文献类型：期刊文献

英文题名：Noninvasive Prediction of Perineural Invasion and Lymphovascular Invasion in Prostate Cancer Using bpMRI Radiomic Signatures

作者：Zhang, Yun-Feng[1];Zhou, Chuan[2];Liu, Di[3];Chen, Hengxin[3];Wang, Qidong[3];Hu, Hongde[1];He, Han[1];Wang, Jia[3];Zhang, Wenbo[3];Wu, Xi[3];Ren, Yongqi[3];Zhou, Fenghai[1,3,4]

第一作者：Zhang, Yun-Feng

通信作者：Zhou, FH[1];Zhou, FH[2];Zhou, FH[3]

机构：[1]Lanzhou Univ, Clin Med Coll 1, Lanzhou, Peoples R China;[2]Univ Elect Sci & Technol China, Sichuan Prov Peoples Hosp, Sch Med, Dept Geriatr Gen Surg, Chengdu 611731, Peoples R China;[3]Gansu Univ Chinese Med, Clin Med Coll 1, Lanzhou 730000, Peoples R China;[4]Gansu Prov Hosp, Dept Urol, Lanzhou 730000, Peoples R China

第一机构：Lanzhou Univ, Clin Med Coll 1, Lanzhou, Peoples R China

通信机构：[1]corresponding author), Lanzhou Univ, Clin Med Coll 1, Lanzhou, Peoples R China;[2]corresponding author), Gansu Univ Chinese Med, Clin Med Coll 1, Lanzhou 730000, Peoples R China;[3]corresponding author), Gansu Prov Hosp, Dept Urol, Lanzhou 730000, Peoples R China.|[10735]甘肃中医药大学;

年份：2026

卷号：33

期号：3

起止页码：976

外文期刊名：ACADEMIC RADIOLOGY

收录：;Scopus(收录号：2-s2.0-105027211742);WOS:【SCI-EXPANDED(收录号:WOS:001708623500001)】；

基金：This research was funded by the Gansu Provincial Science and Technology Plan-Excellent Doctoral Student Program (Project No.25JRRA318) and the Intra-Hospital Fund Project of Gansu Provincial Hospital (Project No.24GSSYE-7) .

语种：英文

外文关键词：Magnetic resonance imaging (MRI); Radiomics; Prostate cancer; Peripheral nerve invasion; Lymphovascular invasion

摘要：Objective Perineural invasion (PNI) and lymphovascular invasion (LVI) are critical predictors of aggressive behavior and poor prognosis in prostate cancer (PCa), yet their diagnosis relies on postoperative histopathology. This study aims to develop a noninvasive radiomic model based on biparametric magnetic resonance imaging (bpMRI) for preoperative prediction of PNI and LVI. Methods A total of 256 patients with pathologically confirmed PCa who underwent radical prostatectomy were retrospectively enrolled. Patients from Center 1 (n = 179) constituted the training set, while those from Center 2 (n = 77) formed the external test set. A rigorous imaging-pathology correlation protocol was applied to ensure accurate lesion matching. Inter-observer variability in segmentation was assessed (ICC > 0.75 for 85% of features), with final ROIs determined by consensus. Radiomic features were extracted from T2-weighted and diffusion-weighted imaging. Feature selection was performed using Spearman's correlation and LASSO algorithm. Multiple machine learning classifiers were constructed and interpreted with SHAP. Results The best-performing model for PNI prediction was Multilayer Perceptron (MLP), with an AUC of 0.805 (95% CI: 0.741-0.869) in the training set and 0.795 (95% CI: 0.698-0.896) in the test set. For LVI prediction, Logistic Regression achieved the highest performance, with an AUC of 0.859 (95% CI: 0.804-0.914) in the training set and 0.810 (95% CI: 0.714-0.906) in the test set. Calibration curves and decision curve analysis indicated good model accuracy and clinical utility. Conclusion Radiomic models derived from bpMRI can noninvasively and robustly predict PNI and LVI in PCa, demonstrating good generalizability across independent cohorts.