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

Abdurahman Ali Mohammed, Wallapak Tavanapong, Catherine Fonder, Donald Sakaguchi
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1127-1144, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-mohammed26a, title = {CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation}, author = {Mohammed, Abdurahman Ali and Tavanapong, Wallapak and Fonder, Catherine and Sakaguchi, Donald}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1127--1144}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/mohammed26a/mohammed26a.pdf}, url = {https://proceedings.mlr.press/v301/mohammed26a.html}, 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.} }
Endnote
%0 Conference Paper %T CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation %A Abdurahman Ali Mohammed %A Wallapak Tavanapong %A Catherine Fonder %A Donald Sakaguchi %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-mohammed26a %I PMLR %P 1127--1144 %U https://proceedings.mlr.press/v301/mohammed26a.html %V 301 %X 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.
APA
Mohammed, A.A., Tavanapong, W., Fonder, C. & Sakaguchi, D.. (2026). CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1127-1144 Available from https://proceedings.mlr.press/v301/mohammed26a.html.

Related Material