Roest Christian, Kwee Thomas C, de Jong Igle J, Schoots Ivo G, van Leeuwen Pim, Heijmink Stijn W T P J, van der Poel Henk G, Fransen Stefan J, Saha Anindo, Huisman Henkjan, Yakar Derya
Department of Radiology, University Medical Center Groningen, Groningen, the Netherlands.
Department of Urology, University Medical Center Groningen, Groningen, the Netherlands.
Radiol Imaging Cancer. 2025 Jan;7(1):e240078. doi: 10.1148/rycan.240078.
Purpose To validate a deep learning (DL) model for predicting the risk of prostate cancer (PCa) progression based on MRI and clinical parameters and compare it with established models. Materials and Methods This retrospective study included 1607 MRI scans of 1143 male patients (median age, 64 years; IQR, 59-68 years) undergoing MRI for suspicion of clinically significant PCa (csPCa) (International Society of Urological Pathology grade > 1) between January 2012 and May 2022 who were negative for csPCa at baseline MRI. A DL model was developed using baseline MRI and clinical parameters (age, prostate-specific antigen [PSA] level, PSA density, and prostate volume) to predict the time to PCa progression (defined as csPCa diagnosis at follow-up). Internal and external testing was performed. The model's ability to predict progression to csPCa was assessed by Cox regression analyses. Predictive performance of the DL model up to 5 years after baseline MRI in comparison with the European Randomized Study of Screening for Prostate Cancer (ERSPC) future-risk calculator, Prostate Cancer Prevention Trial (PCPT) risk calculator, and Prostate Imaging Reporting and Data System (PI-RADS) was assessed using the Harrell C-index. Optimized follow-up intervals were derived from Kaplan-Meier curves. Results DL scores predicted csPCa progression (internal cohort: hazard ratio [HR], 1.97 [95% CI: 1.61, 2.41; < .001]; external cohort: HR, 1.32 [95% CI: 1.14, 1.55; < .001]). The model identified a subgroup of patients (approximately 20%) with risks for csPCa of 3% or less, 8% or less, and 18% or less after 1-, 2-, and 4-year follow-up, respectively. DL scores had a C-index of 0.68 (95% CI: 0.63, 0.74) at internal testing and 0.56 (95% CI: 0.51, 0.61) at external testing, outperforming ERSPC and PCPT (both < .001) at internal testing. Conclusion The DL model accurately predicted PCa progression and provided improved risk estimations, demonstrating its ability to aid in personalized follow-up for low-risk PCa. MRI, Prostate Cancer, Deep Learning ©RSNA, 2025.
目的 验证一种基于MRI和临床参数预测前列腺癌（PCa）进展风险的深度学习（DL）模型，并将其与已建立的模型进行比较。材料与方法 这项回顾性研究纳入了2012年1月至2022年5月期间因怀疑患有临床显著性PCa（csPCa）（国际泌尿病理学会分级>1）而接受MRI检查的1143例男性患者的1607次MRI扫描，这些患者在基线MRI时csPCa呈阴性。使用基线MRI和临床参数（年龄、前列腺特异性抗原[PSA]水平、PSA密度和前列腺体积）开发了一个DL模型，以预测PCa进展时间（定义为随访时csPCa诊断）。进行了内部和外部测试。通过Cox回归分析评估该模型预测进展为csPCa的能力。使用Harrell C指数评估DL模型在基线MRI后长达5年的预测性能，并与欧洲前列腺癌筛查随机研究（ERSPC）未来风险计算器、前列腺癌预防试验（PCPT）风险计算器和前列腺影像报告和数据系统（PI-RADS）进行比较。从Kaplan-Meier曲线得出优化的随访间隔。结果 DL评分可预测csPCa进展（内部队列：风险比[HR]，1.97[95%CI：1.61，2.41；P<.001]；外部队列：HR，1.32[95%CI：1.14，1.55；P<.001]）。该模型识别出一组患者（约20%），在1年、2年和4年随访后，其csPCa风险分别为3%或更低、8%或更低和18%或更低。DL评分在内部测试中的C指数为0.68（95%CI：0.63，0.74），在外部测试中的C指数为0.56（95%CI：0.51，0.61），在内部测试中优于ERSPC和PCPT（均P<.001）。结论 DL模型准确预测了PCa进展并提供了改进的风险估计，证明了其有助于低风险PCa个性化随访的能力。MRI、前列腺癌、深度学习 ©RSNA，202
