EUVIMEDEUVIMED entdecken
Validierungsstudie

Development and Validation of a Deep Learning System to Differentiate HER2 ‐Zero, HER2 ‐Low, and HER2 ‐Positive Breast Cancer Based on Dynamic Contrast‐Enhanced MRI

Yi Dai iD, Chun Lian, Zhuo Zhang, Jing Gao, Fan Lin, Ziyin Li, Qi Wang, Tongpeng Chu iD, Dilinuer Aishanjiang, Meiying Chen, Ximing Wang iD, Guanxun Cheng iD und 4 weitere

Journal of Magnetic Resonance Imaging · 2025

DOI: 10.1002/jmri.29670 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Magnetic Resonance Imaging, 2025. Verfasst von Yi Dai und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Imaging, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning, Magnetic Resonance Imaging, Erb-b2 Receptor Tyrosine Kinases. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Projects of China Medicine Education Association, Natural Science Foundation of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Previous studies explored MRI‐based radiomic features for differentiating between human epidermal growth factor receptor 2 (HER2)‐zero, HER2‐low, and HER2‐positive breast cancer, but deep learning's effectiveness is uncertain.

Purpose

This study aims to develop and validate a deep learning system using dynamic contrast‐enhanced MRI (DCE‐MRI) for automated tumor segmentation and classification of HER2‐zero, HER2‐low, and HER2‐positive statuses. Study Type Retrospective. Population One thousand two hundred ninety‐four breast cancer patients from three centers who underwent DCE‐MRI before surgery were included in the study (52 ± 11 years, 811/204/279 for training/internal testing/external testing). Field Strength/Sequence 3 T scanners, using T1‐weighted 3D fast spoiled gradient‐echo sequence, T1‐weighted 3D enhanced fast gradient‐echo sequence and T1‐weighted turbo field echo sequence. Assessment An automated model segmented tumors utilizing DCE‐MRI data, followed by a deep learning models (ResNetGN) trained to classify HER2 statuses. Three models were developed to distinguish HER2‐zero, HER2‐low, and HER2‐positive from their respective non‐HER2 categories. Statistical Tests Dice similarity coefficient (DSC) was used to evaluate the segmentation performance of the model. Evaluation of the model performances for HER2 statuses involved receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC), accuracy, sensitivity, and specificity. The P ‐values

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsDeep LearningMagnetic Resonance ImagingErb-b2 Receptor Tyrosine KinasesContrast MediaHumansFemaleMiddle AgedRetrospective StudiesAdultReproducibility of ResultsImage Interpretation, Computer-AssistedAgedBreastROC CurveSensitivity and Specificity

Stichwörter der Autor:innen

breast cancerdeep learningdynamic contrast‐enhanced MRIhuman epidermal growth factor receptor 2

Substanzen

Erb-b2 Receptor Tyrosine KinasesContrast MediaERBB2 protein, human

Autor:innen und Institutionen

  • Department of Medical Imaging, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China.
  • School of Computer Science and Technology, Shandong Technology and Business University, Yantai, Shandong, China.
  • Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, China.
  • Big Data and Artificial Intelligence Laboratory, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, China.
  • Shandong Provincial Key Medical and Health Laboratory of Intelligent Diagnosis and Treatment for Women's Diseases, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, China.
  • Department of Radiology, Shandong Provincial Hospital, Jinan, Shandong, China.

ORCID-Profile: Yi Dai, Tongpeng Chu, Ximing Wang, Guanxun Cheng, Ning Mao

Förderung

  • National Natural Science Foundation of China
  • Key Projects of China Medicine Education Association
  • Natural Science Foundation of Shandong Province
  • China Postdoctoral Science Foundation
  • The Open Fund of National Innovation Center for Advanced Medical Devices
  • The Scientific Research Foundation of Peking University Shenzhen Hospital
  • Taishan Scholar Project of Shandong Province
  • Beijing Postdoctoral Science Foundation

Zitieren

APA

Dai, Y., Lian, C., Zhang, Z., Gao, J., Lin, F., Li, Z., Wang, Q., Chu, T., Aishanjiang, D., Chen, M., Wang, X., Cheng, G., Huang, R., Dong, J., Zhang, H., & Mao, N. (2025). Development and Validation of a Deep Learning System to Differentiate HER2 ‐Zero, HER2 ‐Low, and HER2 ‐Positive Breast Cancer Based on Dynamic Contrast‐Enhanced MRI. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29670

Vancouver

Dai Y, Lian C, Zhang Z, Gao J, Lin F, Li Z, et al. Development and Validation of a Deep Learning System to Differentiate HER2 ‐Zero, HER2 ‐Low, and HER2 ‐Positive Breast Cancer Based on Dynamic Contrast‐Enhanced MRI. Journal of Magnetic Resonance Imaging. 2025. doi:10.1002/jmri.29670

BibTeX
@article{Dai2025,
  author = {Dai, Yi and Lian, Chun and Zhang, Zhuo and Gao, Jing and Lin, Fan and Li, Ziyin and Wang, Qi and Chu, Tongpeng and Aishanjiang, Dilinuer and Chen, Meiying and Wang, Ximing and Cheng, Guanxun and Huang, Rong and Dong, Jianjun and Zhang, Haicheng and Mao, Ning},
  title = {Development and Validation of a Deep Learning System to Differentiate HER2 ‐Zero, HER2 ‐Low, and HER2 ‐Positive Breast Cancer Based on Dynamic Contrast‐Enhanced MRI},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2025},
  doi = {10.1002/jmri.29670}
}
Kostenlos starten →