文献类型：期刊文献

英文题名：Noninvasive prediction of lymphovascular invasion in rectal cancer without lymph node metastasis using a SHAP-interpretable combined model integrating MRI radiomics features and clinical immune-inflammatory biomarkers: a bicenter study

作者：Peng, Leping[1];Niu, Jingjing[2];Huang, Gang[2];Zhang, Fan[1];Ma, Fang[1];Zhang, Xiuling[1];Wang, Yu[5];Ai, Kai[3];Zhang, Xiaoyue[3];He, Yuqi[1];Cai, Wei[4];Zuo, Xiaona[2];Jia, Yingmei[2];Gao, Shuhong[5];Wang, Yuan-Cheng[5];Wang, Lili[2]

第一作者：Peng, Leping

通信作者：Wang, LL[1];Wang, YC[2]

机构：[1]Gansu Univ Chinese Med, Lanzhou 730000, Peoples R China;[2]Gansu Prov Hosp, Dept Radiol, Lanzhou 730000, Peoples R China;[3]Philips Healthcare, Dept Clin & Tech Support, Xian 710065, Peoples R China;[4]Gansu Prov Hosp, Dept Pathol, Lanzhou 730000, Peoples R China;[5]Southeast Univ, Zhongda Hosp, Nurturing Ctr Jiangsu Prov State Lab AI Imaging &, Sch Med,Dept Radiol, Nanjing 210009, Peoples R China

第一机构：甘肃中医药大学

通信机构：[1]corresponding author), Gansu Prov Hosp, Dept Radiol, Lanzhou 730000, Peoples R China;[2]corresponding author), Southeast Univ, Zhongda Hosp, Nurturing Ctr Jiangsu Prov State Lab AI Imaging &, Sch Med,Dept Radiol, Nanjing 210009, Peoples R China.

年份：2025

卷号：25

期号：1

外文期刊名：CANCER IMAGING

收录：;Scopus(收录号：2-s2.0-105020391106);WOS:【SCI-EXPANDED(收录号:WOS:001604869400001)】；

基金：We appreciate the efforts of the staff from the Department of Radiology, the Department of Pathology, and the Department of Colorectal Surgery at Gansu Provincial Hospital and the Department of Radiology at Zhongda Hospital Southeast University for, their efforts in collecting the information used in this study. Meanwhile, we express our sincere gratitude to Feixiang Li and Yun Sun from Gansu University of Chinese Medicine and Xiaodi Zhang, a scientist from Philips, for providing valuable technical support for this research.

语种：英文

外文关键词：Rectal cancer; Lymphovascular invasion; Magnetic resonance imaging; Radiomics; Immune-inflammatory

摘要：BackgroundLymphovascular invasion (LVI) status in rectal cancer (RC) without lymph node metastasis (LNM) can significantly influence the patient's treatment decisions. This study aims to develop and validate a combined model based on MRI radiomics features integrated with clinical immune-inflammatory biomarkers for the prediction of LVI status in RC without LNM. The Shapley Additive Explanation (SHAP) method was employed to visualize the prediction process and enhance interpretability for clinical application.MethodsWe retrospectively collected data from 257 RC patients without LNM from two centers. Univariate and multivariate logistic regression analyses were performed on clinical data to identify independent predictors of LVI. Volumes of interest were manually delineated on T2WI and ADC sequences, and corresponding radiomic features were extracted. A combined model was constructed by combining rad-score and clinical immune-inflammatory biomarkers, and the SHAP was used to visualize the prediction process.ResultsThe area under the curve (AUC) of the combined model was based on intratumoral features (training vs. testing vs. validation datasets: 0.813 vs. 0.854 vs. 0.807). The AUC of the combined model was based on both intra- and peritumoral features (training vs. testing vs. validation datasets: 0.855 vs. 0.841 vs. 0.860). After comparison, the combined model (C + Q) based on intra- and peritumoral MRI radiomics features integrated with clinical immune-inflammatory biomarkers demonstrated better predictive performance.ConclusionThe combined model (C + Q) has great potential in the non-invasive prediction of LVI in RC without LNM, providing a basis for stratified management and individualized treatment decisions for RC patients.