CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation

TL;DR

CountXplain introduces a prototype-based density map estimation method for interpretable cell counting in biomedical images, enabling visual understanding of model decisions without sacrificing accuracy.

Contribution

The paper presents a novel prototype layer integrated into density estimation networks, enhancing interpretability in cell counting tasks.

Findings

Achieves interpretability validated by biologists' survey

Maintains high counting accuracy on public datasets

Provides transparent visual explanations of cell identification

Abstract

Cell counting in biomedical imaging is pivotal for various clinical applications, yet the interpretability of deep learning models in this domain remains a significant challenge. We propose a novel prototype-based method for interpretable cell counting via density map estimation. Our approach integrates a prototype layer into the density estimation network, enabling the model to learn representative visual patterns for both cells and background artifacts. The learned prototypes were evaluated through a survey of biologists, who confirmed the relevance of the visual patterns identified, further validating the interpretability of the model. By generating interpretations that highlight regions in the input image most similar to each prototype, our method offers a clear understanding of how the model identifies and counts cells. Extensive experiments on two public datasets demonstrate that our method achieves interpretability without compromising counting effectiveness. This work provides researchers and clinicians with a transparent and reliable tool for cell counting, potentially increasing trust and accelerating the adoption of deep learning in critical biomedical applications. Code is available at https://github.com/NRT-D4/CountXplain.