EL USO DE LA INTELIGENCIA ARTIFICIAL COMO AYUDA EN EL DIAGNÓSTICO DEL CÁNCER DE MAMA
DOI:
https://doi.org/10.56238/arev7n9-200Palabras clave:
Inteligencia Artificial, Diagnóstico, Resonancia Magnética, Cáncer de MamaResumen
La Inteligencia Artificial ha demostrado ser muy eficaz para facilitar el diagnóstico del cáncer, incluido el de mama. Diversas herramientas pueden utilizarse en este proceso, lo que facilita la elección de la más eficaz según el caso. A pesar de los avances, es importante comprender sus limitaciones y buscar soluciones para superarlas. Este estudio propone una breve discusión sobre el uso de la Inteligencia Artificial como herramienta auxiliar en el diagnóstico del cáncer. Este estudio implicó una revisión bibliográfica integradora, realizada entre julio y septiembre de 2025. La revisión se basó en la Biblioteca Virtual en Salud (BVS) y la Biblioteca Nacional de Medicina de los Estados Unidos (PUBMED), utilizando los siguientes descriptores y términos MeSH: Inteligencia Artificial, Diagnóstico, Imágenes por Resonancia Magnética y Cáncer de Mama; Inteligencia Artificial, diagnóstico, Imágenes por Resonancia Magnética y cáncer de mama. Criterios de inclusión: artículos de texto completo publicados en portugués, inglés o español entre 2020 y 2025, con texto completo disponible. Tras la selección inicial, se aplicaron los siguientes criterios de exclusión: artículos duplicados, artículos que se desviaban del tema abordado, artículos con temas paralelos, editoriales y artículos publicados hace más de cinco años. Se incluyeron 39 artículos en este estudio para fomentar el debate entre los autores. El uso de la IA ha revolucionado el diagnóstico del cáncer de mama mediante la evaluación de imágenes radiológicas. Su uso aumenta la precisión de los resultados y mejora la calidad de vida de las pacientes. La reducción de la carga de trabajo de los radiólogos y la disminución del error humano son ventajas del uso de estas herramientas. Los modelos multimodales y radiómicos han destacado en la predicción de la respuesta a la quimioterapia y el estado de los ganglios linfáticos. Es importante destacar que estas herramientas requieren perfeccionamiento y supervisión humana para corregir y evitar posibles errores. Por lo tanto, los avances presentados por la Inteligencia Artificial se están consolidando como una herramienta aliada en el diagnóstico del cáncer de mama. Su uso en medicina mejora la eficiencia en la toma de decisiones. Sin embargo, requiere un perfeccionamiento y una validación constantes entre investigadores y profesionales sanitarios. Fortalecer la integración entre la IA y la experiencia médica es esencial para garantizar la seguridad y la precisión de los diagnósticos de cáncer de mama.
Descargas
Referencias
AL-HEJRI, A. M. et al. A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors. Scientific Reports, v. 15, n. 1, p. 01-23, 2025. DOI: https://doi.org/10.1038/s41598-025-96527-0
ALSAMHORI, J. F. et al. Artificial intelligence for breast cancer: implications for diagnosis and management. J Med Surg Public Health, v. 3, p. 100120, 2024. DOI: 10.1016/j.glmedi.2024.100120. DOI: https://doi.org/10.1016/j.glmedi.2024.100120
AMIR, T. et al. A role for breast ultrasound artificial intelligence decision support in the evaluation of small invasive lobular carcinomas. Clinical Imaging, v.101, p.77-85, 2023.
https://doi.org/10.1016/j.clinimag.2023.05.005 DOI: https://doi.org/10.1016/j.clinimag.2023.05.005
ARBYN, M., et al. Estimates of incidence and mortality of cervical cancer in 2018: a worldwide analysis. Lancet Glob Health, v.8, n.2, p.191-203, 2020. DOI: https://doi.org/10.1016/S2214-109X(19)30482-6
BAHL, M. Artificial intelligence applications in breast imaging: validation in real-world clinical settings. Semin Roentgenol., v. 57, n. 2, p. 160–167, 2022. DOI: 10.1053/j.ro.2021.12.005. DOI: https://doi.org/10.1053/j.ro.2021.12.005
BALTZER, P. A. T. Künstliche Intelligenz in der Mammadiagnostik. Anwendungsgebiete aus klinischer Perspektive. Radiologe, v. 61, p. 192–198, 2021. DOI: 10.1007/s00117-020-00802-2. DOI: https://doi.org/10.1007/s00117-020-00802-2
BITENCOURT, A. G. V. et al. AI-enhanced breast imaging: applications in risk prediction, lesion detection/classification, radiogenomics. Eur J Radiol., v. 142, p. 109882, 2021. DOI: 10.1016/j.ejrad.2021.109882. DOI: https://doi.org/10.1016/j.ejrad.2021.109882
BITENCOURT, A. G. V. et al. Clinical and MRI radiomic features coupled with machine learning to assess HER2 expression level and predict pathologic response (pCR) in HER2 overexpressing breast cancer patients receiving neoadjuvant chemotherapy (NAC). EBioMedicine, v. 61, p. 103042, 2020. DOI: 10.1016/j.ebiom.2020.103042. DOI: https://doi.org/10.1016/j.ebiom.2020.103042
BYEON, H. et al. A study on the combination of fine-tuned Inception V3 methods for improved classification of cancer and noncancer images. Wolters Kluwer Health, 2025.
CASTILHO, B; BENINI, G; CASSENOTE, A. Pesquisa em Inteligência Artiicial para Detecção Precoce do Câncer de Mama. In: REPOSITÓRIO VIRTUAL -PRÊMIO MARCOS MORAES 2023, n° 2, 2023, Campinas, Galoá, 2023.
CHALLA, B. et al. Artificial Intelligence-Aided Diagnosis of Breast Cancer Lymph Node Metastasis on Histologic Slides in a Digital Workflow. Modern Pathology, v.36, n.8, p.100216, 2023.
https://doi.org/10.1016/j.modpat.2023.100216 DOI: https://doi.org/10.1016/j.modpat.2023.100216
CHEN, Y. et al., Review of AI trends in breast cancer imaging research. Seminars in Nuclear Medicine, v. 55, n. 3, p. 358-370, 2025. DOI: 10.1053/j.semnuclmed.2025.01.008. DOI: https://doi.org/10.1053/j.semnuclmed.2025.01.008
CHUNG, H. S. et al. Simulated contrast-enhanced breast MRIs generated using deep learning demonstrate no significant quantitative or qualitative differences compared to real contrast-enhanced MRIs. Radiology, v. 306, n. 3, p. e213199, 2023. DOI: 10.1148/radiol.213199. DOI: https://doi.org/10.1148/radiol.213199
GOTO, M. et al. Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists’ interpretations at various levels. Japanese Journal of Radiology, v. 41, p. 1094–1103, 2023. DOI: 10.1007/s11604-023-01435-w. DOI: https://doi.org/10.1007/s11604-023-01435-w
GUERREIRO, A. A. P. et al. Integrando inteligência artificial à mamografia: uma abordagem complementar no diagnóstico do câncer de mama. Revista Ibero-Americana de Humanidades, v.10, n. 5, p.479-485, 2024. DOI: https://doi.org/10.51891/rease.v10i5.13684
HE, J. et al. New progress in imaging diagnosis and immunotherapy of breast cancer. Front. Immunol., v. 16, p. 1560257, 2025. DOI: 10.3389/fimmu.2025.1560257. DOI: https://doi.org/10.3389/fimmu.2025.1560257
HUANG, Y.-H. et al. Artificial intelligence model construction, independent validation, and biological interpretability analysis in breast cancer. Advanced Science, 2025. DOI: 10.1002/advs.202413702. DOI: https://doi.org/10.1002/advs.202413702
JING, X. et al. Using deep learning to safely exclude lesions with only ultrafast breast MRI to shorten acquisition and reading time. Eur Radiol, v. 32, n. 12, p. 8706–8715, 2022. DOI: 10.1007/s00330-022-08706-9. DOI: https://doi.org/10.1007/s00330-022-08863-8
LI, W. et al. Artificial Intelligence for Early Predicting Residual Cancer Burden in Breast Cancer. Annals of Surgery, v. 281, n. 4, p. 649, 2025. DOI: https://doi.org/10.1097/SLA.0000000000006279
LI, Z. et al. Multiregional dynamic contrast-enhanced MRI-based integrated system for predicting pathological complete response of axillary lymphnode to neoadjuvant chemotherapy in breast cancer: multicentre study. eBioMedicine, v. 107, p. 105311, 2024. DOI: 10.1016/j.ebiom.2024.105311. DOI: https://doi.org/10.1016/j.ebiom.2024.105311
LIN, Y. et al. Non-invasive combining models to predict the therapeutic response of primary breast cancer and axillary positive-node prior to NAC. The Breast, v. 76, p. 103737, 2024. DOI: 10.1016/j.breast.2024.103737. DOI: https://doi.org/10.1016/j.breast.2024.103737
MAHANT, S. et al. Traditional machine learning. Cureus, v. 14, n. 9, p. e28945, 2022. DOI: 10.7759/cureus.28945. DOI: https://doi.org/10.7759/cureus.28945
MARCON, M. et al. Summary recommendations on breast cancer screening. European Radiology, v. 34, p. 6348–6357, 2024. DOI: 10.1007/s00330-024-10681-z. DOI: https://doi.org/10.1007/s00330-024-10740-5
MCCAFFREY, C. et al. Artificial intelligence in digital histopathology for predicting patient prognosis and treatment efficacy in breast cancer. Expert Rev Mol Diagn., v. 24, p. 363-77, 2024. DOI: 10.1080/14737159.2024.2346545. DOI: https://doi.org/10.1080/14737159.2024.2346545
MELLO, J. M. R. B. Inteligência artificial na imaginologia mamária. Radiologia Brasileira, v.56, 2023. DOI: https://doi.org/10.1590/0100-3984.2023.56.5e1-en
NASCIMENTO, G. R. et al. Câncer de mama: A importância do diagnóstico precoce para o controle de doença. Revista de Epidemiologia e Saúde Pública-RESP, v.1, n.2, 2023. DOI: https://doi.org/10.59788/resp.v1i2.23
NG, A. Y. et al. Evaluate an Artificial Intelligence (AI) system in breast screening through stratified results across age, breast density, ethnicity and screening centres, from different UK regions. BMJ Health & Care Informatics, p. 10.1136/bmjhci-2024-101318, 2025. DOI: 10.1136/bmjhci-2024-101318. DOI: https://doi.org/10.1136/bmjhci-2024-101318
NISHIZAWA, T. et al. Pathologic complete response after neoadjuvant chemotherapy and impact on breast cancer recurrence and survival. Journal of Translational Medicine, v. 23, p. 774, 2025. DOI: 10.1186/s12967-025-06617-w. DOI: https://doi.org/10.1186/s12967-025-06617-w
OVIEDO, F. et al. Anomaly detection model for cancer detection on screening breast MRI scans using large, imbalanced breast MRI data-sets. Radiology, v. 316, n. 1, p. e241629, 2025. DOI: 10.1148/radiol.241629. DOI: https://doi.org/10.1148/radiol.241629
POLAT, D. S. et al. Machine Learning Prediction of Lymph Node Metastasis in Breast Cancer: Performance of a Multi-institutional MRI-based 4D Convolutional Neural Network. Radiology: Imaging Cancer, v. 6, n. 3, p. e230107, 2024. DOI: 10.1148/rycan.230107. DOI: https://doi.org/10.1148/rycan.230107
SILVA, R. L. et al. Inteligência Artificial no rastreio do câncer de mama: novas tecnologias e suas influências na saúde da mulher. Revista de Estudos Multidisciplinares UNDB, v.3, n.3, 2023.
SOUZA, M. T.; SILVA, M. D.; CARVALHO, R. Revisão integrativa: o que é e como fazer Integrative review: what is it? How to do it? Einstein, v. 8, n. 1, p. 102–108, 2010. DOI: https://doi.org/10.1590/s1679-45082010rw1134
TURIBIO, E. C. et al., O USO DE INTELIGÊNCIA ARTIFICIAL (IA) NO DIAGNÓSTICO PRECOCE DO CÂNCER DE MAMA. Revista Contemporânea, v.5, n.4, p.e7971, 2025. DOI: 10.56083/RCV5N4-078. DOI: https://doi.org/10.56083/RCV5N4-078
UWIMANA, A. et al. Artificial intelligence for breast cancer detection and its health technology assessment: a scoping review. Comput Biol Med., v. 184, p. 109391, 2025. DOI: 10.1016/j.compbiomed.2024.109391. DOI: https://doi.org/10.1016/j.compbiomed.2024.109391
WANG, W.; WANG, Y. Deep Learning-Based Modified YOLACT Algorithm on Magnetic Resonance Imaging Images for Screening Common and Difficult Samples of Breast Cancer. Diagnostics, v. 13, p. 1582, 2023. DOI: 10.3390/diagnostics13091582. DOI: https://doi.org/10.3390/diagnostics13091582
WITOWSKI, J. et al. AI system to predict the probability of breast cancer in patients undergoing DCE-MRI. Sci Transl Med., v. 14, n. 664, p. eabo4802, 2022. DOI: 10.1126/scitranslmed.abo4802. DOI: https://doi.org/10.1126/scitranslmed.abo4802
YU, Y. et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: A machine learning, multicenter study. EBioMedicine, v. 69, p. 103460, 2021. DOI: 10.1016/j.ebiom.2021.103460. DOI: https://doi.org/10.1016/j.ebiom.2021.103460
YUE, W. et al. Radiomics model performance among several breast cancer subtype classifications. J Comput Assist Tomogr, v. 47, n. 5, 2023.
ZHANG, M. et al. Discrimination of benign and malignant breast lesions on dynamic contrast enhanced magnetic resonance imaging using deep learning. J Can Res Ther, v. 19, p. 1589-1596, 2023. DOI: 10.4103/jcrt.jcrt_325_23. DOI: https://doi.org/10.4103/jcrt.jcrt_325_23
ZHANG, Y. et al. Recurrent network using CLSTM to track changes in signal intensity during DCE acquisition for breast cancer molecular subtype classification. Eur Radiol., v. 31, n. 4, p. 2559–2567, 2021. DOI: 10.1007/s00330-020-07274-x. DOI: https://doi.org/10.1007/s00330-020-07274-x
ZHU, T. et al. A non-invasive artificial intelligence model for identifying axillary pathological complete response to neoadjuvant chemotherapy in breast cancer: a secondary analysis to multicenter clinical trial. British Journal of Cancer p. 692 – 701, 2024. DOI: 10.1038/s41416-024-02726-3. DOI: https://doi.org/10.1038/s41416-024-02726-3
ZHU, T. et al. A retrospective cohort study on predicting axillary lymph node response to NAC and non-sentinel lymph node metastasis in breast cancer. International Journal of Surgery, v. 109, p. 3383–3394, 2023. DOI: 10.1097/JS9.0000000000000621. DOI: https://doi.org/10.1097/JS9.0000000000000621
