Automated Classification of Cell Shapes: A Comparative Evaluation of Shape Descriptors

TL;DR

This study addresses the challenge of classifying cell shapes from noisy contours, such as those obtained through cell instance segmentation of histological images, by identifying the most suitable shape descriptors and applying them to a set of real images for qualitative analysis.

Abstract

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.

Figures (3)

• Figure 1: Noisy cell shapes synthetized for model training.
• Figure 2: Qualitative results on real data.
• Figure 3: (a) Examples of registered contours (black) and reconstructed contours from PCA 95 (red, top 3 rows). First 10 shape modes from PCA 95 (cyan, bottom 2 rows). (b) Performance of contour descriptors for shape classification (c) Aggregated confusion matrix from the 5 folds of cross validation for PCA 99. (d) Top 5 important features for each feature set.