Quantification of Intratumoral Heterogeneity Based on Habitat Analysis for Preoperative Assessment of Lymphovascular Invasion in Colorectal Cancer

作者：Yexin Su, Hongyue Zhao, Zhehao Lyu, Peng Xu, Ziyue Zhang, Huiting Zhang, Mengjiao Wang, Lin Tian, Peng Fu · 发表于：Academic Radiology · 年份：2025 · DOI：10.1016/j.acra.2025.03.014 · 被引用次数：7 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Colorectal Cancer Surgical Treatments、Inflammatory Biomarkers in Disease Prognosis

RATIONALE AND OBJECTIVES: F-fluorodeoxyglucose (FDG) positron emission tomography (PET) images in predicting LVI. MATERIALS AND METHODS: F-FDG PET scans. The output probabilities of the imaging-based random forest model were used to generate a radiomics score (Radscore) and intratumoral heterogeneity score (ITHscore). Multivariate logistic regression analysis was used to determine the independent risk factors for LVI. On this basis, four LVI status classification models were developed using (a) clinical variables (Clinical model), (b) tumor heterogeneity features (ITHscore model), (c) radiomics features (Radscore model), and (d) clinical variables, tumor heterogeneity features, and radiomics features (Combined model). The area under the curve (AUC) and decision curve analysis were used to evaluate model performance. RESULTS: Among all of the variables, the PET/CT-reported lymph node status, ITHscore, and Radscore were retained as predictors related to the risk of LVI in CRC patients (P<0.05). The predictive effect of the ITHscore model (AUC: 0.712) was better than that of the Radscore model (AUC: 0.650) and Clinical model (AUC: 0.652) in the validation cohort. The Combined model achieved better classification effects and clinical usefulness, and the AUCs of the training and validation cohorts were 0.857 and 0.798, respectively. A nomogram of the Combined model was established, and the calibration plot was well fitted (P>0.05). In addition, the results of Spearman's rank corre...