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

TL;DR

This paper presents GLAM, a deep learning approach that effectively segments human kidney lesions by leveraging mouse model data through hybrid learning, addressing the challenge of cross-species transfer in pathological segmentation.

Contribution

Introduces a hybrid learning method for applying mouse model segmentation techniques to human kidney lesions, improving accuracy in pathological tissue analysis.

Findings

Hybrid learning outperforms zero-shot transfer in segmentation accuracy.

Mouse-to-human transfer learning is feasible for pathological glomeruli.

The model effectively captures morphological variations in diseased tissues.

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: ``\textit{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.