Marcon Julian, Weinhold Philipp, Rzany Mona, Fabritius Matthias P, Winkelmann Michael, Buchner Alexander, Eismann Lennert, Jokisch Jan-Friedrich, Casuscelli Jozefina, Schulz Gerald B, Knösel Thomas, Ingrisch Michael, Ricke Jens, Stief Christian G, Rodler Severin, Kazmierczak Philipp M
Department of Urology, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany.
Department of Radiology, University Hospital, LMU Munich, Munich, Germany.
BMC Med Imaging. 2025 May 30;25(1):196. doi: 10.1186/s12880-025-01727-9.
To investigate a non-invasive radiomics-based machine learning algorithm to differentiate upper urinary tract urothelial carcinoma (UTUC) from renal cell carcinoma (RCC) prior to surgical intervention.
Preoperative computed tomography venous-phase datasets from patients that underwent procedures for histopathologically confirmed UTUC or RCC were retrospectively analyzed. Tumor segmentation was performed manually, and radiomic features were extracted according to the International Image Biomarker Standardization Initiative. Features were normalized using z-scores, and a predictive model was developed using the least absolute shrinkage and selection operator (LASSO). The dataset was split into a training cohort (70%) and a test cohort (30%).
A total of 236 patients [30.5% female, median age 70.5 years (IQR: 59.5-77), median tumor size 5.8 cm (range: 4.1-8.2 cm)] were included. For differentiating UTUC from RCC, the model achieved a sensitivity of 88.4% and specificity of 81% (AUC: 0.93, radiomics score cutoff: 0.467) in the training cohort. In the validation cohort, the sensitivity was 80.6% and specificity 80% (AUC: 0.87, radiomics score cutoff: 0.601). Subgroup analysis of the validation cohort demonstrated robust performance, particularly in distinguishing clear cell RCC from high-grade UTUC (sensitivity: 84%, specificity: 73.1%, AUC: 0.84) and high-grade from low-grade UTUC (sensitivity: 57.7%, specificity: 88.9%, AUC: 0.68). Limitations include the need for independent validation in future randomized controlled trials (RCTs).
Machine learning-based radiomics models can reliably differentiate between RCC and UTUC in preoperative CT imaging. With a suggested performance benefit compared to conventional imaging, this technology might be added to the current preoperative diagnostic workflow.
Local ethics committee no. 20-179.
研究一种基于非侵入性放射组学的机器学习算法，以在手术干预前区分上尿路尿路上皮癌（UTUC）和肾细胞癌（RCC）。
回顾性分析接受过组织病理学确诊的UTUC或RCC手术患者的术前计算机断层扫描静脉期数据集。手动进行肿瘤分割，并根据国际影像生物标志物标准化倡议提取放射组学特征。使用z分数对特征进行标准化，并使用最小绝对收缩和选择算子（LASSO）开发预测模型。将数据集分为训练队列（70%）和测试队列（30%）。
共纳入236例患者[女性占30.5%，中位年龄70.5岁（四分位间距：59.5 - 77），中位肿瘤大小5.8 cm（范围：4.1 - 8.2 cm）]。对于区分UTUC和RCC，该模型在训练队列中的敏感性为88.4%，特异性为81%（曲线下面积：0.93，放射组学评分临界值：0.467）。在验证队列中，敏感性为80.6%，特异性为80%（曲线下面积：0.87，放射组学评分临界值：0.601）。验证队列的亚组分析显示性能稳健，特别是在区分透明细胞RCC与高级别UTUC（敏感性：84%，特异性：73.1%，曲线下面积：0.84）以及高级别与低级别UTUC（敏感性：57.7%，特异性：88.9%，曲线下面积：0.68）方面。局限性包括未来需要在随机对照试验（RCT）中进行独立验证。
基于机器学习的放射组学模型能够在术前CT成像中可靠地区分RCC和UTUC。与传统成像相比，该技术具有性能优势，可能会被纳入当前的术前诊断工作流程。
当地伦理委员会编号20 - 179。
