Inteligencia Artificial Basada en Aprendizaje Profundo para la Detección del Cáncer de Mama en Mamografía: Una Revisión Sistemática
Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197 · 21.04.2026 · 5 (2) · 467-485
DOI: 10.63371/ic.v5.n2.a987 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197, online erschienen am 21.04.2026. Verfasst von Byron González Jara und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
The incorporation of artificial intelligence (AI) into mammographic assessment has been considered a strategy to improve breast cancer detection and optimize reading workload in population-based screening programs. In this review, the scientific evidence published between 2020 and 2025 was evaluated regarding the clinical implications and performance of AI in mammography-based breast cancer screening; for this purpose, a systematic review was conducted following PRISMA guidelines through the systematic search of studies in PubMed, Scopus, and Google Scholar, selecting 33 studies for qualitative synthesis without performing a meta-analysis. These studies encompassed retrospective evaluations of population screening, trials, and prospective implementations in which AI was used as a second reader, an additional reader, interpretation support, triage, localization of lesions suspicious for malignancy, and quality control of the radiological report. The results showed that AI increased or maintained the breast cancer detection rate in several scenarios, including the identification of recurrences, and reduced the workload and reading time of mammographic examinations; however, the data varied in scenarios where the radiologist presented discordances with AI, even recording increases in recalls and/or arbitrations. It was concluded that AI is a useful tool to optimize mammography screening, especially through triage and reading support, and that, in scenarios of discordance, clinical supervision and arbitration were decisive in maximizing benefits.
Zitieren
APA
Jara, B. G., Ramírez, R. A., Beltran, J. P., & Jara, L. G. (2026). Inteligencia Artificial Basada en Aprendizaje Profundo para la Detección del Cáncer de Mama en Mamografía: Una Revisión Sistemática. Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197, 5(2), 467-485. https://doi.org/10.63371/ic.v5.n2.a987
Vancouver
Jara BG, Ramírez RA, Beltran JP, Jara LG. Inteligencia Artificial Basada en Aprendizaje Profundo para la Detección del Cáncer de Mama en Mamografía: Una Revisión Sistemática. Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197. 2026;5(2):467-485. doi:10.63371/ic.v5.n2.a987
BibTeX
@article{Jara2026,
author = {Jara, Byron González and Ramírez, Rebeca Arizaga and Beltran, José Patricio and Jara, Lizbeth González},
title = {Inteligencia Artificial Basada en Aprendizaje Profundo para la Detección del Cáncer de Mama en Mamografía: Una Revisión Sistemática},
journal = {Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197},
year = {2026},
volume = {5},
number = {2},
pages = {467--485},
doi = {10.63371/ic.v5.n2.a987}
}
EUVIMED