Radiology research and practice · 2026
Multicenter Study Suggests Unsupervised Learning Derived From MRI Identifies Prognostic Subgroups in Prostate Cancer Patients After Prostatectomy.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Hu Guoqing, Liu Xiaofeng, Chen Zhangzhe, Zhou Bingni, Gan Hualei, Chen Ruchuan, Zhou Liangping, Gu Yajia, Liu Xiaohang
Аннотация
OBJECTIVE: To identify subgroups of patients with prostate cancer (PCa) after radical prostatectomy (RP) based on clinical and magnetic resonance imaging (MRI) radiomics features and evaluate the prognostic value in predicting 5-year progression-free survival (PFS).
MATERIALS: Preoperative MRI and clinical data from 400 patients (185 with recurrence) were collected from three centers (one training and two external validation groups). Radiomics features were extracted from index lesions. PFS-associated clinical and radiomics features were selected by least absolute shrinkage and selection operator (LASSO)-Cox analysis. The K-means clustering method was used to identify subgroups and construct a Radiomic-Clinical model. PFS differences across subgroups were assessed using Kaplan-Meier survival analyses. The predictive performance of the Radiomic-Clinical model was compared with the European Association of Urology (EAU), University of California, San Francisco (UCSF) Cancer of the Prostate Risk Assessment (CAPRA), and PIPEN models using the concordance index (C-index).
RESULTS: A total of 5 clinical and 13 radiomics features were selected, and three distinct prognostic subgroups were identified within the Radiomic-Clinical model. The Radiomic-Clinical model demonstrated superior predictive accuracy with C-indices of 0.82 (training group), 0.78 (validation group 1), and 0.79 (validation group 2), outperforming the EAU (0.68, 0.70, and 0.65), CAPRA (0.71, 0.67, and 0.70), and PIPEN models (0.71, 0.70, and 0.68) (p < 0.05).
CONCLUSION: Unsupervised learning using radiomics and clinical data effectively identifies distinct prognostic subgroups in PCa patients after RP, offering superior predictive performance over existing models for 5-year PFS.
MATERIALS: Preoperative MRI and clinical data from 400 patients (185 with recurrence) were collected from three centers (one training and two external validation groups). Radiomics features were extracted from index lesions. PFS-associated clinical and radiomics features were selected by least absolute shrinkage and selection operator (LASSO)-Cox analysis. The K-means clustering method was used to identify subgroups and construct a Radiomic-Clinical model. PFS differences across subgroups were assessed using Kaplan-Meier survival analyses. The predictive performance of the Radiomic-Clinical model was compared with the European Association of Urology (EAU), University of California, San Francisco (UCSF) Cancer of the Prostate Risk Assessment (CAPRA), and PIPEN models using the concordance index (C-index).
RESULTS: A total of 5 clinical and 13 radiomics features were selected, and three distinct prognostic subgroups were identified within the Radiomic-Clinical model. The Radiomic-Clinical model demonstrated superior predictive accuracy with C-indices of 0.82 (training group), 0.78 (validation group 1), and 0.79 (validation group 2), outperforming the EAU (0.68, 0.70, and 0.65), CAPRA (0.71, 0.67, and 0.70), and PIPEN models (0.71, 0.70, and 0.68) (p < 0.05).
CONCLUSION: Unsupervised learning using radiomics and clinical data effectively identifies distinct prognostic subgroups in PCa patients after RP, offering superior predictive performance over existing models for 5-year PFS.