Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis

Abstract Objective This meta-analysis evaluates the diagnostic accuracy of machine learning (ML)-based magnetic resonance imaging (MRI) models in distinguishing benign from malignant breast lesions and explores factors influencing their performance. Methods A systematic search of PubMed, Embase, Coc...

Full description

Saved in:
Bibliographic Details
Main Authors: Jupeng Zhang, Qi Wu, Peng Lei, Xiqi Zhu, Baosheng Li
Format: Article
Language:English
Published: BMC 2025-06-01
Series:World Journal of Surgical Oncology
Subjects:
Online Access:https://doi.org/10.1186/s12957-025-03874-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335754149330944
author Jupeng Zhang
Qi Wu
Peng Lei
Xiqi Zhu
Baosheng Li
author_facet Jupeng Zhang
Qi Wu
Peng Lei
Xiqi Zhu
Baosheng Li
author_sort Jupeng Zhang
collection DOAJ
description Abstract Objective This meta-analysis evaluates the diagnostic accuracy of machine learning (ML)-based magnetic resonance imaging (MRI) models in distinguishing benign from malignant breast lesions and explores factors influencing their performance. Methods A systematic search of PubMed, Embase, Cochrane Library, Scopus, and Web of Science identified 12 eligible studies (from 3,739 records) up to August 2024. Data were extracted to calculate sensitivity, specificity, and area under the curve (AUC) using bivariate models in R 4.4.1. Study quality was assessed via QUADAS-2. Results Pooled sensitivity and specificity were 0.86 (95% CI: 0.82–0.90) and 0.82 (95% CI: 0.78–0.86), respectively, with an overall AUC of 0.90 (95% CI: 0.85–0.90). Diagnostic odds ratio (DOR) was 39.11 (95% CI: 25.04–53.17). Support vector machine (SVM) classifiers outperformed Naive Bayes, with higher sensitivity (0.88 vs. 0.86) and specificity (0.82 vs. 0.78). Heterogeneity was primarily attributed to MRI equipment (P = 0.037). Conclusion ML-based MRI models demonstrate high diagnostic accuracy for breast cancer classification, with pooled sensitivity of 0.86 (95% CI: 0.82–0.90), specificity of 0.82 (95% CI: 0.78–0.86), and AUC of 0.90 (95% CI: 0.85–0.90). These results support their clinical utility as screening and diagnostic adjuncts, while highlighting the need for standardized protocols to improve generalizability.
format Article
id doaj-art-313cb80668514e9ca08dc1787e5cb809
institution Kabale University
issn 1477-7819
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series World Journal of Surgical Oncology
spelling doaj-art-313cb80668514e9ca08dc1787e5cb8092025-08-20T03:45:11ZengBMCWorld Journal of Surgical Oncology1477-78192025-06-0123111110.1186/s12957-025-03874-3Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysisJupeng Zhang0Qi Wu1Peng Lei2Xiqi Zhu3Baosheng Li4Department of Radiology, Affiliated Hospital of Youjiang Medical university for NationalitiesDepartment of Radiology, Affiliated Hospital of Youjiang Medical university for NationalitiesDepartment of Radiology, Affiliated Hospital of Youjiang Medical university for NationalitiesDepartment of Radiology, Affiliated Hospital of Youjiang Medical university for NationalitiesDepartment of Radiology, Affiliated Hospital of Youjiang Medical university for NationalitiesAbstract Objective This meta-analysis evaluates the diagnostic accuracy of machine learning (ML)-based magnetic resonance imaging (MRI) models in distinguishing benign from malignant breast lesions and explores factors influencing their performance. Methods A systematic search of PubMed, Embase, Cochrane Library, Scopus, and Web of Science identified 12 eligible studies (from 3,739 records) up to August 2024. Data were extracted to calculate sensitivity, specificity, and area under the curve (AUC) using bivariate models in R 4.4.1. Study quality was assessed via QUADAS-2. Results Pooled sensitivity and specificity were 0.86 (95% CI: 0.82–0.90) and 0.82 (95% CI: 0.78–0.86), respectively, with an overall AUC of 0.90 (95% CI: 0.85–0.90). Diagnostic odds ratio (DOR) was 39.11 (95% CI: 25.04–53.17). Support vector machine (SVM) classifiers outperformed Naive Bayes, with higher sensitivity (0.88 vs. 0.86) and specificity (0.82 vs. 0.78). Heterogeneity was primarily attributed to MRI equipment (P = 0.037). Conclusion ML-based MRI models demonstrate high diagnostic accuracy for breast cancer classification, with pooled sensitivity of 0.86 (95% CI: 0.82–0.90), specificity of 0.82 (95% CI: 0.78–0.86), and AUC of 0.90 (95% CI: 0.85–0.90). These results support their clinical utility as screening and diagnostic adjuncts, while highlighting the need for standardized protocols to improve generalizability.https://doi.org/10.1186/s12957-025-03874-3Machine learningDiagnostic accuracyMeta-analysisBreast cancerMagnetic resonance imaging
spellingShingle Jupeng Zhang
Qi Wu
Peng Lei
Xiqi Zhu
Baosheng Li
Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis
World Journal of Surgical Oncology
Machine learning
Diagnostic accuracy
Meta-analysis
Breast cancer
Magnetic resonance imaging
title Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis
title_full Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis
title_fullStr Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis
title_full_unstemmed Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis
title_short Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: a systematic review and meta-analysis
title_sort diagnostic accuracy of machine learning based magnetic resonance imaging models in breast cancer classification a systematic review and meta analysis
topic Machine learning
Diagnostic accuracy
Meta-analysis
Breast cancer
Magnetic resonance imaging
url https://doi.org/10.1186/s12957-025-03874-3
work_keys_str_mv AT jupengzhang diagnosticaccuracyofmachinelearningbasedmagneticresonanceimagingmodelsinbreastcancerclassificationasystematicreviewandmetaanalysis
AT qiwu diagnosticaccuracyofmachinelearningbasedmagneticresonanceimagingmodelsinbreastcancerclassificationasystematicreviewandmetaanalysis
AT penglei diagnosticaccuracyofmachinelearningbasedmagneticresonanceimagingmodelsinbreastcancerclassificationasystematicreviewandmetaanalysis
AT xiqizhu diagnosticaccuracyofmachinelearningbasedmagneticresonanceimagingmodelsinbreastcancerclassificationasystematicreviewandmetaanalysis
AT baoshengli diagnosticaccuracyofmachinelearningbasedmagneticresonanceimagingmodelsinbreastcancerclassificationasystematicreviewandmetaanalysis