Department of Radiology, Addenbrooke's Hospital and University of Cambridge, Cambridge, UK.
Department of Radiology, University of Cambridge School of Clinical Medicine, Box 218, Cambridge Biomedical Campus, Cambridge, CB2 0QQ, UK.
Eur Radiol. 2022 Jan;32(1):680-689. doi: 10.1007/s00330-021-08151-x. Epub 2021 Jul 13.
To compare the performance of the PRECISE scoring system against several MRI-derived delta-radiomics models for predicting histopathological prostate cancer (PCa) progression in patients on active surveillance (AS).
The study included AS patients with biopsy-proven PCa with a minimum follow-up of 2 years and at least one repeat targeted biopsy. Histopathological progression was defined as grade group progression from diagnostic biopsy. The control group included patients with both radiologically and histopathologically stable disease. PRECISE scores were applied prospectively by four uro-radiologists with 5-16 years' experience. T2WI- and ADC-derived delta-radiomics features were computed using baseline and latest available MRI scans, with the predictive modelling performed using the parenclitic networks (PN), least absolute shrinkage and selection operator (LASSO) logistic regression, and random forests (RF) algorithms. Standard measures of discrimination and areas under the ROC curve (AUCs) were calculated, with AUCs compared using DeLong's test.
The study included 64 patients (27 progressors and 37 non-progressors) with a median follow-up of 46 months. PRECISE scores had the highest specificity (94.7%) and positive predictive value (90.9%), whilst RF had the highest sensitivity (92.6%) and negative predictive value (92.6%) for predicting disease progression. The AUC for PRECISE (84.4%) was non-significantly higher than AUCs of 81.5%, 78.0%, and 80.9% for PN, LASSO regression, and RF, respectively (p = 0.64, 0.43, and 0.57, respectively). No significant differences were observed between AUCs of the three delta-radiomics models (p-value range 0.34-0.77).
PRECISE and delta-radiomics models achieved comparably good performance for predicting PCa progression in AS patients.
• The observed high specificity and PPV of PRECISE are complemented by the high sensitivity and NPV of delta-radiomics, suggesting a possible synergy between the two image assessment approaches. • The comparable performance of delta-radiomics to PRECISE scores applied by expert readers highlights the prospective use of the former as an objective and standardisable quantitative tool for MRI-guided AS follow-up. • The marginally superior performance of parenclitic networks compared to conventional machine learning algorithms warrants its further use in radiomics research.
比较 PRECISE 评分系统与几种基于 MRI 的 delta 放射组学模型在预测主动监测（AS）患者中前列腺癌（PCa）组织病理学进展方面的性能。
本研究纳入了经活检证实患有 PCa 的 AS 患者，这些患者的随访时间至少为 2 年，且至少进行了一次重复靶向活检。组织病理学进展定义为从诊断性活检到诊断性活检的分级组进展。对照组包括影像学和组织病理学均稳定的患者。PRECISE 评分由 4 名具有 5-16 年经验的泌尿放射科医生前瞻性应用。使用基线和最新的 MRI 扫描计算 T2WI 和 ADC 衍生的 delta 放射组学特征，使用 Parzen 网络（PN）、最小绝对收缩和选择算子（LASSO）逻辑回归和随机森林（RF）算法进行预测建模。计算了鉴别力的标准度量和 ROC 曲线下面积（AUCs），并使用 DeLong 检验比较 AUC。
本研究纳入了 64 名患者（27 名进展者和 37 名非进展者），中位随访时间为 46 个月。PRECISE 评分具有最高的特异性（94.7%）和阳性预测值（90.9%），而 RF 具有最高的敏感性（92.6%）和阴性预测值（92.6%），可预测疾病进展。PRECISE 的 AUC（84.4%）与 PN、LASSO 回归和 RF 的 AUC 分别为 81.5%、78.0%和 80.9%相比无显著差异（p=0.64、0.43 和 0.57）。三个 delta 放射组学模型的 AUC 之间无显著差异（p 值范围为 0.34-0.77）。
PRECISE 和 delta 放射组学模型在预测 AS 患者 PCa 进展方面均取得了较好的性能。
• PRECISE 的高特异性和 PPV 与 delta 放射组学的高灵敏度和 NPV 相辅相成，提示这两种图像评估方法可能具有协同作用。• 与专家读者应用的 PRECISE 评分相比，delta 放射组学的性能相当，这突出了前者作为一种用于 MRI 引导的 AS 随访的客观和标准化定量工具的潜在应用。• 与传统机器学习算法相比，Parzen 网络的性能略有优势，这支持了其在放射组学研究中的进一步应用。
