Self-supervised representation learning of filtration barrier in kidney

• Published in: FRONTIERS IN IMAGING Vol. 3
• Main Authors: Sergei, German, Unnersjö-Jess, David, Butt, Linus, Benzing, Thomas, Bozek, Katarzyna
• Format: Journal Article Publication
• Language: English
• Published: 01.03.2024
• ISSN: 2813-3315; 2813-3315
• DOI: 10.3389/fimag.2024.1339770

While the advance of deep learning has allowed to automate many tasks in bioimage analysis, quantifying key visual features of biological objects in an image, such as cells, organs, or tissues, is still a multi-step and laborious task. It requires image segmentation and definition of features of interest, which often might be image- and problem-specific. This approach requires image labeling and training of the segmentation method as well as manual feature design and implementation of dedicated procedures for their quantification. Here we propose a self-supervised learning (SSL) approach to encoding in microscopy images morphological features of molecular structures that play role in disease phenotype and patient clinical diagnosis. We encode super-resolution images of slit diaphragm (SD)—a specialized membrane between podocyte cells in kidney—in a high-dimensional embedding space in an unsupervised manner, without the need of image segmentation and feature quantification. We inspect the embedding space and demonstrate its relationship to the morphometric parameters of the SD estimated with a previously published method. The SSL-derived image representations additionally reflect the level of albuminuria—a key marker of advancement of kidney disease in a cohort of chronic kidney disease patients. Finally, the embeddings allow for distinguishing mouse model of kidney disease from the healthy subjects with a comparable accuracy to classification based on SD morphometric features. In a one step and label-free manner the SSL approach offers possibility to encode meaningful details in biomedical images and allow for their exploratory, unsupervised analysis as well as further fine-tuning for specialized supervised tasks.