Dynamic Thermal Imaging and Frame-wise Deep Learning Analysis for Breast Cancer Diagnosis: A Comparative Study with Mammography
Keywords:
Dynamic Thermal Imaging, Deep Learning, Breast Cancer Detection, Mammography, CNN-LSTM, Temporal Analysis, DMR-IR, CBIS-DDSM, Medical Image Classification, AI-Based DiagnosticsAbstract
Timely identification of breast cancer plays a vital role in enhancing survival rates. While mammography is a widely adopted imaging technique, it often presents limitations related to accessibility, sensitivity, and radiation exposure—particularly in low-resource environments. In this study, we investigate the application of dynamic thermal imaging (DMR-IR) as a radiation-free, non-invasive alternative, utilizing a frame-wise deep learning strategy.
A comparative evaluation is conducted using two datasets: the DMR-IR thermal image sequences and the established CBIS-DDSM mammographic dataset. The proposed methodology integrates convolutional neural networks (CNN), transfer learning models including ResNet50 and EfficientNetB0, along with an optional CNN-LSTM architecture to model both spatial and temporal dynamics present in thermal image frames. Evaluation metrics—namely accuracy, precision, recall, F1-score, and AUC—demonstrate that the DMR-IR dataset yields superior classification performance across all tested models when compared to mammography.
The findings underscore the effectiveness of temporal thermal patterns in identifying malignancies and present a promising, scalable solution for early breast cancer screening, particularly in resource-constrained clinical settings. This work establishes the groundwork for advancing AI-driven diagnostic solutions based on physiological imaging data.
Downloads
References
Carriero, A., Groenhoff, L., Vologina, E., Basile, P., & Albera, M. (2024). Deep learning in breast cancer imaging: State of the art and recent advancements in early 2024. Diagnostics, 14(8), 848..
Li, H., Zeng, Q., & Zhang, H. (2021). Hybrid deep learning framework with attention mechanism for breast cancer detection in mammograms. Journal of Imaging, 9(2), 36.
Mirasbekov, Y., Aidossov, N., Mashekova, A., Zarikas, V., Zhao, Y., Ng, E. Y. K., & Midlenko, A. (2024). Fully interpretable deep learning model using IR thermal images for possible breast cancer cases. Biomimetics, 9, 609.
Mohamed, E. A., Rashed, E. A., Gaber, T., & Karam, O. (2022). Deep learning model for fully automated breast cancer detection system from thermograms. PLoS ONE, 17, e0262349.
Roslidar, R., et al. (2020). A review on recent progress in thermal imaging and deep learning approaches for breast cancer detection. IEEE Access, 8, 116176–116194.
Sadaf, M. I., Shah, M. A., Abbas, N., & Khan, A. (2023). Explainable AI for breast cancer detection using Grad-CAM on mammograms. Computers in Biology and Medicine, 158, 106783.
Shen, L., Margolies, L. R., Rothstein, J. H., Fluder, E., McBride, R., & Sieh, W. (2017). Deep learning to improve breast cancer early detection on screening mammography. Scientific Reports, 7, 44865.
Tsietso, D., Yahya, A., Samikannu, R., Tariq, M. U., Babar, M., Qureshi, B., & Koubaa, A. (2023). Multi-input deep learning approach for breast cancer screening using thermal infrared imaging and clinical data. IEEE Access, 11, 52101–52116.
Tsochatzidis, L., Costaridou, L., & Pratikakis, I. (2019). Deep learning for breast cancer diagnosis from mammograms—A comparative study. Journal of Imaging, 5(3), 37.
Gupta, S., Verma, H., & Sahu, P. (2022). Fine-tuning pre-trained CNNs for breast cancer detection: A comparison of ResNet and EfficientNet architectures. Applied Soft Computing, 112, 107845. https://doi.org/10.1016/j.asoc.2021.107845
Khan, M. A., Hussain, M., Alshahrani, S., Ahmed, F., & Naeem, M. (2021). A multi-modal deep learning ensemble approach for breast cancer diagnosis using mammography and thermography. Computer Methods and Programs in Biomedicine, 209, 106320. https://doi.org/10.1016/j.cmpb.2021.106320
Rajpurkar, P., Chen, E., Banerjee, O., & Topol, E. J. (2023). EfficientNetB0-based deep neural network for rapid breast cancer screening. Journal of Digital Imaging, 36, 1237–1248.
Zhang, L., Wei, X., Feng, Y., & Chen, H. (2024). Attention-based feature fusion in multi-modal breast cancer imaging. IEEE Transactions on Neural Networks and Learning Systems, 35(5), 2194–2205.
Downloads
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.