EVALUATING THE FEASIBILITY OF THERMOGRAPHIC IMAGES FOR PREDICTING BREAST TUMOR STAGE USING DCNN
Zakaryae Khomsi
zakaryae_khomsi@um5.ac.maMohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) (Morocco)
https://orcid.org/0000-0003-2321-9622
Mohamed El Fezazi
Mohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) (Morocco)
https://orcid.org/0000-0001-6072-325X
Achraf Elouerghi
Mohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) (Morocco)
https://orcid.org/0000-0001-5880-0172
Larbi Bellarbi
Mohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) (Morocco)
Abstract
Early-stage and advanced breast cancer represent distinct disease processes. Thus, identifying the stage of tumor is a crucial procedure for optimizing treatment efficiency. Breast thermography has demonstrated significant advancements in non-invasive tumor detection. However, the accurate determination of tumor stage based on temperature distribution represents a challenging task, primarily due to the scarcity of thermal images labeled with the stage of tumor. This work proposes a transfer learning approach based on Deep Convolutional Neural Network (DCNN) with thermal images for predicting breast tumor stage. Various tumor stage scenarios including early and advanced tumors are embedded in a 3D breast model using the Finite Element Method (FEM) available on COMSOL Multiphysics software. This allows the generation of the thermal image dataset for training the DCNN model. A detailed investigation of the hyperparameters tuning process has been conducted to select the optimal predictive model. Thus, various evaluation metrics, including accuracy, sensitivity, and specificity, are computed using the confusion matrix. The results demonstrate the DCNN model's ability to accurately predict breast tumor stage from thermographic images, with an accuracy of 98.2%, a sensitivity of 98.8%, and a specificity of 97.7%. This study indicates the promising potential of thermographic images in enhancing deep learning algorithms for the non-invasive prediction of breast tumor stage.
Keywords:
image analysis, classification, tumor prediction, transfer learning, thermographyReferences
Ahlawat P. et al.: Tumour Volumes: Predictors of Early Treatment Response in Locally Advanced Head and Neck Cancers Treated with Definitive Chemoradiation. Reports of Practical Oncology and Radiotherapy 21(5), 2016, 419–426 [https://doi.org/10.1016/j.rpor.2016.04.002].
Google Scholar
Alghamdi S. et al.: The Impact of Reporting Tumor Size in Breast Core Needle Biopsies on Tumor Stage: A Retrospective Review of Five Years of Experience at a Single Institution. Annals of Diagnostic Pathology, vol. 38, 2019, 26–28 [https://doi.org/10.1016/j.anndiagpath.2018.10.002].
Google Scholar
De Miglio M. R., Mello-Thoms C.: Editorial: Reviews in Breast Cancer. Frontiers in Oncology 13, 2023, 1161583
Google Scholar
[https://doi.org/10.3389/fonc.2023.1161583].
Google Scholar
Farhangi F.: Investigating the Role of Data Preprocessing, Hyperparameters Tuning, and Type of Machine Learning Algorithm in the Improvement of Drowsy EEG Signal Modeling. Intelligent Systems with Applications 15, 2022, 200100 [https://doi.org/10.1016/j.iswa.2022.200100].
Google Scholar
Gavazzi S. et al.: Advanced Patient-Specific Hyperthermia Treatment Planning. International Journal of Hyperthermia 37(1), 2020, 992–1007 [https://doi.org/10.1080/02656736.2020.1806361].
Google Scholar
Giuliano A. E. et al.: Breast Cancer-Major Changes in the American Joint Committee on Cancer Eighth Edition Cancer Staging Manual. CA: A Cancer Journal for Clinicians 67(4), 2017, 290–303 [https://doi.org/10.3322/caac.21393].
Google Scholar
Horvath L. E. et al.: The Relationship between Tumor Size and Stage in Early versus Advanced Ovarian Cancer. Medical Hypotheses 80(5), 2013, 684–687 [https://doi.org/10.1016/j.mehy.2013.01.027].
Google Scholar
Huang W. et al.: Wearable Health Monitoring System Based on Layered 3D-Mobilenet. Procedia Computer Science 202, 2022, 373–378 [https://doi.org/10.1016/j.procs.2022.04.051].
Google Scholar
Jacob G. et al.: Breast Cancer Detection: A Comparative Review on Passive and Active Thermography. Infrared Physics and Technology 134, 2023, 104932 [https://doi.org/10.1016/j.infrared.2023.104932].
Google Scholar
Jones S. C. et al.: Australian Women’s Perceptions of Breast Cancer Risk Factors and the Risk of Developing Breast Cancer. Women’s Health Issues 21(5), 2011, 353–360 [https://doi.org/10.1016/j.whi.2011.02.004].
Google Scholar
Kandlikar S. G. et al.: Infrared Imaging Technology for Breast Cancer Detection – Current Status, Protocols and New Directions. International Journal of Heat and Mass Transfer 108, 2017, 2303–2320 [https://doi.org/10.1016/j.ijheatmasstransfer.2017.01.086].
Google Scholar
Khomsi Z. et al.: Towards Development of Synthetic Data in Surface Thermography to Enable Deep Learning Models for Early Breast Tumor Prediction. Masrour T. et al. (eds): Artificial Intelligence and Industrial Applications. Springer Cham, Switzerland, 2023, 356–365 [https://doi.org/10.1007/978-3-031-43520-1_30].
Google Scholar
Lu S. Y. et al.: A Classification Method for Brain MRI via MobileNet and Feedforward Network with Random Weights. Pattern Recognition Letters 140, 2020, 252–260 [https://doi.org/10.1016/j.patrec.2020.10.017].
Google Scholar
Magario M. B. et al.: Mammography Coverage and Tumor Stage in the Opportunistic Screening Context. Clinical Breast Cancer 19(6), 2019, 456–459 [https://doi.org/10.1016/j.clbc.2019.04.014].
Google Scholar
Muruganandam S. et al.: A Deep Learning Based Feed Forward Artificial Neural Network to Predict the K-Barriers for Intrusion Detection Using a Wireless Sensor Network. Measurement: Sensors 25, 2023, 100613 [https://doi.org/10.1016/j.measen.2022.100613].
Google Scholar
Ragab M. et al.: Heat Transfer in Biological Spherical Tissues during Hyperthermia of Magnetoma. Biology 10(12), 2021, 1–16 [https://doi.org/10.3390/biology10121259].
Google Scholar
Rahman M. H. et al.: Real-Time Face Mask Position Recognition System Based on MobileNet Model. Smart Health 28, 2023, 100382 [https://doi.org/10.1016/j.smhl.2023.100382].
Google Scholar
Sardanelli F., Helbich T. H.: Mammography: EUSOBI Recommendations for Women’s Information. Insights into Imaging 3(1), 2012, 7–10 [https://doi.org/10.1007/s13244-011-0127-y].
Google Scholar
Wang H. et al.: A Model for Detecting Safety Hazards in Key Electrical Sites Based on Hybrid Attention Mechanisms and Lightweight Mobilenet. Energy Reports 7, 2021, 716–724 [https://doi.org/10.1016/j.egyr.2021.09.200].
Google Scholar
Zhu D. et al.: Efficient Precision-Adjustable Architecture for Softmax Function in Deep Learning. IEEE Transactions on Circuits and Systems II: Express Briefs 67(12), 2020, 3382–3386 [https://doi.org/10.1109/TCSII.2020.3002564].
Google Scholar
Authors
Zakaryae Khomsizakaryae_khomsi@um5.ac.ma
Mohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) Morocco
https://orcid.org/0000-0003-2321-9622
Authors
Mohamed El FezaziMohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) Morocco
https://orcid.org/0000-0001-6072-325X
Authors
Achraf ElouerghiMohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) Morocco
https://orcid.org/0000-0001-5880-0172
Authors
Larbi BellarbiMohammed V University in Rabat, Ecole Nationale Supérieure d’Arts et Métiers (ENSAM), Ecole Nationale Supérieure d’Informatique et d’Analyse des Systèmes (ENSIAS), Electronic Systems Sensors and Nanobiotechnologies (E2SN) Morocco
Statistics
Abstract views: 134PDF downloads: 114
Most read articles by the same author(s)
- Abdelmalek Makhir, My Hachem El Yousfi Alaoui, Larbi Bellarbi, Abdelilah Jilbab, IOT BASED ECG: HYBRID CNN-BILSTM APPROACH FOR MYOCARDIAL INFARCTION CLASSIFICATION , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 14 No. 3 (2024)
