Radiomics model for predicting distant metastasis in soft tissue sarcoma of the extremities and trunk treated with surgery
Clinical and Translational Oncology · 01.10.2024 · 27 (5) · 2307-2315
DOI: 10.1007/s12094-024-03746-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical and Translational Oncology, online erschienen am 01.10.2024. Verfasst von Miaomiao Yang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Southeast University Zhongda Hospital, Southeast University, 87 Dingjiaqiao Road, Gulou District, Nanjing, Jiangsu, China. Hauptthemen laut MEDLINE: Sarcoma, Magnetic Resonance Imaging, Extremities, Torso. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 19 Literaturangaben.
Abstract (Originalsprache)
PURPOSE: The aim of this study was to develop a radiomics model based on magnetic resonance imaging (MRI) for predicting metastasis in soft tissue sarcomas (STSs) treated with surgery. METHODS/PATIENTS: MRI and clinical data of 73 patients with STSs of the extremities and trunk were obtained from TCIA database and Jiangsu Cancer Hospital as the training set, data of other 40 patients were retrospectively collected at our institution as the external validation set. Radiomics features were extracted from both intratumoral and peritumoral regions of fat-suppressed T2-weighted images (FS-T2WIs) of patients, and 3D ResNet10 was used to extract deep learning features. Recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) algorithms were used for the selection of features. Based on 4 different sets of features, 5 machine learning algorithms were used to construct intratumor, peritumor, combined intratumor and peritumor radiomics models and deep learning radiomics (DLR) model. The area under the ROC curve (AUC) and Decision curve analysis (DCA) were used to evaluate the ability of models to predict metastasis. RESULTS AND CONCLUSIONS: Based on 20 selected features from the deep-learning and radiomics features set, the DLR model was able to predict metastasis in the validation dataset, with an AUC of 0.9770. The DCA and Hosmer-Lemeshow test revealed that the DLR model had good clinical benefit and consistency. By getting richer information from MRI, The DLR model is a noninvasive, low-cost method for predicting the risk of metastasis in STSs, and can help develop appropriate treatment programs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Southeast University Zhongda Hospital, Southeast University, 87 Dingjiaqiao Road, Gulou District, Nanjing, Jiangsu, China.
- Department of Radiology, Southeast University Zhongda Hospital, Southeast University, 87 Dingjiaqiao Road, Gulou District, Nanjing, Jiangsu, China. jy_jin@126.com.
Zitieren
APA
Yang, M., & Jin, J. (2024). Radiomics model for predicting distant metastasis in soft tissue sarcoma of the extremities and trunk treated with surgery. Clinical and Translational Oncology, 27(5), 2307-2315. https://doi.org/10.1007/s12094-024-03746-4
Vancouver
Yang M, Jin J. Radiomics model for predicting distant metastasis in soft tissue sarcoma of the extremities and trunk treated with surgery. Clinical and Translational Oncology. 2024;27(5):2307-2315. doi:10.1007/s12094-024-03746-4
BibTeX
@article{Yang2024,
author = {Yang, Miaomiao and Jin, Jiyang},
title = {Radiomics model for predicting distant metastasis in soft tissue sarcoma of the extremities and trunk treated with surgery},
journal = {Clinical and Translational Oncology},
year = {2024},
volume = {27},
number = {5},
pages = {2307--2315},
doi = {10.1007/s12094-024-03746-4}
}
EUVIMED