Machine Learning Model Based on Multiparametric MRI for Distinguishing HER2 Expression Level in Breast Cancer
Current Oncology · 16.01.2026 · 33 (1) · 53
DOI: 10.3390/curroncol33010053 ↗Kurz gefasst
Fachartikel in der Zeitschrift Current Oncology, online erschienen am 16.01.2026. Verfasst von Yongxin Chen und 8 weiteren Autor:innen. Beteiligte Einrichtung: The First School of Clinical Medicine, Jinan University, Guangzhou 510632, China. Hauptthemen laut MEDLINE: Breast Neoplasms, Machine Learning, Erb-b2 Receptor Tyrosine Kinases, Multiparametric Magnetic Resonance Imaging. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Science and technology Projects in Guangzhou.
Abstract (Originalsprache)
This study aimed to develop machine learning models based on conventional MRI features to classify HER2 expression levels in invasive breast cancer and explore their association with disease-free survival (DFS). A total of 678 patients from two centers were included, with Center 1 divided into training and internal test sets and Center 2 serving as an external test set. Random Forest models were trained to distinguish HER2-positive vs. HER2-negative (Task 1) and HER2-low vs. HER2-zero tumors (Task 2) using BI-RADS–based MRI features. SHapley Additive exPlanations were applied to rank feature importance, assist feature selection, and enhance model interpretability. DFS was analyzed using Kaplan–Meier curves and log-rank tests. In Task 1, key features included tumor size, axillary lymph nodes, fibroglandular tissue, peritumoral edema, and multifocal, achieving AUCs of 0.75 and 0.73 in the internal and external test sets, respectively. In Task 2, tumor size, peritumoral edema, and multifocal yielded AUCs of 0.73 and 0.72, respectively. Higher task-specific model scores were associated with shorter DFS in Task 1 (p = 0.037) and longer DFS in Task 2 (p = 0.046). MRI-based machine learning models can noninvasively stratify HER2 expression levels, with potential for prognostic stratification and clinical application.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- The First School of Clinical Medicine, Jinan University, Guangzhou 510632, China.
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou 510180, China.
- Department of Radiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, China.
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Science and technology Projects in Guangzhou
- Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Chen, Y., Liu, W., Tang, W., Kong, Q., Chen, S., Liu, S., Pan, L., Guo, Y., & Jiang, X. (2026). Machine Learning Model Based on Multiparametric MRI for Distinguishing HER2 Expression Level in Breast Cancer. Current Oncology, 33(1), 53. https://doi.org/10.3390/curroncol33010053
Vancouver
Chen Y, Liu W, Tang W, Kong Q, Chen S, Liu S, et al. Machine Learning Model Based on Multiparametric MRI for Distinguishing HER2 Expression Level in Breast Cancer. Current Oncology. 2026;33(1):53. doi:10.3390/curroncol33010053
BibTeX
@article{Chen2026,
author = {Chen, Yongxin and Liu, Weifeng and Tang, Wenjie and Kong, Qingcong and Chen, Siyi and Liu, Shuang and Pan, Liwen and Guo, Yuan and Jiang, Xinqing},
title = {Machine Learning Model Based on Multiparametric MRI for Distinguishing HER2 Expression Level in Breast Cancer},
journal = {Current Oncology},
year = {2026},
volume = {33},
number = {1},
pages = {53},
doi = {10.3390/curroncol33010053}
}
EUVIMED