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.

Pathologists light level preferences using the microscope-study to guide digital pathology display use.

Background: Currently, there is a paucity of guidelines relating to displays used for digital pathology making procurement decisions, and optimal display configuration, challenging.Experience suggests pathologists have personal preferences for brightness when using a conventional microscope which we hypothesized could be used as a predictor for display setup. Methods: We conducted an online survey across six NHS hospitals, totalling 108 practicing pathologists, to capture brightness adjustment habits on both microscopes and displays.A convenience subsample of respondents was then invited to take part in a practical task to determine microscope brightness and display luminance preferences in the normal working environment. A novel adaptation for a lightmeter was developed to directly measure the light output from the microscope eyepiece. Results: The survey (response rate 59% n=64) indicates 81% of respondents adjust the brightness on their microscope. In comparison, only 11% report adjusting their digital display. Display adjustments were more likely to be for visual comfort and ambient light compensation rather than for tissue factors, common for microscope adjustments. Part of this discrepancy relates to lack of knowledge of how to adjust displays and lack of guidance on whether this is safe; But, 66% felt that the ability to adjust the light on the display was important.Twenty consultants took part in the practical brightness assessment. Light preferences on the microscope showed no correlation with display preferences, except where a pathologist has a markedly brighter microscope light preference. All of the preferences in this cohort were for a display luminance of <500 cd/m2, with 90% preferring 350 cd/m2 or less. There was no correlation between these preferences and the ambient lighting in the room. Conclusions: We conclude that microscope preferences can only be used to predict display luminance requirements where the microscope is being used at very high brightness levels. A display capable of a brightness of 500 cd/m2 should be suitable for almost all pathologists with 300 cd/m2 suitable for the majority. Although display luminance is not frequently changed by users, the ability to do so was felt to be important by the majority of respondents.Further work needs to be undertaken to establish the relationship between diagnostic performance, luminance preferences, and ambient lighting levels.

Quantitative assessment of H&E staining for pathology: development and clinical evaluation of a novel system.

BACKGROUND: Staining tissue samples to visualise cellular detail and tissue structure is at the core of pathology diagnosis, but variations in staining can result in significantly different appearances of the tissue sample. While the human visual system is adept at compensating for stain variation, with the growth of digital imaging in pathology, the impact of this variation can be more profound. Despite the ubiquity of haematoxylin and eosin staining in clinical practice worldwide, objective quantification is not yet available. We propose a method for quantitative haematoxylin and eosin stain assessment to facilitate quality assurance of histopathology staining, enabling truly quantitative quality control and improved standardisation. METHODS: The stain quantification method comprises conventional microscope slides with a stain-responsive biopolymer film affixed to one side, called stain assessment slides. The stain assessment slides were characterised with haematoxylin and eosin, and implemented in one clinical laboratory to quantify variation levels. RESULTS: Stain assessment slide stain uptake increased linearly with duration of haematoxylin and eosin staining (r = 0.99), and demonstrated linearly comparable staining to samples of human liver tissue (r values 0.98-0.99). Laboratory implementation of this technique quantified intra- and inter-instrument variation of staining instruments at one point in time and across a five-day period. CONCLUSION: The proposed method has been shown to reliably quantify stain uptake, providing an effective laboratory quality control method for stain variation. This is especially important for whole slide imaging and the future development of artificial intelligence in digital pathology.

Immune subtyping of melanoma whole slide images using multiple instance learning.

Determining early-stage prognostic markers and stratifying patients for effective treatment are two key challenges for improving outcomes for melanoma patients. Previous studies have used tumour transcriptome data to stratify patients into immune subgroups, which were associated with differential melanoma specific survival and potential predictive biomarkers. However, acquiring transcriptome data is a time-consuming and costly process. Moreover, it is not routinely used in the current clinical workflow. Here, we attempt to overcome this by developing deep learning models to classify gigapixel haematoxylin and eosin (H&E) stained pathology slides, which are well established in clinical workflows, into these immune subgroups. We systematically assess six different multiple instance learning (MIL) frameworks, using five different image resolutions and three different feature extraction methods. We show that pathology-specific self-supervised models using 10x resolution patches generate superior representations for the classification of immune subtypes. In addition, in a primary melanoma dataset, we achieve a mean area under the receiver operating characteristic curve (AUC) of 0.80 for classifying histopathology images into 'high' or 'low immune' subgroups and a mean AUC of 0.82 in an independent TCGA melanoma dataset. Furthermore, we show that these models are able to stratify patients into 'high' and 'low immune' subgroups with significantly different melanoma specific survival outcomes (log rank test, P< 0.005). We anticipate that MIL methods will allow us to find new biomarkers of high importance, act as a tool for clinicians to infer the immune landscape of tumours and stratify patients, without needing to carry out additional expensive genetic tests.

Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy.

Ensuring diagnostic performance of artificial intelligence (AI) before introduction into clinical practice is essential. Growing numbers of studies using AI for digital pathology have been reported over recent years. The aim of this work is to examine the diagnostic accuracy of AI in digital pathology images for any disease. This systematic review and meta-analysis included diagnostic accuracy studies using any type of AI applied to whole slide images (WSIs) for any disease. The reference standard was diagnosis by histopathological assessment and/or immunohistochemistry. Searches were conducted in PubMed, EMBASE and CENTRAL in June 2022. Risk of bias and concerns of applicability were assessed using the QUADAS-2 tool. Data extraction was conducted by two investigators and meta-analysis was performed using a bivariate random effects model, with additional subgroup analyses also performed. Of 2976 identified studies, 100 were included in the review and 48 in the meta-analysis. Studies were from a range of countries, including over 152,000 whole slide images (WSIs), representing many diseases. These studies reported a mean sensitivity of 96.3% (CI 94.1-97.7) and mean specificity of 93.3% (CI 90.5-95.4). There was heterogeneity in study design and 99% of studies identified for inclusion had at least one area at high or unclear risk of bias or applicability concerns. Details on selection of cases, division of model development and validation data and raw performance data were frequently ambiguous or missing. AI is reported as having high diagnostic accuracy in the reported areas but requires more rigorous evaluation of its performance.