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.
ABSTRACT
Background: Up to 20% of patients with inflammatory bowel disease (IBD) who are refractory to thiopurine therapy preferentially produce 6-methylmercaptopurine (6-MMP) at the expense of 6-thioguanine nucleotides (6-TGN), resulting in a high 6-MMP:6-TGN ratio (>20). The objective of this study was to evaluate whether genetic variability in guanine monophosphate synthetase (GMPS) contributes to preferential 6-MMP metabolizer phenotype. Methods: Exome sequencing was performed in a cohort of IBD patients with 6-MMP:6-TGN ratios of >100 to identify nonsynonymous single nucleotide polymorphisms (nsSNPs). In vitro assays were performed to measure GMPS activity associated with these nsSNPs. Frequency of the nsSNPs was measured in a cohort of 530 Caucasian IBD patients. Results: Two nsSNPs in GMPS (rs747629729, rs61750370) were detected in 11 patients with very high 6-MMP:6-TGN ratios. The 2 nsSNPs were predicted to be damaging by in silico analysis. In vitro assays demonstrated that both nsSNPs resulted in a significant reduction in GMPS activity (P < 0.05). The SNP rs61750370 was significantly associated with 6-MMP:6-TGN ratios ≥100 (odds ratio, 5.64; 95% confidence interval, 1.01-25.12; P < 0.031) in a subset of 264 Caucasian IBD patients. Conclusions: The GMPS SNP rs61750370 may be a reliable risk factor for extreme 6MMP preferential metabolism.
