Digital pathology for reporting histopathology samples, including cancer screening samples - definitive evidence from a multisite study.

AIMS: To conduct a definitive multicentre comparison of digital pathology (DP) with light microscopy (LM) for reporting histopathology slides including breast and bowel cancer screening samples. METHODS: A total of 2024 cases (608 breast, 607 GI, 609 skin, 200 renal) were studied, including 207 breast and 250 bowel cancer screening samples. Cases were examined by four pathologists (16 study pathologists across the four speciality groups), using both LM and DP, with the order randomly assigned and 6 weeks between viewings. Reports were compared for clinical management concordance (CMC), meaning identical diagnoses plus differences which do not affect patient management. Percentage CMCs were computed using logistic regression models with crossed random-effects terms for case and pathologist. The obtained percentage CMCs were referenced to 98.3% calculated from previous studies. RESULTS: For all cases LM versus DP comparisons showed the CMC rates were 99.95% [95% confidence interval (CI) = 99.90-99.97] and 98.96 (95% CI = 98.42-99.32) for cancer screening samples. In speciality groups CMC for LM versus DP showed: breast 99.40% (99.06-99.62) overall and 96.27% (94.63-97.43) for cancer screening samples; [gastrointestinal (GI) = 99.96% (99.89-99.99)] overall and 99.93% (99.68-99.98) for bowel cancer screening samples; skin 99.99% (99.92-100.0); renal 99.99% (99.57-100.0). Analysis of clinically significant differences revealed discrepancies in areas where interobserver variability is known to be high, in reads performed with both modalities and without apparent trends to either. CONCLUSIONS: Comparing LM and DP CMC, overall rates exceed the reference 98.3%, providing compelling evidence that pathologists provide equivalent results for both routine and cancer screening samples irrespective of the modality used.

Development and validation of artificial intelligence-based prescreening of large-bowel biopsies taken in the UK and Portugal: a retrospective cohort study.

BACKGROUND: Histopathological examination is a crucial step in the diagnosis and treatment of many major diseases. Aiming to facilitate diagnostic decision making and improve the workload of pathologists, we developed an artificial intelligence (AI)-based prescreening tool that analyses whole-slide images (WSIs) of large-bowel biopsies to identify typical, non-neoplastic, and neoplastic biopsies. METHODS: This retrospective cohort study was conducted with an internal development cohort of slides acquired from a hospital in the UK and three external validation cohorts of WSIs acquired from two hospitals in the UK and one clinical laboratory in Portugal. To learn the differential histological patterns from digitised WSIs of large-bowel biopsy slides, our proposed weakly supervised deep-learning model (Colorectal AI Model for Abnormality Detection [CAIMAN]) used slide-level diagnostic labels and no detailed cell or region-level annotations. The method was developed with an internal development cohort of 5054 biopsy slides from 2080 patients that were labelled with corresponding diagnostic categories assigned by pathologists. The three external validation cohorts, with a total of 1536 slides, were used for independent validation of CAIMAN. Each WSI was classified into one of three classes (ie, typical, atypical non-neoplastic, and atypical neoplastic). Prediction scores of image tiles were aggregated into three prediction scores for the whole slide, one for its likelihood of being typical, one for its likelihood of being non-neoplastic, and one for its likelihood of being neoplastic. The assessment of the external validation cohorts was conducted by the trained and frozen CAIMAN model. To evaluate model performance, we calculated area under the convex hull of the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and specificity compared with our previously published iterative draw and rank sampling (IDaRS) algorithm. We also generated heat maps and saliency maps to analyse and visualise the relationship between the WSI diagnostic labels and spatial features of the tissue microenvironment. The main outcome of this study was the ability of CAIMAN to accurately identify typical and atypical WSIs of colon biopsies, which could potentially facilitate automatic removing of typical biopsies from the diagnostic workload in clinics. FINDINGS: A randomly selected subset of all large bowel biopsies was obtained between Jan 1, 2012, and Dec 31, 2017. The AI training, validation, and assessments were done between Jan 1, 2021, and Sept 30, 2022. WSIs with diagnostic labels were collected between Jan 1 and Sept 30, 2022. Our analysis showed no statistically significant differences across prediction scores from CAIMAN for typical and atypical classes based on anatomical sites of the biopsy. At 0·99 sensitivity, CAIMAN (specificity 0·5592) was more accurate than an IDaRS-based weakly supervised WSI-classification pipeline (0·4629) in identifying typical and atypical biopsies on cross-validation in the internal development cohort (p<0·0001). At 0·99 sensitivity, CAIMAN was also more accurate than IDaRS for two external validation cohorts (p<0·0001), but not for a third external validation cohort (p=0·10). CAIMAN provided higher specificity than IDaRS at some high-sensitivity thresholds (0·7763 vs 0·6222 for 0·95 sensitivity, 0·7126 vs 0·5407 for 0·97 sensitivity, and 0·5615 vs 0·3970 for 0·99 sensitivity on one of the external validation cohorts) and showed high classification performance in distinguishing between neoplastic biopsies (AUROC 0·9928, 95% CI 0·9927-0·9929), inflammatory biopsies (0·9658, 0·9655-0·9661), and atypical biopsies (0·9789, 0·9786-0·9792). On the three external validation cohorts, CAIMAN had AUROC values of 0·9431 (95% CI 0·9165-0·9697), 0·9576 (0·9568-0·9584), and 0·9636 (0·9615-0·9657) for the detection of atypical biopsies. Saliency maps supported the representation of disease heterogeneity in model predictions and its association with relevant histological features. INTERPRETATION: CAIMAN, with its high sensitivity in detecting atypical large-bowel biopsies, might be a promising improvement in clinical workflow efficiency and diagnostic decision making in prescreening of typical colorectal biopsies. FUNDING: The Pathology Image Data Lake for Analytics, Knowledge and Education Centre of Excellence; the UK Government's Industrial Strategy Challenge Fund; and Innovate UK on behalf of UK Research and Innovation.

Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study.

OBJECTIVE: To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis. DESIGN: A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site. RESULTS: Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features. CONCLUSION: The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption.

Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study.

BACKGROUND: Determining the status of molecular pathways and key mutations in colorectal cancer is crucial for optimal therapeutic decision making. We therefore aimed to develop a novel deep learning pipeline to predict the status of key molecular pathways and mutations from whole-slide images of haematoxylin and eosin-stained colorectal cancer slides as an alternative to current tests. METHODS: In this retrospective study, we used 502 diagnostic slides of primary colorectal tumours from 499 patients in The Cancer Genome Atlas colon and rectal cancer (TCGA-CRC-DX) cohort and developed a weakly supervised deep learning framework involving three separate convolutional neural network models. Whole-slide images were divided into equally sized tiles and model 1 (ResNet18) extracted tumour tiles from non-tumour tiles. These tumour tiles were inputted into model 2 (adapted ResNet34), trained by iterative draw and rank sampling to calculate a prediction score for each tile that represented the likelihood of a tile belonging to the molecular labels of high mutation density (vs low mutation density), microsatellite instability (vs microsatellite stability), chromosomal instability (vs genomic stability), CpG island methylator phenotype (CIMP)-high (vs CIMP-low), BRAFmut (vs BRAFWT), TP53mut (vs TP53WT), and KRASWT (vs KRASmut). These scores were used to identify the top-ranked titles from each slide, and model 3 (HoVer-Net) segmented and classified the different types of cell nuclei in these tiles. We calculated the area under the convex hull of the receiver operating characteristic curve (AUROC) as a model performance measure and compared our results with those of previously published methods. FINDINGS: Our iterative draw and rank sampling method yielded mean AUROCs for the prediction of hypermutation (0·81 [SD 0·03] vs 0·71), microsatellite instability (0·86 [0·04] vs 0·74), chromosomal instability (0·83 [0·02] vs 0·73), BRAFmut (0·79 [0·01] vs 0·66), and TP53mut (0·73 [0·02] vs 0·64) in the TCGA-CRC-DX cohort that were higher than those from previously published methods, and an AUROC for KRASmut that was similar to previously reported methods (0·60 [SD 0·04] vs 0·60). Mean AUROC for predicting CIMP-high status was 0·79 (SD 0·05). We found high proportions of tumour-infiltrating lymphocytes and necrotic tumour cells to be associated with microsatellite instability, and high proportions of tumour-infiltrating lymphocytes and a low proportion of necrotic tumour cells to be associated with hypermutation. INTERPRETATION: After large-scale validation, our proposed algorithm for predicting clinically important mutations and molecular pathways, such as microsatellite instability, in colorectal cancer could be used to stratify patients for targeted therapies with potentially lower costs and quicker turnaround times than sequencing-based or immunohistochemistry-based approaches. FUNDING: The UK Medical Research Council.

Deep learning based digital cell profiles for risk stratification of urine cytology images.

Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low-risk and high-risk malignancy. Computer-assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning-based approaches. Based on the best performing network predictions at the cell level, we identified low-risk and high-risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology-based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.

Diagnostic concordance and discordance in digital pathology: a systematic review and meta-analysis.

BACKGROUND: Digital pathology (DP) has the potential to fundamentally change the way that histopathology is practised, by streamlining the workflow, increasing efficiency, improving diagnostic accuracy and facilitating the platform for implementation of artificial intelligence-based computer-assisted diagnostics. Although the barriers to wider adoption of DP have been multifactorial, limited evidence of reliability has been a significant contributor. A meta-analysis to demonstrate the combined accuracy and reliability of DP is still lacking in the literature. OBJECTIVES: We aimed to review the published literature on the diagnostic use of DP and to synthesise a statistically pooled evidence on safety and reliability of DP for routine diagnosis (primary and secondary) in the context of validation process. METHODS: A comprehensive literature search was conducted through PubMed, Medline, EMBASE, Cochrane Library and Google Scholar for studies published between 2013 and August 2019. The search protocol identified all studies comparing DP with light microscopy (LM) reporting for diagnostic purposes, predominantly including H&E-stained slides. Random-effects meta-analysis was used to pool evidence from the studies. RESULTS: Twenty-five studies were deemed eligible to be included in the review which examined a total of 10 410 histology samples (average sample size 176). For overall concordance (clinical concordance), the agreement percentage was 98.3% (95% CI 97.4 to 98.9) across 24 studies. A total of 546 major discordances were reported across 25 studies. Over half (57%) of these were related to assessment of nuclear atypia, grading of dysplasia and malignancy. These were followed by challenging diagnoses (26%) and identification of small objects (16%). CONCLUSION: The results of this meta-analysis indicate equivalent performance of DP in comparison with LM for routine diagnosis. Furthermore, the results provide valuable information concerning the areas of diagnostic discrepancy which may warrant particular attention in the transition to DP.

Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images.

Digital histology images are amenable to the application of convolutional neural networks (CNNs) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches (e.g. 224×224 ) extracted from digital histology images due to computational and memory constraints. However, this approach does not incorporate high-resolution contextual information in histology images. We propose a novel way to incorporate a larger context by a context-aware neural network based on images with a dimension of 1792×1792 pixels. The proposed framework first encodes the local representation of a histology image into high dimensional features then aggregates the features by considering their spatial organization to make a final prediction. We evaluated the proposed method on two colorectal cancer datasets for the task of cancer grading. Our method outperformed the traditional patch-based approaches, problem-specific methods, and existing context-based methods. We also presented a comprehensive analysis of different variants of the proposed method.

Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images.

Nuclear segmentation and classification within Haematoxylin & Eosin stained histology images is a fundamental prerequisite in the digital pathology work-flow. The development of automated methods for nuclear segmentation and classification enables the quantitative analysis of tens of thousands of nuclei within a whole-slide pathology image, opening up possibilities of further analysis of large-scale nuclear morphometry. However, automated nuclear segmentation and classification is faced with a major challenge in that there are several different types of nuclei, some of them exhibiting large intra-class variability such as the nuclei of tumour cells. Additionally, some of the nuclei are often clustered together. To address these challenges, we present a novel convolutional neural network for simultaneous nuclear segmentation and classification that leverages the instance-rich information encoded within the vertical and horizontal distances of nuclear pixels to their centres of mass. These distances are then utilised to separate clustered nuclei, resulting in an accurate segmentation, particularly in areas with overlapping instances. Then, for each segmented instance the network predicts the type of nucleus via a devoted up-sampling branch. We demonstrate state-of-the-art performance compared to other methods on multiple independent multi-tissue histology image datasets. As part of this work, we introduce a new dataset of Haematoxylin & Eosin stained colorectal adenocarcinoma image tiles, containing 24,319 exhaustively annotated nuclei with associated class labels.

Oesophageal pemphigoid: a rare cause of dysphagia.

Pemphigus vulgaris (PV) is a rare autoimmune bullous disease which affects the skin and mucous membranes. Oesophageal involvement is rare and has previously been limited to case reports and case series. A recent large case series of 477 PV patients showed that 26/477 (5.4%) had symptomatic oesophageal involvement. We present the case of a 54-year-old Somalian lady with a 10-year history of cutaneous PV, currently in remission, who developed dysphagia and odynophagia and was subsequently found to have oesophageal PV involvement with multiple flaccid bullae which were positive for anti-DSG3 antibodies on in-direct immunofluorescence. She had her treatment switched from azathioprine to mycophenolate and prednisolone, leading to resolution of her symptoms.