Multimodal deep learning for breast tumor classification: Integrating mammography and ultrasound for enhanced diagnostic accuracy
Journal of Applied Clinical Medical Physics · 2026
DOI: 10.1002/acm2.70464 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, 2026. Verfasst von Yu Yan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Equipment, Jiangsu Province Hospital of Chinese Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjin…. Hauptthemen laut MEDLINE: Breast Neoplasms, Mammography, Deep Learning, Ultrasonography, Mammary. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Postgraduate Research & Practice Innovation Program of Jiangsu Province.
Abstract (Originalsprache)
Background
Deep learning has advanced breast tumor prediction research, but traditional single‐modality models limit feature diversity and accuracy.
Purpose
To develop and validate a multimodal deep learning approach that combines mammography and ultrasound imaging for improved breast tumor classification and enhanced clinical decision‐making.
Methods
This retrospective study analyzed 663 female patients with breast lesions from 2018 to 2021, including 384 benign and 279 malignant cases. The two‐stage prediction model employed improved modality‐specific attention mechanisms: efficient channel attention (ECA‐Net) for ultrasound and convolutional block attention module (CBAM) for mammography. The fused features were input into a stacking ensemble module with logistic regression (LR), support vector machine (SVM), random forest (RF), and Extra‐Trees (ET) as base learners, and multilayer perceptron (MLP) neural network as meta‐learner. Data was divided into training (464), validation (133), and test (66) sets with a 7:2:1 ratio.
Results
The proposed multimodal prediction model—mammography ultrasound (MPM‐MU) achieved superior performance with an area under the receiver operating characteristic (ROC) Curve (AUC) of 87.9 ± 0.21%, representing improvements of 13.4% and 15.6% over attention‐enhanced mammography (74.5%) and ultrasound (72.3%) models, respectively. Ablation studies confirmed the effectiveness of both multimodal feature fusion and attention mechanisms in enhancing diagnostic performance.
Conclusions
The multimodal prediction model—mammography ultrasound (MPM‐MU) with modality‐specific attention mechanisms demonstrated superior performance in distinguishing between benign and malignant breast tumors compared to single‐modality approaches. This approach assists radiologists in improving breast lesion classification accuracy and enhancing clinical decision‐making, potentially reducing unnecessary biopsies and improving diagnostic consistency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Equipment, Jiangsu Province Hospital of Chinese Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu, China.
- School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing, Jiangsu, China.
ORCID-Profile: Xu He
Förderung
- Postgraduate Research & Practice Innovation Program of Jiangsu Province
Zitieren
APA
Yan, Y., Xu, Y., Fang, G., He, X., Qian, Y., & Zhu, W. (2026). Multimodal deep learning for breast tumor classification: Integrating mammography and ultrasound for enhanced diagnostic accuracy. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70464
Vancouver
Yan Y, Xu Y, Fang G, He X, Qian Y, Zhu W. Multimodal deep learning for breast tumor classification: Integrating mammography and ultrasound for enhanced diagnostic accuracy. Journal of Applied Clinical Medical Physics. 2026. doi:10.1002/acm2.70464
BibTeX
@article{Yan2026,
author = {Yan, Yu and Xu, Yichen and Fang, Ge and He, Xu and Qian, Yifei and Zhu, Wenwen},
title = {Multimodal deep learning for breast tumor classification: Integrating mammography and ultrasound for enhanced diagnostic accuracy},
journal = {Journal of Applied Clinical Medical Physics},
year = {2026},
doi = {10.1002/acm2.70464}
}
EUVIMED