Current Medical Imaging

Background There remains a lack of methods to accurately assess the efficacy of neoadjuvant chemoradiotherapy for locally advanced rectal cancer. Objective This study aimed to investigate the value of shear-wave elastography in evaluating the treatment response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer. Materials and Methods This prospective observational study enrolled 275 patients with locally advanced rectal cancer who received neoadjuvant chemoradiotherapy during September 2021–March 2023. All patients underwent endorectal ultrasound and shear-wave elastography examination before total mesorectal excision. Clinical baseline data, endorectal ultrasound, and shear-wave elastography examination data were collected from all patients. The independent predictors of complete response were analyzed and screened, followed by the establishment of a logistic regression model. The diagnostic efficacy of the model was compared with that of radiologists. Results The results of binary multivariate logistic regression suggested that the mean elastography value of the tumor lesion acted as an independent predictor for the diagnosis of complete response [OR: 0.894 (0.816, 0.981)]. The optimal cutoff value was 14.6 kPa. The area under the receiver operating characteristic curve of the model for predicting complete response in the training and test cohorts was 0.850 and 0.824, respectively. The diagnostic accuracy of the model was significantly higher than that of radiologists (P < 0.001). Conclusion Shear-wave elastography can be used as a feasible method to evaluate the complete response of locally advanced rectal cancer after neoadjuvant chemoradiotherapy.

Background Primary cardiac tumors are rare. Most primary cardiac tumors are benign, with approximately 10.83% being malignant. We present a rare case of Primary Cardiac Angiosarcoma (PCA) with multiple metastases diagnosed using multimodality imaging, to enhance the understanding of PCA among clinicians and radiologists. Case Description A 29-year-old woman presented to our hospital with a 2-day history of chest tightness, chest pain, palpitations, and dyspnea after physical activity. Ultrasonography and Computed Tomography (CT) of the heart revealed a mass in the right atrium. Cardiac magnetic resonance imaging suggested either a large cardiac lymphoma or angiosarcoma. The histopathological diagnosis confirmed a cardiac angiosarcoma. Positron Emission Tomography-Computed Tomography (PET/CT) revealed intense 18F-fluorodeoxyglucose (18F-FDG) uptake in the right side of the heart, with a maximum standardized uptake value of 10.9. Three months later, the patient was re-examined using abdominal CT, echocardiography, and PET/CT. PET/CT revealed increased 18F-FDG uptake which had become more extensive, with multifocal metastatic nodules in both the lungs and mediastinum. The patient was lost to follow-up after being discharged on May 1, 2022. Conclusion The combined evaluation using multimodality imaging plays a vital role in determining the precise size and localization of the PCA, detecting distant metastases, and assessing patient prognosis.

Objective This study aimed to investigate the utility of ultrasonic attenuation imaging (ATI) in assessing the relationship between hepatic fat content and lipid metabolism in patients diagnosed with type 2 diabetes mellitus (T2DM) and non-alcoholic fatty liver disease (NAFLD). Methods 239 patients diagnosed with T2DM were included, with liver fat quantified using proton density fat fraction (PDFF). We analyzed the variance in ATI across various grades of fatty liver and its correlation with clinical parameters. Additionally, a receiver operating characteristic curve (ROC) was employed to evaluate the diagnostic accuracy of ATI for different degrees of fatty liver, determining optimal diagnostic thresholds while calculating sensitivity and specificity. Furthermore, we assessed the reliability of ATI and SWE in measuring liver acoustic attenuation and elastic stiffness using the intraclass correlation coefficient (ICC). Results We observed significant variations in ATI across different grades of fatty liver (p<0.001). ATI exhibited positive correlations with SWE, BMI, GLU (OH), steatosis grade, ALT, TG, and UA, while demonstrating a negative correlation with HDL-c. Notably, the correlation coefficient with steatosis grade was 0.76, indicating a strong association. The equation for the stepwise multiple linear regression model used is as follows: ATI=0.338+0.014×TG+0.052×BMI+0.001×ALT+0.113×SWE. AUROCs indicated the best cutoffs for ATI in different degrees of steatosis to be as follows: ≥ S1 = 0.665 dB·cm-1·MHz-1 (AUC = 0.857); ≥ S2 = 0.705 dB·cm-1·MHz-1 (AUC = 0.921); ≥ S3 = 0.745 dB·cm-1·MHz-1 (AUC = 0.935). The ICC values for ATI and SWE in liver-mimicking measurements exceeded 0.75 (p<0.001), signifying excellent repeatability. Conclusion The ATI could quantitatively assess the severity of fatty liver, enabling effective identification of patients suitable for liver biopsy referral.

Background Muscle infiltration of bladder cancer has become the most important index to evaluate its prognosis. Machine learning is expected to accurately identify its muscle infiltration status on images. Objective This study aimed to establish and validate a machine learning prediction model based on multi-phase contrast-enhanced CT (MCECT) for preoperatively evaluating the muscle-invasive status of bladder cancer. Methods A retrospective study was conducted on bladder cancer patients who underwent surgical resection and pathological confirmation by MCECT scans. They were randomly divided into training and testing groups at a ratio of 8:2; we used an independent external testing set for verification. The radiomics features of lesions were extracted from MCECT images and radiomics signatures were established by dual sample T-test and least absolute shrinkage selection operator (LASSO) regression. Afterward, four machine learning classifier models were established. The receiver operating characteristic (ROC) curve, calibration, and decision curve analysis were employed to evaluate the efficiency of the model and analyze diagnostic performance using accuracy, precision, sensitivity, specificity, and F1-score. Results The best predictive model was found to have logic regression as the classifier. The AUC value was 0.89 (5-fold cross-validation range 0.83-0.96) in the training group, 0.80 in the test group, and 0.87 in the external testing group. In the testing and external testing group, the diagnostic accuracy, precision, sensitivity, specificity, and F1-score were 0.759, 0.826, 0.863, 0.729, 0.785, and 0.794, 0.755, 0.953, 0.720, and 0.809, respectively. Conclusion The machine learning model showed good accuracy in predicting the muscle infiltration status of bladder cancer before surgery.

Objective This study aimed to develop and assess the performance of a YOLOv8 algorithm-aided detection model for identifying rib fractures on multiplane reconstruction (MPR) images, addressing the limitations of current AI models and the labor-intensive nature of manual diagnosis. Methods Ethical approval was obtained, and a dataset comprising 624 MPR images, confirmed by CT, was collected from three regions of Tongji Hospital between May 2020 and May 2023. The images were categorized into training, validation, and external test sets. A musculoskeletal radiologist labeled the images, and a YOLOV8n model was trained and validated using these datasets. The performance metrics, including sensitivity, specificity, accuracy, precision, recall, and F1 score, were calculated. Results The refined YOLO model demonstrated high diagnostic accuracy, with sensitivity, specificity, and accuracy rates of 96%, 97%, and 97%, respectively. The AI model significantly outperformed the radiologist in terms of diagnostic speed, with an average interpretation time of 2.02 seconds for 144 images compared to 288 seconds required by the radiologist. Conclusion The YOLOv8 algorithm shows promise in expediting the diagnosis of rib fractures on MPR images with high accuracy, potentially improving clinical efficiency and reducing the workload for radiologists. Future work will focus on enhancing the model with more feature learning capabilities and integrating it into the PACS system for human-computer interaction.

Introduction The fundamental problem with the transmission and storage of medical images is their inherent redundancy and large size necessitating higher bandwidth and a significant amount of storage space. Background Any medical image's fundamental problem is its inherent redundancy and huge size, which needs higher bandwidth for transmission of the image from one place to another and a large amount of storage space. Objectives The main objective is to enhance the compression efficiency through accurate segmentation followed by non-uniform compression through a cascade of encoders. Background Due to a sharp growth in digital imaging data, it is highly desirable to reduce the size of medical images by a significant amount, without losing clinically important diagnostic information. The majority of the compression techniques reported in the literature use either manual or traditional segmentation techniques to extract the informative parts of the images. The methods based upon non-uniform compression require accurate extraction of the informative part of the image to achieve higher compression rate. Methods This research proposes unsupervised machine learning modified fuzzy c-means (FCM) clustering-based segmentation for accurate extraction of informative parts of MR images. The spatial constraints of the images are extracted using an automated region-growing algorithm and incorporated into the objective function of FCM clustering (RG-FCM) to enhance the performance of the segmentation process even in the presence of noise. Further, informative and background parts are subjected to two separate series of encoders, with higher bit rates for the informative part of the image. Results Empirical analysis was done on the Magnetic Resonance Imaging (MRI)dataset, and experimental results indicate that the proposed technique outperforms similar existing techniques in terms of segmentation and compression metrics. Conclusion This integration of different segmentation techniques exhibits improvement in Jaccard and dice indexes, and cascade of different encoders endorse the superior performance of the proposed compression technique. The proposed technique can help in achieving higher compression of medical images without compromising clinically significant information.

Purpose MRI could be considered as a non-destructive disease diagnosis procedure, this procedure does not allow directly molecular types of cancer. Herein, we aimed to evaluate the correlation of breast MRI background parenchymal enhancement (BPE) and fibroglandular tissue (FGT) with the molecular subtypes and immunohistochemical markers of breast cancer. Methods This was a single-cross-sectional retrospective study.Fifty-six patients diagnosed with unilateral breast cancer who underwent breast MRI scans before needle biopsy or surgery were selected. The relationship between qualitative and quantitative BPE/FGT ratios and the expression of breast cancer molecular subtypes and immunohistochemical markers were evaluated in patients with breast cancer. Results Quantitative BPE (BPE%) of luminal A and luminal B was significantly lower than that of triple-negative breast cancer. There was no significant difference in the qualitative BPE/FGT between the different breast cancer subtypes. The quantitative BPE (BPE%) of estrogen receptor (ER)- negative tumors was higher than that of the ER-positive tumors, and the expression of FGT%, BPE%, and other immunohistochemical markers (human epidermal growth factor receptor-2(HER-2), progesterone receptor (PR), and Ki-67) were not significantly different. The proportion of high BPE distribution in HER-2 positive tumors was higher than that in the HER-2 negative group; however, there was no significant difference in the expression of qualitative BPE/FGT and other immunohistochemical markers (ER, PR, and Ki-67). Conclusion There were significant differences in the levels of BPE among the different molecular subtypes. Therefore, BPE may be a potential imaging biomarker for the diagnosis of the molecular subtypes of breast cancer.

Introduction Primary Squamous Cell Carcinoma of the Liver (PSCCL) is an exceptionally rare clinical entity characterized by diagnostic challenges, aggressive behavior, and poor prognosis. Globally, few studies have investigated PSCCL. Case Presentation We report the case of a 76-year-old male patient with PSCCL, detailing his clinical presentation and imaging findings, to offer insights into the preoperative diagnosis of this disease. The patient presented with upper abdominal pain that had lasted for over two weeks without any specific triggers. Laboratory tests revealed abnormal liver function. Ultrasound examination showed a large, solid, hypoechoic mass in the right anterior lobe of the liver with heterogeneous internal echoes. Color Doppler imaging detected limited blood flow signals. Contrast-enhanced Computed Tomography (CT) of the whole abdomen revealed a low-density mass with indistinct margins in the right lobe of the liver, showing uneven and progressive peripheral enhancement. Comprehensive whole-body CT, gastroscopy, and liver biopsy were performed, excluding metastatic disease in other organs. Based on the pathological findings from a percutaneous ultrasound-guided liver biopsy, the patient was diagnosed with PSCCL. Conclusion PSCCL is a rare malignancy that presents significant diagnostic difficulties, often evading easy identification through clinical and imaging examinations. This case report aims to contribute to improving the preoperative diagnosis of PSCCL.

Aim This research aims to develop and evaluate a novel health classification and severity detection system based on Vision Transformers (ViTs) for fetal ultrasound imagery. This contributes to improved precision in fetal health status detection and abnormalities with more accurate results than other traditional models. Background Amidst the other imperatives of resource-deficient developing nations, mitigating neonatal mortality rates is a challenge that demands precisionbased solutions in the era of artificial intelligence. Though the advent of machine learning models has added an optimal dimension to deal with emerging complexity in fetal ultrasound imagery, there is a call to address the huge gap in the demanded precision for prediction than the existing interpretation. Background Amidst the other imperatives of resource-deficient developing nations, mitigating neonatal mortality rates is a challenge that demands precisionbased solutions in the era of artificial intelligence. Though the advent of machine learning models has added an optimal dimension to deal with emerging complexity in fetal ultrasound imagery, there is a call to address the huge gap in the demanded precision for prediction than the existing interpretation. Objective This research strives to formulate and access a novel health classification and severity detection system based on the implementation of the Vision Transformers frameworks. This pioneering investigation represents an unparalleled exploration into the efficacy of ViTs for discerning intricate patterns within fetal ultrasonographic imagery, facilitating precise categorization of fetal well-being and prognosticating the magnitude of potential anomalies. Methodology A private and confidential dataset of 500 fetal ultrasound images has been collected from diverse hospitals. Each image has been annotated by radiologists according to two main labels: the health status of the fetus, which includes healthy, mild, moderate, or severe, and the severity of abnormalities as a continuous measure. At different levels, the dataset underwent pre-processing via distinct techniques. Then, the composite loss function Cross-Entropy has been deployed to train the optimized VIT model using the Adam algorithm. Results The classification accuracy of the proposed model is 90% for detecting the severity with an F1-score of 0.87 and MAE of 0.30. The research ascertained that the model ViT evinced a superlative efficacy for the capturing of fine-grained spatial relations in ultrasound images to produce revolutionary predictions. Conclusion These results emphasize that ViTs have the potential to revolutionize fetal health monitoring and will contribute significantly to reducing neonatal mortality by supplying clinicians with accurate and reliable predictions for early interventions. This work stands as a yardstick for further diagnostic applications using AI in fetal health care.

Background: Bronchogenic cysts are congenital cystic anomalies of the bronchus that originate from abnormal development of the bronchial tree during the embryonic period. Their common manifestation is a space-occupying lesion in the lungs or mediastinum. Common imaging modalities for detecting bronchogenic cysts include chest X-ray and chest computed tomography (CT) scans. Case Presentation: A 24-year-old female presented with an abnormal space-occupying lesion in the mediastinum detected through imaging examinations. Echocardiography revealed a cystic mass located between the descending aorta and the right pulmonary artery. A CT scan identified a low-density mass with a distinct density relative to adjacent tissues, situated near the left main bronchus. The final diagnosis of a bronchogenic cyst was established following surgical intervention and pathological examination. Conclusion: Bronchogenic cysts are rare congenital anomalies. Common clinical symptoms include chest pain, cough, and dyspnea. On standard chest radiographs and CT scans, most cysts present as homogenous water-density shadows, with the mediastinum being the most frequently affected location. The diagnosis is confirmed through pathological examination. Surgical intervention remains the most effective treatment method, typically resulting in a favorable prognosis.

Background An effective preoperative diagnosis between minute pulmonary meningothelial-like nodules (MPMNs) and adenocarcinoma in situ (AIS) can provide clinicians with appropriate treatment strategies Objective This study aimed to differentiate MPMNs from AIS via computed tomography (CT) radiomics approaches. Methods Clinical and imaging data from fifty-one patients diagnosed with MPMNs and 55 patients diagnosed with AIS were collected from Jiangsu Province Hospital and Nanjing First Hospital from January 2016 to December 2022. All patients underwent chest CT scans before surgery. All CT images were segmented with ITK-SNAP software, and the radiomics features were further extracted with the Python PyRadiomics package. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to select the optimal radiomics features for the construction of the model. The ROC curve was used to evaluate the diagnostic efficacy of the model. Results After feature reduction and selection, 16 radiomics features were selected to construct the radiomics model. In the test set, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the k-nearest neighbor model were 87.5%, 88.9%, 96.9%, 77.8%, and 88.5%, respectively, and the AUC of the ROC curve was 0.969 (95% CI: 0.72-1.00). Conclusion The CT radiomics model has exhibited high diagnostic value in the differential diagnosis between MPMNs and AIS.

Background With the rapid development of computer technology, the application of digital technology to the display and processing of medical images has become a common concern. In recent years, oral digital imaging technology has received more and more attention. Objective This paper mainly aims at the ODIS-1 oral digital imaging system to analyze and study the image quality and image aims at the ODIS-1 oral digital imaging system to analyze and study the image quality and processing technology, of which X-ray imaging is indispensable. Methods In this paper, the ODIS-1 digital scanning technology is used to detect different types of dental tissues, and its application in diagnosing oral diseases is evaluated. This paper takes 320 inpatients as the research object and uses Kodak dental film to compare the image quality of different positions. Results It is found that there is no significant difference in image quality between the maxillary anterior teeth and mandibular anterior teeth and the maxillary posterior teeth and mandibular posterior teeth (P>0.05); the image quality of maxillary anterior teeth, mandibular anterior teeth, and maxillary posterior teeth and mandibular teeth are significantly different (P<0.05); among the various positions of the ODIS-1 oral digital imaging system, the image quality of the anterior teeth area is the best, while the image quality of the maxillary posterior teeth area is the worst. Conclusion However, the system has a variety of image post-processing functions, which can adjust the brightness and contrast of the image arbitrarily, select the area of interest in the image according to the detection requirements, and perform local amplification, edge enhancement, and other technologies to make the image achieve the best effect. In the case of poor image quality, the clarity of the image can be further improved through image post-processing and analysis.

Objective We examined the effectiveness of integrating three-dimensional (3D) visualization reconstruction technology with Problem-Based Learning (PBL) in the clinical teaching of resident physicians focusing on pheochromocytoma. Methods Fifty resident physicians specializing in urology at Peking Union Medical College Hospital were randomly divided into two groups over the period spanning January 2022 to January 2024: an experimental group and a control group. The experimental group underwent instruction utilizing a pedagogical approach that integrated 3D visualization reconstruction technology with PBL, while the control group used a traditional teaching model. A comparative analysis of examination performance and teaching satisfaction between both groups of resident physicians was conducted to assess the efficacy of the integrated 3D visualization and PBL teaching methods in clinical instruction. Results The experimental group demonstrated superior performance in both theoretical assessment and clinical skills evaluation, along with heightened levels of teaching satisfaction compared to the control group, with statistically significant differences (p < 0.05). Additionally, the experimental group exhibited markedly higher scores in both theoretical examinations and practical assessments compared to their counterparts in the control group (p < 0.05). The results of theoretical examinations for the experimental group and the control group were 92.15±3.22 and 81.09±4.46, respectively (< 0.0001). The results of practical examinations for the experimental group and the control group were 90.17±3.48 and 70.75±5.11, respectively (< 0.0001). Conclusion In the clinical teaching of training resident physicians specializing in urology for the management of pheochromocytoma, the integration of 3D visualization reconstruction technology with the PBL method significantly enhanced the teaching efficacy, improving both the quality of instruction and the level of satisfaction among participants.

Aims In the dynamic landscape of healthcare, integrating Artificial Intelligence paradigms has become essential for sophisticated brain image analysis, especially in tumor detection. This research addresses the need for heightened learning precision in handling sensitive medical images by introducing the Fragmented Segment Detection Technique. Background The ever-evolving healthcare landscape demands advanced methods for brain image analysis, particularly in detecting tumors. This study responds to this need by introducing the Feature Segmentation and Detection Technique (FSDT), a novel approach designed to identify brain tumors precisely using MRI images. The focus is on enhancing detection accuracy, even for diminutive tumors. The primary objective of this study is to introduce and evaluate the efficacy of FSDT in identifying and sizing brain tumors through advanced medical image analysis. The proposed technique utilizes cross-section segmentation and pixel distribution analysis to improve detection accuracy, particularly in size-based tumor detection scenarios. Methods The proposed technique commences by fragmenting the input through cross-section segmentation, enabling meticulous separation of pixel distribution in various sections. A Convolutional Neural Network then independently operates sequentially on the minimum and maximum representations. The segmented cross-section feature, exhibiting maximum accuracy, is employed in the neural network training process. Finetuning of the neural network optimizes feature distribution and pixel arrangements, specifically in consecutive size-based tumor detection scenarios. Results The FSDT employs cross-sectional segmentation and pixel distribution analysis to enhance detection accuracy by leveraging a diverse dataset encompassing central nervous system CNS tumors. Comparative evaluations against existing methods, including ERV-Net, MRCNN, and ENet- B0, reveal FSDT's superiority in accuracy, training rate, analysis ratio, precision, recall, F1-score, and computational efficiency. The proposed technique demonstrates a remarkable 10.45% increase in accuracy, 14.12% in training rate, and a 10.78% reduction in analysis time. Conclusion The proposed FSDT emerges as a promising solution for advancing the accurate identification and sizing of brain tumors through cutting-edge medical image analysis. The demonstrated improvements in accuracy, training rate, and analysis time showcase its potential for effective realworld healthcare applications.

Background The basal ganglia area is a frequent site of stroke, which commonly causes intricate functional impairments. This study aims to uncover disparities in static and dynamic functional connectivity (FC) of the brain in patients afflicted with left-sided basal ganglia stroke (L-BGS) and right-sided basal ganglia region stroke (R-BGS), furthermore scrutinising the mechanism behind the lateralisation of the stroke. Methods A total of 23 patients with L-BGS and 20 patients with R-BGS were recruited, alongside 20 healthy control subjects. Resting-state functional magnetic resonance imaging and sliding window techniques were employed to conduct static and dynamic FC analyses on both patient groups and controls, which can enable a more refined evaluation of the variations in neural signals. Results The inter-network connectivity analysis showed significant changes only in the L-BGS patient group (p < 0.05). The R-BGS group showed increased connectivity in the auditory and posterior visual networks, while the L-BGS group showed reduced connectivity. In dynamic connectivity analyses, the L-BGS group exhibited greater positive network connectivity reorganization. Conclusion Within one month of stroke onset, the L-BGS group showed a more pronounced impairment of inter-network connectivity, alongside enhanced FC compensatory changes of a positive nature. Differential changes in the two patient groups may provide useful information for individualized rehabilitation strategies.

Objective Glaucoma is a leading cause of irreversible visual impairment and blindness worldwide, primarily linked to increased intraocular pressure (IOP). Early detection is essential to prevent further visual impairment, yet the manual diagnosis of retinal fundus images (RFIs) is both time-consuming and inefficient. Although automated methods for glaucoma detection (GD) exist, they often rely on individual models with manually optimized hyperparameters. This study aims to address these limitations by proposing an ensemble-based approach that integrates multiple deep learning (DL) models with automated hyperparameter optimization, with the goal of improving diagnostic accuracy and enhancing model generalization for practical clinical applications. Materials and Methods The RFIs used in this study were sourced from two publicly available datasets (ACRIMA and ORIGA), consisting of a total of 1,355 images for GD. Our method combines a custom Multi-branch convolutional neural network (CNN), pretrained MobileNet, and DenseNet201 to extract complementary features from RFIs. Moreover, to optimize model performance, we apply Bayesian Optimization (BO) for automated hyperparameter tuning, eliminating the need for manual adjustments. The predictions from these models are then combined using a Dirichlet-based Weighted Average Ensemble (Dirichlet-WAE), which adaptively adjusts the weight of each model based on its performance. Results The proposed ensemble model demonstrated state-of-the-art performance, achieving an accuracy (ACC) of 95.09%, precision (PREC) of 95.51%, sensitivity (SEN) of 94.55%, an F1-score (F1) of 94.94%, and an area under the curve (AUC) of 0.9854. The innovative Dirichlet-based WAE substantially reduced the false positive rate, enhancing diagnostic reliability for GD. When compared to individual models, the ensemble method consistently outperformed across all evaluation metrics, underscoring its robustness and potential scalability for clinical applications. Conclusion The integration of ensemble learning (EL) and advanced optimization techniques significantly improved the ACC of GD in RFIs. The enhanced WAE method proved to be a critical factor in achieving well-balanced and highly accurate diagnostic performance, underscoring the importance of EL in medical diagnosis.

Objective An ultrasound-based radiomics Machine Learning Model (ML) was utilized to assess non-invasively the conditions of diabetic nephropathy and non-diabetic renal disease in diabetic patients. Methods A retrospective examination was conducted on 166 diabetic patients who had undergone renal biopsies guided by ultrasound, with the group comprising 114 individuals diagnosed with diabetic nephropathy and 52 with non-diabetic renal disease. The participants were randomly divided into the training set and the testing set (7:3). Following the extraction of radiomics features from the renal ultrasound images, a univariate analysis was conducted, and the Least Absolute Shrinkage And Selection Operator (LASSO) algorithm was applied to select the most significant features. Three ML algorithms were applied to construct the prediction models. Subsequently, the patients' clinical characteristics were evaluated through both univariate and multivariate logistic regression analyses, which facilitated the development of a clinical model, following a clinical radiomics model was formulated, integrating the radiomics scores (Radscore), along with the independent clinical variables identified through the screening process. The diagnostic performance of the three models constructed was evaluated using the receiver operating characteristic (ROC) curve analysis. Results Among the three radiomics ML models, the logistic regression (LR) model achieved the best performance, with the area under the curve (AUC) values of 0.872 (95%CI, 0.800-0.944) and 0.836 (95%CI, 0.716-0.957) for the training set and the testing set, respectively. The decision curve analysis (DCA) verified the clinical practicability of the ML model. Within the same testing set, the AUC of the clinical model was 0.761 (95%CI, 0.606-0.916). The nomogram model based on clinical features plus Radscore showed the best discrimination, with an AUC value of 0.881 (95%CI, 0.779-0.982), which was better than that of the single clinical model and the radiomics model. Conclusion The ML model of radiomics based on ultrasound images has potential value in the non-invasive differential diagnosis of patients with diabetic nephropathy. The nomogram constructed based on rad score and clinical features could effectively distinguish DN from NDRD.

Background Lipomas represent a rare benign etiology of intussusception in adults, affecting both the small intestine and the colon. Diagnosing intussusception in adults can be challenging, and there are no reports on the use of positron emission tomography/CT (PET/CT) in the diagnosis of lipoma-induced intussusception. This study aimed to preliminarily explore the potential diagnostic utility of 18F-FDG PET/CT in the diagnosis of intussusception caused by lipomas. Methods We conducted a retrospective review of the clinical characteristics and imaging findings of three patients diagnosed with lipoma-induced intussusception using 18F-FDG PET/CT from 2019 to 2023 at our hospital. Results The three cases presented with diverse clinical presentations and were diagnosed based on PET/CT imaging. Surgical confirmation was obtained in two cases. Lipomas were identified in both the small intestine and the colon, with one case displaying increased metabolic activity on FDG uptake, suggesting a possible link between FDG uptake and clinical severity. Conclusion Lipoma is a benign cause of intussusception that can occur in both the small intestine and the colon. The symptoms of adult intussusception are often atypical and variable. Imaging modalities, particularly PET/CT, are instrumental in diagnosing intussusception due to lipomas, differentiating between benign and malignant causes, and assessing the severity to inform treatment strategies.

Purpose The study aimed to investigate the association of CT-relevant skeletal muscle parameters, such as sarcopenia and myosteatosis, with survival outcomes in patients receiving chemotherapy for unresectable pancreatic ductal adenocarcinoma (PDAC). Methods In this retrospective analysis, patients who began chemotherapy for unresectable PDAC were included. Sarcopenia and myosteatosis were assessed on pretreatment CT at the L3 level by skeletal muscle index and mean muscle attenuation with predefined cutoff values. The Cox proportional hazards model was used to analyze the factors associated with progression-free survival (PFS) and overall survival (OS). Results A total of 150 patients were enrolled. Compared to patients without sarcopenia, patients with sarcopenia had significantly worse PFS (p=0.003) and OS (p<0.001). Patients with myosteatosis had significantly worse PFS (p=0.01) and OS (p=0.002) compared to those without myosteatosis. In multivariate analysis, after adjusting for age, sex, tumor size, location, treatment modality, smoking, drinking, underlying diseases, and partial laboratory tests, sarcopenia remained an independent predictor of PFS (p=0.006) and OS (p<0.001). Myosteatosis remained an independent predictor of OS (p=0.008), but not of PFS. Conclusion Sarcopenia and myosteatosis are independent prognostic factors for patients with unresectable pancreatic ductal adenocarcinoma after chemotherapy.

Background/Objective Brain tumor is characterized by its aggressive nature and low survival rate and therefore, it is regarded as one of the deadliest diseases. Thus, misdiagnosis or miss-classification of brain tumors can lead to miss-treatment or incorrect treatment and reduce survival chances. Therefore, there is a need to develop a technique that can identify and detect brain tumors at early stages. Methods Here, we proposed a framework titled I-Brainer which is an Artificial Intelligence/Internet of Things (AI/IoT)-powered classification of MRI into 4 classes. We employed a Br35H+SARTAJ brain MRI dataset which contains 7023 total images including no tumor, pituitary, meningioma, and glioma. To accurately classify MRI into 4 classes, we developed the LeNet model from scratch, and implemented 2 pre-trained models which include EfficientNet and ResNet-50 as well as feature extraction of these models coupled with 2 Machine Learning (ML) classifiers namely; k- Nearest Neighbours (KNN) and Support Vector Machine (SVM). Results Evaluation and comparison of the performance of the 3 models have shown that ResNet-50 achieved the best result in terms of AUC (99%) and ResNet-50-KNN ranked higher in terms of accuracy (94%) on the testing set. Conclusion This framework can be harnessed by patients residing in remote areas and as a confirmatory approach for medical experts.

Introduction The purpose of this study was to investigate the morphology and distribution characteristics of fat globules in osteomyelitis on magnetic resonance imaging (MRI). Materials and Methods Patients with pathologically-confirmed osteomyelitis and MRI scans were retrospectively enrolled, and fat globules on the MRI images were analyzed. Results Among 103 patients with non-traumatic osteomyelitis, 75 were fat globule negative and 28 were positive. There was no statistically significant difference in age and gender between patients with and without fat globules (p>0.05). The inflammatory indicators (CRP, ESR, WBC, and NEUT) in the fat globule positive group were significantly higher (p<0.05) than those in the negative group. The lesions were mainly located in the long bones of the limbs in patients with positive fat globules. Twenty-eight patients (27.2% or 28/103) were detected to have fat globules on MRI images, including 20 males (71%) and 8 females (29%) aged 5-64 years (mean 16 years). The time from onset to MRI examination was 8 days to 4 months. The location of fat globules was in the tibia in 10 patients (35.7%), femur in 8 (28.6%), humerus in 4 (14.3%), radius in 2 (7.1%), ulna in 1 (3.6%), calcaneus in 1 (3.6%), sacrum in 1 (3.6%), and fibula in 1 patient (3.6%). On MRI imaging, 28 cases (100%) showed widely distributed patches or tortuous and sinuous abnormal signals in the bone marrow. In 25 cases (89.2%), a grid-like abnormal signal was found in the subcutaneous soft tissue. In 21 patients (75%), pus was found in the adjacent extraosseous soft tissues. Among 28 patients with fat globules, 17 patients (60.7%) had fat globules only in the adjacent extraosseous soft tissue, 6 patients (21.4%) had only intraosseous fat globules [including 5 cases with halo signs around the fat globules and 1 case (3.6%) with fat globules located at the edge of the pus cavity inside the bone without a halo sign], and 5 patients (17.8%) had both intraosseous and extraosseous fat globules. Of 6 patients (21.4% or 6/28) with liquid levels, the liquid level appeared outside the bone. Conclusion The appearance of fat globules on MRI in patients with osteomyelitis indicates severe infection. Fat globules of osteomyelitis may present with diverse shapes inside and outside the bone marrow as one of the MRI signs of osteomyelitis, with a probability of approximately 27.2%. They have high specificity in diagnosing osteomyelitis and can be used for diagnosis and differential diagnosis.

Aims Studies specifically examining the sonographic features of juvenile fibroadenoma in the pediatric population have not been documented. We aimed to analyze sonograms of juvenile fibroadenoma in children. Subjects and Methods Patients aged ≤ 18 years who underwent breast ultrasound examinations at our department and had pathologically proven juvenile fibroadenoma from September 2002 to January 2022 were included in this study. Demographic data, clinical findings, and sonograms were retrospectively analyzed. Patients were further divided into the puberty and post-puberty subgroups, and their results were compared. Results A total of 24 girls aged 10-18 years with 27 masses diagnosed as juvenile fibroadenomas were identified. The diameter of the masses averaged 5.8 ± 3.3 cm, with a range of 1.5-13.6 cm. Twenty-one (87.5%) patients had a single mass and 3 had double lesions. Over 80% of the lesions were oval-shaped and encapsulated with circumscribed margins and parallel orientation. All masses showed internal hypoechogenicity, either uniform or heterogeneous. For masses that had a diameter > 5 cm, screening with high-frequency transducers revealed no posterior acoustic features or posterior shadowing. However, these features changed to posterior acoustic enhancement when the masses were re-evaluated using low-frequency transducers. Ultrasonic color Doppler showed blood flow in 24 (88.9%) masses. There were no significant differences in the incidence and sonographic features between the two subgroups. Conclusion Most juvenile fibroadenomas in children are oval, circumscribed, encapsulated masses with detectable blood flow. All juvenile fibroadenomas presented in this study exhibit internal hypoechogenicity with no posterior acoustic shadowing detected in any cases. Our findings suggest that screening with low-frequency transducers should be performed for a mass that has a diameter > 5 cm.

Objective This study aimed to explore the diagnostic value of multiorgan (heart, lungs, blood vessels) point-of-care ultrasound (PoCUS) in patients with high-risk and medium-to-low-risk pulmonary embolism (PE). Methods Clinical data of 92 patients with suspected PE, admitted to Hangzhou TCM Hospital affiliated with Zhejiang Chinese Medical University from July 2021 to June 2023, were retrospectively analyzed. According to hemodynamic status, patients were divided into the high-risk (n=28) and the medium-to-low-risk groups (n=64). Using computed tomography (CT) and pulmonary angiography (CTPA) as the gold standard, all patients underwent multiorgan PoCUS examination. The sensitivity, specificity, and accuracy of different methods for diagnosing PE, as well as the time difference between multiorgan PoCUS examination and CTPA, were compared. Differences in measurement values of relevant indicators in all groups were analyzed. Results In the high-risk group of patients, CTPA identified 15 cases of PE. In contrast, the PoCUS examination confirmed PE diagnosis in 14 cases (true positive), while 10 cases were diagnosed as true negative, one case as false negative, and three cases as false positive. In the medium-to-low-risk group, CTPA identified 50 patients with PE, while multiorgan PoCUS confirmed PE diagnosis in 33 cases (true positive), and identified 9 true negative, 17 false negative, and 5 false positive PE cases. Kappa test of the consistency between the results of multiorgan PoCUS and CTPA showed that multiorgan PoCUS had higher sensitivity, negative predictive value, and accuracy in the high-risk group compared to the medium-tolow- risk group (p<0.05). Cohen's Kappa value of the high-risk group was 0.710, indicating moderate consistency between PoCUS and CTPA results, while Cohen's Kappa value of 0.231 for the medium and low-risk group indicated poor consistency. There was a significant difference in ultrasound parameters between the high-risk and the medium-to-low-risk group (p<0.05). The time required for multiorgan PoCUS in both groups was significantly shorter than that for the CTPA. There was no significant difference in the time required for PoCUS between the two groups (p>0.05). Conclusion Multiorgan PoCUS has been found to have higher sensitivity and accuracy in diagnosing patients with high-risk PE compared to those with medium-to-low-risk PE, and a shorter imaging time compared to CTPA.

Objective This study aimed to compare automated three-dimensional Intrapulmonary Vessel Volume (IPVV) differences between lung and mediastinal windows in healthy individuals using quantitative measurements obtained from chest Computed Tomography (CT) plain scans. Methods A total of 258 participants (aged 21–83 years) with negative chest CT scans from routine physical examinations conducted between January to November 2023 were retrospectively enrolled. For each healthy participant, an algorithm was used to automatically extract total lung IPVVs as well as IPVVs for vessels of specific diameter. Differences in IPVVs were then compared between those extracted using the lung window and those extracted using the mediastinal window. Results The IPVVs for the entire lung, intrapulmonary arteries, intrapulmonary veins, and small pulmonary vessels (categorized by different diameters) extracted from the lung window were significantly higher than those extracted from the mediastinal window (p<0.01). No significant sex-based differences in IPVV were observed for pulmonary arteries and veins with diameters between 0.8 and 1.6 mm, as well as pulmonary veins with diameters between 2.4 and 3.2 mm. However, in pulmonary arteries and veins with diameters between 1.6 and 2.4 mm, females had significantly higher IPVVs than males. In all other cases, IPVVs were larger in males than in females. Conclusion This method of automatic IPVV extraction and quantitative assessment has been proven to be feasible. Automated IPVV expression effectively identified morphological characteristics of intrapulmonary vessels. The study has concluded IPVVs extracted from the lung window to be generally larger than those extracted from the mediastinal window.

Introduction: Screening ultrasound proves to be remarkably beneficial in pre-hospital settings, particularly in geographically remote areas with technological constraints and no medical specialties. Urological pathology has a high frequency of occurrence in the emergency department and is part of the wide range of occurrences that can benefit from this ultrasound screening as a clinical guide for patients. Case Presentation: In this case, a patient experiencing lower abdominal pain and symptoms of renal colic sought assistance at a basic emergency service facility. Utilizing a renal screening ultrasound executed by a sonographer, the clinical team identified images indicative of a significant bladder calculus. Subsequently, the patient was referred to a referral hospital for a comprehensive evaluation by medical specialties. Conclusion: The images obtained in both health units exhibited congruence, indicating that the screening ultrasound, while not intended to replace the specialized orthodox ultrasound executed by a radiologist, served as a crucial tool for diagnostic presumption, providing consistency in clinical decision-making for referring patients. This capability allowed emergency physicians to promptly transfer a patient requiring urgent further investigation to a referral hospital with compelling and substantiated data. This shift in the approach to patient triage in a remote setting could enhance patient safety.