Interpretando modelos de ia en cáncer de mama con shap y lime
Article Sidebar
Publicado
jul 12, 2024
##plugins.pubIds.doi.readerDisplayName##
https://doi.org/10.36677/ideaseningenieria.v2i2.23952
Main Article Content
Angélica Guzmán Ponce
http://orcid.org/0000-0002-7844-1266
Joana López-Bautista
http://orcid.org/0009-0003-1849-5478
Rubén Fernández-Beltrán
http://orcid.org/0000-0003-1374-8416
http://orcid.org/0000-0002-7844-1266
Joana López-Bautista
http://orcid.org/0009-0003-1849-5478
Rubén Fernández-Beltrán
http://orcid.org/0000-0003-1374-8416
Resumen
La Inteligencia Artificial (IA) ha transformado múltiples disciplinas, en concreto en el área médica se ha distinguido por su capacidad de mejorar diagnósticos y tratamientos. No obstante, la falta de transparencia en los sistemas ha generado desafíos prácticos. La Inteligencia Artificial Explicable (XAI) ha surgido como una solución para abordar estos problemas, permitiendo a los profesionales de la salud comprender y verificar las decisiones de los algoritmos. En este trabajo se aplicarán dos técnicas comúnmente usadas de XAI, específicamente SHapley Additive exPlanations (SHAP) y Local Interpretable Model-Agnostic Explanations (LIME), para interpretar un modelo de red neuronal convolucional usado en el diagnóstico de cáncer de mama a partir de imágenes histológicas del Carcinoma Ductal Invasivo (IDC). Los resultados muestran que ambas técnicas son efectivas para identificar las contribuciones individuales de las características en las predicciones del modelo, resaltando que LIME ofrece una granularidad detallada a nivel de píxel.
Article Details
Como citar
GUZMÁN PONCE, Angélica; LÓPEZ-BAUTISTA, Joana; FERNÁNDEZ-BELTRÁN, Rubén.
Interpretando modelos de ia en cáncer de mama con shap y lime.
Ideas en Ciencias de la Ingeniería, [S.l.], v. 2, n. 2, p. 15-29, jul. 2024.
ISSN 2992-7447.
Disponible en: <https://ideasencienciasingenieria.uaemex.mx/article/view/23952>. Fecha de acceso: 26 ago. 2026
doi: https://doi.org/10.36677/ideaseningenieria.v2i2.23952.
Sección
Artículos
Esta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial-SinObrasDerivadas 4.0.
Citas
1. A. Guzmán-Ponce, J. L. González-Ruíz, and I. Francisco-Valencia, “Review on the application of big data algorithms to understand a pandemic virus,” in Handbook of Research on Applied Artificial Intelligence and Robotics for Government Processes. IGI Global, 2023, pp. 211–233.
2. H. Li, N. Zeng, P. Wu, and K. Clawson, “Cov-net: A computer-aided diagnosis method for recognizing covid-19 from chest x-ray images via machine vision,” Expert Systems with Applications, vol. 207, p. 118029, 2022. doi: 10.1016/j.eswa.2022.118029
3. F. Kamalov, K. Rajab, A. K. Cherukuri, A. Elnagar, and M. Safaraliev, “Deep learning for covid-19 forecasting: State-of-the-art review.” Neurocomputing, vol. 511, pp. 142–154, 2022. doi:10.1016/j.neucom.2022.09.005
4. L. Longo, M. Brcic, F. Cabitza, J. Choi, R. Confalonieri, J. Del Ser, R. Guidotti, Y. Hayashi, F. Herrera, A. Holzinger, R. Jiang, H. Khosravi, F. Lecue, G. Malgieri, A. Páez, W. Samek, J. Schneider, T. Speith, and S. Stumpf, “Explainable artificial intelligence (xai) 2.0: A manifesto of open challenges and interdisciplinary research directions,” Information Fusion, vol. 106, p. 102301, 2024. doi: 10.1016/j.inffus.2024.102301
5. L. Malinverno, V. Barros, F. Ghisoni, G. Visonà, R. Kern, P. J. Nickel, B. E. Ventura, I. Šimić, S. Stryeck, F. Manni, C. Ferri, C. Jean-Quartier, L. Genga, G. Schweikert, M. Lovri ́c, and M. Rosen-Zvi, “A historical perspective of biomedical explainable ai research,” Patterns, vol. 4, no. 9, p. 100830, 2023. doi: 10.1016/j.patter.2023.100830
6. R. O. Alabi, M. Elmusrati, I. Leivo, A. Almangush, and A. A. Mäkitie, “Machine learning explainability in nasopharyngeal cancer survival using lime and shap,” Scientific Reports, vol. 13, no. 1, p. 8984, 2023. doi: 10.1038/s41598-023-35795-0
7. M. M. Abdelsamea, U. Zidan, Z. Senousy, M. M. Gaber, E. A. Rakha, and M. Ilyas, “A survey on artificial intelligence in histopathology image analysis,” WIREs Data Mining and Knowledge Discovery, vol. 12, 2022. doi: 10.1002/widm.1474
8. M. N. S. Choudary, V. B. Bommineni, G. Tarun, G. P. Reddy, and G. Gopakumar, “Predicting Covid-19 Positive Cases and Analysis on the Relevance of Features using SHAP (SHapley Additive exPlanation),” in 2021 Second ICESC, Coimbatore, India, 2021, pp. 1892–1896. doi:10.1109/ICESC51422.2021.9532829
9. K. Borys, Y. A. Schmitt, M. Nauta, C. Seifert, N. Krämer, C. M. Friedrich, and F. Nensa, “Explainable ai in medical imaging: An overview for clinical practitioners – saliency-based xai approaches,” European Journal of Radiology, vol. 162, p. 110787, 2023. doi: 10.1016/j.ejrad.2023.110787
10. M. S. H. Shovon, M. F. Mridha, K. M. Hasib, S. Alfarhood, M. Safran, and D. Che, “Addressing uncertainty in imbalanced histopathology image classification of her2 breast cancer: An interpretable ensemble approach with threshold filtered single instance evaluation (sie),” IEEE Access, vol. 11, pp. 122 238–122 251, 2023. doi: 10.1109/ACCESS.2023.3327898
11. D. Kaplun, A. Krasichkov, P. Chetyrbok, N. Oleinikov, A. Garg, and H. S. Pannu, “Cancer cell profiling using image moments and neural networks with model agnostic explainability: A case study of breast cancer histopathological (breakhis) database,” Mathematics, vol. 9, no. 20, p. 2616, 2021. doi: 10.3390/math9202616
12. A. Janowczyk and A. Madabhushi, “Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases,” Journal of Pathology Informatics, vol. 7, no. 1, p. 29, 2016. doi: 10.4103/2153-3539.186902
13. “Predicting IDC in Breast Cancer Histology Images,” Kaggel, 2018, consultado el 29 de mayo del 2024. [en línea]. Disponible: https://www.kaggle.com/code/paultimothymooney/predicting-idc-in-breast-cancer-histology-images
2. H. Li, N. Zeng, P. Wu, and K. Clawson, “Cov-net: A computer-aided diagnosis method for recognizing covid-19 from chest x-ray images via machine vision,” Expert Systems with Applications, vol. 207, p. 118029, 2022. doi: 10.1016/j.eswa.2022.118029
3. F. Kamalov, K. Rajab, A. K. Cherukuri, A. Elnagar, and M. Safaraliev, “Deep learning for covid-19 forecasting: State-of-the-art review.” Neurocomputing, vol. 511, pp. 142–154, 2022. doi:10.1016/j.neucom.2022.09.005
4. L. Longo, M. Brcic, F. Cabitza, J. Choi, R. Confalonieri, J. Del Ser, R. Guidotti, Y. Hayashi, F. Herrera, A. Holzinger, R. Jiang, H. Khosravi, F. Lecue, G. Malgieri, A. Páez, W. Samek, J. Schneider, T. Speith, and S. Stumpf, “Explainable artificial intelligence (xai) 2.0: A manifesto of open challenges and interdisciplinary research directions,” Information Fusion, vol. 106, p. 102301, 2024. doi: 10.1016/j.inffus.2024.102301
5. L. Malinverno, V. Barros, F. Ghisoni, G. Visonà, R. Kern, P. J. Nickel, B. E. Ventura, I. Šimić, S. Stryeck, F. Manni, C. Ferri, C. Jean-Quartier, L. Genga, G. Schweikert, M. Lovri ́c, and M. Rosen-Zvi, “A historical perspective of biomedical explainable ai research,” Patterns, vol. 4, no. 9, p. 100830, 2023. doi: 10.1016/j.patter.2023.100830
6. R. O. Alabi, M. Elmusrati, I. Leivo, A. Almangush, and A. A. Mäkitie, “Machine learning explainability in nasopharyngeal cancer survival using lime and shap,” Scientific Reports, vol. 13, no. 1, p. 8984, 2023. doi: 10.1038/s41598-023-35795-0
7. M. M. Abdelsamea, U. Zidan, Z. Senousy, M. M. Gaber, E. A. Rakha, and M. Ilyas, “A survey on artificial intelligence in histopathology image analysis,” WIREs Data Mining and Knowledge Discovery, vol. 12, 2022. doi: 10.1002/widm.1474
8. M. N. S. Choudary, V. B. Bommineni, G. Tarun, G. P. Reddy, and G. Gopakumar, “Predicting Covid-19 Positive Cases and Analysis on the Relevance of Features using SHAP (SHapley Additive exPlanation),” in 2021 Second ICESC, Coimbatore, India, 2021, pp. 1892–1896. doi:10.1109/ICESC51422.2021.9532829
9. K. Borys, Y. A. Schmitt, M. Nauta, C. Seifert, N. Krämer, C. M. Friedrich, and F. Nensa, “Explainable ai in medical imaging: An overview for clinical practitioners – saliency-based xai approaches,” European Journal of Radiology, vol. 162, p. 110787, 2023. doi: 10.1016/j.ejrad.2023.110787
10. M. S. H. Shovon, M. F. Mridha, K. M. Hasib, S. Alfarhood, M. Safran, and D. Che, “Addressing uncertainty in imbalanced histopathology image classification of her2 breast cancer: An interpretable ensemble approach with threshold filtered single instance evaluation (sie),” IEEE Access, vol. 11, pp. 122 238–122 251, 2023. doi: 10.1109/ACCESS.2023.3327898
11. D. Kaplun, A. Krasichkov, P. Chetyrbok, N. Oleinikov, A. Garg, and H. S. Pannu, “Cancer cell profiling using image moments and neural networks with model agnostic explainability: A case study of breast cancer histopathological (breakhis) database,” Mathematics, vol. 9, no. 20, p. 2616, 2021. doi: 10.3390/math9202616
12. A. Janowczyk and A. Madabhushi, “Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases,” Journal of Pathology Informatics, vol. 7, no. 1, p. 29, 2016. doi: 10.4103/2153-3539.186902
13. “Predicting IDC in Breast Cancer Histology Images,” Kaggel, 2018, consultado el 29 de mayo del 2024. [en línea]. Disponible: https://www.kaggle.com/code/paultimothymooney/predicting-idc-in-breast-cancer-histology-images