Glomerular Lesion Recognition Based on Pathology Images With Annotation Noise via Noisy Label Learning

Abstract

Background: Glomerular lesion recognition is one of the most crucial steps in the diagnosis of kidney disease. Deep learning, which relies on large numbers of pathology images, assists pathologists to access glomerular lesions more efficiently, objectively and accurately. However, due to different pathological development of glomeruli, complicated lesion patterns, and limited resolution of pathology images, there is annotation noise in datasets, making the deep learning model under-or over-fit. Methods: In this paper, we propose a novel noisy label learning model for lesion recognition in glomerular datasets with annotation noise. The model integrates uncertainty-based noisy label discriminator, contrastive learning, and consistency regularization to achieve high signal-to-noise supervision, pathology feature extraction, and utilization of pathology images. Results: We constructed large-scale glomerular datasets from 870 kidney disease cases using different stainings including Periodic acid-Schiff (PAS), Masson Trichrome (MT) and Periodic Schiff-Methenamine (PASM). Intensive experiments demonstrated the superiority of the proposed model for glomerular lesion recognition compared to other methods, as 25% of the lesions had f 1 − score above 85%, 43.75% had f 1 − score above 80%, and 75% had f 1 − score at or above 70%. Additionally, further experiments demonstrate the effectiveness of each module. Conclusions: The noisy label learning model proposed is able to recognize the most glomerular lesions, with the annotation noise discrimination and large amounts of pathology images utilization, laying the foundation for the development of computer-aided evaluation system for renal pathology.

Registration‐enhanced multiple instance learning for cervical cancer whole slide image classification

“…It has been applied to medical image analysis and made significant improvements. [33][34][35] Tang et al 36 adopted self-supervised learning to train vision transformers for multiple tasks of medical image analysis. Azizi et al 37 explored the effectiveness of selfsupervised pretraining based on ImageNet 38 and unlabeled medical image datasets.…”