Zhang Meng, Zhao Yizhong, Hao Dapeng, Song Yancheng, Lin Xiaotong, Hou Feng, Huang Yonghua, Yang Shifeng, Niu Haitao, Lu Cheng, Wang Hexiang
Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
NPJ Precis Oncol. 2025 Aug 16;9(1):288. doi: 10.1038/s41698-025-01083-5.
Predicting the prognosis of bladder cancer remains challenging despite standard treatments. We developed an interpretable bladder cancer deep learning (BCDL) model using preoperative CT scans to predict overall survival. The model was trained on a cohort (n = 765) and validated in three independent cohorts (n = 438; n = 181; n = 72). The BCDL model outperformed other models in survival risk prediction, with the SHapley Additive exPlanation method identifying pixel-level features contributing to predictions. Patients were stratified into high- and low-risk groups using deep learning score cutoff. Adjuvant therapy significantly improved overall survival in high-risk patients (p = 0.028) and women in the low-risk group (p = 0.046). RNA sequencing analysis revealed differential gene expression and pathway enrichment between risk groups, with high-risk patients exhibiting an immunosuppressive microenvironment and altered microbial composition. Our BCDL model accurately predicts survival risk and supports personalized treatment strategies for improved clinical decision-making.
尽管有标准治疗方法,但预测膀胱癌的预后仍然具有挑战性。我们开发了一种可解释的膀胱癌深度学习(BCDL)模型,使用术前CT扫描来预测总生存期。该模型在一个队列(n = 765)上进行训练,并在三个独立队列(n = 438;n = 181;n = 72)中进行验证。BCDL模型在生存风险预测方面优于其他模型,通过SHapley加法解释方法识别出有助于预测的像素级特征。使用深度学习评分临界值将患者分为高风险和低风险组。辅助治疗显著改善了高风险患者的总生存期(p = 0.028)和低风险组女性的总生存期(p = 0.046)。RNA测序分析揭示了风险组之间的差异基因表达和通路富集,高风险患者表现出免疫抑制微环境和微生物组成改变。我们的BCDL模型准确预测生存风险,并支持个性化治疗策略以改善临床决策。