A combined model integrating radiomics and deep learning based on multiparametric magnetic resonance imaging for classification of brain metastases
Acta Radiologica · 2025
DOI: 10.1177/02841851241292528 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Radiologica, 2025. Verfasst von Bo Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou, PR China. Hauptthemen laut MEDLINE: Deep Learning, Brain Neoplasms, Multiparametric Magnetic Resonance Imaging, Lung Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Key Medical Discipline Construction Unit of Jiangsu Province for the 14th Five-year plan in China, Suzhou Radiotherapy Clinical Medical Center in China, Science and Technology Program of Suzhou.
Abstract (Originalsprache)
Background
Radiomics and deep learning (DL) can individually and efficiently identify the pathological type of brain metastases (BMs).
Purpose
To investigate the feasibility of utilizing multi-parametric MRI-based deep transfer learning radiomics (DTLR) for the classification of lung adenocarcinoma (LUAD) and non-LUAD BMs. Material and Methods A retrospective analysis was performed on 342 patients with 1389 BMs. These instances were randomly assigned to a training set of 273 (1179 BMs) and a testing set of 69 (210 BMs) in an 8:2 ratio. Eight machine learning algorithms were employed to construct the radiomics models. A DL model was developed using four pre-trained convolutional neural networks (CNNs). The DTLR model was formulated by integrating the optimal performing radiomics model and the DL model using a classification probability averaging approach. The area under the curve (AUC), calibration curve, and decision curve analysis (DCA) were utilized to assess the performance and clinical utility of the models.
Results
The AUC for the optimal radiomics and DL model in the testing set were 0.824 (95% confidence interval [CI]= 0.726–0.923) and 0.775 (95% CI=0.666–0.884), respectively. The DTLR model demonstrated superior discriminatory power, achieving an AUC of 0.880 (95% CI=0.803–0.957). In addition, the DTLR model exhibited good consistency between actual and predicted probabilities based on the calibration curve and DCA analysis, indicating its significant clinical value.
Conclusion
Our study's DTLR model demonstrated high diagnostic accuracy in distinguishing LUAD from non-LUAD BMs. This method shows potential for the non-invasive identification of the histological subtype of BMs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou, PR China.
- Department of Radiation Oncology, The Second Affiliated Hospital of Soochow University, Suzhou, PR China.
- Department of Respiratory & Critical Care Medicine, The Second Affiliated Hospital of Soochow University, Suzhou, PR China.
- Department of Radiotherapy & Oncology, The Second Affiliated Hospital of Soochow University, Suzhou, PR China.
- Institute of Radiotherapy & Oncology, Soochow University, Suzhou, PR China.
- Suzhou Key Laboratory for Radiation Oncology, Suzhou, PR China.
ORCID-Profile: Bo Zhang
Förderung
- Key Medical Discipline Construction Unit of Jiangsu Province for the 14th Five-year plan in China
- Suzhou Radiotherapy Clinical Medical Center in China
- Science and Technology Program of Suzhou
Zitieren
APA
Zhang, B., Zhu, J., Xu, R., Zou, L., Lian, Y., Xie, X., & Tian, Y. (2025). A combined model integrating radiomics and deep learning based on multiparametric magnetic resonance imaging for classification of brain metastases. Acta Radiologica. https://doi.org/10.1177/02841851241292528
Vancouver
Zhang B, Zhu J, Xu R, Zou L, Lian Y, Xie X, et al. A combined model integrating radiomics and deep learning based on multiparametric magnetic resonance imaging for classification of brain metastases. Acta Radiologica. 2025. doi:10.1177/02841851241292528
BibTeX
@article{Zhang2025,
author = {Zhang, Bo and Zhu, Jinling and Xu, Ruizhe and Zou, Li and Lian, Yixin and Xie, Xin and Tian, Ye},
title = {A combined model integrating radiomics and deep learning based on multiparametric magnetic resonance imaging for classification of brain metastases},
journal = {Acta Radiologica},
year = {2025},
doi = {10.1177/02841851241292528}
}
EUVIMED