No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
ARTIFICIAL INTELLIGENCE IN PATHOLOGY: PRESENT AND FUTURE
Abstract
Artificial intelligence is the future and its use in pathology can create a tremendous impact on health care in different aspects.Its use is being initiated in the field of pathology and is on the rise with a increasing acceptance.Pathology services will undergo a paradigm shift due to the implementation of computational pathology and the use of tools based on AI, which would increase the effectiveness and would be able to satisfy the demands of the precision medicine age. Moving AI models from research to clinical applications has been sluggish, notstanding their success. There may be too much distance and neglect between the clinical setting and self-contained research. The merge of AI technologies into pathology has significantly impacted diagnostic precision and speed. Digital pathology platforms equipped with machine learning algorithms enable pathologists to analyze large volumes of histological images with enhanced accuracy. These systems have demonstrated remarkable capabilities in identifying subtle morphological features indicative of various diseases such as cancerous lesions or infectious conditions. Moreover, AI-driven image analysis tools can assist pathologists in differentiating between benign and malignant tumors by quantifying cellular characteristics beyond human visual perception. Furthermore,AI-powered predictive models have the potential to refine prognostic assessments based on pathological findings. By leveraging vast datasets encompassing clinical outcomes and molecular profiles associated with specific diseases or tissue alterations, these algorithms can generate more tailored predictions regarding disease progression or treatment responsiveness. Through this approach,pathologists can offer more precise guidance on patient management while harnessing valuable insights from diverse sources for optimizing therapeutic intervention.The convergence of advanced image recognition techniques,virtual microscopy,and genomics data analysis could enable comprehensive profiling of individual disease phenotypes at an unprecedented level.In conclusion,AI technologies have already begun reshaping the landscapeof modern pathologypracticesthrough improved diagnostic capabilities,enriched prognostic insights,and envisaged pathways towards personalized healthcare delivery.The seamless integrationofAI-driven solutionsinto daily laboratory workflowswill undeniably propelpathologyintoa new era marked by heightened efficiencyand unparalleled precisionin diagnosticsand therapeuticsupport.
ResearchGate has not been able to resolve any citations for this publication.
Pathology departments must rise to new staffing challenges caused by the coronavirus disease-19 pandemic and may need to work more flexibly for the foreseeable future. In light of this, many pathologists and departments are considering the merits of remote or home reporting of digital cases. While some individuals have experience of this, little work has been done to determine optimum conditions for home reporting, including technical and training considerations. In this publication produced in response to the pandemic, we provide information regarding risk assessment of home reporting of digital slides, summarize available information on specifications for home reporting computing equipment, and share access to a novel point-of-use quality assurance tool for assessing the suitability of home reporting screens for digital slide diagnosis. We hope this study provides a useful starting point and some practical guidance in a difficult time. This study forms the basis of the guidance issued by the Royal College of Pathologists, available at:https://www.rcpath.org/uploads/assets/626ead77-d7dd-42e1-949988e43dc84c97/RCPath-guidance-for-remote-digital-pathology.pdf.
Breast cancer is the most common cancer and second leading cause of cancer-related death worldwide. The mainstay of breast cancer workup is histopathological diagnosis - which guides therapy and prognosis. However, emerging knowledge about the complex nature of cancer and the availability of tailored therapies have exposed opportunities for improvements in diagnostic precision. In parallel, advances in artificial intelligence (AI) along with the growing digitization of pathology slides for the primary diagnosis are a promising approach to meet the demand for more accurate detection, classification and prediction of behaviour of breast tumours. In this article, we cover the current and prospective uses of AI in digital pathology for breast cancer, review the basics of digital pathology and AI, and outline outstanding challenges in the field.
Abstract Background Breast ductal carcinoma in situ (DCIS) represent approximately 20% of screen-detected breast cancers. The overall risk for DCIS patients treated with breast-conserving surgery stems almost exclusively from local recurrence. Although a mastectomy or adjuvant radiation can reduce recurrence risk, there are significant concerns regarding patient over-/under-treatment. Current clinicopathological markers are insufficient to accurately assess the recurrence risk. To address this issue, we developed a novel machine learning (ML) pipeline to predict risk of ipsilateral recurrence using digitized whole slide images (WSI) and clinicopathologic long-term outcome data from a retrospectively collected cohort of DCIS patients (n = 344) treated with lumpectomy at Nottingham University Hospital, UK. Methods The cohort was split case-wise into training (n = 159, 31 with 10-year recurrence) and validation (n = 185, 26 with 10-year recurrence) sets. The sections from primary tumors were stained with H&E, then digitized and analyzed by the pipeline. In the first step, a classifier trained manually by pathologists was applied to digital slides to annotate the areas of stroma, normal/benign ducts, cancer ducts, dense lymphocyte region, and blood vessels. In the second step, a recurrence risk classifier was trained on eight select architectural and spatial organization tissue features from the annotated areas to predict recurrence risk. Results The recurrence classifier significantly predicted the 10-year recurrence risk in the training [hazard ratio (HR) = 11.6; 95% confidence interval (CI) 5.3–25.3, accuracy (Acc) = 0.87, sensitivity (Sn) = 0.71, and specificity (Sp) = 0.91] and independent validation [HR = 6.39 (95% CI 3.0–13.8), p
In this White Paper, experts from the Digital Pathology Association (DPA) define terminology and concepts in the emerging field of computational pathology, with a focus on its application to histology images analyzed together with their associated patient data to extract information. This review offers a historical perspective and describes the potential clinical benefits from research and applications in this field, as well as significant obstacles to adoption. Best practices for implementing computational pathology workflows are presented. These include infrastructure considerations, acquisition of training data, quality assessments, as well as regulatory, ethical and cyber‐security concerns. Recommendations are provided for regulators, vendors, and computational pathology practitioners in order to facilitate progress in the field. This article is protected by copyright. All rights reserved.
Background: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades.
Methods: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network.
Results: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques.
Conclusions: The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.
Automatic detection of lymphocyte in H&E images is a necessary first step in lots of tissue image analysis algorithms. An accurate and robust automated lymphocyte detection approach is of great importance in both computer science and clinical studies. Most of the existing approaches for lymphocyte detection are based on traditional image processing algorithms and/or classic machine learning methods. In the recent years, deep learning techniques have fundamentally transformed the way that a computer interprets images and have become a matchless solution in various pattern recognition problems. In this work, we design a new deep neural network model which extends the fully convolutional network by combining the ideas in several recent techniques, such as shortcut links. Also, we design a new training scheme taking the prior knowledge about lymphocytes into consideration. The training scheme not only efficiently exploits the limited amount of free-form annotations from pathologists, but also naturally supports efficient fine-tuning. As a consequence, our model has the potential of self-improvement by leveraging the errors collected during real applications. Our experiments show that our deep neural network model achieves good performance in the images of different staining conditions or different types of tissues.
Background:
Deep learning (DL) is a representation learning approach ideally suited for image analysis challenges in digital pathology (DP). The variety of image analysis tasks in the context of DP includes detection and counting (e.g., mitotic events), segmentation (e.g., nuclei), and tissue classification (e.g., cancerous vs. non-cancerous). Unfortunately, issues with slide preparation, variations in staining and scanning across sites, and vendor platforms, as well as biological variance, such as the presentation of different grades of disease, make these image analysis tasks particularly challenging. Traditional approaches, wherein domain-specific cues are manually identified and developed into task-specific “handcrafted” features, can require extensive tuning to accommodate these variances. However, DL takes a more domain agnostic approach combining both feature discovery and implementation to maximally discriminate between the classes of interest. While DL approaches have performed well in a few DP related image analysis tasks, such as detection and tissue classification, the currently available open source tools and tutorials do not provide guidance on challenges such as (a) selecting appropriate magnification, (b) managing errors in annotations in the training (or learning) dataset, and (c) identifying a suitable training set containing information rich exemplars. These foundational concepts, which are needed to successfully translate the DL paradigm to DP tasks, are non-trivial for (i) DL experts with minimal digital histology experience, and (ii) DP and image processing experts with minimal DL experience, to derive on their own, thus meriting a dedicated tutorial.
Aims:
This paper investigates these concepts through seven unique DP tasks as use cases to elucidate techniques needed to produce comparable, and in many cases, superior to results from the state-of-the-art hand-crafted feature-based classification approaches.
Results:
Specifically, in this tutorial on DL for DP image analysis, we show how an open source framework (Caffe), with a singular network architecture, can be used to address: (a) nuclei segmentation (F-score of 0.83 across 12,000 nuclei), (b) epithelium segmentation (F-score of 0.84 across 1735 regions), (c) tubule segmentation (F-score of 0.83 from 795 tubules), (d) lymphocyte detection (F-score of 0.90 across 3064 lymphocytes), (e) mitosis detection (F-score of 0.53 across 550 mitotic events), (f) invasive ductal carcinoma detection (F-score of 0.7648 on 50 k testing patches), and (g) lymphoma classification (classification accuracy of 0.97 across 374 images).
Conclusion:
This paper represents the largest comprehensive study of DL approaches in DP to date, with over 1200 DP images used during evaluation. The supplemental online material that accompanies this paper consists of step-by-step instructions for the usage of the supplied source code, trained models, and input data.
There is a need to improve prediction of response to chemotherapy in breast cancer in order to improve clinical management and this may be achieved by harnessing computational metrics of tissue pathology. We investigated the association between quantitative image metrics derived from computational analysis of digital pathology slides and response to chemotherapy in women with breast cancer who received neoadjuvant chemotherapy.
We digitised tissue sections of both diagnostic and surgical samples of breast tumours from 768 patients enrolled in the Neo-tAnGo randomized controlled trial. We subjected digital images to systematic analysis optimised for detection of single cells. Machine-learning methods were used to classify cells as cancer, stromal or lymphocyte and we computed estimates of absolute numbers, relative fractions and cell densities using these data. Pathological complete response (pCR), a histological indicator of chemotherapy response, was the primary endpoint. Fifteen image metrics were tested for their association with pCR using univariate and multivariate logistic regression.
Median lymphocyte density proved most strongly associated with pCR on univariate analysis (OR 4.46, 95 % CI 2.34-8.50, p < 0.0001; observations = 614) and on multivariate analysis (OR 2.42, 95 % CI 1.08-5.40, p = 0.03; observations = 406) after adjustment for clinical factors. Further exploratory analyses revealed that in approximately one quarter of cases there was an increase in lymphocyte density in the tumour removed at surgery compared to diagnostic biopsies. A reduction in lymphocyte density at surgery was strongly associated with pCR (OR 0.28, 95 % CI 0.17-0.47, p < 0.0001; observations = 553).
A data-driven analysis of computational pathology reveals lymphocyte density as an independent predictor of pCR. Paradoxically an increase in lymphocyte density, following exposure to chemotherapy, is associated with a lack of pCR. Computational pathology can provide objective, quantitative and reproducible tissue metrics and represents a viable means of outcome prediction in breast cancer.
Trial registration
ClinicalTrials.gov NCT00070278; 03/10/2003
Context:
We define the scope and needs within the new discipline of computational pathology, a discipline critical to the future of both the practice of pathology and, more broadly, medical practice in general.
Objective:
To define the scope and needs of computational pathology.
Data sources:
A meeting was convened in Boston, Massachusetts, in July 2014 prior to the annual Association of Pathology Chairs meeting, and it was attended by a variety of pathologists, including individuals highly invested in pathology informatics as well as chairs of pathology departments.
Conclusions:
The meeting made recommendations to promote computational pathology, including clearly defining the field and articulating its value propositions; asserting that the value propositions for health care systems must include means to incorporate robust computational approaches to implement data-driven methods that aid in guiding individual and population health care; leveraging computational pathology as a center for data interpretation in modern health care systems; stating that realizing the value proposition will require working with institutional administrations, other departments, and pathology colleagues; declaring that a robust pipeline should be fostered that trains and develops future computational pathologists, for those with both pathology and nonpathology backgrounds; and deciding that computational pathology should serve as a hub for data-related research in health care systems. The dissemination of these recommendations to pathology and bioinformatics departments should help facilitate the development of computational pathology.
Numerous studies have shown the prognostic significance of nuclear morphometry in breast cancer patients. Wide acceptance of morphometric methods has, however, been hampered by the tedious and time consuming nature of the manual segmentation of nuclei and the lack of equipment for high throughput digitization of slides. Recently, whole slide imaging became more affordable and widely available, making fully digital pathology archives feasible. In this study, we employ an automatic nuclei segmentation algorithm to extract nuclear morphometry features related to size and we analyze their prognostic value in male breast cancer. The study population comprised 101 male breast cancer patients for whom survival data was available (median follow-up of 5.7 years). Automatic segmentation was performed on digitized tissue microarray slides, and for each patient, the mean nuclear area and the standard deviation of the nuclear area were calculated. In univariate survival analysis, a significant difference was found between patients with low and high mean nuclear area (P=0.022), while nuclear atypia score did not provide prognostic value. In Cox regression, mean nuclear area had independent additional prognostic value (P=0.032) to tumor size and tubule formation. In conclusion, we present an automatic method for nuclear morphometry and its application in male breast cancer prognosis. The automatically extracted mean nuclear area proved to be a significant prognostic indicator. With the increasing availability of slide scanning equipment in pathology labs, these kinds of quantitative approaches can be easily integrated in the workflow of routine pathology practice.Modern Pathology advance online publication, 17 August 2012; doi:10.1038/modpathol.2012.126.
The COST Action IC0604 "Telepathology Network in Europe" (EURO-TELEPATH) is an initiative of the COST (European Cooperation in the field of Scientific and Technical Research) framework, supported by the Seventh Framework Programme for research and technological development (FP7), of the European Union will be running from 2007 to 2011 and is aimed to coordinate research efforts to develop the most adequate technological framework for the management of multimedia electronic healthcare records (data and images) applied to Anatomic Pathology. Sixteen countries are participating in EURO-TELEPATH. Activities are organized in four Working Groups (WGs): WG1 - Pathology Business Modeling, WG2 - Informatics Standards in Pathology, WG3 - Images: Analysis, Processing, Retrieval and Management, and WG4 - Technology and Automation in Pathology. During the first year of work, the collaboration between software engineers, computer scientists, pathologists and other clinicians has been essential to detect three main areas of interest in digital pathology research: virtual microscopy scanning solutions, health informatics standards, and image processing and analysis. Research in these areas is essential to a correct approach to telepathology, including primary diagnosis, and secondary or teleconsultation services. Managing microscopic pathology images (virtual slides) is a challenge to existing information systems, mainly due to its large size, large number, and complex interpretation. Regarding interoperability, the integration of pathology reports and images into eHealth records is an essential objective that research groups should consider. Promoting participation in standards bodies (DICOM, IHE, HL7, IHTSDO) is an essential part of the project work. Understanding the business process of pathology departments in daily practice, including healthcare, education, research, and quality control activities, is the starting point to be sure that standardization efforts converge with user needs. Following a recent IHE proposal, coordination with public health services like national or regional tumor registries must also be supported. Virtual or digital slides are fostering the use of image processing and analysis in pathology not only for research purposes, but also in daily practice. Nowadays, further discussion is needed on the adequacy of current existing technical solutions, including for instance quality of images obtained by scanners, or the efficiency of image analysis applications.
PURPOSE
To develop an artificial intelligence (AI)–based model for identifying patients with lymph node (LN) metastasis based on digital evaluation of primary tumors and train the model using cystectomy specimens available from The Cancer Genome Atlas (TCGA) Project; patients from our institution were included for validation of the leave-out test cohort.
METHODS
In all, 307 patients were identified for inclusion in the study (TCGA, n = 294; in-house, n = 13). Deep learning models were trained from image patches at 2.5×, 5×, 10×, and 20× magnifications, and spatially resolved prediction maps were combined with microenvironment (lymphocyte infiltration) features to derive a final patient-level AI score (probability of LN metastasis). Training and validation included 219 patients (training, n = 146; validation, n = 73); 89 patients (TCGA, n = 75; in-house, n = 13) were reserved as an independent testing set. Multivariable logistic regression models for predicting LN status based on clinicopathologic features alone and a combined model with AI score were fit to training and validation sets.
RESULTS
Several patients were determined to have positive LN metastasis in TCGA (n = 105; 35.7%) and in-house (n = 3; 23.1%) cohorts. A clinicopathologic model that considered using factors such as age, T stage, and lymphovascular invasion demonstrated an area under the curve (AUC) of 0.755 (95% CI, 0.680 to 0.831) in the training and validation cohorts compared with the cross validation of the AI score (likelihood of positive LNs), which achieved an AUC of 0.866 (95% CI, 0.812 to 0.920; P = .021). Performance in the test cohort was similar, with a clinicopathologic model AUC of 0.678 (95% CI, 0.554 to 0.802) and an AI score of 0.784 (95% CI, 0.702 to 0.896; P = .21). In addition, the AI score remained significant after adjusting for clinicopathologic variables ( P = 1.08 × 10 ⁻⁹ ), and the combined model significantly outperformed clinicopathologic features alone in the test cohort with an AUC of 0.807 (95% CI, 0.702 to 0.912; P = .047).
CONCLUSION
Patients who are at higher risk of having positive LNs during cystectomy can be identified on primary tumor samples using novel AI-based methodologies applied to digital hematoxylin and eosin–stained slides.
Aim:
The rate of deployment of digital pathology (DP) systems for primary diagnosis in the UK is accelerating. The flexibility and resilience of digital slides versus standard glass slides could be of great benefit in the NHS breast screening programme (NHSBSP). This study aims to document the safety and benefits of DP for preoperative tissue diagnosis of screen detected breast lesions.
Methods:
Concordance data for glass and digital slides of the same cases from 4 sites, were subjected to detailed concordance:discordance analysis. A literature review of DP in the primary diagnosis of breast lesions is presented making this the most comprehensive synthesis of digital breast cancer histopathological diagnostic data to date.
Results:
Detailed concordance analysis of experimental data from 2 histopathology departments reveals clinical concordance rates for breast biopsies of 96% (216/225) and 99.6% (249/250). Data from direct comparison validation studies in 2 histopathology departments, utilizing the protocol recommended by Royal College of Pathologists found concordance rates for breast histology cases of 99.4% (180/181) and 99.0% (887/896). An intraobserver variation study for glass versus digital slides for difficult cases from the NHSBSP yielded a kappa statistic of 0.80 indicating excellent agreement. Discordances encountered in the studies most frequently concerned discrepancies in grading attributable to mitotic count scoring and identification of weddelite.
Conclusions:
The experience of 4 histopathology laboratories, and our review of pre-existing literature suggest that DP is safe for the primary diagnosis of NHSBSP breast histology specimens, and does not increase the risk of misclassification.
Deep learning algorithms have shown benefits for pathology in the context of risk stratification of tumors. Although the results are promising, several steps have to be made to confirm clinical utility. In a recent issue of The Journal of Pathology, Colling et al. present a perspective manuscript providing a roadmap to routine use of artificial intelligence in histopathology. In this commentary, we aimed to put these key points in the context of recent findings of AI and digital image analysis studies. This article is protected by copyright. All rights reserved.
The use of artificial intelligence will likely transform clinical practice over the next decade and the early impact of this will likely be the integration of image analysis and machine learning into routine histopathology. In the UK and around the world, a digital revolution is transforming the reporting practice of diagnostic histopathology and this has sparked a proliferation of image analysis software tools. While this is an exciting development that could discover novel predictive clinical information and potentially address international pathology work‐force shortages, there is a clear need for a robust and evidence‐based framework in which to develop these new tools in a collaborative manner that meets regulatory approval. With these issues in mind, the NCRI Cellular Molecular Pathology (CM‐Path) initiative and the British In Vitro Diagnostics Association (BIVDA) has set out a roadmap to help academia, industry and clinicians develop new software tools to the point of approved clinical use.
This article is protected by copyright. All rights reserved.
In modern clinical practice, digital pathology has a crucial role and is increasingly a technological requirement in the scientific laboratory environment. The advent of whole-slide imaging, availability of faster networks, and cheaper storage solutions has made it easier for pathologists to manage digital slide images and share them for clinical use. In parallel, unprecedented advances in machine learning have enabled the synergy of artificial intelligence and digital pathology, which offers image-based diagnosis possibilities that were once limited only to radiology and cardiology. Integration of digital slides into the pathology workflow, advanced algorithms, and computer-aided diagnostic techniques extend the frontiers of the pathologist's view beyond a microscopic slide and enable true utilisation and integration of knowledge that is beyond human limits and boundaries, and we believe there is clear potential for artificial intelligence breakthroughs in the pathology setting. In this Review, we discuss advancements in digital slide-based image diagnosis for cancer along with some challenges and opportunities for artificial intelligence in digital pathology.
Aims
Virtual microscopy utilising digital whole slide imaging (WSI) is increasingly used in breast pathology. Histologic grade is one of the strongest prognostic factors in breast cancer (BC). This study aims at investigating the agreement between BC grading using traditional light microscopy (LM) and digital WSI with consideration of reproducibility and impact on outcome prediction.
Methods
A large (n=1675) well-characterised cohort of BC originally graded by LM was re-graded using WSI. Two separate virtual-based grading sessions (V1 and V2) were performed with a 3-month washout period. Outcome was assessed using BC-specific and distant metastasis-free survival.
Results
The concordance between LM grading and WSI was strong (LM/WSI Cramer’s V: V1=0.576, and V2=0.579). The agreement regarding grade components was as follows: tubule formation=0.538, pleomorphism=0.422 and mitosis=0.514. Greatest discordance was observed between adjacent grades, whereas high/low grade discordance was uncommon (1.5%). The intraobserver agreement for the two WSI sessions was substantial for grade (V1/V2 Cramer’s V=0.676; kappa=0.648) and grade components (Cramer’s V T=0.628, p=0.573 and M=0.580). Grading using both platforms showed strong association with outcome (all p values <0.001). Although mitotic scores assessed using both platforms were strongly associated with outcome, WSI tends to underestimate mitotic counts.
Conclusions
Virtual microscopy is a reliable and reproducible method for assessing BC histologic grade. Regardless of the observer or assessment platform, histologic grade is a significant predictor of outcome. Continuing advances in imaging technology could potentially provide improved performance of WSI BC grading and in particular mitotic count assessment.
Breast cancer is the most common malignant disease in women worldwide. In recent decades, earlier diagnosis and better adjuvant therapy have substantially improved patient outcome. Diagnosis by histopathology has proven to be instrumental to guide breast cancer treatment, but new challenges have emerged as our increasing understanding of cancer over the years has revealed its complex nature. As patient demand for personalized breast cancer therapy grows, we face an urgent need for more precise biomarker assessment and more accurate histopathologic breast cancer diagnosis to make better therapy decisions. The digitization of pathology data has opened the door to faster, more reproducible, and more precise diagnoses through computerized image analysis. Software to assist diagnostic breast pathology through image processing techniques have been around for years. But recent breakthroughs in artificial intelligence (AI) promise to fundamentally change the way we detect and treat breast cancer in the near future. Machine learning, a subfield of AI that applies statistical methods to learn from data, has seen an explosion of interest in recent years because of its ability to recognize patterns in data with less need for human instruction. One technique in particular, known as deep learning, has produced groundbreaking results in many important problems including image classification and speech recognition. In this review, we will cover the use of AI and deep learning in diagnostic breast pathology, and other recent developments in digital image analysis.
Aim:
To train and individually validate a group of breast pathologists in specialty specific digital primary diagnosis using a novel protocol endorsed by the Royal College of Pathologists' new guideline for digital pathology. The protocol allows early exposure to live digital reporting, in a risk mitigated environment, and focusses on patient safety and professional development.
Methods and results:
3 specialty breast pathologist completed training in use of a digital microscopy system, and were exposed to a training set of 20 challenging cases, designed to help them identify personal digital diagnostic pitfalls. Following this, the 3 pathologists viewed a total of 694 live, entire breast cases. All primary diagnoses were made on digital slides, with immediate glass review and reconciliation before final case sign out. There was complete clinical concordance between the glass and digital impression of the case in 98.8% of cases. Only 1.2% of cases had a clinically significant difference in diagnosis/prognosis on glass and digital slide reads. All pathologists elected to continue using the digital microscope as standard for breast histopathology specimens, with deferral to glass for a limited number of clinical/histological scenarios as a safety net.
Conclusion:
Individual training and validation for digital primary diagnosis allows pathologists to develop competence and confidence in their digital diagnostic skills, and aids safe and responsible transition from the light microscope to the digital microscope. This article is protected by copyright. All rights reserved.
Context:
- Relatively little is known about the significance and potential impact of glass-digital discordances, and this is likely to be of importance when considering digital pathology adoption.
Objective:
- To apply evidence-based medicine to collect and analyze reported instances of glass-digital discordance from the whole slide imaging validation literature.
Design:
- We used our prior systematic review protocol to identify studies assessing the concordance of light microscopy and whole slide imaging between 1999 and 2015. Data were extracted and analyzed by a team of histopathologists to classify the type, significance, and potential root cause of discordances.
Results:
- Twenty-three studies were included, yielding 8069 instances of a glass diagnosis being compared with a digital diagnosis. From these 8069 comparisons, 335 instances of discordance (4%) were reported, in which glass was the preferred diagnostic medium in 286 (85%), and digital in 44 (13%), with no consensus in 5 (2%). Twenty-eight discordances had the potential to cause moderate/severe patient harm. Of these, glass was the preferred diagnostic medium for 26 (93%). Of the 335 discordances, 109 (32%) involved the diagnosis or grading of dysplasia. For these cases, glass was the preferred diagnostic medium in 101 cases (93%), suggesting that diagnosis and grading of dysplasia may be a potential pitfall of digital diagnosis. In 32 of 335 cases (10%), discordance on digital was attributed to the inability to find a small diagnostic/prognostic object.
Conclusions:
- Systematic analysis of concordance studies reveals specific areas that may be problematic on whole slide imaging. It is important that pathologists are aware of these to ensure patient safety.
Aims:
Previous concordance studies examining accuracy of breast diagnosis by pathologists, typically targeting difficult, histologically challenging breast lesions using artificial and restrictive environments, have reported aberrantly high levels of diagnostic discordance. The results of these studies may be misinterpreted by non-pathologists and raise concerns relating to routine practice. This study aims to assess the diagnostic agreement among UK breast pathologists.
Methods:
Two hundred and forty consecutive breast lesions, submitted by participants from their routine practice, included in the UK National Health Service Breast Screening Programme (NHSBSP) breast pathology EQA scheme during the last 10 years were reviewed. An average of approximately 600 participants viewed each case. Data on diagnostic categories (benign, atypical, in-situ malignant and invasive malignant) were collected. In this study, benign and atypical diagnoses were grouped together.
Results:
The overall diagnostic agreement level was in the almost perfect range. Thirty-five cases (14.6%) showed diagnostic concordance of ≤95%. Reasons for discordance included one or more of: (1) scheme methodology limitations such as: (i) miscoding of certain lesions (e.g. phyllodes tumours and lobular neoplasia) (n = 7) and (ii) variable representation of the index lesion on glass slides (n = 18); and (2) diagnostically challenging cases that may be interpreted more easily using immunohistochemistry (n = 28). These latter included benign and malignant papillary lesions (n = 12), complex sclerosing lesions (n = 7), intraductal epithelial proliferative lesions (n = 6) and an unusual special tumour type (n = 1). Further review identified pathologists' misinterpretation in 13 cases (5.4%), with an average discordance rate of only 4.2%.
Conclusions:
The performance of breast pathologists is high. Exclusion of the effect of the scheme methodology limitations highlights further the high performance rate and identifies true diagnostically challenging entities. These difficult cases may benefit from additional diagnostic work-up and second opinions.
Background
The National Health Service Breast Screening Programme (NHSBSP; pathology) external quality assurance (EQA) scheme aims to provide a mechanism for examination and monitoring of concordance of pathology reporting within the UK. This study aims to review the breast EQA scheme performance data collected over a 24-year period following its introduction.
Methods
Data on circulations, number of cases and diagnosis were collected. Detailed analyses with and without combinations of certain diagnostic entities, and over different time periods were performed.
Results
Overall, of 576 cases (172 benign, 11 atypical hyperplasia, 98 ductal carcinoma in situ/microinvasive and 295 invasive disease), consistency of assessment of diagnostic parameters was very high (overall k=0.80; k for benign diagnosis=0.79; k for invasive disease=0.91). For distinguishing benign versus malignant lesions, no further improvement is considered possible in view of the limitations of the scheme methodology. Although diagnostic consistency of atypical hyperplasia remains at a low level, combining it with the benign category results in a high level of agreement (k=0.93). The level of consistency of reporting prognostic information is variable and some items such as lymphovascular invasion and tumour size measurement may need further intervention to improve their reporting consistency. Although the level of consistency of reporting of histological grade remained at a moderate level overall (k=0.48), it was variable among cases and appears to have levelled off; no further significant improvement is expected and no significant impact of the previous publication of guidelines is observed.
Conclusions
These results provide further evidence to indicate the value of the breast EQA scheme in monitoring performance and the identification of specific areas where improvement or new approaches are required. For most parameters, the concordance of reporting reached a plateaux a few years after the introduction of the EQA scheme. It is important to maintain this high level and also to tackle specific low-performance areas innovatively.
The proliferative activity of breast tumors, which is routinely estimated by
counting of mitotic figures in hematoxylin and eosin stained histology
sections, is considered to be one of the most important prognostic markers.
However, mitosis counting is laborious, subjective and may suffer from low
inter-observer agreement. With the wider acceptance of whole slide images in
pathology labs, automatic image analysis has been proposed as a potential
solution for these issues. In this paper, the results from the Assessment of
Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The
challenge was based on a data set consisting of 12 training and 11 testing
subjects, with more than one thousand annotated mitotic figures by multiple
observers. Short descriptions and results from the evaluation of eleven methods
are presented. The top performing method has an error rate that is comparable
to the inter-observer agreement among pathologists.
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 dif-ferent classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make train-ing faster, we used non-saturating neurons and a very efficient GPU implemen-tation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Al‐Janabi S, Huisman A & Van Diest P J
(2012) Histopathology 61, 1–9
Digital pathology: current status and future perspectives
During the last decade pathology has benefited from the rapid progress of image digitizing technology. The improvement in this technology had led to the creation of slide scanners which are able to produce whole slide images (WSI) which can be explored by image viewers in a way comparable to the conventional microscope. The file size of the WSI ranges from a few megabytes to several gigabytes, leading to challenges in the area of image storage and management when they will be used routinely in daily clinical practice. Digital slides are used in pathology for education, diagnostic purposes (clinicopathological meetings, consultations, revisions, slide panels and, increasingly, for upfront clinical diagnostics) and archiving. As an alternative to conventional slides, WSI are generally well accepted, especially in education, where they are available to a large number of students with the full possibilities of annotations without the problem of variation between serial sections. Image processing techniques can also be applied to WSI, providing pathologists with tools assisting in the diagnosis‐making process. This paper will highlight the current status of digital pathology applications and its impact on the field of pathology.