A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas
Medical & Biological Engineering & Computing · 2023-10 · 61 (10) · 2699-2712
DOI: 10.1007/s11517-023-02875-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 11.07.2023. Verfasst von Viet Huan Le und 3 weiteren Autor:innen. Beteiligte Einrichtung: International Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei, 110, Taiwan. Hauptthemen laut MEDLINE: Brain Neoplasms, Glioma, Glioblastoma. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Science and Technology Council.
Abstract (Originalsprache)
Lower-grade gliomas (LGG) can eventually progress to glioblastoma (GBM) and death. In the context of the transfer learning approach, we aimed to train and test an MRI-based radiomics model for predicting survival in GBM patients and validate it in LGG patients. From each patient's 704 MRI-based radiomics features, we chose seventeen optimal radiomics signatures in the GBM training set (n = 71) and used these features in both the GBM testing set (n = 31) and LGG validation set (n = 107) for further analysis. Each patient's risk score, calculated based on those optimal radiomics signatures, was chosen to represent the radiomics model. We compared the radiomics model with clinical, gene status models, and combined model integrating radiomics, clinical, and gene status in predicting survival. The average iAUCs of combined models in training, testing, and validation sets were respectively 0.804, 0.878, and 0.802, and those of radiomics models were 0.798, 0.867, and 0.717. The average iAUCs of gene status and clinical models ranged from 0.522 to 0.735 in all three sets. The radiomics model trained in GBM patients can effectively predict the overall survival of GBM and LGG patients, and the combined model improved this ability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- International Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei, 110, Taiwan.
- Department of Thoracic Surgery, Khanh Hoa General Hospital, Nha Trang City, 65000, Vietnam.
- Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, 110, Taiwan. khanhlee@tmu.edu.tw.
- Research Center for Artificial Intelligence in Medicine, Taipei Medical University, Taipei, 110, Taiwan. khanhlee@tmu.edu.tw.
- AIBioMed Research Group, Taipei Medical University, Taipei, 110, Taiwan. khanhlee@tmu.edu.tw.
- Translational Imaging Research Center, Taipei Medical University Hospital, Taipei, 110, Taiwan. khanhlee@tmu.edu.tw.
Förderung
- National Science and Technology Council
Zitieren
APA
Le, V. H., Minh, T. N. T., Kha, Q. H., & Le, N. Q. K. (2023). A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas. Medical & Biological Engineering & Computing, 61(10), 2699-2712. https://doi.org/10.1007/s11517-023-02875-2
Vancouver
Le VH, Minh TNT, Kha QH, Le NQK. A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas. Medical & Biological Engineering & Computing. 2023;61(10):2699-2712. doi:10.1007/s11517-023-02875-2
BibTeX
@article{Le2023,
author = {Le, Viet Huan and Minh, Tran Nguyen Tuan and Kha, Quang Hien and Le, Nguyen Quoc Khanh},
title = {A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas},
journal = {Medical & Biological Engineering & Computing},
year = {2023},
volume = {61},
number = {10},
pages = {2699--2712},
doi = {10.1007/s11517-023-02875-2}
}
EUVIMED