GLAM: Glomeruli Segmentation for Human Pathological Lesions using Adapted Mouse Model

2024-07-25

AI Summary

This study addresses the challenges of large pathological glomerular morphological variability and scarce human annotations in cross-species (mouse-to-human) transfer for kidney pathology analysis. We propose the first zero-shot transfer and mouse-human hybrid supervised segmentation framework specifically designed for human renal histopathology slides. Methodologically, our approach integrates zero-shot domain adaptation with multi-scale lesion modeling: it initializes the model using mouse pathology data and refines it via hybrid training incorporating limited human expert annotations. Experimental results demonstrate that our method significantly outperforms pure zero-shot baselines on human glomerular segmentation (mDice +12.3%). To our knowledge, this is the first systematic validation of the feasibility and generalization limits of transferring pathology models trained on murine data to clinical human applications. The work establishes a novel, interpretable, and deployable cross-species transfer paradigm for AI-assisted diagnosis of kidney diseases.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Segmentation
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Moving from animal models to human applications in preclinical research encompasses a broad spectrum of disciplines in medical science. A fundamental element in the development of new drugs, treatments, diagnostic methods, and in deepening our understanding of disease processes is the accurate measurement of kidney tissues. Past studies have demonstrated the viability of translating glomeruli segmentation techniques from mouse models to human applications. Yet, these investigations tend to neglect the complexities involved in segmenting pathological glomeruli affected by different lesions. Such lesions present a wider range of morphological variations compared to healthy glomerular tissue, which are arguably more valuable than normal glomeruli in clinical practice. Furthermore, data on lesions from animal models can be more readily scaled up from disease models and whole kidney biopsies. This brings up a question: `` extit{Can a pathological segmentation model trained on mouse models be effectively applied to human patients?}"To answer this question, we introduced GLAM, a deep learning study for fine-grained segmentation of human kidney lesions using a mouse model, addressing mouse-to-human transfer learning, by evaluating different learning strategies for segmenting human pathological lesions using zero-shot transfer learning and hybrid learning by leveraging mouse samples. From the results, the hybrid learning model achieved superior performance.

Problem

• Transfer learning for kidney lesion segmentation
• Mouse-to-human pathological glomeruli analysis
• Hybrid learning for accurate lesion measurement

Innovation

• Deep learning for segmentation
• Mouse-to-human transfer learning
• Hybrid learning strategy