Spatial pathomics toolkit for quantitative analysis of podocyte nuclei in renal pathology
Presenting author: Yu Wang, Department of Biostatistics, Vanderbilt University Medical Center
- Jiayuan Chen, Department of Computer Science, Vanderbilt University
- Ruining Deng, Department of Computer Science, Vanderbilt University
Podocytes play a pivotal role in maintaining renal health. The current description and quantification of features on pathology slides are limited, prompting the need for innovative solutions to assess diverse phenotypic attributes within Whole Slide Images. AI-assisted pathomics presents an approach that improves quantitative analysis across nuclei, cells, and elements in pathological specimens. This paper introduces the Spatial Pathomics Toolkit (SPT) and applies it to podocyte pathomics. The SPT consists of three main components: (1) instance object segmentation, enabling precise identification of podocyte nuclei; (2) pathomics feature generation, extracting a comprehensive array of quantitative features from the identified nuclei; and (3) robust statistical analyses, facilitating a comprehensive exploration of spatial relationships and patterns. To evaluate the SPT's effectiveness, we utilized a mouse proximal tubular injury model, where traditional renal pathologists face challenges in identifying glomerular changes and podocyte morphology alterations. The SPT successfully extracted and analyzed morphological and textural features from podocyte nuclei, revealing a multitude of podocyte morphomic features through statistical analysis. Notably, these pathomic features differentiated podocyte phenotypes between disease-affected and healthy mice, indicating its diagnostic potential. Additionally, we demonstrated the SPT's ability to unravel spatial information inherent to podocyte distribution. The toolkit is available at: https://github.com/hrlblab/spatial_pathomics.