Optimizing recurrence prediction and risk stratification in prostate cancer using a 2.5D deep learning model: a multicenter MRI-based study

作者：Li Fan, Ruishan Liu, Pei Wang, Yue Lv, Ping Hu, Xiaodong Liu, Lian Yang, Qichao Ruan, Shaoqiang Wu, Ruohan Feng, Yuqi Chen, Meng Zhou, Junqiang Yang, Fei Wang, Haibo Qu, Gang Ning, Lihua Zhuo · 发表于：International Journal of Surgery · 年份：2025 · DOI：10.1097/js9.0000000000004584 · 被引用次数：3 · 研究领域：Prostate Cancer Diagnosis and Treatment、MRI in cancer diagnosis、Prostate Cancer Treatment and Research

BACKGROUND: High tumor recurrence after surgery remains a significant challenge in managing prostate cancer (PCa). We aimed to develop and validate a 2.5D deep learning model based on a transformer architecture utilizing T2WI, ADC, DWI, and CE-T1WI images for the preoperative prediction of biochemical recurrence (BCR) in PCa, and to further investigate its capability for risk stratification. METHODS: A total of 923 PCa patients (10 153 images) who underwent radical prostatectomy (RP) at five tertiary medical centers were retrospectively enrolled, with follow-up completed by September 2024. Among the five evaluated classifiers, ResNet18 was selected as the best-performing backbone for feature extraction. A Transformer-based deep learning (DL) model was developed using preoperative mpMRI data, and a deep learning fusion (DLF) model was constructed by integrating DL scores with weighted clinical variables, and its performance was compared with the traditional clinical risk score (CAPRA), a clinical model (Clinical), an ensemble learning model (Ensemble), and a multiple instance learning model (MIL). Model performance was evaluated using receiver operating characteristic (ROC) curves. Model comparisons were conducted using the DeLong test, decision curve analysis (DCA) and calibration curves were used to assess the clinical utility and calibration of the models. Furthermore, Grad-CAM was used to visualize model attention and improve interpretability. RESULTS: The DLF model exhibi...