Cross-Validation Deep Learning for Breast Cancer Detection Using DMR-IR Infrared Images

Renata dos Santos Melo; Henrique Coelho Fernandes; André Ricardo Backes

doi:10.22456/2175-2745.150755

Authors

Renata dos Santos Melo Universidade Federal de Uberlândia (UFU)
Henrique Coelho Fernandes Universidade Federal de Uberlândia (UFU) https://orcid.org/0000-0002-7078-9620
André Ricardo Backes Universidade Federal de São Carlos (UFSCar) https://orcid.org/0000-0002-7486-4253

DOI:

https://doi.org/10.22456/2175-2745.150755

Keywords:

breast cancer, infrared imaging, deep learning, CNN, cross-validation

Abstract

Breast cancer detection is a global health priority. While traditional methods have limitations, infrared thermography offers a promising, non-invasive alternative by detecting subtle thermal changes that can indicate tumors. This paper assessed five pre-trained Convolutional Neural Networks (CNNs) for breast cancer detection using DMR-IR thermal images, employing a 5-fold cross-validation. Among the tested models, ResNet50 achieved the best overall performance, with the highest average accuracy (92.79%), precision (95.00%), specificity (98.67%), sensitivity (72.00%), and F1-score (79.43%). The model was trained using raw thermal images from three anatomical views (frontal, lateral 90°, and lateral 45°), totaling five images per patient, an approach still uncommon in the literature. These results highlight ResNet50's strong potential for reliable and clinically applicable breast cancer detection using thermography.

Downloads

Download data is not yet available.

References

[1] INCA. Estimativa 2014: Incidência de câncer no Brasil. 2014. Disponível em: https://www.inca.gov.br/bvscontrolecancer/publicacoes/Estimativa_2014.pdf.

[2] VIEIRA, S. C. et al. Oncologia básica. Teresina, MA: Fundação Quixote, 2012.

[3] SMETHERMAN, D. H. Screening, imaging, and image-guided biopsy techniques for breast cancer. Surgical Clinics, Elsevier, v. 93, n. 2, p. 309–327, 2013.

[4] ETEHADTAVAKOL, M.; NG, E. Y. Breast thermography as a potential non-contact method in the early detection of cancer: a review. Journal of Mechanics in Medicine and Biology, World Scientific, v. 13, n. 02, p. 1330001, 2013.

[5] NG, E.-K. Improved sensitivity and specificity of breast cancer thermography. In: Cancer Imaging. [S.l.]: Elsevier, 2008. p. 435–444.

[6] MORALES-CERVANTES, A. et al. An automated method for the evaluation of breast cancer using infrared thermography. EXCLI journal, Leibniz Research Centre for Working Environment and Human Factors, v. 17, p. 989, 2018.

[7] CHEBBAH, N. K.; OUSLIM, M.; BENABID, S. New computer aided diagnostic system using deep neural network and svm to detect breast cancer in thermography. Quantitative InfraRed Thermography Journal, Taylor & Francis, v. 20, n. 2, p. 62–77, 2023.

[8] FAUST, O. et al. Application of infrared thermography in computer aided diagnosis. Infrared Physics & Technology, Elsevier, v. 66, p. 160–175, 2014.

[9] SANTOS, L. C. et al. A computing platform to analyze breast abnormalities using infrared images. Medical & Biological Engineering & Computing, Springer, v. 61, n. 2, p. 305–315, 2023.

[10] KHAN, A. A.; ARORA, A. S. Thermography as an economical alternative modality to mammography for early detection of breast cancer. Journal of Healthcare Engineering, Hindawi, v. 2021, 2021.

[11] HUSAINI, M. A. S. A. et al. A systematic review of breast cancer detection using thermography and neural networks. IEEE Access, IEEE, v. 8, p. 208922–208937, 2020.

[12] KAYALIBAY, B.; JENSEN, G.; SMAGT, P. van der. CNN-based segmentation of medical imaging data. arXiv preprint arXiv:1701.03056, 2017.

[13] CIVILIBAL, S.; CEVIK, K. K.; BOZKURT, A. A deep learning approach for automatic detection, segmentation and classification of breast lesions from thermal images. Expert Systems with Applications, Elsevier, v. 212, p. 118774, 2023.

[14] PRAMANIK, R.; PRAMANIK, P.; SARKAR, R. Breast cancer detection in thermograms using a hybrid of GA and GWO based deep feature selection method. Expert Systems with Applications, Elsevier, v. 219, p. 119643, 2023.

[15] CHI, T. N. et al. A lightweight method for breast cancer detection using thermography images with optimized CNN feature and efficient classification. Journal of Imaging Informatics in Medicine, Springer, p. 1–18, 2024.

[16] TSIETSO, D. et al. Multi-input deep learning approach for breast cancer screening using thermal infrared imaging and clinical data. IEEE Access, IEEE, v. 11, p. 52101–52116, 2023.

[17] MADHAVI, V.; THOMAS, C. B. Multi-view breast thermogram analysis by fusing texture features. Quantitative InfraRed Thermography Journal, Taylor & Francis, v. 16, n. 1, p. 111–128, 2019.

[18] SÁNCHEZ-CAUCE, R.; PÉREZ-MARTÍN, J.; LUQUE, M. Multi-input convolutional neural network for breast cancer detection using thermal images and clinical data. Computer Methods and Programs in Biomedicine, Elsevier, v. 204, p. 106045, 2021.

[19] TIWARI, D.; DIXIT, M.; GUPTA, K. Deep multi-view breast cancer detection: A multi-view concatenated infrared thermal images based breast cancer detection system using deep transfer learning. Traitement du Signal, v. 38, n. 6, p. 1699–1711, 2021.

[20] MAMMOOTTIL, M. J. et al. Detection of breast cancer from five-view thermal images using convolutional neural networks. Journal of Healthcare Engineering, Wiley Online Library, v. 2022, n. 1, p. 4295221, 2022.

[21] TIWARI, D.; DIXIT, M.; GUPTA, K. Breast cancer-caps: a breast cancer screening system based on capsule network utilizing the multiview breast thermal infrared images. Turkish Journal of Electrical Engineering and Computer Sciences, v. 30, n. 5, p. 1804–1820, 2022.

[22] MAHORO, E.; AKHLOUFI, M. A. Breast cancer classification on thermograms using deep CNN and transformers. Quantitative InfraRed Thermography Journal, Taylor & Francis, v. 21, n. 1, p. 30–49, 2024.

[23] SAMANTARAY, S. et al. Breast cancer diagnostics using angular view infrared images. In: SPIE. Medical Imaging 2024: Imaging Informatics for Healthcare, Research, and Applications. [S.l.], 2024. v. 12931, p. 181–189.

[24] PATTERSON, J.; GIBSON, A. Deep learning: A practitioner’s approach. [S.l.]: "O’Reilly Media, Inc.", 2017.

[25] O’SHEA, K.; NASH, R. An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458, 2015.

[26] ALSHEHRI, A.; ALSAEED, D. Breast cancer detection in thermography using convolutional neural networks (CNNs) with deep attention mechanisms. Applied Sciences, MDPI, v. 12, n. 24, p. 12922, 2022.

[27] MĂCĂȘOI, I.-R.; NEAGOE, V.-E. Breast cancer detection using thermal infrared image analysis based on Dempster-Shafer decision fusion of CNN classifiers. In: IEEE. 2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI). [S.l.], 2023. p. 01–06.

[28] ABDEL-NASSER, M.; MORENO, A.; PUIG, D. Breast cancer detection in thermal infrared images using representation learning and texture analysis methods. Electronics, MDPI, v. 8, n. 1, p. 100, 2019.

[29] MAHMOUD, A. Automatic breast thermography images classification based on deep neural networks. Annals of Optimization Theory and Practice, Firouzabad Institute of Higher Education, v. 3, n. 2, p. 71–79, 2020.

[30] TIWARI, D.; DIXIT, M.; GUPTA, K. Performance comparison of the ResNet50 and InceptionV3 deep transfer learning models over the breast cancer thermogram dataset. BSSS Journal of Computer, v. 13, n. 1, p. 1–10, 2022. ISSN 0975-7228.

[31] HUSAINI, M. A. S. A. et al. Thermal-based early breast cancer detection using Inception V3, Inception V4 and modified Inception MV4. Neural Computing and Applications, Springer, v. 34, n. 1, p. 333–348, 2022.

[32] VENKATACHALAM, N. et al. Automated breast boundary segmentation to improve the accuracy of identifying abnormalities in breast thermograms. IETE Journal of Research, Taylor & Francis, v. 70, n. 2, p. 1462–1471, 2024.

[33] MOHAMED, E. A. et al. A novel CNN pooling layer for breast cancer segmentation and classification from thermograms. PLOS ONE, Public Library of Science San Francisco, CA USA, v. 17, n. 10, p. e0276523, 2022.

[34] SILVA, L. et al. A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, American Scientific Publishers, v. 4, n. 1, p. 92–100, 2014.

[35] BARATLOO, A. et al. Part 1: Simple definition and calculation of accuracy, sensitivity and specificity. Emerg (Tehran), v. 3, n. 2, p. 48–49, 2015. PMID: 26495380; PMCID: PMC4614595.