AI WAVEMAR: Design of an artificial intelligence model for detecting suspicious findings in screening mammography
Radiología (English Edition) · 2026-07 · 68 (4) · 501741
DOI: 10.1016/j.rxeng.2026.501741 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiología (English Edition), 2026-07. Verfasst von E N Arenas Rivera und 6 weiteren Autor:innen. Beteiligte Einrichtung: Universidad Pompeu Fabra, Barcelona, Spain; Departamento de Radiología y Medicina Nuclear, DIBI-Hospital del Mar, Barcelona, Spain. Electronic addres…. Hauptthemen laut MEDLINE: Mammography, Breast Neoplasms, Artificial Intelligence, Early Detection of Cancer. Die Arbeit nennt 40 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVE To describe the development, training and evaluation of AI WaveMar, an artificial intelligence (AI)-based tool designed for the automated detection of suspicious mammographic findings in breast cancer screening. MATERIALS AND METHODS An image classification model based on convolutional neural networks has been developed. The model has been trained on a mixed dataset of 48,562 anonymised mammographic projections, obtained from a public hospital in Spain and the external Chinese Mammography Database (CMMD). The model was evaluated on an independent test set composed of 4902 images. Performance metrics calculated included sensitivity (S or recall), specificity (SP), positive predictive value (PPV or precision), negative predictive value (NPV), accuracy and F1-score. RESULTS AI WaveMar achieved a sensitivity of 92.95% (P < .001) and a specificity of 98.12% (P < .001). The PPV was 89.79% (P < .001), and the NPV was 98.74% (P < .001). Accuracy reached 97,34% (P < .001), with an F1-score of 92.34%, indicating high and balanced diagnostic performance. CONCLUSION AI WaveMar is an AI-based tool developed to support mammographic interpretation, with preliminary results suggesting it could help optimise breast cancer screening. However, prospective clinical validation in real-world practice is required to confirm its diagnostic utility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Universidad Pompeu Fabra, Barcelona, Spain; Departamento de Radiología y Medicina Nuclear, DIBI-Hospital del Mar, Barcelona, Spain. Electronic address: earenasrivera@hmar.cat.
- Departamento de Radiología y Medicina Nuclear, DIBI-Hospital del Mar, Barcelona, Spain.
- Universidad Pompeu Fabra, Barcelona, Spain; Departamento de Radiología y Medicina Nuclear, DIBI-Hospital del Mar, Barcelona, Spain; Universidad Autónoma de Barcelona, Barcelona, Spain.
- Departamento de Epidemiología y Evaluación, Hospital del Mar, Barcelona, Spain; Hospital del Mar Research Institute, Barcelona, Spain; Red de Investigación en Cronicidad, Atención Primaria y Promoción de la Salud (RICAP…
- Universidad Pompeu Fabra, Barcelona, Spain; Departamento de Epidemiología y Evaluación, Hospital del Mar, Barcelona, Spain; Hospital del Mar Research Institute, Barcelona, Spain; Red de Investigación en Cronicidad, Aten…
Zitieren
APA
Arenas Rivera, E. N., Maiques, J. M., Alcantara, R., Román, M., Burón, A., Sala, M., & Busto, M. (2026). AI WAVEMAR: Design of an artificial intelligence model for detecting suspicious findings in screening mammography. Radiología (English Edition), 68(4), 501741. https://doi.org/10.1016/j.rxeng.2026.501741
Vancouver
Arenas Rivera EN, Maiques JM, Alcantara R, Román M, Burón A, Sala M, et al. AI WAVEMAR: Design of an artificial intelligence model for detecting suspicious findings in screening mammography. Radiología (English Edition). 2026;68(4):501741. doi:10.1016/j.rxeng.2026.501741
BibTeX
@article{ArenasRivera2026,
author = {Arenas Rivera, E N and Maiques, J M and Alcantara, R and Román, M and Burón, A and Sala, M and Busto, M},
title = {AI WAVEMAR: Design of an artificial intelligence model for detecting suspicious findings in screening mammography},
journal = {Radiología (English Edition)},
year = {2026},
volume = {68},
number = {4},
pages = {501741},
doi = {10.1016/j.rxeng.2026.501741}
}
EUVIMED