Enhancing glomeruli segmentation through cross-species pre-training

• Published in: Neurocomputing (Amsterdam) Vol. 563; p. 126947
• Main Authors: Andreini, Paolo, Bonechi, Simone, Dimitri, Giovanna Maria
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2024
• Subjects: Deep Learning; Histopathology; Kidney; Semantic segmentation; Histopathology; Semantic segmentation; Deep Learning; Kidney
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2023.126947

The importance of kidney biopsy, a medical procedure in which a small tissue sample is extracted from the kidney for examination, is increasing due to the rising incidence of kidney disorders. This procedure helps diagnosing several kidney diseases which are cause of kidney function changes, as well as guiding treatment decisions, and evaluating the suitability of potential donor kidneys for transplantation. In this work, a deep learning system for the automatic segmentation of glomeruli in biopsy kidney images is presented. A novel cross-species transfer learning approach, in which a semantic segmentation network is trained on mouse kidney tissue images and then fine-tuned on human data, is proposed to boost the segmentation performance. The experiments conducted using two deep semantic segmentation networks, MobileNet and SegNeXt, demonstrated the effectiveness of the cross-species pre-training approach leading to an increased generalization ability of both models. •Train a deep neural network for the segmentation of human glomeruli.•Explore the use of models pre-training on mice glomeruli histological images.•Cross-species transfer learning for increased model performance and generalization.•Experiments carried out with two different deep segmentation models.