top of page
Clasificación de cáncer de mama en imágenes termográficas mediante aprendizaje profundo y segmentación basada en Level Set

Breast Cancer Classification in Thermographic Images Using Deep Learning and Level Set-Based Segmentation

Pérez Ibarra Guillermo

Instituto Tecnológico de la Laguna

m.gperezi@lalaguna.tecnm.mx

https://orcid.org/0009-0003-5437-0795
Tello Mijares Santiago

Instituto Tecnológico de la Laguna

jjstellom@lalaguna.tecnm.mx

https://orcid.org/0000-0002-2575-8251
Flores García Francisco

Instituto Tecnológico de la Laguna

fgfloresg@correo.itlalaguna.edu.mx

https://orcid.org/0000-0002-6661-8191

Volumen:

1

Edición:

12

Resumen

El cáncer de mama constituye uno de los principales problemas de salud en la población femenina, por lo que la detección temprana resulta fundamental para mejorar el pronóstico clínico y aumentar las posibilidades de supervivencia. En este trabajo se presenta un método computacional para la clasificación automática de imágenes termográficas mamarias mediante técnicas de procesamiento digital de imágenes y aprendizaje profundo. El procedimiento propuesto emplea un proceso de segmentación basado en niveles de temperatura para identificar regiones térmicas de interés, las cuales son utilizadas como entrada de cinco modelos de redes neuronales convolucionales profundas. La evaluación experimental se realizó utilizando una base de datos compuesta por 1027 imágenes termográficas, correspondientes a 645 pacientes con cáncer de mama y 382 pacientes sin la enfermedad. Los resultados obtenidos muestran que el modelo VGG19 alcanzó el mejor desempeño de clasificación, con una sensibilidad del 100 %, una precisión del 100 % y una exactitud del 99.09 % utilizando un esquema de validación cruzada de dos particiones. Estos hallazgos demuestran el potencial del enfoque propuesto como herramienta de apoyo para la detección temprana del cáncer de mama y evidencian la efectividad del aprendizaje por transferencia en el análisis de imágenes médicas.

Palabras clave

Aprendizaje por transferencia, Diagnóstico asistido por computadora, Imágenes infrarrojas, Segmentación térmica

Referencias Bibliográficas

  • Siegel, R. L., Miller, K. D. y Jemal, A. (2020). Cancer statistics, 2020. CA: Cancer Journal for Clinicians, 70(3), 145-164. https://doi.org/10.3322/caac.21601

  • Cruz-Ramirez, N., Efrén, M. M. y María Yaneli, A. A. (2013). Evaluation of the diagnostic power of thermography in breast cancer using bayesian network classifiers. Computational and Mathematical Methods in Medicine, 2013, 264246. https://doi.org/10.1155/2013/264246

  • Ibrahim, A., Mohammed, S., Ali, H. A. y Hussein, S. E. (2020). Breast cancer segmentation from thermal images based on chaotic salp swarm algorithm. IEEE Access, 8, 122121-122134. https://doi.org/10.1109/ACCESS.2020.3007336

  • Etehad Tavakol, M., Chandran, V., Ng, E. Y. K. y Kafieh, R. (2013). Breast cancer detection from thermal images using bispectral invariant features. International Journal of Thermal Sciences, 69, 21-36. https://doi.org/10.1016/j.ijthermalsci.2013.03.001

  • Mahmoudzadeh, E., Montazeri, M. A., Zekri, M. y Sadri, S. (2015). Extended hidden Markov model for optimized segmentation of breast thermography images. Infrared Physics & Technology, 72, 19-28. https://doi.org/10.1016/j.infrared.2015.06.012

  • Silva, L. F., Saade, D. C. M., Sequeiros, G. O., Silva, A. C., Paiva, A. C., Bravo, R. S. y Conci, A. (2014). A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, 4(1), 92-100. https://doi.org/10.1166/jmihi.2014.1226

  • Parisky, Y. R., Sardi, A., Hamm, R., Hughes, K., Esserman, L., Rust, S. y Callahan, K. (2003). Efficacy of computerized infrared imaging analysis to evaluate mammographically suspicious lesions. American Journal of Roentgenology, 180(1), 263-269. https://doi.org/10.2214/ajr.180.1.1800263

  • Kennedy, D., Lee, T. y Seely, D. (2009). A comparative review of thermography as a breast screening technique. Integrative Cancer Therapies, 8, 9-16. https://doi.org/10.1177/1534735408326171

  • Tello-Mijares, S., Woo, F. y Flores, F. (2019). Breast cancer identification via thermography image segmentation with a gradient vector flow and a convolutional neural network. Journal of Healthcare Engineering, 2019, Article 9807619. https://doi.org/10.1155/2019/9807619

  • Ng, E. Y. K. (2007). Detection and differentiation of breast cancer using neural classifiers with first warning thermal sensors. Information Sciences, 177(20), 4526-4538. https://doi.org/10.1016/j.ins.2007.03.027

  • Schaefer, G., Závišek, M. y Nakashima, T. (2009). Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern Recognition, 42(6), 1133-1137. https://doi.org/10.1016/j.patcog.2008.08.007

  • Etehad Tavakol, M., Lucas, C., Sadri, S. y Ng, E. Y. K. (2010). Analysis of breast thermography using fractal dimension to establish possible difference between malignant and benign patterns. Journal of Healthcare Engineering, 1(1), 27-43. https://doi.org/10.1260/2040-2295.1.1.27

  • Araújo, M. C., Lima, R. C. y De Souza, R. M. (2014). Interval symbolic feature extraction for thermography breast cancer detection. Expert Systems with Applications, 41(15), 6728-6737. https://doi.org/10.1016/j.eswa.2014.04.027

  • Francis, S. V., Sasikala, M., Bharathi, G. B. y Jaipurkar, S. D. (2014). Breast cancer detection in rotational thermography images using texture features. Infrared Physics & Technology, 67, 490-496. https://doi.org/10.1016/j.infrared.2014.08.019

  • Milosevic, M., Jankovic, D. y Peulic, A. (2014). Thermography based breast cancer detection using texture features and minimum variance quantization. EXCLI Journal, 13, 1204-1215.

  • Rassiwala, M., Mathur, P., Mathur, R., Farid, K., Shukla, S., Gupta, P. K. y Jain, B. (2014). Evaluation of digital infra-red thermal imaging as an adjunctive screening method for breast carcinoma: A pilot study. International Journal of Surgery, 12(12), 1439-1443. https://doi.org/10.1016/j.ijsu.2014.11.027

  • Antonini, S., Kolarić, D., Herceg, Ž., Kuliš, T., Ferenčić, Ž., Katančić, J. y Banić, M. (2015). Thermographic visualization of multicentric breast carcinoma. Proceedings of the IEEE 57th International Symposium ELMAR, 13-16. https://doi.org/10.1109/ELMAR.2015.7334484

  • Gaber, T., Ismail, G., Anter, A., Soliman, M., Ali, M., Semary, N. y Snasel, V. (2015). Thermogram breast cancer prediction approach based on neutrosophic sets and fuzzy c-means algorithm. Proceedings of the IEEE 37th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 4254- 4257. https://doi.org/10.1109/EMBC.2015.7319334

  • Mejía, T. M., Pérez, M. G., Andaluz, V. H. y Conci, A. (2015). Automatic segmentation and analysis of thermograms using texture descriptors for breast cancer detection. Proceedings of the IEEE Asia-Pacific Conference on Computer Aided System Engineering (APCASE), 24-29. https://doi.org/10.1109/APCASE.2015.12

  • Madhu, H., Kakileti, S. T., Venkataramani, K. y Jabbireddy, S. (2016). Extraction of medically interpretable features for classification of malignancy in breast thermography. Proceedings of the IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 1062-1065. https://doi.org/10.1109/EMBC.2016.7590886

  • Rastghalam, R. y Pourghassem, H. (2016). Breast cancer detection using MRF-based probable texture feature and decision-level fusion-based classification using HMM on thermography images. Pattern Recognition, 51, 176-186. https://doi.org/10.1016/j.patcog.2015.09.009

  • Celaya-Padilla, J. M., Guzmán-Valdivia, C. H., Galván-Tejada, C. E., Galván-Tejada, J. I., Gamboa-Rosales, H. y Luna-García, H. (2018). Contralateral asymmetry for breast cancer detection: A CADx approach. Biocybernetics and Biomedical Engineering, 38(1), 115-125. https://doi.org/10.1016/j.bbe.2017.10.005

  • Vasconcelos, J. H., dos Santos, W. P. y Lima, R. C. F. (2018). Analysis of methods of classification of breast thermographic images to determine their viability in the early breast cancer detection. IEEE Latin America Transactions, 16(6), 1631-1637. https://doi.org/10.1109/TLA.2018.8444159

  • Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J. y Socher, R. (2021). Deep learning-enabled medical computer vision. NPJ Digital Medicine, 4, 5. https://doi.org/10.1038/s41746-020-00376-2

  • Al Husaini, M. A. S., Habaebi, M. H., Hameed, S. A., Islam, M. R. y Gunawan, T. S. (2020). A systematic review of breast cancer detection using thermography and neural networks. IEEE Access, 8, 208922-208937. https://doi.org/10.1109/ACCESS.2020.3038817

  • Mambou, S., Maresova, P., Krejcar, O., Selamat, A. y Kuca, K. (2018). Breast cancer detection using infrared thermal imaging and a deep learning model. Sensors, 18(9), 2799. https://doi.org/10.3390/s18092799

  • de Freitas Oliveira Baffa, M. y Lattari, L. G. (2018). Convolutional neural networks for static and dynamic breast infrared imaging classification. Proceedings of the 31st SIBGRAPI Conference on Graphics, Patterns and Images, 174-181. https://doi.org/10.1109/SIBGRAPI.2018.00029

  • Roslidar, R., Saddami, K., Arnia, F., Syukri, M. y Munadi, K. (2019). A study of fine-tuning CNN models based on thermal imaging for breast cancer classification. Proceedings of the IEEE International Conference on Cybernetics and Computational Intelligence, 77-81. https://doi.org/10.1109/CYBERNETICSCOM.2019.8875661

  • Torres-Galvan, J. C., Guevara, E. y Gonzalez, F. J. (2019). Comparison of deep learning architectures for pre-screening of breast cancer thermograms. Proceedings of Photonics North, 1-2. https://doi.org/10.1109/PN.2019.8819587

  • Zuluaga-Gomez, J., Al Masry, Z., Benaggoune, K., Meraghni, S. y Zerhouni, N. (2020). A CNN-based methodology for breast cancer diagnosis using thermal images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 9(2), 131-145. https://doi.org/10.1080/21681163.2020.1824685

  • Fernández-Ovies, F. J., Santiago Alférez-Baquero, E., Andrés-Galiana, E. J. D., Cernea, A., Fernández-Muñiz, Z. y Fernández-Martínez, J. L. (2019). Detection of breast cancer using infrared thermography and deep neural networks. International Work-Conference on Bioinformatics and Biomedical Engineering, 514-523. https://doi.org/10.1007/978-3-030-17935-9_46

  • Alvarado-Robles, G., Terol-Villalobos, I. R., Garduño-Ramon, M. A. y Morales-Hernandez, L. A. (2017). Segmentation of green areas using bivariate histograms based in hue-saturation type color spaces. International Conference on Image Analysis and Processing, 277-287. https://doi.org/10.1007/978-3-319-68548- 9_26

  • LeCun, Y., Bottou, L., Bengio, Y. y Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE,

  • 86(11), 2278-2324. https://doi.org/10.1109/5.726791 Karami, A. et al. (2025). Development of a predictive model for breast

  • cancer detection using radiomics-based mammography and machine learning. Egyptian Journal of Radiology and Nuclear Medicine, 56, 68. https://doi.org/10.1186/s43055-025-01456-3

  • Escobar, M. de la L., De la Rosa, J. I., Galván-Tejada, C. E., GalvánTejada, J. I., Gamboa-Rosales, H. y Celaya-Padilla, J. M. (2021). Machine learning for breast cancer detection. Computación y Sistemas, 25(5).

  • Montero-Cadena, F. J. y Silva-Acosta, J. D. (2025). Use of artificial intelligence in breast cancer diagnosis. Ciencia Latina Revista Científica Multidisciplinar, 9(1). https://doi.org/10.37811/cl_rcm.v9i1.12289

  • Castillo, C., Pavia, G. y García, D. (2025). Artificial intelligence model for breast cancer diagnosis: A neural network-based approach. Universidad del Norte.

  • Celis, E., Sarmiento, O. y Calderón, B. (2022). Development of a convolutional neural network for breast cancer detection through mammography image classification. Revista Colombiana de Tecnologías de Avanzada, 2(40).

  • Mercedes, M. y Bogotá, S. C. (2021). Characterization of breast lesions through digital mammography image processing. EIEI ACOFI Papers.

  • Patiño, M., Pérez, E. y S. S. (2024). Early breast cancer detection: Mammogram classification using a deep learning model. Revista Ibérica de Sistemas e Tecnologías de Informação (RIST), 55, 21- 30. https://doi.org/10.17013/risti.55.21-30

  • Acosta, L., Macías, M. y Ramírez, A. (2021). Classification of breast cancer histology images using a lightweight convolutional neural network. Revista Electrónica de Ingeniería del IT Chihuahua.

  • Sosa, M. (2021). Digital mammography image processing for the characterization of breast lesions. Repositorio Escuela Colombiana de Ingeniería Julio Garavito.

  • Loaiza, L. S. y Restrepo, H. (2021). Automatic segmentation of breast thermal images to support cancer detection. Revista Sistemas & Telemática, 13(34). https://doi.org/10.18046/syt.v13i34.4731

  • Boubchir, L., Wang, A., Mdletshe, S., Williamson, B. y Xu, G. (2023). Fast segmentation and diagnosis of breast tumor ultrasound

  • images at sonographer level using deep learning. Frontiers in Oncology. https://doi.org/10.3389/fonc.2023.1165415

  • Li, Y. et al. (2024). Automatic joint segmentation and classification of breast ultrasound images using multitask learning with object context attention (MTL-OCA). Frontiers in Oncology. https://doi.org/10.3389/fonc.2024.1402216

  • Xu, H. et al. (2023). Efficient deep learning strategy for accurate and automatic segmentation of breast tumors in ultrasound (U2NETLite). Frontiers in Oncology. https://doi.org/10.3389/fonc.2023.1185381

  • Zhang, L. et al. (2024). Segmentation-based classification of mammograms using deep learning. BMC Medical Imaging. https://doi.org/10.1186/s12880-024-01085-6

  • Chen, J. et al. (2023). Modified LeNet convolutional network for breast cancer diagnosis in ultrasound images. Frontiers in Oncology. https://doi.org/10.3389/fonc.2023.1186023

  • Zhao, Q. et al. (2023). Multitask learning for tumor segmentation and classification in breast ultrasound images. Frontiers in Oncology. https://doi.org/10.3389/fonc.2023.1207474

  • Ahmed, K. et al. (2023). Automatic breast tumor segmentation in ultrasound using optimized hybrid U-Net and shallow CNN for classification. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2023.107921

  • Liu, X. et al. (2024). Deep learning for describing breast ultrasound images using BI-RADS. Journal of Digital Imaging. https://doi.org/10.1007/s10278-023-00980-2

  • Zhang, Y. et al. (2022). Dual convolutional neural networks for breast mass segmentation and diagnosis in mammography (DualCoreNet). arXiv preprint, arXiv:2204.01772.

  • Alzahrani, R. M. et al. (2025). Early detection of breast cancer using infrared thermography and convolutional neural networks. Scientific Reports, 15. https://doi.org/10.1038/s41598-025-85841-y

  • El-Banby, G. M., Salem, N. S., Tafweek, E. A. y Abd El-Azziz, E. N. (2024). Automated anomaly detection in mammograms using a deep U-Net framework. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2024.107993

  • Shilaskar, S., Bhatlawande, S., Talewar, M., Goud, S., Tak, S., Kurian, S. y Solanke, A. (2025). Classification and segmentation of breast tumors in ultrasound images using VGG-16 and U-Net. Biomedical and Pharmacology Journal, 18(1). https://doi.org/10.13005/bpj/2740

  • Wang, R. et al. (2023). Multi-feature fusion and multitask model for breast tumor ultrasound images (MFFMT). Current Oncology, 31(9), 374. https://doi.org/10.3390/curroncol31090374

  • El-Banby, G. M., Salem, N. S., Tafweek, E. A. y Abd El-Azziz, E. N. (2024). Automated detection of mammography anomalies using a deep U-Net framework. Complex & Intelligent Systems. https://doi.org/10.1007/s40747-024-01254-0

by.png

Esta obra está bajo licencia internacional Creative Commons Reconocimiento 4.0.

Ciencia, Ingeniería y Desarrollo (CID-TecLerdo) es una revista científica arbitrada, de publicación anual, editada por el Instituto Tecnológico Superior de Lerdo (Av. Tecnológico N 1555 Sur Periférico Gómez Lerdo Km. 14.5C.P. 35150 Cd. Lerdo, Dgo; Tels. 871 725 23 71, 871 725 57 79, 871 725 58 02), dedicada a la difusión de resultados originales de investigación en las áreas de ingeniería, tecnología, innovación y desarrollo científico. Publica contribuciones originales sometidas a un proceso de evaluación por pares académicos bajo la modalidad triple ciego.

by.png
Esta obra está bajo una licencia de Creative Commons Atribución/Reconocimiento 4.0 Internacional
  • Facebook
  • X
  • YouTube
bottom of page