Robust Radiomics Models for Predicting HIFU Prognosis in Uterine Fibroids Using SHAP Explanations: A Multicenter Cohort Study
Journal of Imaging Informatics in Medicine · 11.11.2024 · 38 (4) · 1950-1962
DOI: 10.1007/s10278-024-01318-0 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 11.11.2024. Verfasst von Huan Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Medical University, Yuzhong District, No…. Hauptthemen laut MEDLINE: High-Intensity Focused Ultrasound Ablation, Leiomyoma, Magnetic Resonance Imaging, Uterine Neoplasms. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Chongqing Talent Program Project, Innovative Research Group Project of the National Natural Science Foundation of China, Chongqing Natural Science Foundation Innovation and Development Joint Fund Project.
Abstract (Originalsprache)
This study sought to develop and validate different machine learning (ML) models that leverage non-contrast MRI radiomics to predict the degree of nonperfusion volume ratio (NVPR) of high-intensity focused ultrasound (HIFU) treatment for uterine fibroids, equipping clinicians with an early prediction tool for decision-making. This study conducted a retrospective analysis on 221 patients with uterine fibroids who received HIFU treatment and were divided into a training set (N = 117), internal validation (N = 49), and an external test set (N = 55). The 851 radiomics features were extracted from T2-weighted imaging (T2WI), and the max-relevance and min-redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection. Several ML models were constructed by logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM). These models underwent internal and external validation, and the best model's feature significance was assessed via the Shapley additive explanations (SHAP) method. Four significant non-contrast MRI radiomics features were identified, with the SVM model outperforming others in both internal and external validations, and the AUCs of the T2WI models were 0.860, 0.847, and 0.777, respectively. SHAP analysis highlighted five critical predictors of postoperative NVPR degree, encompassing two radiomics features from non-contrast MRI and three clinical data indicators. The SVM model combining radiomics features and clinical parameters effectively predicts NVPR degree post-HIFU, which enables timely and effective interventions of HIFU.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- State Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Medical University, Yuzhong District, No.74 Linjiang Rd, Chongqing, 400010, China.
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
- Chongqing Haifu Hospital, Chongqing, China.
- State Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Medical University, Yuzhong District, No.74 Linjiang Rd, Chongqing, 400010, China. uslichenghai@cqmu.edu.cn.
- NMPA Key Laboratory for Quality Evaluation of Ultrasonic Surgical Equipment, Wuhan, China. uslichenghai@cqmu.edu.cn.
- State Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Medical University, Yuzhong District, No.74 Linjiang Rd, Chongqing, 400010, China. lifq@cqmu.edu.cn.
Förderung
- Chongqing Talent Program Project
- Innovative Research Group Project of the National Natural Science Foundation of China
- Chongqing Natural Science Foundation Innovation and Development Joint Fund Project
- Open Research Project of the Key Laboratory of Quality Evaluation for Ultrasonic Surgical Equipment
- Chongqing Medical University Major Scientific and Technological Innovation Project,
Zitieren
APA
Liu, H., Zeng, J., Jinyun, C., Liu, X., Deng, Y., Li, C., & Li, F. (2024). Robust Radiomics Models for Predicting HIFU Prognosis in Uterine Fibroids Using SHAP Explanations: A Multicenter Cohort Study. Journal of Imaging Informatics in Medicine, 38(4), 1950-1962. https://doi.org/10.1007/s10278-024-01318-0
Vancouver
Liu H, Zeng J, Jinyun C, Liu X, Deng Y, Li C, et al. Robust Radiomics Models for Predicting HIFU Prognosis in Uterine Fibroids Using SHAP Explanations: A Multicenter Cohort Study. Journal of Imaging Informatics in Medicine. 2024;38(4):1950-1962. doi:10.1007/s10278-024-01318-0
BibTeX
@article{Liu2024,
author = {Liu, Huan and Zeng, Jincheng and Jinyun, Chen and Liu, Xiaohua and Deng, Yongbin and Li, Chenghai and Li, Faqi},
title = {Robust Radiomics Models for Predicting HIFU Prognosis in Uterine Fibroids Using SHAP Explanations: A Multicenter Cohort Study},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {38},
number = {4},
pages = {1950--1962},
doi = {10.1007/s10278-024-01318-0}
}
EUVIMED