Fu Jia, Fang Mengjie, Lin Zhiyong, Qiu Jianxing, Yang Min, Tian Jie, Dong Di, Zou Yinghua
Department of Interventional Radiology and Vascular Surgery, Peking University First Hospital, Beijing, 100043, China.
Department of Radiology, Peking University First Hospital, Beijing, 100043, China.
Vis Comput Ind Biomed Art. 2024 Jan 12;7(1):1. doi: 10.1186/s42492-023-00152-5.
This study aimed to comprehensively evaluate non-contrast computed tomography (CT)-based radiomics for predicting early outcomes in patients with severe atherosclerotic renal artery stenosis (ARAS) after percutaneous transluminal renal angioplasty (PTRA). A total of 52 patients were retrospectively recruited, and their clinical characteristics and pretreatment CT images were collected. During a median follow-up period of 3.7 mo, 18 patients were confirmed to have benefited from the treatment, defined as a 20% improvement from baseline in the estimated glomerular filtration rate. A deep learning network trained via self-supervised learning was used to enhance the imaging phenotype characteristics. Radiomics features, comprising 116 handcrafted features and 78 deep learning features, were extracted from the affected renal and perirenal adipose regions. More features from the latter were correlated with early outcomes, as determined by univariate analysis, and were visually represented in radiomics heatmaps and volcano plots. After using consensus clustering and the least absolute shrinkage and selection operator method for feature selection, five machine learning models were evaluated. Logistic regression yielded the highest leave-one-out cross-validation accuracy of 0.780 (95%CI: 0.660-0.880) for the renal signature, while the support vector machine achieved 0.865 (95%CI: 0.769-0.942) for the perirenal adipose signature. SHapley Additive exPlanations was used to visually interpret the prediction mechanism, and a histogram feature and a deep learning feature were identified as the most influential factors for the renal signature and perirenal adipose signature, respectively. Multivariate analysis revealed that both signatures served as independent predictive factors. When combined, they achieved an area under the receiver operating characteristic curve of 0.888 (95%CI: 0.784-0.992), indicating that the imaging phenotypes from both regions complemented each other. In conclusion, non-contrast CT-based radiomics can be leveraged to predict the early outcomes of PTRA, thereby assisting in identifying patients with ARAS suitable for this treatment, with perirenal adipose tissue providing added predictive value.
本研究旨在全面评估基于非增强计算机断层扫描（CT）的放射组学，以预测经皮腔内肾血管成形术（PTRA）后严重动脉粥样硬化性肾动脉狭窄（ARAS）患者的早期预后。共回顾性招募了52例患者，并收集了他们的临床特征和治疗前CT图像。在中位随访期3.7个月期间，18例患者被证实从治疗中获益，定义为估计肾小球滤过率较基线提高20%。使用通过自监督学习训练的深度学习网络来增强成像表型特征。从患肾和肾周脂肪区域提取了放射组学特征，包括116个手工特征和78个深度学习特征。单变量分析确定，后者的更多特征与早期预后相关，并在放射组学热图和火山图中直观呈现。在使用一致性聚类和最小绝对收缩和选择算子方法进行特征选择后，评估了五种机器学习模型。逻辑回归对肾特征的留一法交叉验证准确率最高，为0.780（95%CI：0.660-0.880），而支持向量机对肾周脂肪特征的准确率为0.865（95%CI：0.769-0.942）。使用SHapley加性解释法直观解释预测机制，确定直方图特征和深度学习特征分别是肾特征和肾周脂肪特征的最有影响因素。多变量分析显示，两种特征均为独立预测因素。两者结合时，受试者操作特征曲线下面积为0.888（95%CI：0.784-0.992），表明两个区域的成像表型相互补充。总之，基于非增强CT的放射组学可用于预测PTRA的早期预后，从而有助于识别适合该治疗的ARAS患者，肾周脂肪组织具有额外的预测价值。
