Article Text
Abstract
Background Machine learning (ML) models can help assisting diagnosis by rapidly localising and classifying regions of interest (ROIs) within whole slide images (WSIs). Effective ML models for clinical decision support require a substantial dataset of ‘real’ data, and in reality, it should be robust, user-friendly and universally applicable.
Methods WSIs of primary IgAN were collected and annotated. The H-AI-L algorithm which could facilitate direct WSI viewing and potential ROI detection for clinicians was built on the cloud server of matpool, a shared internet-based service platform. Model performance was evaluated using F1-score, precision, recall and Matthew’s correlation coefficient (MCC).
Results The F1-score of glomerular localisation in WSIs was 0.85 and 0.89 for the initial and pretrained models, respectively, with corresponding recall values of 0.79 and 0.83, and precision scores of 0.92 and 0.97. Dichotomous differentiation between global sclerotic (GS) and other glomeruli revealed F1-scores of 0.70 and 0.91, and MCC values of 0.55 and 0.87, for the initial and pretrained models, respectively. The overall F1-score of multiclassification was 0.81 for the pretrained models. The total glomerular recall rate was 0.96, with F1-scores of 0.68, 0.56 and 0.26 for GS, segmental glomerulosclerosis and crescent (C), respectively. Interstitial fibrosis/tubular atrophy lesion similarity between the true label and model predictions was 0.75.
Conclusions Our results underscore the efficacy of the ML integration algorithm in segmenting ROIs in IgAN WSIs, and the internet-based model deployment is in favour of widespread adoption and utilisation across multiple centres and increased volumes of WSIs.
- Machine Learning
- KIDNEY
- TELEPATHOLOGY
- DIAGNOSIS
Data availability statement
All data relevant to the study are included in the article or uploaded as online supplemental information.
Statistics from Altmetric.com
Data availability statement
All data relevant to the study are included in the article or uploaded as online supplemental information.
Footnotes
Handling editor Runjan Chetty.
Contributors The study was conceptualised by KLM and Y-LH. The methodology was devised by KLM, Y-LH, XQL, YH, FYJ, QZ and QYW. Experimental work was carried out by Y-LH, and resources were managed by KLM. The original draft of the manuscript was written by Y-LH, and reviewed and edited by KLM and Y-LH. Supervision and funding acquisition were handled by KLM.
Funding This study was supported by the National Natural Science Foundation of China (82370716, 82170736, 81970629) and the Natural Science Foundation of Zhejiang Province (LHDMY23H070002).
Competing interests None declared.
Provenance and peer review Not commissioned; externally peer reviewed.