Colormaps Matter: Evaluating Their Impact on CNN-Based Clinical Thermal Imaging

Allison Ng, Miriam Asare-Baiden, Sharon Eve Sonenblum, Kathleen Jordan, Judy Gichoya, Vicki Hertzberg, Joyce C. Ho
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:1403-1431, 2026.

Abstract

Thermal imaging is an increasingly used modality for clinical deep learning, yet a key preprocessing step in convolutional neural network (CNN)-based pipelines has gone largely unexamined. Each thermal image encodes scalar temperature values rendered into RGB via a colormap, determining how temperature information is visually represented. While existing work shows colormap selection influences human interpretation of thermal images, its impact on CNN-based classification remains unstudied. We address this gap through an evaluation of five colormaps across three pretrained CNN architectures and two clinical prediction tasks. Our results show that colormap choice produces consistent differences in predictive performance and substantially shifts the spatial regions CNNs attend to when making predictions. These findings suggest that colormap selection must be treated and reported as a factor shaping model behavior, with direct implications for how CNN-based pipelines are developed, validated, and deployed in clinical thermal imaging.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-ng26a, title = {Colormaps Matter: Evaluating Their Impact on CNN-Based Clinical Thermal Imaging}, author = {Ng, Allison and Asare-Baiden, Miriam and Sonenblum, Sharon Eve and Jordan, Kathleen and Gichoya, Judy and Hertzberg, Vicki and Ho, Joyce C.}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {1403--1431}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/ng26a/ng26a.pdf}, url = {https://proceedings.mlr.press/v340/ng26a.html}, abstract = {Thermal imaging is an increasingly used modality for clinical deep learning, yet a key preprocessing step in convolutional neural network (CNN)-based pipelines has gone largely unexamined. Each thermal image encodes scalar temperature values rendered into RGB via a colormap, determining how temperature information is visually represented. While existing work shows colormap selection influences human interpretation of thermal images, its impact on CNN-based classification remains unstudied. We address this gap through an evaluation of five colormaps across three pretrained CNN architectures and two clinical prediction tasks. Our results show that colormap choice produces consistent differences in predictive performance and substantially shifts the spatial regions CNNs attend to when making predictions. These findings suggest that colormap selection must be treated and reported as a factor shaping model behavior, with direct implications for how CNN-based pipelines are developed, validated, and deployed in clinical thermal imaging.} }
Endnote
%0 Conference Paper %T Colormaps Matter: Evaluating Their Impact on CNN-Based Clinical Thermal Imaging %A Allison Ng %A Miriam Asare-Baiden %A Sharon Eve Sonenblum %A Kathleen Jordan %A Judy Gichoya %A Vicki Hertzberg %A Joyce C. Ho %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-ng26a %I PMLR %P 1403--1431 %U https://proceedings.mlr.press/v340/ng26a.html %V 340 %X Thermal imaging is an increasingly used modality for clinical deep learning, yet a key preprocessing step in convolutional neural network (CNN)-based pipelines has gone largely unexamined. Each thermal image encodes scalar temperature values rendered into RGB via a colormap, determining how temperature information is visually represented. While existing work shows colormap selection influences human interpretation of thermal images, its impact on CNN-based classification remains unstudied. We address this gap through an evaluation of five colormaps across three pretrained CNN architectures and two clinical prediction tasks. Our results show that colormap choice produces consistent differences in predictive performance and substantially shifts the spatial regions CNNs attend to when making predictions. These findings suggest that colormap selection must be treated and reported as a factor shaping model behavior, with direct implications for how CNN-based pipelines are developed, validated, and deployed in clinical thermal imaging.
APA
Ng, A., Asare-Baiden, M., Sonenblum, S.E., Jordan, K., Gichoya, J., Hertzberg, V. & Ho, J.C.. (2026). Colormaps Matter: Evaluating Their Impact on CNN-Based Clinical Thermal Imaging. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:1403-1431 Available from https://proceedings.mlr.press/v340/ng26a.html.

Related Material