Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 10 Center Drive, Bethesda, MD, 20892-1109, USA.
Urology Oncology Branch, National Cancer Institute, National Institutes of Health, 10 Center Drive, Bethesda, MD, 20892-1109, USA.
Abdom Radiol (NY). 2024 Apr;49(4):1202-1209. doi: 10.1007/s00261-023-04162-y. Epub 2024 Feb 12.
Classification of clear cell renal cell carcinoma (ccRCC) growth rates in patients with Von Hippel-Lindau (VHL) syndrome has several ramifications for tumor monitoring and surgical planning. Using two separate machine-learning algorithms, we sought to produce models to predict ccRCC growth rate classes based on qualitative MRI-derived characteristics.
We used a prospectively maintained database of patients with VHL who underwent surgical resection for ccRCC between January 2015 and June 2022. We employed a threshold growth rate of 0.5 cm per year to categorize ccRCC tumors into two distinct groups-'slow-growing' and 'fast-growing'. Utilizing a questionnaire of qualitative imaging features, two radiologists assessed each lesion on different MRI sequences. Two machine-learning models, a stacked ensemble technique and a decision tree algorithm, were used to predict the tumor growth rate classes. Positive predictive value (PPV), sensitivity, and F1-score were used to evaluate the performance of the models.
This study comprises 55 patients with VHL with 128 ccRCC tumors. Patients' median age was 48 years, and 28 patients were males. Each patient had an average of two tumors, with a median size of 2.1 cm and a median growth rate of 0.35 cm/year. The overall performance of the stacked and DT model had 0.77 ± 0.05 and 0.71 ± 0.06 accuracies, respectively. The best stacked model achieved a PPV of 0.92, a sensitivity of 0.91, and an F1-score of 0.90.
This study provides valuable insight into the potential of machine-learning analysis for the determination of renal tumor growth rate in patients with VHL. This finding could be utilized as an assistive tool for the individualized screening and follow-up of this population.
对 von Hippel-Lindau（VHL）综合征患者的透明细胞肾细胞癌（ccRCC）生长速度进行分类，这对肿瘤监测和手术计划有多种影响。我们使用两种独立的机器学习算法，旨在根据定性 MRI 衍生特征构建预测 ccRCC 生长速度类别的模型。
我们使用了一个前瞻性维护的数据库，其中包括 2015 年 1 月至 2022 年 6 月期间接受手术切除 ccRCC 的 VHL 患者。我们采用 0.5cm/年的阈值生长率将 ccRCC 肿瘤分为两个不同的组 - “缓慢生长”和“快速生长”。两位放射科医生使用定性成像特征问卷评估了每个病变的不同 MRI 序列。我们使用了一种堆叠集成技术和决策树算法的两种机器学习模型来预测肿瘤生长速度类别。使用阳性预测值（PPV）、敏感性和 F1 评分来评估模型的性能。
这项研究包括 55 名 VHL 患者，共 128 个 ccRCC 肿瘤。患者的中位年龄为 48 岁，28 名男性。每位患者平均有两个肿瘤，肿瘤大小中位数为 2.1cm，中位生长率为 0.35cm/年。堆叠和 DT 模型的总体性能分别为 0.77±0.05 和 0.71±0.06。最佳的堆叠模型实现了 0.92 的 PPV、0.91 的敏感性和 0.90 的 F1 评分。
本研究为机器学习分析在确定 VHL 患者肾肿瘤生长速度方面的潜力提供了有价值的见解。这一发现可作为该人群个体化筛查和随访的辅助工具。
