EUVIMEDEUVIMED entdecken
Crossref

MRI-based habitat analysis for Intratumoral heterogeneity quantification combined with deep learning for HER2 status prediction in breast cancer

Qing-Yu Li, Yue Liang, Lan Zhang, Jia-Hao Li, Bin-Jie Wang, Chang-Fu Wang

Magnetic Resonance Imaging · 2025-10 · 122 · 110429

DOI: 10.1016/j.mri.2025.110429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2025-10. Verfasst von Qing-Yu Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Background: Huai-he Hospital of Henan University, Kaifeng, China. Hauptthemen laut MEDLINE: Breast Neoplasms, Erb-b2 Receptor Tyrosine Kinases, Deep Learning, Magnetic Resonance Imaging. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Human epidermal growth factor receptor 2 (HER2) is a crucial determinant of breast cancer prognosis and treatment options. The study aimed to establish an MRI-based habitat model to quantify intratumoral heterogeneity (ITH) and evaluate its potential in predicting HER2 expression status. METHODS: Data from 340 patients with pathologically confirmed invasive breast cancer were retrospectively analyzed. Two tasks were designed for this study: Task 1 distinguished between HER2-positive and HER2-negative breast cancer. Task 2 distinguished between HER2-low and HER2-zero breast cancer. We developed the ITH, deep learning (DL), and radiomics signatures based on the features extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Clinical independent predictors were determined by multivariable logistic regression. Finally, a combined model was constructed by integrating the clinical independent predictors, ITH signature, and DL signature. The area under the receiver operating characteristic curve (AUC) served as the standard for assessing the performance of models. RESULTS: In task 1, the ITH signature performed well in the training set (AUC = 0.855) and the validation set (AUC = 0.842). In task 2, the AUCs of the ITH signature were 0.844 and 0.840, respectively, which still showed good prediction performance. In the validation sets of both tasks, the combined model exhibited the best prediction performance, with AUCs of 0.912 and 0.917 respectively, making it the optimal model. CONCLUSION: A combined model integrating clinical independent predictors, ITH signature, and DL signature can predict HER2 expression status preoperatively and noninvasively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsErb-b2 Receptor Tyrosine KinasesDeep LearningMagnetic Resonance ImagingHumansFemaleMiddle AgedRetrospective StudiesAdultAgedROC CurveContrast MediaBreastPrognosis

Stichwörter der Autor:innen

Breast cancerDeep learningDynamic contrast-enhanced magnetic resonance imagingHER2Habitat analysisRadiomics

Substanzen

Erb-b2 Receptor Tyrosine KinasesContrast MediaERBB2 protein, human

Autor:innen und Institutionen

  • Background: Huai-he Hospital of Henan University, Kaifeng, China.
  • Background: Huai-he Hospital of Henan University, Kaifeng, China. Electronic address: 1974103323@qq.com.

Zitieren

APA

Li, Q. Y., Liang, Y., Zhang, L., Li, J. H., Wang, B. J., & Wang, C. F. (2025). MRI-based habitat analysis for Intratumoral heterogeneity quantification combined with deep learning for HER2 status prediction in breast cancer. Magnetic Resonance Imaging, 122, 110429. https://doi.org/10.1016/j.mri.2025.110429

Vancouver

Li QY, Liang Y, Zhang L, Li JH, Wang BJ, Wang CF. MRI-based habitat analysis for Intratumoral heterogeneity quantification combined with deep learning for HER2 status prediction in breast cancer. Magnetic Resonance Imaging. 2025;122:110429. doi:10.1016/j.mri.2025.110429

BibTeX
@article{Li2025,
  author = {Li, Qing-Yu and Liang, Yue and Zhang, Lan and Li, Jia-Hao and Wang, Bin-Jie and Wang, Chang-Fu},
  title = {MRI-based habitat analysis for Intratumoral heterogeneity quantification combined with deep learning for HER2 status prediction in breast cancer},
  journal = {Magnetic Resonance Imaging},
  year = {2025},
  volume = {122},
  pages = {110429},
  doi = {10.1016/j.mri.2025.110429}
}
Kostenlos starten →