Thermal Breast Cancer Detection Using Deep Learning and Grad-CAM Visualization
DOI:
https://doi.org/10.56294/saludcyt20251518Keywords:
Thermal imaging, Breast cancer detection, Deep learning, VGG16, Grad-CAMAbstract
This paper presents a robust deep learning framework for thermal breast cancer detection using grayscale thermal images. Leveraging a pre-trained VGG16 model, we classify images into 'normal' and 'abnormal' categories, integrating data augmentation techniques to improve model generalization. Grad-CAM visualization elucidates the regions influencing predictions, aiding interpretability. Testing on the DMR-IR dataset yielded a remarkable AUC-ROC score of 0.97 and accuracy exceeding 94%. These findings underscore the potential of thermal imaging and deep learning in non-invasive cancer screening, bridging diagnostic accuracy with interpretability for clinical application.
References
[1] “Journal of Healthcare Engineering - 2022 - Mammoottil - Detection of Breast Cancer from Five‐View Thermal Images Using.pdf.”
[2] A. Carriero, L. Groenhoff, E. Vologina, P. Basile, and M. Albera, “Deep Learning in Breast Cancer Imaging: State of the Art and Recent Advancements in Early 2024,” Diagnostics, vol. 14, no. 8, 2024, doi: 10.3390/diagnostics14080848.
[3] H. Dihmani, A. Bousselham, and O. Bouattane, “A New Computer-Aided Diagnosis System for Breast Cancer Detection from Thermograms Using Metaheuristic Algorithms and Explainable AI,” Algorithms, vol. 17, no. 10, 2024, doi: 10.3390/a17100462.
[4] L. F. Silva et al., “A new database for breast research with infrared image,” J. Med. Imaging Heal. Informatics, vol. 4, no. 1, pp. 92–100, 2014, doi: 10.1166/jmihi.2014.1226.
[5] S. Chakravarthy, B. Nagarajan, V. V. Kumar, T. R. Mahesh, R. Sivakami, and J. R. Annand, “Breast Tumor Classification with Enhanced Transfer Learning Features and Selection Using Chaotic Map-Based Optimization,” Int. J. Comput. Intell. Syst., vol. 17, no. 1, 2024, doi: 10.1007/s44196-024-00409-8.
[6] R. Pataky, N. Phillips, S. Peacock, and A. J. Coldman, “Cost-effectiveness of population-based mammography screening strategies by age range and frequency,” J. Cancer Policy, vol. 2, no. 4, pp. 97–102, 2014, doi: 10.1016/j.jcpo.2014.09.001.
[7] S. Arooj et al., “Breast Cancer Detection and Classification Empowered With Transfer Learning,” Front. Public Heal., vol. 10, no. July, pp. 1–18, 2022, doi: 10.3389/fpubh.2022.924432.
[8] Z. Jafari and E. Karami, “Breast Cancer Detection in Mammography Images: A CNN-Based Approach with Feature Selection,” Inf., vol. 14, no. 7, 2023, doi: 10.3390/info14070410.
[9] K. Vanitha et al., “Attention-based Feature Fusion with External Attention Transformers for Breast Cancer Histopathology Analysis,” IEEE Access, vol. 12, no. July, pp. 126296–126312, 2024, doi: 10.1109/ACCESS.2024.3443126.
[10] A. Alshehri and D. AlSaeed, “Breast Cancer Detection in Thermography Using Convolutional Neural Networks (CNNs) with Deep Attention Mechanisms,” Appl. Sci., vol. 12, no. 24, 2022, doi: 10.3390/app122412922.
[11] Y. Mirasbekov et al., “Fully Interpretable Deep Learning Model Using IR Thermal Images for Possible Breast Cancer Cases,” Biomimetics, vol. 9, no. 10, 2024, doi: 10.3390/biomimetics9100609.
[12] B. Yousefi, M. Hershman, H. C. Fernandes, and X. P. V. Maldague, “Concentrated Thermomics for Early Diagnosis of Breast Cancer †,” Eng. Proc., vol. 8, no. 1, 2021, doi: 10.3390/engproc2021008030.
[13] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2017-Octob, pp. 618–626, 2017, doi: 10.1109/ICCV.2017.74.
[14] Y. Çetin-Kaya, “Equilibrium Optimization-Based Ensemble CNN Framework for Breast Cancer Multiclass Classification Using Histopathological Image,” Diagnostics, vol. 14, no. 19, 2024, doi: 10.3390/diagnostics14192253.
[15] T. A. Retson and M. Eghtedari, “Expanding Horizons: The Realities of CAD, the Promise of Artificial Intelligence, and Machine Learning’s Role in Breast Imaging beyond Screening Mammography,” Diagnostics, vol. 13, no. 13, 2023, doi: 10.3390/diagnostics13132133.
[16] M. S. Al Reshan et al., “Enhancing Breast Cancer Detection and Classification Using Advanced Multi-Model Features and Ensemble Machine Learning Techniques,” Life, vol. 13, no. 10, 2023, doi: 10.3390/life13102093.
[17] L. Sacca et al., “Promoting Artificial Intelligence for Global Breast Cancer Risk Prediction and Screening in Adult Women: A Scoping Review,” J. Clin. Med., vol. 13, no. 9, 2024, doi: 10.3390/jcm13092525.
[18] A. Lou, S. Guan, N. Kamona, and M. Loew, “Segmentation of Infrared Breast Images Using MultiResUnet Neural Networks,” pp. 1–6, 2021, doi: 10.1109/aipr47015.2019.9316541.
[19] S. Chakravarthy et al., “Multi-class Breast Cancer Classification Using CNN Features Hybridization,” Int. J. Comput. Intell. Syst., vol. 17, no. 1, 2024, doi: 10.1007/s44196-024-00593-7.
[20] A. Khalid et al., “Breast Cancer Detection and Prevention Using Machine Learning,” Diagnostics, vol. 13, no. 19, pp. 1–21, 2023, doi: 10.3390/diagnostics13193113.
[21] K. M. K. R. & G. S. M. T. R. Mahesh, V. Vinoth Kumar, V. Vivek, “Early predictive model for breast cancer classification using blended ensemble learning,” Int. J. Syst. Assur. Eng. Manag., [Online]. Available: https://link.springer.com/article/10.1007/s13198-022-01696-0
[22] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–14, 2015.
[23] Z. Zhu, Y. Sun, and B. Honarvar Shakibaei Asli, “Early Breast Cancer Detection Using Artificial Intelligence Techniques Based on Advanced Image Processing Tools,” Electron., vol. 13, no. 17, pp. 1–45, 2024, doi: 10.3390/electronics13173575.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Latha D U , Mahesh T R (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
