Xv Yingjie, Wei Zongjie, Jiang Qing, Zhang Xuan, Chen Yong, Xiao Bangxin, Yin Siwen, Xia Zongyu, Qiu Ming, Li Yang, Tan Hao, Xiao Mingzhao
Department of Urology, The First Affiliated Hospital of Chongqing Medical University.
Department of Urology, The Second Affiliated Hospital of Chongqing Medical University.
Int J Surg. 2024 Nov 1;110(11):7034-7046. doi: 10.1097/JS9.0000000000001808.
Current prognostic models have limited predictive abilities for the growing number of localized (stage I-III) ccRCCs. It is, therefore, crucial to explore novel preoperative recurrence prediction models to accurately stratify patients and optimize clinical decisions. The purpose of this study was to develop and externally validate a computed tomography (CT)-based deep learning (DL) model for presurgical disease-free survival (DFS) prediction.
Patients with localized ccRCC were retrospectively enrolled from six independent medical centers. Three-dimensional (3D) tumor regions from CT images were utilized as input to architect a ResNet 50 model, which outputted DL computed risk score (DLCR) of each patient for DFS prediction later. The predictive performance of DLCR was assessed and compared to the radiomics model (Rad-Score), the clinical model the authors built and two existing prognostic models (UISS and Leibovich). The complementary value of DLCR to the UISS, Leibovich, as well as Rad-Score were evaluated by stratified analysis.
Seven hundred seven patients with localized ccRCC were finally enrolled for models' training and validating. The DLCR the authors established can perfectly stratify patients into low-risks, intermediate-risks, and high-risks, and outperformed the Rad-Score, clinical model, UISS and Leibovich score in DFS prediction, with a C-index of 0.754 (0.689-0.821) in the external testing set. Furthermore, the DLCR presented excellent risk stratification capacity in subgroups defined by almost all clinic-pathological features. Moreover, patients classified as low-risk by the UISS/Leibovich score/Rad-Score but as intermediate - or high-risk by DLCR were significantly more likely to experience ccRCC recurrence than those stratified as intermediate- or high-risk by UISS/Leibovich score/Rad-Score but as low-risk by DLCR (all Log-rank P- values<0.05).
Our DL model, derived from preoperative CT, is superior to radiomics and current models in precisely DFS predicting of localized ccRCC, and can provide complementary values to them, which may assist more informed clinical decisions and adjuvant therapies adoptions.
对于越来越多的局限性（I - III期）肾透明细胞癌（ccRCC），当前的预后模型预测能力有限。因此，探索新的术前复发预测模型以准确对患者进行分层并优化临床决策至关重要。本研究的目的是开发并外部验证一种基于计算机断层扫描（CT）的深度学习（DL）模型，用于术前无病生存期（DFS）预测。
从六个独立的医疗中心回顾性纳入局限性ccRCC患者。将CT图像中的三维（3D）肿瘤区域用作输入，构建一个ResNet 50模型，该模型随后输出每位患者的DL计算风险评分（DLCR）用于DFS预测。评估DLCR的预测性能，并与放射组学模型（Rad - Score）、作者构建的临床模型以及两个现有的预后模型（UISS和Leibovich）进行比较。通过分层分析评估DLCR对UISS、Leibovich以及Rad - Score的补充价值。
最终纳入707例局限性ccRCC患者进行模型训练和验证。作者建立的DLCR能够完美地将患者分为低风险、中风险和高风险组，并且在DFS预测方面优于Rad - Score、临床模型、UISS和Leibovich评分，在外部测试集中C指数为0.754（0.689 - 0.821）。此外，DLCR在几乎所有临床病理特征定义的亚组中均表现出出色的风险分层能力。而且，被UISS/Leibovich评分/Rad - Score分类为低风险但被DLCR分类为中风险或高风险的患者比被UISS/Leibovich评分/Rad - Score分类为中风险或高风险但被DLCR分类为低风险的患者更有可能经历ccRCC复发（所有对数秩P值<0.05）。
我们基于术前CT的DL模型在准确预测局限性ccRCC的DFS方面优于放射组学和当前模型，并且可以为它们提供补充价值，这可能有助于做出更明智的临床决策和采用辅助治疗。
