Automated Classification of Cell Shapes: A Comparative Evaluation of Shape Descriptors
This work addresses the challenge of cell type identification and tissue characterization in biological research and histopathology, but it is incremental as it focuses on comparative evaluation of existing descriptors.
The study tackled the problem of classifying cell shapes from noisy contours by evaluating various shape descriptors, identifying the most suitable ones through tests on a synthetic dataset and applying them to real images for qualitative analysis.
This study addresses the challenge of classifying cell shapes from noisy contours, such as those obtained through cell instance segmentation of histological images. We assess the performance of various features for shape classification, including Elliptical Fourier Descriptors, curvature features, and lower dimensional representations. Using an annotated synthetic dataset of noisy contours, we identify the most suitable shape descriptors and apply them to a set of real images for qualitative analysis. Our aim is to provide a comprehensive evaluation of descriptors for classifying cell shapes, which can support cell type identification and tissue characterization-critical tasks in both biological research and histopathological assessments.