PyCellMech: A shape-based feature extraction pipeline for use in medical and biological studies
Janan Arslan, Henri Chhoa, Ines Khemir, Romain Valabregue, Kurt K. Benke
TL;DR
PyCellMech introduces an open-source, shape-focused feature extraction pipeline for medical and biological studies, addressing the lack of a unified tool for morphometric features. The pipeline comprises image pre-processing, feature extraction, and visualization, and supports three feature classes—one-dimensional functions, geometric, and polygonal—delivering per-ROI CSV outputs and feature maps. It accommodates both single- and multi-class data, with multi-class labeling supported via NIfTI to preserve spatial context, and includes utilities to generate labels when needed. Demonstrated on open data with clear pathways to integration with mechanobiology and potential MRI applications, PyCellMech aims to extend shape-analysis capabilities beyond existing radiomics tools. Future work will add scale-space and transform-domain features, automated feature ranking, and broader biological interpretations to enhance disease mechanistic studies.
Abstract
Summary: Medical researchers obtain knowledge about the prevention and treatment of disability and disease using physical measurements and image data. To assist in this endeavor, feature extraction packages are available that are designed to collect data from the image structure. In this study, we aim to augment current works by adding to the current mix of shape-based features. The significance of shape-based features has been explored extensively in research for several decades, but there is no single package available in which all shape-related features can be extracted easily by the researcher. PyCellMech has been crafted to address this gap. The PyCellMech package extracts three classes of shape features, which are classified as one-dimensional, geometric, and polygonal. Future iterations will be expanded to include other feature classes, such as scale-space. Availability and implementation: PyCellMech is freely available at https://github.com/icm-dac/pycellmech.