A Multimodal Fusion Model of Radiomics and Deep Learning Integrating the Tumor Microenvironment Accurately Predicts Pathological Complete Response in Breast Cancer
Academic Radiology · 2026-04 · 33 (4) · 1473-1483
DOI: 10.1016/j.acra.2026.01.016 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Academic Radiology, 2026-04. Verfasst von Deqing Hong und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computational Science and Technology, Guangzhou University, Guangzhou, China (D.H., P.X., W.L., Z.Y.). Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning, Magnetic Resonance Imaging, Predictive Learning Models. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Special Project for Research and Development in Key areas of Guangdong Province.
Abstract (Originalsprache)
BACKGROUND: Pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) is a critical prognostic marker in breast cancer, yet its prediction remains challenging due to tumor heterogeneity and limitations of conventional imaging. While radiomics and deep learning (DL) have shown promise, prior studies often neglect the peritumoral microenvironment, a key determinant of therapeutic response. METHODS: We developed a multimodal model integrating intratumoral radiomics, peritumoral features (9-mm expansion), and DL-derived patterns from pre-NAC MRI. The model was trained and internally validated on a high-quality, multicenter cohort from the I-SPY2 trial (n = 929) and externally validated on an independent cohort (n = 95). We extracted 3190 radiomic and 2048 DL features, selecting optimal subsets via Lasso regression and bidirectional selection. Nine machine learning algorithms were evaluated, with logistic regression (LR) emerging as the top performer. RESULTS: The final integrated model (Intra-Peri-DL) demonstrated favorable performance, achieving an area under the curve (AUC) of 0.888 (95% CI: 0.841-0.933) in internal validation and 0.890 (95% CI: 0.804-0.958) in external validation. This performance was statistically superior to single-modality models (intratumoral radiomics, peritumoral radiomics, or DL features alone; all P 0.91) in both cohorts and suggested potential clinical utility in decision curve analysis. CONCLUSION: By synergizing radiomics and DL to capture tumor-microenvironment interplay, our model enhances pCR prediction accuracy, offering a potential clinically actionable tool for personalized NAC decision-making. This framework bridges imaging phenotypes with biological insights, paving the way for precision oncology in breast cancer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Computational Science and Technology, Guangzhou University, Guangzhou, China (D.H., P.X., W.L., Z.Y.).
- Department of Radiology, Guangdong Provincial People's Hospital, Guangzhou, China (J.P., Z.L.).
- Institute of Computational Science and Technology, Guangzhou University, Guangzhou, China (D.H., P.X., W.L., Z.Y.). Electronic address: charles_ye@126.com.
Förderung
- Special Project for Research and Development in Key areas of Guangdong Province
Zitieren
APA
Hong, D., Peng, J., Xu, P., Liu, W., Liu, Z., & Ye, Z. (2026). A Multimodal Fusion Model of Radiomics and Deep Learning Integrating the Tumor Microenvironment Accurately Predicts Pathological Complete Response in Breast Cancer. Academic Radiology, 33(4), 1473-1483. https://doi.org/10.1016/j.acra.2026.01.016
Vancouver
Hong D, Peng J, Xu P, Liu W, Liu Z, Ye Z. A Multimodal Fusion Model of Radiomics and Deep Learning Integrating the Tumor Microenvironment Accurately Predicts Pathological Complete Response in Breast Cancer. Academic Radiology. 2026;33(4):1473-1483. doi:10.1016/j.acra.2026.01.016
BibTeX
@article{Hong2026,
author = {Hong, Deqing and Peng, Jiayi and Xu, Peng and Liu, Wenbin and Liu, Zaiyi and Ye, Zheng},
title = {A Multimodal Fusion Model of Radiomics and Deep Learning Integrating the Tumor Microenvironment Accurately Predicts Pathological Complete Response in Breast Cancer},
journal = {Academic Radiology},
year = {2026},
volume = {33},
number = {4},
pages = {1473--1483},
doi = {10.1016/j.acra.2026.01.016}
}
EUVIMED