AI WAVEMAR: creación de un modelo de inteligencia artificial para detectar hallazgos sospechosos en la mamografía de cribado

IF 1.5 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

RADIOLOGIA Pub Date : 2026-07-01 Epub Date: 2025-08-19 DOI:10.1016/j.rx.2025.501741

E.N. Arenas Rivera, J.M. Maiques, R. Alcantara, M. Román, A. Burón, M. Sala, M. Busto

{"title":"AI WAVEMAR: creación de un modelo de inteligencia artificial para detectar hallazgos sospechosos en la mamografía de cribado","authors":"E.N. Arenas Rivera, J.M. Maiques, R. Alcantara, M. Román, A. Burón, M. Sala, M. Busto","doi":"10.1016/j.rx.2025.501741","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>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.</div></div><div><h3>Materials and methods</h3><div>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 4,902 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.</div></div><div><h3>Results</h3><div>AI WaveMar achieved a sensitivity of 92.95% <em>(P</em><.001) and a specificity of 98.12% <em>(P</em><.001). The PPV was 89.79% <em>(P</em><.001), and the NPV was 98.74% <em>(P</em><.001). Accuracy reached 97,34% <em>(P</em><.001), with an F1-score of 92.34%, indicating high and balanced diagnostic performance.</div></div><div><h3>Conclusion</h3><div>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.</div></div>","PeriodicalId":31509,"journal":{"name":"RADIOLOGIA","volume":"68 4","pages":"Article 501741"},"PeriodicalIF":1.5000,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"RADIOLOGIA","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0033833825001250","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/8/19 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

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 4,902 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.

Abstract Image

查看原文本刊更多论文

AI WAVEMAR：创建一个人工智能模型，用于检测筛查乳房x线照相术中的可疑发现

目的介绍人工智能（AI）工具WaveMar的开发、培训和评估，该工具旨在自动检测乳腺癌筛查中的可疑乳房x线检查结果。材料与方法基于卷积神经网络建立了一种图像分类模型。该模型在48,562个匿名乳房x线摄影投影的混合数据集上进行了训练，这些数据集来自西班牙一家公立医院和外部中国乳房x线摄影数据库（CMMD）。该模型在一个由4,902张图像组成的独立测试集上进行评估。计算的性能指标包括灵敏度（S或召回率）、特异性（SP）、阳性预测值（PPV或精度）、阴性预测值（NPV）、准确性和f1评分。结果WaveMar的敏感性为92.95% (p < 0.01)，特异性为98.12% （p < 0.01）。PPV为89.79% (p < 0.01)， NPV为98.74% （p < 0.01）。准确率达到97,34% (P<.001)， f1评分为92.34%，显示出较高的、平衡的诊断性能。ai WaveMar是一种基于人工智能的工具，用于支持乳房x线摄影解释，初步结果表明它可以帮助优化乳腺癌筛查。然而，在现实世界的实践中，需要前瞻性临床验证来确认其诊断效用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

RADIOLOGIA RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-

CiteScore

1.60

自引率

7.70%

发文量

105

审稿时长

52 days

期刊介绍： La mejor revista para conocer de primera mano los originales más relevantes en la especialidad y las revisiones, casos y notas clínicas de mayor interés profesional. Además es la Publicación Oficial de la Sociedad Española de Radiología Médica.