U.S. payer budget impact of using an AI-augmented cancer risk discrimination digital histopathology platform to identify high-risk of recurrence in women with early-stage invasive breast cancer.

Aims: Use of gene expression signatures to predict adjuvant chemotherapy benefit in women with early-stage breast cancer is increasing. However, high cost, limited access, and eligibility for these tests results in the adoption of less precise assessment approaches. This study evaluates the cost impact of PreciseDx Breast (PDxBr), an AI-augmented histopathology platform that assesses the 6-year risk of recurrence in early-stage invasive breast cancer patients to help improve informed use of adjuvant chemotherapy.Materials and Methods: A decision-tree Markov model was developed to compare the costs of treatment guided by standard of care (SOC) risk assessment (i.e., clinical diagnostic workup with or without Oncotype DX) versus PDxBr with SOC in a hypothetical cohort of U.S. women with early-stage invasive breast cancer. A commercial payer perspective compares costs of testing, adjuvant therapy, recurrence, adverse events, surveillance, and end-of-life care.Results: PDxBr use in prognostic evaluation resulted in savings of $4 million (M) in year one compared to current SOC in 1M females members. Over 6-years, savings increased to $12.5M. The per-treated patient costs in year one amounted to $19.5 thousand (K) for SOC and $16.9K for PDxBr.Limitations: For simplicity, recurrence was not specified. We performed scenario analyses to account for variations in rates for local, regional, and distant recurrence. Second, a recurrent patient incurs the total cost of treated recurrence in the first year and goes back to remission or death. Third, CDK4/6i treatment is only incorporated in the recurrence costs but not in the first line of treatment for early-stage breast cancer due to limited data.Conclusions: Sensitivity analyses demonstrated robust overall savings to changes in all variables in the model. The use of PDxBr to assess breast cancer recurrence risk has the potential to fill gaps in care and reduce costs when gene expression signatures are not available.

Enhancing Medical Imaging Segmentation with GB-SAM: A Novel Approach to Tissue Segmentation Using Granular Box Prompts.

Recent advances in foundation models have revolutionized model development in digital pathology, reducing dependence on extensive manual annotations required by traditional methods. The ability of foundation models to generalize well with few-shot learning addresses critical barriers in adapting models to diverse medical imaging tasks. This work presents the Granular Box Prompt Segment Anything Model (GB-SAM), an improved version of the Segment Anything Model (SAM) fine-tuned using granular box prompts with limited training data. The GB-SAM aims to reduce the dependency on expert pathologist annotators by enhancing the efficiency of the automated annotation process. Granular box prompts are small box regions derived from ground truth masks, conceived to replace the conventional approach of using a single large box covering the entire H&E-stained image patch. This method allows a localized and detailed analysis of gland morphology, enhancing the segmentation accuracy of individual glands and reducing the ambiguity that larger boxes might introduce in morphologically complex regions. We compared the performance of our GB-SAM model against U-Net trained on different sizes of the CRAG dataset. We evaluated the models across histopathological datasets, including CRAG, GlaS, and Camelyon16. GB-SAM consistently outperformed U-Net, with reduced training data, showing less segmentation performance degradation. Specifically, on the CRAG dataset, GB-SAM achieved a Dice coefficient of 0.885 compared to U-Net's 0.857 when trained on 25% of the data. Additionally, GB-SAM demonstrated segmentation stability on the CRAG testing dataset and superior generalization across unseen datasets, including challenging lymph node segmentation in Camelyon16, which achieved a Dice coefficient of 0.740 versus U-Net's 0.491. Furthermore, compared to SAM-Path and Med-SAM, GB-SAM showed competitive performance. GB-SAM achieved a Dice score of 0.900 on the CRAG dataset, while SAM-Path achieved 0.884. On the GlaS dataset, Med-SAM reported a Dice score of 0.956, whereas GB-SAM achieved 0.885 with significantly less training data. These results highlight GB-SAM's advanced segmentation capabilities and reduced dependency on large datasets, indicating its potential for practical deployment in digital pathology, particularly in settings with limited annotated datasets.

Joining forces for pathology diagnostics with AI assistance: The EMPAIA initiative.

Over the past decade, artificial intelligence (AI) methods in pathology have advanced substantially. However, integration into routine clinical practice has been slow due to numerous challenges, including technical and regulatory hurdles in translating research results into clinical diagnostic products and the lack of standardized interfaces. The open and vendor-neutral EMPAIA initiative addresses these challenges. Here, we provide an overview of EMPAIA's achievements and lessons learned. EMPAIA integrates various stakeholders of the pathology AI ecosystem, i.e., pathologists, computer scientists, and industry. In close collaboration, we developed technical interoperability standards, recommendations for AI testing and product development, and explainability methods. We implemented the modular and open-source EMPAIA Platform and successfully integrated 14 AI-based image analysis apps from eight different vendors, demonstrating how different apps can use a single standardized interface. We prioritized requirements and evaluated the use of AI in real clinical settings with 14 different pathology laboratories in Europe and Asia. In addition to technical developments, we created a forum for all stakeholders to share information and experiences on digital pathology and AI. Commercial, clinical, and academic stakeholders can now adopt EMPAIA's common open-source interfaces, providing a unique opportunity for large-scale standardization and streamlining of processes. Further efforts are needed to effectively and broadly establish AI assistance in routine laboratory use. To this end, a sustainable infrastructure, the non-profit association EMPAIA International, has been established to continue standardization and support broad implementation and advocacy for an AI-assisted digital pathology future.

Masked pre-training of transformers for histology image analysis.

In digital pathology, whole-slide images (WSIs) are widely used for applications such as cancer diagnosis and prognosis prediction. Vision transformer (ViT) models have recently emerged as a promising method for encoding large regions of WSIs while preserving spatial relationships among patches. However, due to the large number of model parameters and limited labeled data, applying transformer models to WSIs remains challenging. In this study, we propose a pretext task to train the transformer model in a self-supervised manner. Our model, MaskHIT, uses the transformer output to reconstruct masked patches, measured by contrastive loss. We pre-trained MaskHIT model using over 7000 WSIs from TCGA and extensively evaluated its performance in multiple experiments, covering survival prediction, cancer subtype classification, and grade prediction tasks. Our experiments demonstrate that the pre-training procedure enables context-aware understanding of WSIs, facilitates the learning of representative histological features based on patch positions and visual patterns, and is essential for the ViT model to achieve optimal results on WSI-level tasks. The pre-trained MaskHIT surpasses various multiple instance learning approaches by 3% and 2% on survival prediction and cancer subtype classification tasks, and also outperforms recent state-of-the-art transformer-based methods. Finally, a comparison between the attention maps generated by the MaskHIT model with pathologist's annotations indicates that the model can accurately identify clinically relevant histological structures on the whole slide for each task.

Eco-evolutionary Guided Pathomic Analysis to Predict DCIS Upstaging.

Cancers evolve in a dynamic ecosystem. Thus, characterizing cancer's ecological dynamics is crucial to understanding cancer evolution and can lead to discovering novel biomarkers to predict disease progression. Ductal carcinoma in situ (DCIS) is an early-stage breast cancer characterized by abnormal epithelial cell growth confined within the milk ducts. Although there has been extensive research on genetic and epigenetic causes of breast carcinogenesis, none of these studies have successfully identified a biomarker for the progression and/or upstaging of DCIS. In this study, we show that ecological habitat analysis of hypoxia and acidosis biomarkers can significantly improve prediction of DCIS upstaging. First, we developed a novel eco-evolutionary designed approach to define habitats in the tumor intra-ductal microenvironment based on oxygen diffusion distance in our DCIS cohort of 84 patients. Then, we identify cancer cells with metabolic phenotypes attributed to their habitat conditions, such as the expression of CA9 indicating hypoxia responding phenotype, and LAMP2b indicating a hypoxia-induced acid adaptation. Traditionally these markers have shown limited predictive capabilities for DCIS upstaging, if any. However, when analyzed from an ecological perspective, their power to differentiate between indolent and upstaged DCIS increased significantly. Second, using eco-evolutionary guided computational and digital pathology techniques, we discovered distinct spatial patterns of these biomarkers and used the distribution of such patterns to predict patient upstaging. The patterns were characterized by both cellular features and spatial features. With a 5-fold validation on the biopsy cohort, we trained a random forest classifier to achieve the area under curve(AUC) of 0.74. Our results affirm the importance of using eco-evolutionary-designed approaches in biomarkers discovery studies in the era of digital pathology by demonstrating the role of eco-evolution dynamics in predicting cancer progression.

Evaluating the efficacy of few-shot learning for GPT-4Vision in neurodegenerative disease histopathology: A comparative analysis with convolutional neural network model.

AIMS: Recent advances in artificial intelligence, particularly with large language models like GPT-4Vision (GPT-4V)-a derivative feature of ChatGPT-have expanded the potential for medical image interpretation. This study evaluates the accuracy of GPT-4V in image classification tasks of histopathological images and compares its performance with a traditional convolutional neural network (CNN). METHODS: We utilised 1520 images, including haematoxylin and eosin staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer's disease (AD), progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). We assessed GPT-4V's performance using multi-step prompts to determine how textual context influences image interpretation. We also employed few-shot learning to enhance improvements in GPT-4V's diagnostic performance in classifying three specific tau lesions-astrocytic plaques, neuritic plaques and tufted astrocytes-and compared the outcomes with the CNN model YOLOv8. RESULTS: GPT-4V accurately recognised staining techniques and tissue origin but struggled with specific lesion identification. The interpretation of images was notably influenced by the provided textual context, which sometimes led to diagnostic inaccuracies. For instance, when presented with images of the motor cortex, the diagnosis shifted inappropriately from AD to CBD or PSP. However, few-shot learning markedly improved GPT-4V's diagnostic capabilities, enhancing accuracy from 40% in zero-shot learning to 90% with 20-shot learning, matching the performance of YOLOv8, which required 100-shot learning to achieve the same accuracy. CONCLUSIONS: Although GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its performance. This approach is especially promising for neuropathology, where acquiring extensive labelled datasets is often challenging.

Assessment of Ki-67 and mitoses in pituitary neuroendocrine tumours-Consistency counts.

Pituitary neuroendocrine tumour Ki-67 proliferation index varies according to the number of tumour cells assessed. Consistent Ki-67 scoring approaches and re-evaluation of the recommended Ki-67 3% cut-off are required to clarify controversies in pituitary neuroendocrine tumour Ki-67 proliferation index assessment.

Fluorescence confocal microscopy can accelerate diagnosis of cervical lymphadenopathy.

Fluorescence confocal microscopy (FCM) is an optical technique that uses laser light sources of different wavelengths to generate real-time images of fresh, unfixed tissue specimens. Unlike conventional histological evaluation methods, FCM is able to assess fresh tissue samples without the associated cryo artifacts typically observed after frozen sectioning. The purpose of this study was to evaluate the utility of FCM imaging in the differential diagnosis of cervical lymphadenopathy. Twenty-two cervical lymph node specimens from patients with lymphadenopathy of unknown origin were imaged by FCM. Two pathologists independently evaluated the scans for suspicion of malignancy and preliminary diagnosis. Malignancy was reliably excluded or confirmed by both pathologists with a sensitivity of 90.9% for pathologist 1 and 100% for pathologist 2. The specificity was 100% for both pathologists. For the preliminary diagnosis, almost perfect agreement with the final diagnosis was observed for both pathologists (κ= 0.94 for pathologist 1 and κ= 1.00 for pathologist 2). This is the first study to investigate lymph node specimens with different diagnoses, including lymphoma, using FCM. Our results indicate that differential diagnosis of lymph node specimens is feasible in FCM images, thus encouraging further exploration of FCM imaging in lymph node specimens to accelerate diagnosis and open the possibility of digitizing diagnosis on fresh, unfixed tissue.

A selective CutMix approach improves generalizability of deep learning-based grading and risk assessment of prostate cancer.

The Gleason score is an important predictor of prognosis in prostate cancer. However, its subjective nature can result in over- or under-grading. Our objective was to train an artificial intelligence (AI)-based algorithm to grade prostate cancer in specimens from patients who underwent radical prostatectomy (RP) and to assess the correlation of AI-estimated proportions of different Gleason patterns with biochemical recurrence-free survival (RFS), metastasis-free survival (MFS), and overall survival (OS). Training and validation of algorithms for cancer detection and grading were completed with three large datasets containing a total of 580 whole-mount prostate slides from 191 RP patients at two centers and 6218 annotated needle biopsy slides from the publicly available Prostate Cancer Grading Assessment dataset. A cancer detection model was trained using MobileNetV3 on 0.5 mm × 0.5 mm cancer areas (tiles) captured at 10× magnification. For cancer grading, a Gleason pattern detector was trained on tiles using a ResNet50 convolutional neural network and a selective CutMix training strategy involving a mixture of real and artificial examples. This strategy resulted in improved model generalizability in the test set compared with three different control experiments when evaluated on both needle biopsy slides and whole-mount prostate slides from different centers. In an additional test cohort of RP patients who were clinically followed over 30 years, quantitative Gleason pattern AI estimates achieved concordance indexes of 0.69, 0.72, and 0.64 for predicting RFS, MFS, and OS times, outperforming the control experiments and International Society of Urological Pathology system (ISUP) grading by pathologists. Finally, unsupervised clustering of test RP patient specimens into low-, medium-, and high-risk groups based on AI-estimated proportions of each Gleason pattern resulted in significantly improved RFS and MFS stratification compared with ISUP grading. In summary, deep learning-based quantitative Gleason scoring using a selective CutMix training strategy may improve prognostication after prostate cancer surgery.

ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts.

Introduction: The development of next-generation tissue-engineered medical devices such as tissue-engineered vascular grafts (TEVGs) is a leading trend in translational medicine. Microscopic examination is an indispensable part of animal experimentation, and histopathological analysis of regenerated tissue is crucial for assessing the outcomes of implanted medical devices. However, the objective quantification of regenerated tissues can be challenging due to their unusual and complex architecture. To address these challenges, research and development of advanced ML-driven tools for performing adequate histological analysis appears to be an extremely promising direction. Methods: We compiled a dataset of 104 representative whole slide images (WSIs) of TEVGs which were collected after a 6-month implantation into the sheep carotid artery. The histological examination aimed to analyze the patterns of vascular tissue regeneration in TEVGs in situ. Having performed an automated slicing of these WSIs by the Entropy Masker algorithm, we filtered and then manually annotated 1,401 patches to identify 9 histological features: arteriole lumen, arteriole media, arteriole adventitia, venule lumen, venule wall, capillary lumen, capillary wall, immune cells, and nerve trunks. To segment and quantify these features, we rigorously tuned and evaluated the performance of six deep learning models (U-Net, LinkNet, FPN, PSPNet, DeepLabV3, and MA-Net). Results: After rigorous hyperparameter optimization, all six deep learning models achieved mean Dice Similarity Coefficients (DSC) exceeding 0.823. Notably, FPN and PSPNet exhibited the fastest convergence rates. MA-Net stood out with the highest mean DSC of 0.875, demonstrating superior performance in arteriole segmentation. DeepLabV3 performed well in segmenting venous and capillary structures, while FPN exhibited proficiency in identifying immune cells and nerve trunks. An ensemble of these three models attained an average DSC of 0.889, surpassing their individual performances. Conclusion: This study showcases the potential of ML-driven segmentation in the analysis of histological images of tissue-engineered vascular grafts. Through the creation of a unique dataset and the optimization of deep neural network hyperparameters, we developed and validated an ensemble model, establishing an effective tool for detecting key histological features essential for understanding vascular tissue regeneration. These advances herald a significant improvement in ML-assisted workflows for tissue engineering research and development.

Fluorescence confocal microscopy for evaluation of fresh surgical specimens and consecutive tumor cell isolation in rare pediatric tumors.

Fluorescence confocal microscopy (FCM) is an optical technique that uses laser light sources of different wavelengths to generate real-time images of fresh, unfixed tissue specimens. FCM allows histological evaluation of fresh tissue samples without the associated cryo artifacts after frozen sectioning. The aim of this study was to prospectively evaluate pediatric tumor specimens and assess their suitability for fresh tumor sampling. In addition, we aimed to determine whether tumor cell isolation for stable cell culture is still feasible after FCM imaging. Pediatric tumor specimens were imaged using FCM. Tumor viability and suitability for tissue sampling were evaluated and compared with H&E staining after paraffin embedding. In addition, FCM-processed and non-FCM-processed tissue samples were sent for tumor cell isolation to evaluate possible effects after FCM processing. When comparing estimated tumor cell viability using FCM and H&E, we found good to excellent correlating estimates (intraclass correlation coefficient = 0.891, p < 0.001), as well as substantial agreement in whether the tissue appeared adequate for fresh tissue collection (κ = 0.762, p < 0.001). After FCM, seven out of eight samples yielded passable cell cultures, compared to eight out of eight for non-FCM processed samples. Our study suggests that the use of FCM in tumor sampling can increase the yield of suitable fresh tumor samples by identifying viable tumor areas and ensuring that sufficient tissue remains for diagnosis. Our study also provides first evidence that the isolation and growth of tumor cells in culture are not compromised by the FCM technique.

Liver fibrosis analysis using digital pathology.

Digital pathology has enabled the noninvasive quantification of pathological parameters. In addition, the combination of digital pathology and artificial intelligence has enabled the analysis of a vast amount of information, leading to the sharing of much information and the elimination of knowledge gaps. Fibrosis, which reflects chronic inflammation, is the most important pathological parameter in chronic liver diseases, such as viral hepatitis and metabolic dysfunction-associated steatotic liver disease. It has been reported that the quantitative evaluation of various fibrotic parameters by digital pathology can predict the prognosis of liver disease and hepatocarcinogenesis. Liver fibrosis evaluation methods include 1 fiber quantification, 2 elastin and collagen quantification, 3 s harmonic generation/two photon excitation fluorescence (SHG/TPE) microscopy, and 4 Fibronest™..　In this review, we provide an overview of role of digital pathology on the evaluation of fibrosis in liver disease and the characteristics of recent methods to assess liver fibrosis.

Development of a multi-scanner facility for data acquisition for digital pathology artificial intelligence.

Whole slide imaging (WSI) of pathology glass slides using high-resolution scanners has enabled the large-scale application of artificial intelligence (AI) in pathology, to support the detection and diagnosis of disease, potentially increasing efficiency and accuracy in tissue diagnosis. Despite the promise of AI, it has limitations. 'Brittleness' or sensitivity to variation in inputs necessitates that large amounts of data are used for training. AI is often trained on data from different scanners but not usually by replicating the same slide across scanners. The utilisation of multiple WSI instruments to produce digital replicas of the same slides will make more comprehensive datasets and may improve the robustness and generalisability of AI algorithms as well as reduce the overall data requirements of AI training. To this end, the National Pathology Imaging Cooperative (NPIC) has built the AI FORGE (Facilitating Opportunities for Robust Generalisable data Emulation), a unique multi-scanner facility embedded in a clinical site in the NHS to (1) compare scanner performance, (2) replicate digital pathology image datasets across WSI systems, and (3) support the evaluation of clinical AI algorithms. The NPIC AI FORGE currently comprises 15 scanners from nine manufacturers. It can generate approximately 4,000 WSI images per day (approximately 7 TB of image data). This paper describes the process followed to plan and build such a facility. © 2024 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Ex Vivo Fluorescence Confocal Microscopy for Intraoperative Examinations of Lung Tumors as Alternative to Frozen Sections-A Proof-of-Concept Study.

BACKGROUND: Intraoperative frozen sections (FS) are frequently used to establish the diagnosis of lung cancer when preoperative examinations are not conclusive. The downside of FS is its resource-intensive nature and the risk of tissue depletion when small lesions are assessed. Ex vivo fluorescence confocal microscopy (FCM) is a novel microimaging method for loss-free examinations of native materials. We tested its suitability for the intraoperative diagnosis of lung tumors. METHODS: Samples from 59 lung resection specimens containing 45 carcinomas were examined in the FCM. The diagnostic performance in the evaluation of malignancy and histological typing of lung tumors was evaluated in comparison with FS and the final diagnosis. RESULTS: A total of 44/45 (98%) carcinomas were correctly identified as malignant in the FCM. A total of 33/44 (75%) carcinomas were correctly subtyped, which was comparable with the results of FS and conventional histology. Our tests documented the excellent visualization of cytological features of normal tissues and tumors. Compared to FS, FCM was technically less demanding and less personnel intensive. CONCLUSIONS: The ex vivo FCM is a fast, effective, and safe method for diagnosing and subtyping lung cancer and is, therefore, a promising alternative to FS. The method preserves the tissue without loss for subsequent examinations, which is an advantage in the diagnosis of small tumors and for biobanking.

Ensemble Deep Learning-Based Image Classification for Breast Cancer Subtype and Invasiveness Diagnosis from Whole Slide Image Histopathology.

Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.

Exploration of tissue fixation methods suitable for digital pathological studies of the testis.

BACKGROUND: The way of testicular tissue fixation directly affects the correlation and structural integrity between connective tissue and seminiferous tubules, which is essential for the study of male reproductive development. This study aimed to find the optimal fixative and fixation time to produce high-quality testicular histopathological sections, and provided a suitable foundation for in-depth study of male reproductive development with digital pathology technology. METHODS: Testes were removed from both sides of 25 male C57BL/6 mice. Samples were fixed in three different fixatives, 10% neutral buffered formalin (10% NBF), modified Davidson's fluid (mDF), and Bouin's Fluid (BF), for 8, 12, and 24 h, respectively. Hematoxylin and eosin (H&E) staining, periodic acid Schiff-hematoxylin (PAS-h) staining, and immunohistochemistry (IHC) were used to evaluate the testicle morphology, staging of mouse seminiferous tubules, and protein preservation. Aperio ScanScope CS2 panoramic scanning was used to perform quantitative analyses. RESULTS: H&E staining showed 10% NBF resulted in an approximately 15-17% reduction in the thickness of seminiferous epithelium. BF and mDF provided excellent results when staining acrosomes with PAS-h. IHC staining of synaptonemal complexes 3 (Sycp3) was superior in mDF compared to BF-fixed samples. Fixation in mDF and BF improved testis tissue morphology compared to 10% NBF. CONCLUSIONS: Quantitative analysis showed that BF exhibited a very low IHC staining efficiency and revealed that mouse testes fixed for 12 h with mDF, exhibited morphological details, excellent efficiency of PAS-h staining for seminiferous tubule staging, and IHC results. In addition, the morphological damage of testis was prolonged with the duration of fixation time.

Eye tracking in digital pathology: A comprehensive literature review.

Eye tracking has been used for decades in attempt to understand the cognitive processes of individuals. From memory access to problem-solving to decision-making, such insight has the potential to improve workflows and the education of students to become experts in relevant fields. Until recently, the traditional use of microscopes in pathology made eye tracking exceptionally difficult. However, the digital revolution of pathology from conventional microscopes to digital whole slide images allows for new research to be conducted and information to be learned with regards to pathologist visual search patterns and learning experiences. This has the promise to make pathology education more efficient and engaging, ultimately creating stronger and more proficient generations of pathologists to come. The goal of this review on eye tracking in pathology is to characterize and compare the visual search patterns of pathologists. The PubMed and Web of Science databases were searched using 'pathology' AND 'eye tracking' synonyms. A total of 22 relevant full-text articles published up to and including 2023 were identified and included in this review. Thematic analysis was conducted to organize each study into one or more of the 10 themes identified to characterize the visual search patterns of pathologists: (1) effect of experience, (2) fixations, (3) zooming, (4) panning, (5) saccades, (6) pupil diameter, (7) interpretation time, (8) strategies, (9) machine learning, and (10) education. Expert pathologists were found to have higher diagnostic accuracy, fewer fixations, and shorter interpretation times than pathologists with less experience. Further, literature on eye tracking in pathology indicates that there are several visual strategies for diagnostic interpretation of digital pathology images, but no evidence of a superior strategy exists. The educational implications of eye tracking in pathology have also been explored but the effect of teaching novices how to search as an expert remains unclear. In this article, the main challenges and prospects of eye tracking in pathology are briefly discussed along with their implications to the field.

Validation and three years of clinical experience in using an artificial intelligence algorithm as a second read system for prostate cancer diagnosis-real-world experience.

Background: Prostate cancer ranks as the most frequently diagnosed cancer in men in the USA, with significant mortality rates. Early detection is pivotal for optimal patient outcomes, providing increased treatment options and potentially less invasive interventions. There remain significant challenges in prostate cancer histopathology, including the potential for missed diagnoses due to pathologist variability and subjective interpretations. Methods: To address these challenges, this study investigates the ability of artificial intelligence (AI) to enhance diagnostic accuracy. The Galen™ Prostate AI algorithm was validated on a cohort of Puerto Rican men to demonstrate its efficacy in cancer detection and Gleason grading. Subsequently, the AI algorithm was integrated into routine clinical practice during a 3-year period at a CLIA certified precision pathology laboratory. Results: The Galen™ Prostate AI algorithm showed a 96.7% (95% CI 95.6-97.8) specificity and a 96.6% (95% CI 93.3-98.8) sensitivity for prostate cancer detection and 82.1% specificity (95% CI 73.9-88.5) and 81.1% sensitivity (95% CI 73.7-87.2) for distinction of Gleason Grade Group 1 from Grade Group 2+. The subsequent AI integration into routine clinical use examined prostate cancer diagnoses on >122,000 slides and 9200 cases over 3 years and had an overall AI Impact ™ factor of 1.8%. Conclusions: The potential of AI to be a powerful, reliable, and effective diagnostic tool for pathologists is highlighted, while the AI Impact™ in a real-world setting demonstrates the ability of AI to standardize prostate cancer diagnosis at a high level of performance across pathologists.

A Minimal Approach to Demonstrate Concordance of Digital and Conventional Microscopy in Toxicologic Pathology.

Digitalization of pathology workflows has undergone a rapid evolution and has been widely established in the diagnostic field but remains a challenge in the nonclinical safety context due to lack of regulatory guidance and validation experience for good laboratory practice (GLP) use. One means to demonstrate that digital slides are fit for purpose, that is, provide sufficient quality for pathologists to reach a diagnosis, is conduction of comparison studies, which have been published both, for veterinary and human diagnostic pathology, but not for toxicologic pathology. Here, we present an approach that uses study material from nonclinical safety studies and that allows for the statistical comparison of concordance rates for glass and digital slide evaluation while minimizing time and effort for the involved personnel. Using a benchmark study design, we demonstrate that evaluation of digital slides fits the purpose of nonclinical safety evaluation. These results add to reports of successful workflow validations and support the full adaptation of digital pathology in the regulatory field.

Deep learning framework for comprehensive molecular and prognostic stratifications of triple-negative breast cancer.

Triple-negative breast cancer (TNBC) is the most challenging breast cancer subtype. Molecular stratification and target therapy bring clinical benefit for TNBC patients, but it is difficult to implement comprehensive molecular testing in clinical practice. Here, using our multi-omics TNBC cohort (N = 425), a deep learning-based framework was devised and validated for comprehensive predictions of molecular features, subtypes and prognosis from pathological whole slide images. The framework first incorporated a neural network to decompose the tissue on WSIs, followed by a second one which was trained based on certain tissue types for predicting different targets. Multi-omics molecular features were analyzed including somatic mutations, copy number alterations, germline mutations, biological pathway activities, metabolomics features and immunotherapy biomarkers. It was shown that the molecular features with therapeutic implications can be predicted including the somatic PIK3CA mutation, germline BRCA2 mutation and PD-L1 protein expression (area under the curve [AUC]: 0.78, 0.79 and 0.74 respectively). The molecular subtypes of TNBC can be identified (AUC: 0.84, 0.85, 0.93 and 0.73 for the basal-like immune-suppressed, immunomodulatory, luminal androgen receptor, and mesenchymal-like subtypes respectively) and their distinctive morphological patterns were revealed, which provided novel insights into the heterogeneity of TNBC. A neural network integrating image features and clinical covariates stratified patients into groups with different survival outcomes (log-rank P < 0.001). Our prediction framework and neural network models were externally validated on the TNBC cases from TCGA (N = 143) and appeared robust to the changes in patient population. For potential clinical translation, we built a novel online platform, where we modularized and deployed our framework along with the validated models. It can realize real-time one-stop prediction for new cases. In summary, using only pathological WSIs, our proposed framework can enable comprehensive stratifications of TNBC patients and provide valuable information for therapeutic decision-making. It had the potential to be clinically implemented and promote the personalized management of TNBC.