may guide initiation of adjuvant multimodal therapies.Methods
Patients undergoing endonasal transsphenoidal resection for CD, acromegaly, and mammosomatotroph adenomas between 1992 and 2019 were identified. Good outcomes were defined as hormonal remission without imaging/biochemical evidence of disease recurrence/progression, while suboptimal outcomes were defined as hormonal non-remission or MRI evidence of recurrence/progression despite adjuvant treatment. Multivariate regression modeling and multilayered neural networks (NN) were implemented. The training sets randomly sampled 60% of all FPA patients, and validation/testing sets were 20% samples each.Results348 patients with mean age of 41.7 years were identified. Eighty-one patients (23.3%) reported suboptimal outcomes. Variables predictive of suboptimal outcomes included: Requirement for additional surgery in patients who previously had surgery and continue to have functionally active tumor (p = 0.0069; OR = 1.51, 95%CI 1.12–2.04), Preoperative visual deficit not improved after surgery (p = 0.0033; OR = 1.12, 95%CI 1.04–1.20), Transient diabetes insipidus (p = 0.013; OR = 1.27, 95%CI 1.05–1.52), Higher MIB-1/Ki-67 labeling index (p = 0.038; OR = 1.08, 95%CI 1.01–1.15), and preoperative low cortisol axis (p = 0.040; OR = 2.72, 95%CI 1.06–7.01). The NN had overall accuracy of 87.1%, sensitivity of 89.5%, specificity of 76.9%, positive predictive value of 94.4%, and negative predictive value of 62.5%. NNs for all FPAs were more robust than for CD or acromegaly/mammosomatotroph alone.Conclusion
We demonstrate capability of predicting suboptimal postoperative outcomes with high accuracy. NNs may aid in stratifying patients for risk of suboptimal outcomes, thereby guiding implementation of adjuvant treatment in high-risk patients.
PurposeAccurate brain tumor segmentation on magnetic resonance imaging (MRI) has wide-ranging applications such as radiosurgery planning. Advances in artificial intelligence, especially deep learning (DL), allow development of automatic segmentation that overcome the labor-intensive and operator-dependent manual segmentation. We aimed to evaluate the accuracy of the top-performing DL model from the 2018 Brain Tumor Segmentation (BraTS) challenge, the impact of missing MRI sequences, and whether a model trained on gliomas can accurately segment other brain tumor types.Methods
We trained the model using Medical Decathlon dataset, applied it to the BraTS 2019 glioma dataset, and developed additional models using individual and multimodal MRI sequences. The Dice score was calculated to assess the model’s accuracy compared to ground truth labels by neuroradiologists on BraTS dataset. The model was then applied to a local dataset of 105 brain tumors, performance of which was qualitatively evaluated.ResultsThe DL model using pre- and post-gadolinium contrast T1 and T2 FLAIR sequences performed best, with a Dice score 0.878 for whole tumor, 0.732 tumor core, and 0.699 active tumor. Lack of T1 or T2 sequences did not significantly degrade performance, but FLAIR and T1C were important contributors. All segmentations performed by the model in the local dataset, including non-glioma cases, were considered accurate by a pool of specialists.Conclusion
The DL model could use available MRI sequences to optimize glioma segmentation and adopt transfer learning to segment non-glioma tumors, thereby serving as a useful tool to improve treatment planning and personalized surveillance of patients.
Introduction: Surgical resection of brain tumors is often limited by adjacent critical structures such as blood vessels. Current intraoperative navigations systems are limited; most are based on two-dimensional (2D) guidance systems that require manual segmentation of any regions of interest (ROI; eloquent structures to avoid or tumor to resect). They additionally require time- and labor-intensive processing for any reconstruction steps. We aimed to develop a deep learning model for real-time fully automated segmentation of the intracranial vessels on preoperative non-angiogram imaging sequences.
Methods: We identified 48 pediatric patients (10-months to 22-years old) with high resolution (0.5–1 mm axial thickness) isovolumetric, pre-operative T2 magnetic resonance images (MRIs). Twenty-eight patients had anatomically normal brains, and 20 patients had tumors or other lesions near the skull base. Manually segmented intracranial vessels (internal carotid, middle cerebral, anterior cerebral, posterior cerebral, and basilar arteries) served as ground truth labels. Patients were divided into 80/5/15% training/validation/testing sets. A modified 2-D Unet convolutional neural network (CNN) architecture implemented with 5 layers was trained to maximize the Dice coefficient, a measure of the correct overlap between the predicted vessels and ground truth labels.
Results: The model was able to delineate the intracranial vessels in a held-out test set of normal and tumor MRIs with an overall Dice coefficient of 0.75. While manual segmentation took 1–2 h per patient, model prediction took, on average, 8.3 s per patient.
Conclusions: We present a deep learning model that can rapidly and automatically identify the intracranial vessels on pre-operative MRIs in patients with normal vascular anatomy and in patients with intracranial lesions. The methodology developed can be translated to other critical brain structures. This study will serve as a foundation for automated high-resolution ROI segmentation for three-dimensional (3D) modeling and integration into an augmented reality navigation platform.
Purpose: Accurate prediction of postoperative remission is beneficial for effective patient-physician communication in acromegalic patients. This study aims to train and validate machine learning prediction models for early endocrine remission of acromegalic patients.
Methods: The training cohort included 833 patients with growth hormone (GH) secreting pituitary adenoma from 2010 to 2018. We trained a partial model (only using pre-operative variables) and a full model (using all variables) to predict off-medication endocrine remission at six-month follow-up after surgery using multiple algorithms. The models were validated in 99 prospectively collected patients from a second campus and 52 patients from a third institution.
Results: C-statistic and the accuracy of the best partial model was 0.803 (95% CI 0.757-0.849) and 72.5% (95% CI 67.6-77.5%), respectively. C-statistic and the accuracy of the best full model was 0.888 (95% CI 0.861-0.914) and 80.3% (95% CI 77.5-83.1%), respectively. The c-statistics (and accuracy) of using only Knosp grade, total resection, or postoperative day 1 GH level as the single predictor were lower than our partial model or full model (p < 0.001). C-statistics remained similar in the prospective cohort (partial model 0.798, and full model 0.903) and in the external cohort (partial model 0.771, and full model 0.871). A web-based application integrated with the trained models was published at https://deepvep.shinyapps.io/Acropred/ .
Conclusion: We developed and validated interpretable and applicable machine learning models to predict early endocrine remission after surgical resection of a GH-secreting pituitary adenoma. Predication accuracy of the trained models were better than those using single variables.
PurposeHyponatremia after pituitary surgery is a frequent finding with potential severe complications and the most common cause for readmission. Several studies have found parameters associated with postoperative hyponatremia, but no reliable specific predictor was described yet. This pilot study evaluates the feasibility of machine learning (ML) algorithms to predict postoperative hyponatremia after resection of pituitary lesions.Methods
Retrospective screening of a prospective registry of patients who underwent transsphenoidal surgery for pituitary lesions. Hyponatremia within 30 days after surgery was the primary outcome. Several pre- and intraoperative clinical, procedural and laboratory features were selected to train different ML algorithms. Trained models were compared using common performance metrics. Final model was internally validated on the testing dataset.ResultsFrom 207 patients included in the study, 44 (22%) showed a hyponatremia within 30 days postoperatively. Hyponatremic measurements peaked directly postoperatively (day 0–1) and around day 7. Bootstrapped performance metrics of different trained ML-models showed largest area under the receiver operating characteristic curve (AUROC) for the boosted generalized linear model (67.1%), followed by the Naïve Bayes classifier (64.6%). The discriminative capability of the final model was assessed by predicting on unseen dataset. Large AUROC (84.3%; 67.0–96.4), sensitivity (81.8%) and specificity (77.5%) with an overall accuracy of 78.4% (66.7–88.2) was reached.Conclusion
Our trained ML-model was able to learn the complex risk factor interactions and showed a high discriminative capability on unseen patient data. In conclusion, ML-methods can predict postoperative hyponatremia and thus potentially reduce morbidity and improve patient safety.
Objective:
Machine learning (ML) is an innovative method to analyze large and complex data sets. The aim of this study was to evaluate the use of ML to identify predictors of early postsurgical and long-term outcomes in patients treated for Cushing disease (CD).
Methods:
All consecutive patients in our center who underwent surgery for CD through the endoscopic endonasal approach were retrospectively reviewed. Study endpoints were gross-tumor removal (GTR), postsurgical remission, and long-term control of disease. Several demographic, radiological, and histological factors were assessed as potential predictors. For ML-based modeling, data were randomly divided into 2 sets with an 80% to 20% ratio for bootstrapped training and testing, respectively. Several algorithms were tested and tuned for the area under the curve (AUC).
Results:
The study included 151 patients. GTR was achieved in 137 patients (91%), and postsurgical hypersecretion remission was achieved in 133 patients (88%). At last follow-up, 116 patients (77%) were still in remission after surgery and in 21 patients (14%), CD was controlled with complementary treatment (overall, of 131 cases, 87% were under control at follow-up). At internal validation, the endpoints were predicted with AUCs of 0.81-1.00, accuracy of 81%-100%, and Brier scores of 0.035-0.151. Tumor size and invasiveness and histological confirmation of adrenocorticotropic hormone (ACTH)-secreting cells were the main predictors for the 3 endpoints of interest.
Conclusions:
ML algorithms were used to train and internally validate robust models for all the endpoints, giving accurate outcome predictions in CD cases. This analytical method seems promising for potentially improving future patient care and counseling; however, careful clinical interpretation of the results remains necessary before any clinical adoption of ML. Moreover, further studies and increased sample sizes are definitely required before the widespread adoption of ML to the study of CD.
Background
Cerebrospinal fluid rhinorrhoea (CSFR) is a common complication following endonasal skull base surgery, a technique that is fundamental to the treatment of pituitary adenomas and many other skull base tumours. The CRANIAL study explored CSFR incidence and related risk factors, particularly skull base repair techniques, via a multicentre prospective observational study. We sought to use machine learning to leverage this complex multicentre dataset for CSFR prediction and risk factor analysis.
Methods
A dataset of 865 cases - 725 transsphenoidal approach (TSA) and 140 expanded endonasal approach (EEA) - with cerebrospinal fluid rhinorrhoea as the primary outcome, was used. Relevant variables were extracted from the data, and prediction variables were divided into two categories, preoperative risk factors; and repair techniques, with 6 and 11 variables respectively. Three types of machine learning models were developed in order to predict CSFR: logistic regression (LR); decision tree (DT); and neural network (NN). Models were validated using 5-fold cross-validation, compared via their area under the curve (AUC) evaluation metric, and key prediction variables were identified using their Shapley additive explanations (SHAP) score.
Results
CSFR rates were 3.9% (28/725) for the transsphenoidal approach and 7.1% (10/140) for the expanded endonasal approach. NNs outperformed LR and DT for CSFR prediction, with a mean AUC of 0.80 (0.70-0.90) for TSA and 0.78 (0.60-0.96) for EEA, when all risk factor and intraoperative repair data were integrated into the model. The presence of intraoperative CSF leak was the most prominent risk factor for CSFR. Elevated BMI and revision surgery were also associated with CSFR for the transsphenoidal approach. CSF diversion and gasket sealing appear to be strong predictors of the absence of CSFR for both approaches.
Conclusion
Neural networks are effective at predicting CSFR and uncovering key CSFR predictors in patients following endonasal skull base surgery, outperforming traditional statistical methods. These models will be improved further with larger and more granular datasets, improved NN architecture, and external validation. In the future, such predictive models could be used to assist surgical decision-making and support more individualised patient counselling.
Keywords: cerebrospinal fluid leak, cerebrospinal fluid rhinorrhoea, CSF, endoscopic endonasal, skull base surgery, machine learning - ML, neural network, outcome prediction
Background:
Classifying sphenoid pneumatisation is an important but often overlooked task in reporting sinus CT scans. Artificial intelligence (AI) and one of its key methods, convolutional neural networks (CNNs), can create algorithms that can learn from data without being programmed with explicit rules and have shown utility in radiological image classification.
Objective:
To determine if a trained CNN can accurately classify sphenoid sinus pneumatisation on CT sinus imaging.
Methods:
Sagittal slices through the natural ostium of the sphenoid sinus were extracted from retrospectively collected bone-window CT scans of the paranasal sinuses for consecutive patients over 6 years. Two blinded Otolaryngology residents reviewed each image and classified the sphenoid sinus pneumatisation as either conchal, presellar or sellar. An AI algorithm was developed using the Microsoft Azure Custom Vision deep learning platform to classify the pattern of pneumatisation.
Results:
Seven hundred eighty images from 400 patients were used to train the algorithm, which was then tested on a further 118 images from 62 patients. The algorithm achieved an accuracy of 93.2% (95% confidence interval [CI] 87.1-97.0), 87.3% (95% CI 79.9-92.7) and 85.6% (95% CI 78.0-91.4) in correctly identifying conchal, presellar and sellar sphenoid pneumatisation, respectively. The overall weighted accuracy of the CNN was 85.9%.
Conclusion:
The CNN described demonstrated a moderately accurate classification of sphenoid pneumatisation subtypes on CT scans. The use of CNN-based assistive tools may enable surgeons to achieve safer operative planning through routine automated reporting allowing greater resources to be directed towards the identification of pathology.
Endoscopic endonasal surgery is a medical procedure that utilizes an endoscopic video camera to view and manipulate a surgical site accessed through the nose. Despite these surgeries being video recorded, these videos are seldom reviewed or even saved in patient files due to the size and length of the video file. Editing to a manageable size may necessitate viewing 3 h or more of surgical video and manually splicing together the desired segments. We suggest a novel multi-stage video summarization procedure utilizing deep semantic features, tool detections, and video frame temporal correspondences to create a representative summarization. Summarization by our method resulted in a 98.2% reduction in overall video length while preserving 84% of key medical scenes. Furthermore, resulting summaries contained only 1% of scenes with irrelevant detail such as endoscope lens cleaning, blurry frames, or frames external to the patient. This outperformed leading commercial and open source summarization tools not designed for surgery, which only preserved 57% and 46% of key medical scenes in similar length summaries, and included 36% and 59% of scenes containing irrelevant detail. Experts agreed that on average (Likert Scale = 4) that the overall quality of the video was adequate to share with peers in its current state.
Objective While predictive analytic techniques have been used to analyze meningioma postoperative outcomes, to our knowledge, there have been no studies that have investigated the utility of machine learning (ML) models in prognosticating outcomes among skull base meningioma patients. The present study aimed to develop models for predicting postoperative outcomes among skull base meningioma patients, specifically prolonged hospital length of stay (LOS), nonroutine discharge disposition, and high hospital charges. We also validated the predictive performance of our models on out-of-sample testing data.
Methods Patients who underwent skull base meningioma surgery between 2016 and 2019 at an academic institution were included in our study. Prolonged hospital LOS and high hospital charges were defined as >4 days and >$47,887, respectively. Elastic net logistic regression algorithms were trained to predict postoperative outcomes using 70% of available data, and their predictive performance was evaluated on the remaining 30%.
Results A total of 265 patients were included in our final analysis. Our cohort was majority female (77.7%) and Caucasian (63.4%). Elastic net logistic regression algorithms predicting prolonged LOS, nonroutine discharge, and high hospital charges achieved areas under the receiver operating characteristic curve of 0.798, 0.752, and 0.592, respectively. Further, all models were adequately calibrated as determined by the Spiegelhalter Z-test (p >0.05).
Conclusion Our study developed models predicting prolonged hospital LOS, nonroutine discharge disposition, and high hospital charges among skull base meningioma patients. Our models highlight the utility of ML as a tool to aid skull base surgeons in providing high-value health care and optimizing clinical workflows.
Surgery is the first-line therapy for most benign and malignant skull base tumors. Extent of resection (EOR) is a metric commonly used for preoperative surgical planning and to predict risk of postoperative tumor recurrence. Therefore, understanding the evidence on EOR in skull base neurosurgery is essential to providing optimal care for each patient. Several studies from the skull base neurosurgery literature have presented investigations of various topics related to EOR, including 1) preoperative EOR scoring systems, 2) intraoperative EOR scoring systems, 3) EOR and tumor recurrence, and 4) EOR and functional outcomes. We propose that future investigations should focus on the following elements to improve EOR research in skull base neurosurgery: 1) multi-institutional collaboratives with treatment propensity matching; 2) expert consensus and mixed-methods study design; and 3) predictive analytics/machine learning. We believe that these methods offer several advantages that have been described in the literature and that they address limitations of previous studies. The aim of this review was to inform future study design and improve the overall quality of subsequent investigations on EOR in skull base neurosurgery.
Background:
Unplanned readmission after transsphenoidal resection of pituitary adenoma can occur in up to 10% of patients but is unpredictable.
Objective:
To develop a reliable system for predicting unplanned readmission and create a validated method for stratifying patients by risk.
Methods:
Data sets were retrospectively collected from the National Surgical Quality Improvement Program and 2 tertiary academic medical centers. Eight machine learning classifiers were fit to the National Surgical Quality Improvement Program data, optimized using Bayesian parameter optimization and evaluated on the external data. Permutation analysis identified the relative importance of predictive variables, and a risk stratification system was built using the trained machine learning models.
Results:
Readmissions were accurately predicted by several classification models with an area under the receiving operator characteristic curve of 0.76 (95% CI 0.68-0.83) on the external data set. Permutation analysis identified the most important variables for predicting readmission as preoperative sodium level, returning to the operating room, and total operation time. High-risk and medium-risk patients, as identified by the proposed risk stratification system, were more likely to be readmitted than low-risk patients, with relative risks of 12.2 (95% CI 5.9-26.5) and 4.2 (95% CI 2.3-8.7), respectively. Overall risk stratification showed high discriminative capability with a C-statistic of 0.73.
Conclusion:
In this multi-institutional study with outside validation, unplanned readmissions after pituitary adenoma resection were accurately predicted using machine learning techniques. The features identified in this study and the risk stratification system developed could guide clinical and surgical decision making, reduce healthcare costs, and improve the quality of patient care by better identifying high-risk patients for closer perioperative management.
Survival prediction of patients affected by brain tumors provides essential information to guide surgical planning, adjuvant treatment selection, and patient counseling. Current reliance on clinical factors, such as Karnofsky Performance Status Scale, and simplistic radiological characteristics are, however, inadequate for survival prediction in tumors such as glioma that demonstrate molecular and clinical heterogeneity with variable survival outcomes. Advances in the domain of artificial intelligence have afforded powerful tools to capture a large number of hidden high-dimensional imaging features that reflect abundant information about tumor structure and physiology. Here, we provide an overview of current literature that apply computational analysis tools such as radiomics and machine learning methods to the pipeline of image preprocessing, tumor segmentation, feature extraction, and construction of classifiers to establish survival prediction models based on neuroimaging. We also discuss challenges relating to the development and evaluation of such models and explore ethical issues surrounding the future use of machine learning predictions.
Background:
Accurate specimen analysis of skull base tumors is essential for providing personalized surgical treatment strategies. Intraoperative specimen interpretation can be challenging because of the wide range of skull base pathologies and lack of intraoperative pathology resources.
Objective:
To develop an independent and parallel intraoperative workflow that can provide rapid and accurate skull base tumor specimen analysis using label-free optical imaging and artificial intelligence.
Methods:
We used a fiber laser-based, label-free, nonconsumptive, high-resolution microscopy method (<60 seconds per 1 × 1 mm2), called stimulated Raman histology (SRH), to image a consecutive, multicenter cohort of patients with skull base tumor. SRH images were then used to train a convolutional neural network model using 3 representation learning strategies: cross-entropy, self-supervised contrastive learning, and supervised contrastive learning. Our trained convolutional neural network models were tested on a held-out, multicenter SRH data set.
Results:
SRH was able to image the diagnostic features of both benign and malignant skull base tumors. Of the 3 representation learning strategies, supervised contrastive learning most effectively learned the distinctive and diagnostic SRH image features for each of the skull base tumor types. In our multicenter testing set, cross-entropy achieved an overall diagnostic accuracy of 91.5%, self-supervised contrastive learning 83.9%, and supervised contrastive learning 96.6%. Our trained model was able to segment tumor-normal margins and detect regions of microscopic tumor infiltration in meningioma SRH images.
Conclusion:
SRH with trained artificial intelligence models can provide rapid and accurate intraoperative analysis of skull base tumor specimens to inform surgical decision-making.
Introduction
Although pituitary adenomas (PAs) are common intracranial tumors, literature evaluating the utility of comorbidity indices for predicting post-operative complications in patients undergoing pituitary surgery remains limited, thereby hindering the development of complex models that aim to identify high-risk patient populations. We utilized comparative modeling strategies to evaluate the predictive validity of various comorbidity indices and combinations thereof in predicting key pituitary surgery outcomes.
Methods
The Nationwide Readmissions Database was used to identify patients who underwent pituitary tumor operations (n=19,653) in 2016-2017. Patient frailty was assessed using the Johns Hopkins Adjusted Clinical Groups (JHACG). Charlson Comorbidity Index (CCI) and Elixhauser Comorbidity Index (ECI) were calculated for each patient. Five sets of generalized linear mixed-effects models were developed, using 1) Frailty, 2) CCI, 3) ECI, 4) Frailty+CCI, or 5) Frailty+ECI as the primary predictor. Complications of interest investigated included inpatient mortality, non-routine discharge (e.g., to locations other than home), length of stay (LOS) within the top quartile, cost within the top quartile, and one-year readmission rates.
Results
Postoperative mortality occurred in 73 patients (0.4%), one year readmission was reported in 2,994 patients (15.2%),and non-routine discharge occurred in 2,176 (11.1%) patients. The mean adjusted all-payer cost for the procedure was 25,553.85±26,518.91 (Top Quartile: $28,261.20) and mean LOS was 4.8 days±7.4 days (Top Quartile: 5.0 days). The model using frailty+ECI as the primary predictor consistently outperformed other models, with statistically significant p-values as determined by comparing their AUCs, for most complications. For prediction of mortality, however the Frailty+ECI model (AUC:0.831) was not better than the ECI model alone (AUC:0.831;p=0.95). For prediction of readmission the Frailty+ECI model (AUC:0.617) was not better than the frailty model alone (AUC:0.606;p=0.10) or the Frailty+CCI model (AUC:0.610;p=0.29).
Conclusions
This investigation is the first to implement mixed-effects modeling to study the utility of common comorbidity indices in a large, nationwide cohort of patients undergoing pituitary surgery. Knowledge gained from these models may help neurosurgeons identify high-risk patients whom require additional clinical attention or resource utilization prior to surgical planning.
Purpose Transsphenoidal surgery (TSS) for pituitary adenomas can be complicated by the occurrence of intraoperative cerebrospinal fluid (CSF) leakage (IOL). IOL significantly affects the course of surgery predisposing to the development of postoperative CSF leakage, a major source of morbidity and mortality in the postoperative period. The authors trained and internally validated the Random Forest (RF) prediction model to preoperatively identify patients at high risk for IOL. A locally interpretable model-agnostic explanations (LIME) algorithm is employed to elucidate the main drivers behind each machine learning (ML) model prediction.
Methods The data of 210 patients who underwent TSS were collected; first, risk factors for IOL were identified via conventional statistical methods (multivariable logistic regression). Then, the authors trained, optimized, and audited a RF prediction model.
Results IOL reported in 45 patients (21.5%). The recursive feature selection algorithm identified the following variables as the most significant determinants of IOL: Knosp's grade, sellar Hardy's grade, suprasellar Hardy's grade, tumor diameter (on X, Y, and Z axes), intercarotid distance, and secreting status (nonfunctioning and growth hormone [GH] secreting). Leveraging the predictive values of these variables, the RF prediction model achieved an area under the curve (AUC) of 0.83 (95% confidence interval [CI]: 0.78; 0.86), significantly outperforming the multivariable logistic regression model (AUC = 0.63).
Conclusion A RF model that reliably identifies patients at risk for IOL was successfully trained and internally validated. ML-based prediction models can predict events that were previously judged nearly unpredictable; their deployment in clinical practice may result in improved patient care and reduced postoperative morbidity and healthcare costs.
The heterogeneity of brain tumours at the molecular, metabolic and structural levels poses significant challenge for accurate tissue characterisation. Artificial intelligence and radiomics have emerged as valuable tools to analyse quantitative features extracted from medical images which capture the complex microenvironment of brain tumours. In particular, a number of computational tools including machine learning algorithms have been proposed for image preprocessing, tumour segmentation, feature extraction, classification, and prognostic stratifications as well. In this chapter, we explore the fundamentals of multiparametric brain tumour characterisation, as an understanding of the strengths, limitations and applications of these tools allows clinicians to better develop and evaluate models with improved diagnostic and prognostic value in brain tumour patients.
OBJECTIVE
Surgical workflow analysis involves systematically breaking down operations into key phases and steps. Automatic analysis of this workflow has potential uses for surgical training, preoperative planning, and outcome prediction. Recent advances in machine learning (ML) and computer vision have allowed accurate automated workflow analysis of operative videos. In this Idea, Development, Exploration, Assessment, Long-term study (IDEAL) stage 0 study, the authors sought to use Touch Surgery for the development and validation of an ML-powered analysis of phases and steps in the endoscopic transsphenoidal approach (eTSA) for pituitary adenoma resection, a first for neurosurgery.
METHODS
The surgical phases and steps of 50 anonymized eTSA operative videos were labeled by expert surgeons. Forty videos were used to train a combined convolutional and recurrent neural network model by Touch Surgery. Ten videos were used for model evaluation (accuracy, F1 score), comparing the phase and step recognition of surgeons to the automatic detection of the ML model.
RESULTS
The longest phase was the sellar phase (median 28 minutes), followed by the nasal phase (median 22 minutes) and the closure phase (median 14 minutes). The longest steps were step 5 (tumor identification and excision, median 17 minutes); step 3 (posterior septectomy and removal of sphenoid septations, median 14 minutes); and step 4 (anterior sellar wall removal, median 10 minutes). There were substantial variations within the recorded procedures in terms of video appearances, step duration, and step order, with only 50% of videos containing all 7 steps performed sequentially in numerical order. Despite this, the model was able to output accurate recognition of surgical phases (91% accuracy, 90% F1 score) and steps (76% accuracy, 75% F1 score).
CONCLUSIONS
In this IDEAL stage 0 study, ML techniques have been developed to automatically analyze operative videos of eTSA pituitary surgery. This technology has previously been shown to be acceptable to neurosurgical teams and patients. ML-based surgical workflow analysis has numerous potential uses—such as education (e.g., automatic indexing of contemporary operative videos for teaching), improved operative efficiency (e.g., orchestrating the entire surgical team to a common workflow), and improved patient outcomes (e.g., comparison of surgical techniques or early detection of adverse events). Future directions include the real-time integration of Touch Surgery into the live operative environment as an IDEAL stage 1 (first-in-human) study, and further development of underpinning ML models using larger data sets.
BACKGROUND
Although World Health Organization (WHO) grade I meningiomas are considered “benign” tumors, an elevated Ki-67 is one crucial factor that has been shown to influence tumor behavior and clinical outcomes. The ability to preoperatively discern Ki-67 would confer the ability to guide surgical strategy.
OBJECTIVE
In this study, we develop a machine learning (ML) algorithm using radiomic feature analysis to predict Ki-67 in WHO grade I meningiomas.
METHODS
A retrospective analysis was performed for a cohort of 306 patients who underwent surgical resection of WHO grade I meningiomas. Preoperative magnetic resonance imaging was used to perform radiomic feature extraction followed by ML modeling using least absolute shrinkage and selection operator wrapped with support vector machine through nested cross-validation on a discovery cohort (n = 230), to stratify tumors based on Ki-67 <5% and ≥5%. The final model was independently tested on a replication cohort (n = 76).
RESULTS
An area under the receiver operating curve (AUC) of 0.84 (95% CI: 0.78-0.90) with a sensitivity of 84.1% and specificity of 73.3% was achieved in the discovery cohort. When this model was applied to the replication cohort, a similar high performance was achieved, with an AUC of 0.83 (95% CI: 0.73-0.94), sensitivity and specificity of 82.6% and 85.5%, respectively. The model demonstrated similar efficacy when applied to skull base and nonskull base tumors.
CONCLUSION
Our proposed radiomic feature analysis can be used to stratify WHO grade I meningiomas based on Ki-67 with excellent accuracy and can be applied to skull base and nonskull base tumors with similar performance achieved.
Background:
Despite advances in endoscopic transnasal transsphenoidal surgery (ETNS) for pituitary adenomas (PAs), cerebrospinal fluid (CSF) leakage remains a life-threatening complication predisposing to major morbidity and mortality. In the current study we developed a supervised ML model able to predict the risk of intraoperative CSF leakage by comparing different machine learning (ML) methods and explaining the functioning and the rationale of the best performing algorithm.
Methods:
A retrospective cohort of 238 patients treated via E-TNS for PAs was selected. A customized pipeline of several ML models was programmed and trained; the best five models were tested on a hold-out test and the best classifier was then prospectively validated on a cohort of 35 recently treated patients.
Results:
Intraoperative CSF leak occurred in 54 (22,6%) of 238 patients. The most important risk's predictors were: non secreting status, older age, x-, y- and z-axes diameters, ostedural invasiveness, volume, ICD and R-ratio. The random forest (RF) classifier outperformed other models, with an AUC of 0.84, high sensitivity (86%) and specificity (88%). Positive predictive value and negative predictive value were 88% and 80% respectively. F1 score was 0.84. Prospective validation confirmed outstanding performance metrics: AUC (0,81), sensitivity (83%), specificity (79%), negative predictive value (95%) and F1 score (0,75).
Conclusions:
The RF classifier showed the best performance across all models selected. RF models might predict surgical outcomes in heterogeneous multimorbid and fragile populations outperforming classical statistical analyses and other ML models (SVM, ANN etc.), improving patient management and reducing preventable morbidity and additional costs.
Background: Intuitive, patient-specific identification of critical neurovascular structures remains a primary goal of navigation technology in endoscopic skull base surgery. This study presents the automated segmentation of middle skull base anatomical structures by a deep learning (DL) approach and the incorporation of the predicted models to an enhanced 3D navigation system.
Method: The internal carotid artery (CA), the canalicular optic nerve (ON) and the sella turcica (ST) were manually segmented in 150 clinical CT scans to train a supervised DL algorithm and to build a segmentation prediction model. Objective assessment of the accuracy of the auto-segmented structures was performed using the Dice score and Hausdorff’s error distance (HD). A navigation system was developed to use the generated models to render a 3D virtual scene which simulates the endoscopic view, suitable for image guidance. Target registration error (TRE) was assessed from the surface registration.
Results: The Dice scores were 0.76±0.12; 0.81±0.10; 0.84±0.08 and mean HD in mm were 0.54±0.1; 0.32±0.09 and 0.47±0.12 for the CA, ON and ST respectively on a testing set. Incorporated into an open-source platform, our system was successfully implemented for the transsphenoidal approach to the pituitary on 3 cadaveric heads. The mean TRE was 1.8±0.3 mm, and the surgeon was able to successfully identify the neurovascular targets based on the autosegmented rendering.
Conclusion: We present a solution for the auto-segmentation of middle skull base structures. It can provide valuable anatomic information to promote personalized surgical planning and intraoperative guidance as shown in our prototype three-dimensional enhanced navigation system.
Meningiomas are brain tumors that originate from the meninges and has been primarily classified into three grades by the current WHO guidelines. Although widely prevalent and can be managed by surgery there are instances when the tumors are located in difficult regions. This results in considerable challenges for complete surgical resection and further clinical management. While the genetic signature of the skull base tumors is now known to be different from the non-skull base tumors, there is a lack of information at the functional aspects of these tumors at the proteomic level. Thus, the current study thereby aims to obtain mechanistic insights between the two radiologically distinct groups of meningiomas, namely the skull base & supratentorial (non-skull base-NSB) regions. We have employed a comprehensive mass spectrometry-based label-free quantitative proteomic analysis in Skull base and supratentorial meningiomas. Further, we have used an Artificial Neural Networking employing a sparse Multilayer perceptron (MLP) architecture to predict protein concordance. A patient-derived spectral library has been employed for a novel peptide-level validation of proteins that are specific to the radiological regions using the SRM assay based targeted proteomics approach. The comprehensive proteomics enabled the identification of nearly 4000 proteins with high confidence (1%FDR ≥ 2 unique peptides) among which 170 proteins were differentially abundant in Skull base vs Supratentorial tumors (p-value ≤0.05). In silico analysis enabled mapping of the major alterations and hinted towards an overall perturbation of extracellular matrix and collagen biosynthesis components in the non-skull base meningiomas and a prominent perturbation of molecular trafficking in the skull base meningiomas. Therefore, this study has yielded novel insights into the functional association of the proteins that are differentially abundant in the two radiological subgroups.
Significance
In the current study, we have performed label-free proteomic analysis on fresh frozen tissue of 14 Supratentorial (NSB) and 7 Skull base meningiomas to assess perturbations in the global proteome, we have further employed an in-depth in silico analysis to map the pathways that have enabled functional mapping of the differentially abundant proteins in the Skull base and Supratentorial tumors. The findings from the above were also subjected to a machine learning-based neural networking to find out the proteins that have the most concordance of occurrence to determine the most influential proteins of the network. We further validated the differential abundance of identified protein markers in a larger patient cohort of Skull base and Supratentorial employing targeted proteomics approach to validate key protein candidates emerging from ours and other recent studies.
The previous studies that have explored the skull base and convexity meningiomas have been able to reveal alterations in the genetic mutations in these tumor types. However, there are not many studies that have explored the functional aspects of these tumors, especially at the proteome level. We have attempted for the first time to map the functional modules associated with altered proteins in these tumors and have been able to identify that there is a possibility that the Skull base meningiomas to be considerably different from the Non-skull base (NSB) tumors in terms of the perturbed pathways. Our study employed global as well as targeted proteomics to examine the proteomic alterations in these two tumor groups. The study indicates that proteins that were more abundant in Skull base tumors were part of molecular transport components, non-skull base proteins majorly mapped to the components of extracellular matrix remodeling pathways. In conclusion, this study substantiates the distinction in the proteomic signatures in the skull base and supratentorial meningiomas paving way for further investigation of the identified markers for determining if some of these proteins can be used for therapeutic interventions for cases that pose considerable challenges for complete resection.
BACKGROUND
Current intraoperative orientation methods either rely on preoperative imaging, are resource-intensive to implement, or difficult to interpret. Real-time, reliable anatomic recognition would constitute another strong pillar on which neurosurgeons could rest for intraoperative orientation.
OBJECTIVE
To assess the feasibility of machine vision algorithms to identify anatomic structures using only the endoscopic camera without prior explicit anatomo-topographic knowledge in a proof-of-concept study.
METHODS
We developed and validated a deep learning algorithm to detect the nasal septum, the middle turbinate, and the inferior turbinate during endoscopic endonasal approaches based on endoscopy videos from 23 different patients. The model was trained in a weakly supervised manner on 18 and validated on 5 patients. Performance was compared against a baseline consisting of the average positions of the training ground truth labels using a semiquantitative 3-tiered system.
RESULTS
We used 367 images extracted from the videos of 18 patients for training, as well as 182 test images extracted from the videos of another 5 patients for testing the fully developed model. The prototype machine vision algorithm was able to identify the 3 endonasal structures qualitatively well. Compared to the baseline model based on location priors, the algorithm demonstrated slightly but statistically significantly (P < .001) improved annotation performance.
CONCLUSION
Automated recognition of anatomic structures in endoscopic videos by means of a machine vision model using only the endoscopic camera without prior explicit anatomo-topographic knowledge is feasible. This proof of concept encourages further development of fully automated software for real-time intraoperative anatomic guidance during surgery.
Objective:
Computer vision (CV) is a subset of artificial intelligence which performs computations on image or video data, permitting the quantitative analysis of visual information. Common CV tasks that may be relevant to surgeons include image classification, object detection and tracking, and extraction of higher order features. Despite the potential applications of CV to intraoperative video, however, few surgeons describe the use of CV. A primary roadblock in implementing CV is the lack of a clear workflow to create an intraoperative video dataset to which CV can be applied. We report general principles for creating usable surgical video datasets and the result of their applications.
Methods:
Video annotations from cadaveric endoscopic endonasal skull base simulations (n=20 trials of 1-5 min, size = 8GB) were reviewed by 2 researcher-annotators. An internal, retrospective analysis of workflow for development of the intraoperative video annotations was performed to identify guiding practices.
Results:
Approximately 34,000 frames of surgical video were annotated. Key considerations in developing annotation workflows include: 1) Overcoming software and personnel constraints, 2) Ensuring adequate storage and access infrastructure 3) Optimization and standardization of annotation protocol, and 4) Operationalizing annotated data. Potential tools for use include CVAT and Vott: open-sourced annotation software allowing for local video storage, easy setup, and the use of interpolation.
Conclusion:
CV techniques can be applied to surgical video, but challenges for novice users may limit adoption. We outline principles in annotation workflow that can mitigate initial challenges groups may have when converting raw video into useable, annotated datasets.
Twelve to 66% of patients with clinically non-functioning pituitary adenoma (NFPA) experience tumor recurrence 1–5 years after the first surgery. Nevertheless, there is still no recurrence prediction factor concisely established and reproduced in the literature for NFPA management. The present study evaluates the prognostic value of MRI Radiomics features combined with machine learning models to assess recurrence after the first surgery in patients with clinically non-functioning pituitary adenomas (NFPA). We carried out a retrospective study on 27 patients with NFPA, 10 patients having experienced tumor recurrence after the first surgery and 17 who did not. Preoperative 3D T1 contrast-enhanced MR images of patients were used to extract up to 255 Radiomics features from two and three-dimensional segmented regions. Additionally, gender, age at first surgery, and the presence of remnant tumor tissue were investigated to find the correlation with NFPA recurrence. Conventional statistics tests were used to evaluate whether the outcome patient groups (stable and recurrent) were different considering each feature individually. Additionally, five well-known machine-learning algorithms were used in combination with Radiomic features to classify recurrent and stable lesions. We found statistical evidence (p < 0.02) for 6 two-dimensional and 13 three-dimensional radiomic features. We achieved accuracies of up to 96.3% for 3D-feature based models and up to 92.6% accuracies for 2D-feature based models. 3D-feature based models achieved better performances using considerably fewer features when compared to 2D-feature based models. We concluded that Radiomics have the potential of NFPA recurrence prediction after the first surgery. Three-dimensional Radiomics have superior discrimination power to predict NFPA recurrence than two-dimensional radiomic features. Finally, the combination of Radiomics with machine-learning algorithms can offer computational models capable of non-invasive, unbiased, and quick assessment that might improve the prediction of NFPA recurrence.
Over the last years, the amount, variety, and complexity of neuroimaging data acquired in patients with brain tumors for routine clinical purposes and the resulting number of imaging parameters have substantially increased. Consequently, a timely and cost-effective evaluation of imaging data is hardly feasible without the support of methods from the field of artificial intelligence (AI). AI can facilitate and shorten various time-consuming steps in the image processing workflow, e.g., tumor segmentation, thereby optimizing productivity. Besides, the automated and computer-based analysis of imaging data may help to increase data comparability as it is independent of the experience level of the evaluating clinician. Importantly, AI offers the potential to extract new features from the routinely acquired neuroimages of brain tumor patients. In combination with patient data such as survival, molecular markers, or genomics, mathematical models can be generated that allow, for example, the prediction of treatment response or prognosis, as well as the noninvasive assessment of molecular markers. The subdiscipline of AI dealing with the computation, identification, and extraction of image features, as well as the generation of prognostic or predictive mathematical models, is termed radiomics. This review article summarizes the basics, the current workflow, and methods used in radiomics with a focus on feature-based radiomics in neuro-oncology and provides selected examples of its clinical application.