Development of a multi‐scanner facility for data acquisition for digital pathology artificial intelligence
Open Access
- 10 July 2024
- journal article
- research article
- Published by Wiley in The Journal of Pathology
- Vol. 264 (1) , 80-89
Abstract
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.Keywords
All Related Versions
Funding Information
- UK Research and Innovation (104687)
This publication has 17 references indexed in Scilit:
- Automatic data augmentation to improve generalization of deep learning in H&E stained histopathologyComputers in Biology and Medicine, 2024
- Transparency and the Black Box Problem: Why We Do Not Trust AIPhilosophy & Technology, 2021
- The impact of site-specific digital histology signatures on deep learning model accuracy and biasNature Communications, 2021
- The Effect of Quality Control on Accuracy of Digital Pathology Image AnalysisIEEE Journal of Biomedical and Health Informatics, 2020
- Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic studyThe Lancet Oncology, 2019
- Maintaining quality diagnosis with digital pathology: a practical guide to ISO 15189 accreditationJournal of Clinical Pathology, 2019
- Machine Learning Methods for Histopathological Image AnalysisComputational and Structural Biotechnology Journal, 2018
- Development of a novel tissue‐mimicking color calibration slide for digital microscopyColor Research & Application, 2017
- Colour in digital pathology: a reviewHistopathology, 2016
- Quantification of histochemical stains using whole slide imaging: development of a method and demonstration of its usefulness in laboratory quality controlJournal of Clinical Pathology, 2014