Workload Of Pathologists Research Articles

Pathologist Workload Assessment in Gastrointestinal Subspecialty: A Pilot comparative study in an academic setting

Abstract Introduction/Objective There are no official guidelines regarding the workload to be received by pathologists, and it is challenging to distribute equivalent workloads across subspecialties. This study aims to determine whether slide count is a reliable workload metric in gastrointestinal (GI) pathology. Additionally, we seek to compare the time allocation differences between GI pathologists involved in medical resident teaching and those dedicated only to anatomical pathology duties. Methods/Case Report This is an observational retrospective cohort study. We recorded the first two hours of a workday of three experienced GI pathologists at Stanford Healthcare in 2022, two of whom were engaged in teaching. The authors carefully retrospectively reviewed the recorded videos to extract relevant information: teaching activities, number of histological slides, specimens, types of tissues analyzed, and resultant diagnosis. Results (if a Case Study enter NA) Two attendings (2 and 3) signed out with residents, while only one worked alone (1). The mean time spent on each case was 199 and 486 seconds different between attendings 1 and 2 and 1 and 3, respectively (p<.01). There was a strong positive correlation between the number of slides and time spent analyzing each case, r =.607. The number of slides per case statistically explained 36.8% of the time spent per case, p <.001. Conclusion In conclusion, the slide count metric only explains 36.8% of the time expenditure, suggesting that more sophisticated workload assessment methods must be developed, particularly if used for workload distribution purposes. Also, GI pathologists involved in medical training take longer to sign out cases than GI pathologists who are not, suggesting that this is an essential factor that should be considered when distributing workloads.

Artificial Intelligence in Uropathology.

The global population is currently at unprecedented levels, with an estimated 7.8 billion people inhabiting the planet. We are witnessing a rise in cancer cases, attributed to improved control of cardiovascular diseases and a growing elderly population. While this has resulted in an increased workload for pathologists, it also presents an opportunity for advancement. The accurate classification of tumors and identification of prognostic and predictive factors demand specialized expertise and attention. Fortunately, the rapid progression of artificial intelligence (AI) offers new prospects in medicine, particularly in diagnostics such as image and surgical pathology. This article explores the transformative impact of AI in the field of uropathology, with a particular focus on its application in diagnosing, grading, and prognosticating various urological cancers. AI, especially deep learning algorithms, has shown significant potential in improving the accuracy and efficiency of pathology workflows. This comprehensive review is dedicated to providing an insightful overview of the primary data concerning the utilization of AI in diagnosing, predicting prognosis, and determining drug responses for tumors of the urinary tract. By embracing these advancements, we can look forward to improved outcomes and better patient care.

Tumor detection in breast cancer pathology patches using a Multi-scale Multi-head Self-attention Ensemble Network on Whole Slide Images

Breast cancer (BC) is the most common type of cancer among women globally and is one of the leading causes of cancer-related deaths among women. In the diagnosis of BC, histopathological assessment is the gold standard, where automated tumor detection technologies play a pivotal role. Utilizing Convolutional Neural Networks (CNNs) for automated analysis of image patches from Whole Slide Images (WSIs) enhances detection accuracy and alleviates the workload of pathologists. However, CNNs often face limitations in handling pathological patches due to a lack of sufficient contextual information and limited feature generation capabilities. To address this, we propose a novel Multi-scale Multi-head Self-attention Ensemble Network (MMSEN), which integrates a multi-scale feature generation module, a convolutional self-attention module, and an adaptive feature integration and output module, effectively optimizing the performance of classical CNNs. The design of MMSEN optimizes the capture of key information and the comprehensive integration of features in WSIs pathological patches, significantly enhancing the precision of tumor detection. Validation results from a five-fold cross-validation experiment on the PatchCamelyon (PCam) dataset demonstrate that MMSEN achieves a ROC-AUC of 99.01%±0.02%, an F1 Score of 98.00%±0.08%, a Balanced Accuracy (B-Acc) of 98.00%±0.08%, and a Matthews Correlation Coefficient (MCC) of 96.00%±0.16% (p<0.05). These results demonstrate the effectiveness and potential of MMSEN in detecting tumors from pathological patches in WSIs for BC.

The evaluation of efficiency of new methodology of personified registration and distribution of workload of pathoanatomists

The original methodology developed by authors for personalized registration and distribution of workload of pathologists is implemented into a number of departments of pathological-anatomic service of the Irkutsk Oblast, including pathological-anatomic department of the Oblast State Budget Institution "The Irkutsk Municipal Clinical Hospital № 1". In order to evaluate efficiency of new methodology comparative analysis of workload volumes performed by pathologists with calculated standard workload was carried out for two periods i.e before application of new methodology and after its implementation. It is established that in 2017-2019 before implementation of new methodology, discrepancy between workload performed by physicians and its calculated value exceeded 40% in some specialists. The implementation of new methodology resulted in significant, up to 10-fold, decreasing of discrepancy between workload practically performed by physicians and its standard value. As a result, actually this discrepancy on average does not exceed 4% in most specialists. The application of the Student's t-test to compare value of discrepancy between workload performed by pathologists for two compared periods also permitted to establish statistical significance of given differences related to majority of physicians (p<0.05) that serves as justification of efficiency and reasonability of new methodology.

Single-cell AI-based detection and prognostic and predictive value of DNA mismatch repair deficiency in colorectal cancer

Testing for DNA mismatch repair deficiency (MMRd) is recommended for all colorectal cancers (CRCs). Automating this would enable precision medicine, particularly if providing information on etiology not captured by deep learning (DL) methods. We present AIMMeR, an AI-based method for determination of mismatch repair (MMR) protein expression at a single-cell level in routine pathology samples. AIMMeR shows an area under the receiver-operator curve (AUROC) of 0.98, and specificity of ≥75% at 98% sensitivity against pathologist ground truth in stage II/III in two trial cohorts, with positive predictive value of ≥98% for the commonest pattern of somatic MMRd. Lower agreement with microsatellite instability (MSI) testing (AUROC 0.86) reflects discordance between MMR and MSI PCR rather than AIMMeR misclassification. Analysis of the SCOT trial confirms MMRd prognostic value in oxaliplatin-treated patients; while MMRd does not predict differential benefit of chemotherapy duration, it correlates with difference in relapse by regimen (PInteraction= 0.04). AIMMeR may help reduce pathologist workload and streamline diagnostics in CRC.

The Quantification of Myocardial Fibrosis on Human Histopathology Images by a Semi-Automatic Algorithm

(1) Background: Considering the increasing workload of pathologists, computer-assisted methods have the potential to come to their aid. Considering the prognostic role of myocardial fibrosis, its precise quantification is essential. Currently, the evaluation is performed semi-quantitatively by the pathologist, a method exposed to the issues of subjectivity. The present research proposes validating a semi-automatic algorithm that aims to quantify myocardial fibrosis on microscopic images. (2) Methods: Forty digital images were selected from the slide collection of The Iowa Virtual Slidebox, from which the collagen volume fraction (CVF) was calculated using two semi-automatic methods: CIELAB-MATLAB® and CIELAB-Python. These involve the use of color difference analysis, using Delta E, in a rectangular region for CIELAB-Python and a region with a random geometric shape, determined by the user’s cursor movement, for CIELAB-MATLAB®. The comparison was made between the stereological evaluation and ImageJ. (3) Results: A total of 36 images were included in the study (n = 36), demonstrating a high, statistically significant correlation between stereology and ImageJ on the one hand, and the proposed methods on the other (p &lt; 0.001). The mean CVF determined by the two methods shows a mean bias of 1.5% compared with stereology and 0.9% compared with ImageJ. Conclusions: The combined algorithm has a superior performance compared to the proposed methods, considered individually. Despite the relatively small mean bias, the limits of agreement are quite wide, reflecting the variability of the images included in the study.

Best-Practice Biomarker Testing of Oesophago-Gastric Cancer in the UK: Expert Consensus Recommendations Developed Using a Modified Delphi

AimsOesophago-gastric cancers (OGCs) are amongst the most commonly diagnosed malignancies worldwide and are associated with high disease-related mortality. Predictive biomarkers are molecules that can be objectively measured and used to indicate a likely response to therapeutic intervention, thus facilitating individualised cancer therapy. However, there remains variation in uptake and implementation of biomarker testing across the UK. Materials and methodsWe conducted a modified Delphi study to formulate consensus recommendations for best-practice biomarker testing of OGC in the UK. We employed two rounds of online questionnaires followed by a virtual consensus meeting. Biomarkers for discussion included HER2, MSI/MMR, and PD-L1. Topics comprised the overall biomarker pathway, pre-analytical, analytical, and post-analytical considerations, including challenges in current practice. ResultsTwenty-six and eighteen participants completed the first and second round Delphi questionnaire, respectively, with an even split of pathologists and oncologists from across the UK. There was consensus (>80% agreement) across several topics, including the requirements for standardisation of the pathway, which must include coordination throughout the tissue journey, requirements for a quality-assured process to ensure accuracy and validity of testing, plus the need for clear, detailed information on the pathology report to support treatment decisions. There was consensus amongst oncologists regarding reflex testing of all biomarkers depending on histology; however, concerns over capacity in relation to workload and availability of pathologists were evident among the pathologists. Overall, participants were in the opinion that reflex testing improves the speed of treatment decisions and improves patient care. ConclusionThe recommendations reflect best-practices and should be implemented to support rapid multidisciplinary team decision-making within oesophago-gastric cancer. Results reflect the need for standardisation and demonstrate the challenges faced in clinical practice by those requesting and testing biomarkers for oesophago-gastric cancer, suggesting significant concerns relating to pathologist capacity.

Deep Learning for Histopathological Assessment of Esophageal Adenocarcinoma Precursor Lesions

Histopathological assessment of esophageal biopsies is a key part in the management of patients with Barrett esophagus (BE) but prone to observer variability and reliable diagnostic methods are needed. Artificial intelligence (AI) is emerging as a powerful tool for aided diagnosis but often relies on abstract test and validation sets while real-world behavior is unknown. In this study, we developed a 2-stage AI system for histopathological assessment of BE-related dysplasia using deep learning to enhance the efficiency and accuracy of the pathology workflow. The AI system was developed and trained on 290 whole-slide images (WSIs) that were annotated at glandular and tissue levels. The system was designed to identify individual glands, grade dysplasia, and assign a WSI-level diagnosis. The proposed method was evaluated by comparing the performance of our AI system with that of a large international and heterogeneous group of 55 gastrointestinal pathologists assessing 55 digitized biopsies spanning the complete spectrum of BE-related dysplasia. The AI system correctly graded 76.4% of the WSIs, surpassing the performance of 53 out of the 55 participating pathologists. Furthermore, the receiver-operating characteristic analysis showed that the system’s ability to predict the absence (nondysplastic BE) versus the presence of any dysplasia was with an area under the curve of 0.94 and a sensitivity of 0.92 at a specificity of 0.94. These findings demonstrate that this AI system has the potential to assist pathologists in assessment of BE-related dysplasia. The system’s outputs could provide a reliable and consistent secondary diagnosis in challenging cases or be used for triaging low-risk nondysplastic biopsies, thereby reducing the workload of pathologists and increasing throughput.

MAMILNet: advancing precision oncology with multi-scale attentional multi-instance learning for whole slide image analysis.

Whole Slide Image (WSI) analysis, driven by deep learning algorithms, has the potential to revolutionize tumor detection, classification, and treatment response prediction. However, challenges persist, such as limited model generalizability across various cancer types, the labor-intensive nature of patch-level annotation, and the necessity of integrating multi-magnification information to attain a comprehensive understanding of pathological patterns. In response to these challenges, we introduce MAMILNet, an innovative multi-scale attentional multi-instance learning framework for WSI analysis. The incorporation of attention mechanisms into MAMILNet contributes to its exceptional generalizability across diverse cancer types and prediction tasks. This model considers whole slides as "bags" and individual patches as "instances." By adopting this approach, MAMILNet effectively eliminates the requirement for intricate patch-level labeling, significantly reducing the manual workload for pathologists. To enhance prediction accuracy, the model employs a multi-scale "consultation" strategy, facilitating the aggregation of test outcomes from various magnifications. Our assessment of MAMILNet encompasses 1171 cases encompassing a wide range of cancer types, showcasing its effectiveness in predicting complex tasks. Remarkably, MAMILNet achieved impressive results in distinct domains: for breast cancer tumor detection, the Area Under the Curve (AUC) was 0.8872, with an Accuracy of 0.8760. In the realm of lung cancer typing diagnosis, it achieved an AUC of 0.9551 and an Accuracy of 0.9095. Furthermore, in predicting drug therapy responses for ovarian cancer, MAMILNet achieved an AUC of 0.7358 and an Accuracy of 0.7341. The outcomes of this study underscore the potential of MAMILNet in driving the advancement of precision medicine and individualized treatment planning within the field of oncology. By effectively addressing challenges related to model generalization, annotation workload, and multi-magnification integration, MAMILNet shows promise in enhancing healthcare outcomes for cancer patients. The framework's success in accurately detecting breast tumors, diagnosing lung cancer types, and predicting ovarian cancer therapy responses highlights its significant contribution to the field and paves the way for improved patient care.

Development and external validation of a transfer learning-based system for the pathological diagnosis of colorectal cancer: a large emulated prospective study.

The progress in Colorectal cancer (CRC) screening and management has resulted in an unprecedented caseload for histopathological diagnosis. While artificial intelligence (AI) presents a potential solution, the predominant emphasis on slide-level aggregation performance without thorough verification of cancer in each location, impedes both explainability and transparency. Effectively addressing these challenges is crucial to ensuring the reliability and efficacy of AI in histology applications. In this study, we created an innovative AI algorithm using transfer learning from a polyp segmentation model in endoscopy. The algorithm precisely localized CRC targets within 0.25 mm² grids from whole slide imaging (WSI). We assessed the CRC detection capabilities at this fine granularity and examined the influence of AI on the diagnostic behavior of pathologists. The evaluation utilized an extensive dataset comprising 858 consecutive patient cases with 1418 WSIs obtained from an external center. Our results underscore a notable sensitivity of 90.25% and specificity of 96.60% at the grid level, accompanied by a commendable area under the curve (AUC) of 0.962. This translates to an impressive 99.39% sensitivity at the slide level, coupled with a negative likelihood ratio of <0.01, signifying the dependability of the AI system to preclude diagnostic considerations. The positive likelihood ratio of 26.54, surpassing 10 at the grid level, underscores the imperative for meticulous scrutiny of any AI-generated highlights. Consequently, all four participating pathologists demonstrated statistically significant diagnostic improvements with AI assistance. Our transfer learning approach has successfully yielded an algorithm that can be validated for CRC histological localizations in whole slide imaging. The outcome advocates for the integration of the AI system into histopathological diagnosis, serving either as a diagnostic exclusion application or a computer-aided detection (CADe) tool. This integration has the potential to alleviate the workload of pathologists and ultimately benefit patients.

Assessment of Efficacy and Accuracy of Cervical Cytology Screening With Artificial Intelligence Assistive System

The role of artificial intelligence (AI) in pathology offers many exciting new possibilities for improving patient care. This study contributes to this development by identifying the viability of the AICyte assistive system for cervical screening, and investigating the utility of the system in assisting with workflow and diagnostic capability. In this study, a novel scanner was developed using a Ruiqian WSI-2400, trademarked AICyte assistive system, to create an AI-generated gallery of the most diagnostically relevant images, objects of interest (OOI), and provide categorical assessment, according to Bethesda category, for cervical ThinPrep Pap slides. For validation purposes, 2 pathologists reviewed OOIs from 32,451 cases of ThinPrep Paps independently, and their interpretations were correlated with the original ThinPrep interpretations (OTPI). The analysis was focused on the comparison of reporting rates, correlation between cytological results and histologic follow-up findings, and the assessment of independent AICyte screening utility. Pathologists using the AICyte system had a mean reading time of 55.14 seconds for the first 3000 cases trending down to 12.90 seconds in the last 6000 cases. Overall average reading time was 22.23 seconds per case compared with a manual reading time approximation of 180 seconds. Usage of AICyte compared with OTPI had similar sensitivity (97.89% vs 97.89%) and a statistically significant increase in specificity (16.19% vs 6.77%) for the detection of cervical intraepithelial neoplsia 2 and above lesions. When AICyte was run alone at a 50% negative cutoff value, it was able to read slides with a sensitivity of 99.30% and a specificity of 9.87%. When AICyte was run independently at this cutoff value, no sole case of high-grade squamous intraepithelial lesions/squamous cell carcinoma squamous lesion was missed. AICyte can provide a potential tool to help pathologists in both diagnostic capability and efficiency, which remained reliable compared with the baseline standard. Also unique for AICyte is the development of a negative cutoff value for which AICyte can categorize cases as “not needed for review” to triage cases and lower pathologist workload. This is the largest case number study that pathologists reviewed OOI with an AI-assistive system. The study demonstrates that AI-assistive system can be broadly applied for cervical cancer screening.

An artificial intelligence model for detecting pathological lymph node metastasis in prostate cancer using whole slide images: a retrospective, multicentre, diagnostic study

The pathological examination of lymph node metastasis (LNM) is crucial for treating prostate cancer (PCa). However, the limitations with naked-eye detection and pathologist workload contribute to a high missed-diagnosis rate for nodal micrometastasis. We aimed to develop an artificial intelligence (AI)-based, time-efficient, and high-precision PCa LNM detector (ProCaLNMD) and evaluate its clinical application value. In this multicentre, retrospective, diagnostic study, consecutive patients with PCa who underwent radical prostatectomy and pelvic lymph node dissection at five centres between Sep 2, 2013 and Apr 28, 2023 were included, and histopathological slides of resected lymph nodes were collected and digitised as whole-slide images for model development and validation. ProCaLNMD was trained at a dataset from a single centre (the Sun Yat-sen Memorial Hospital of Sun Yat-sen University [SYSMH]), and externally validated in the other four centres. A bladder cancer dataset from SYSMH was used to further validate ProCaLNMD, and an additional validation (human-AI comparison and collaboration study) containing consecutive patients with PCa from SYSMH was implemented to evaluate the application value of integrating ProCaLNMD into the clinical workflow. The primary endpoint was the area under the receiver operating characteristic curve (AUROC) of ProCaLNMD. In addition, the performance measures for pathologists with ProCaLNMD assistance was also assessed. In total, 8225 slides from 1297 patients with PCa were collected and digitised. Overall, 8158 slides (18,761 lymph nodes) from 1297 patients with PCa (median age 68 years [interquartile range 64-73]; 331 [26%] with LNM) were used to train and validate ProCaLNMD. The AUROC of ProCaLNMD ranged from 0.975 (95% confidence interval 0.953-0.998) to 0.992 (0.982-1.000) in the training and validation datasets, with sensitivities > 0.955 and specificities > 0.921. ProCaLNMD also demonstrated an AUROC of 0.979 in the cross-cancer dataset. ProCaLNMD use triggered true reclassification in 43 (4.3%) slides in which micrometastatic tumour regions were initially missed by pathologists, thereby correcting 28 (8.5%) missed-diagnosed cases of previous routine pathological reports. In the human-AI comparison and collaboration study, the sensitivity of ProCaLNMD (0.983 [0.908-1.000]) surpassed that of two junior pathologists (0.862 [0.746-0.939], P=0.023; 0.879 [0.767-0.950], P=0.041) by 10-12% and showed no difference to that of two senior pathologists (both 0.983 [0.908-1.000], both P>0.99). Furthermore, ProCaLNMD significantly boosted the diagnostic sensitivity of two junior pathologists (both P=0.041) to the level of senior pathologists (both P>0.99), and substantially reduced the four pathologists' slide reviewing time (-31%, P<0.0001;-34%, P<0.0001;-29%, P<0.0001; and-27%, P=0.00031). ProCaLNMD demonstrated high diagnostic capabilities for identifying LNM in prostate cancer, reducing the likelihood of missed diagnoses by pathologists and decreasing the slide reviewing time, highlighting its potential for clinical application. National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, the Guangdong Provincial Clinical Research Centre for Urological Diseases, and the Science and Technology Projects in Guangzhou.

FD-Net: Feature Distillation Network for Oral Squamous Cell Carcinoma Lymph Node Segmentation in Hyperspectral Imagery.

Oral squamous cell carcinoma (OSCC) has the characteristics of early regional lymph node metastasis. OSCC patients often have poor prognoses and low survival rates due to cervical lymph metastases. Therefore, it is necessary to rely on a reasonable screening method to quickly judge the cervical lymph metastastic condition of OSCC patients and develop appropriate treatment plans. In this study, the widely used pathological sections with hematoxylin-eosin (H&E) staining are taken as the target, and combined with the advantages of hyperspectral imaging technology, a novel diagnostic method for identifying OSCC lymph node metastases is proposed. The method consists of a learning stage and a decision-making stage, focusing on cancer and non-cancer nuclei, gradually completing the lesions' segmentation from coarse to fine, and achieving high accuracy. In the learning stage, the proposed feature distillation-Net (FD-Net) network is developed to segment the cancerous and non-cancerous nuclei. In the decision-making stage, the segmentation results are post-processed, and the lesions are effectively distinguished based on the prior. Experimental results demonstrate that the proposed FD-Net is very competitive in the OSCC hyperspectral medical image segmentation task. The proposed FD-Net method performs best on the seven segmentation evaluation indicators: MIoU, OA, AA, SE, CSI, GDR, and DICE. Among these seven evaluation indicators, the proposed FD-Net method is 1.75%, 1.27%, 0.35%, 1.9%, 0.88%, 4.45%, and 1.98% higher than the DeepLab V3 method, which ranks second in performance, respectively. In addition, the proposed diagnosis method of OSCC lymph node metastasis can effectively assist pathologists in disease screening and reduce the workload of pathologists.

Mapping of anatomical pathologist workload via epic beaker flag function

Mapping of anatomical pathologist workload via epic beaker flag function

PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection.

Background: Deep learning models for patch classification in whole-slide images (WSIs) have shown promise in assisting follicular lymphoma grading. However, these models often require pathologists to identify centroblasts and manually provide refined labels for model optimization. Objective: To address this limitation, we propose PseudoCell, an object detection framework for automated centroblast detection in WSI, eliminating the need for extensive pathologist's refined labels. Methods: PseudoCell leverages a combination of pathologist-provided centroblast labels and pseudo-negative labels generated from undersampled false-positive predictions based on cell morphology features. This approach reduces the reliance on time-consuming manual annotations. Results: Our framework significantly reduces the workload for pathologists by accurately identifying and narrowing down areas of interest containing centroblasts. Depending on the confidence threshold, PseudoCell can eliminate 58.18-99.35% of irrelevant tissue areas on WSI, streamlining the diagnostic process. Conclusion: This study presents PseudoCell as a practical and efficient prescreening method for centroblast detection, eliminating the need for refined labels from pathologists. The discussion section provides detailed guidance for implementing PseudoCell in clinical practice.

AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images.

The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions. In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model's predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists. Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system.

Endometrial Pipelle Biopsy Computer-Aided Diagnosis: A Feasibility Study

Endometrial biopsies are important in the diagnostic workup of women who present with abnormal uterine bleeding or hereditary risk of endometrial cancer. In general, approximately 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI)-assisted preselection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (endometrial Pipelle biopsy computer-aided diagnosis), trained on daily-practice whole-slide images instead of highly selected images. Endometrial biopsies were classified into 6 clinically relevant categories defined as follows: nonrepresentative, normal, nonneoplastic, hyperplasia without atypia, hyperplasia with atypia, and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2819 endometrial biopsies) rated the same 91 cases, and we compared its performance using the pathologist’s classification as the reference standard. The interrater reliability among pathologists was moderate with a mean Cohen’s kappa of 0.51, whereas for a binary classification into benign vs (pre)malignant, the agreement was substantial with a mean Cohen’s kappa of 0.66. The AI algorithm performed slightly worse for the 6 categories with a moderate Cohen’s kappa of 0.43 but was comparable for the binary classification with a substantial Cohen’s kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissues, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.

Colorectal cancer detection based on convolutional neural networks (CNN) and ranking algorithm

With the development of targeted therapies, many treatments are based on molecular studies, which require sampling tumor tissue from paraffin blocks for sequencing. An automated solution could potentially reduce the workload of pathologists by acting as a screening device and may reduce the subjectivity in diagnosis. In tissue-based diagnostics, most of the work still needs to be done manually by a pathologist using a microscope to examine stained slides. The foundation of such tasks is to accurately distinguish cancer/malignant cells from normal/benign cells. However, the determination of tumor content is poorly reproducible with significant variation. As the size of tumor regions can be very small, pathologists are often required to use high magnification for detecting tumor cells. This requirement significantly increases the workload for pathologists. As digital pathology datasets have become publicly available and have opened up the possibility of evaluating the feasibility of applying deep learning techniques to improving the efficiency and quality of histologic diagnosis. The model proposed in this work is an application to detect colorectal cancer based on the Convolutional Neural Network and Ranking algorithm. Based on the performance evaluation, it is found that the proposed model is yielding better results in diagnosis of Colorectal Cancer than the existing methods in terms of Recall, Precision and Accuracy.

Immunohistochemical Stain-Aided Annotation Accelerates Machine Learning and Deep Learning Model Development in the Pathologic Diagnosis of Nasopharyngeal Carcinoma.

Nasopharyngeal carcinoma (NPC) is an epithelial cancer originating in the nasopharynx epithelium. Nevertheless, annotating pathology slides remains a bottleneck in the development of AI-driven pathology models and applications. In the present study, we aim to demonstrate the feasibility of using immunohistochemistry (IHC) for annotation by non-pathologists and to develop an efficient model for distinguishing NPC without the time-consuming involvement of pathologists. For this study, we gathered NPC slides from 251 different patients, comprising hematoxylin and eosin (H&E) slides, pan-cytokeratin (Pan-CK) IHC slides, and Epstein-Barr virus-encoded small RNA (EBER) slides. The annotation of NPC regions in the H&E slides was carried out by a non-pathologist trainee who had access to corresponding Pan-CK IHC slides, both with and without EBER slides. The training process utilized ResNeXt, a deep neural network featuring a residual and inception architecture. In the validation set, NPC exhibited an AUC of 0.896, with a sensitivity of 0.919 and a specificity of 0.878. This study represents a significant breakthrough: the successful application of deep convolutional neural networks to identify NPC without the need for expert pathologist annotations. Our results underscore the potential of laboratory techniques to substantially reduce the workload of pathologists.

Masked autoencoders with handcrafted feature predictions: Transformer for weakly supervised esophageal cancer classification

Background and ObjectiveEsophageal cancer is a serious disease with a high prevalence in Eastern Asia. Histopathology tissue analysis stands as the gold standard in diagnosing esophageal cancer. In recent years, there has been a shift towards digitizing histopathological images into whole slide images (WSIs), progressively integrating them into cancer diagnostics. However, the gigapixel sizes of WSIs present significant storage and processing challenges, and they often lack localized annotations. To address this issue, multi-instance learning (MIL) has been introduced for WSI classification, utilizing weakly supervised learning for diagnosis analysis. By applying the principles of MIL to WSI analysis, it is possible to reduce the workload of pathologists by facilitating the generation of localized annotations. Nevertheless, the approach's effectiveness is hindered by the traditional simple aggregation operation and the domain shift resulting from the prevalent use of convolutional feature extractors pretrained on ImageNet. MethodsWe propose a MIL-based framework for WSI analysis and cancer classification. Concurrently, we introduce employing self-supervised learning, which obviates the need for manual annotation and demonstrates versatility in various tasks, to pretrain feature extractors. This method enhances the extraction of representative features from esophageal WSI for MIL, ensuring more robust and accurate performance. ResultsWe build a comprehensive dataset of whole esophageal slide images and conduct extensive experiments utilizing this dataset. The performance on our dataset demonstrates the efficiency of our proposed MIL framework and the pretraining process, with our framework outperforming existing methods, achieving an accuracy of 93.07% and AUC (area under the curve) of 95.31%. ConclusionThis work proposes an effective MIL method to classify WSI of esophageal cancer. The promising results indicate that our cancer classification framework holds great potential in promoting the automatic whole esophageal slide image analysis.