Abstract
Every year, 2.4 million cases of breast cancer are detected worldwide. It is the most prevalent cancer among adults in several countries. The early detection of the disease improves patient prognosis and life expectancy. Infrared thermography of the breast, particularly dynamic thermography that captures subtle changes in temperature over time, has demonstrated promising results for early cancer detection. However, processing this data presents inherent challenges, such as computational resources and temporal relationships. In this paper, we address the classification problem of dynamic thermographies in a novel approach by modeling them into a thermal hypercube and subsequently applying a 3-dimensional convolutional neural network for pattern recognition. Our proposed method achieves an average accuracy of 94.61% and an area under the curve of 93.51% in classifying whether the patient is healthy or cancerous using a K-Fold Cross-Validation experiment. These promising results highlight the potential of our method for early breast cancer detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
National Cancer Institute: Breast cancer treatment (adult) (PDQ) - health professional version (2023). https://www.cancer.gov/types/breast/hp/breast-treatment-pdq. Accessed 20 June 2023
World Health Organization: Breast cancer (2023). https://www.who.int/news-room/fact-sheets/detail/breast-cancer. Accessed 19 June 2023
Amalu, W., Hobbins, W., Head, J., Elliot, R.: Infrared imaging of the breast-an overview. In: The Biomedical Engineering Handbook, Medical Devices and Systems. 3rd edn. CRC Press, Baton Rouge (2006)
Ohashi, Y., Uchida, I.: Applying dynamic thermography in the diagnosis of breast cancer. IEEE Eng. Med. Biol. Mag. 19(3), 42–51 (2000)
Baffa, M.D.F.O., Lattari, L.G.: Convolutional neural networks for static and dynamic breast infrared imaging classification. In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 174–181. IEEE (2018)
Silva, L.F., Santos, A.A.S., Bravo, R.S., Silva, A.C., Muchaluat-Saade, D.C., Conci, A.: Hybrid analysis for indicating patients with breast cancer using temperature time series. Comput. Methods Programs Biomed. 130, 142–153 (2016)
Silva, L., Seixas, F., Fontes, C., Muchaluat-Saade, D., Conci, A.: A computational method for breast abnormality detection using thermographs. In: 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), pp. 469–474. IEEE (2020)
Resmini, R., da Silva, L.F., Medeiros, P.R., Araujo, A.S., Muchaluat-Saade, D.C., Conci, A.: A hybrid methodology for breast screening and cancer diagnosis using thermography. Comput. Biol. Med. 135, 104553 (2021)
Zhu, H., Zhao, P., Chan, Y.P., Kang, H., Lee, D.L.: Breast cancer early detection with time series classification. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 3735–3745 (2022)
Abdel-Nasser, M., Moreno, A., Puig, D.: Breast cancer detection in thermal infrared images using representation learning and texture analysis methods. Electronics 8(1), 100 (2019)
Zadeh, H.G., Fayazi, A., Binazir, B., Yargholi, M.: Breast cancer diagnosis based on feature extraction using dynamic models of thermal imaging and deep autoencoder neural networks. JTE 49(3), 1516–1532 (2020)
Silva, T.A.E.D., Silva, L.F.D., Muchaluat-Saade, D.C., Conci, A.: A computational method to assist the diagnosis of breast disease using dynamic thermography. Sensors 20(14), 3866 (2020)
Silva, L., et al.: A new database for breast research with infrared image. J. Med. Imaging Health Inf. 4(1), 92–100 (2014)
Carlos de Carvalho, E., Martins Coelho, A., Conci, A., de Freitas Oliveira Baffa, M.: U-Net convolutional neural networks for breast IR imaging segmentation on frontal and lateral view. In: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, pp. 1–6 (2022)
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450–6459 (2018)
Abadi, M., et. al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015)
Bradski, G.: The OpenCV library. Dr. Dobb’s J. Softw. Tools (2000)
Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108–122 (2013)
Van der Walt, S., et al.: scikit-image: image processing in Python. PeerJ 2, e453 (2014)
Acknowledgments
M.F.O.B. is supported in part by Coordination for the Improvement of Higher Education Personnel (CAPES) under grants 88887.498626/2020-00 and 88887. 695355/2022-00. A.C. is supported in part by the National Institutes of Science and Technology (INCT - MACC project), National Council for Scientific and Technological (CNPq) under grant 307638/2022-7, the Research Support Foundation of Rio de Janeiro State (FAPERJ) over CNE, SIADE-2, e-Health Rio and Digit3D projects, and NVIDIA Research Grant for Anatomical Structure Segmentations Project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de Freitas Oliveira Baffa, M., Lattari, L.G., Conci, A. (2023). 3D Convolutional Neural Networks for Dynamic Breast Infrared Imaging Classification. In: Kakileti, S.T., Manjunath, G., Schwartz, R.G., Frangi, A.F. (eds) Artificial Intelligence over Infrared Images for Medical Applications. AIIIMA 2023. Lecture Notes in Computer Science, vol 14298. Springer, Cham. https://doi.org/10.1007/978-3-031-44511-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-44511-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45657-2
Online ISBN: 978-3-031-44511-8
eBook Packages: Computer ScienceComputer Science (R0)