DataSheet_1_Computed Tomography-Based Machine Learning Differentiates Adrenal Pheochromocytoma From Lipid-Poor Adenoma.docx

ObjectivesTo assess the accuracy of computed tomography (CT)-based machine learning models for differentiating subclinical pheochromocytoma (sPHEO) from lipid-poor adenoma (LPA) in patients with adrenal incidentalomas.
Patients and MethodsThe study included 188 tumors in the 183 patients with LPA and 92 tumors in 86 patients with sPHEO. Pre-enhanced CT imaging features of the tumors were evaluated. Machine learning prediction models and scoring systems for differentiating sPHEO from LPA were built using logistic regression (LR), support vector machine (SVM) and random forest (RF) approaches.
ResultsThe LR model performed better than other models. The LR model (M1) including three CT features: CTpre value, shape, and necrosis/cystic changes had an area under the receiver operating characteristic curve (AUC) of 0.917 and an accuracy of 0.864. The LR model (M2) including three CT features: CTpre value, shape and homogeneity had an AUC of 0.888 and an accuracy of 0.832. The S2 scoring system (sensitivity: 0.859, specificity: 0.824) had comparable diagnostic value to S1 (sensitivity: 0.815; specificity: 0.910).
ConclusionsOur results indicated the potential of using a non-invasive imaging method such as CT-based machine learning models and scoring systems for predicting histology of adrenal incidentalomas. This approach may assist the diagnosis and personalized care of patients with adrenal tumors.

研究目的：评估基于计算机断层扫描（CT）的机器学习模型，用于区分肾上腺意外瘤患者中的亚临床嗜铬细胞瘤（sPHEO）与乏脂性腺瘤（LPA）的诊断效能。患者与方法：本研究纳入183例乏脂性腺瘤（LPA）患者的188枚肿瘤，以及86例亚临床嗜铬细胞瘤（sPHEO）患者的92枚肿瘤。对肿瘤的增强前CT影像学特征进行评估。采用逻辑回归（LR）、支持向量机（SVM）及随机森林（RF）方法构建用于区分sPHEO与LPA的机器学习预测模型与评分系统。结果：逻辑回归（LR）模型的性能优于其余模型。包含CTpre值、形态及坏死/囊性变3项CT特征的LR模型（M1）的受试者工作特征曲线下面积（AUC）为0.917，准确率为0.864。包含CTpre值、形态及均匀性3项CT特征的LR模型（M2）的AUC为0.888，准确率为0.832。S2评分系统（灵敏度：0.859，特异度：0.824）的诊断价值与S1（灵敏度：0.815；特异度：0.910）相当。结论：本研究结果表明，基于CT的机器学习模型与评分系统这类非侵入性成像方法，有望用于预测肾上腺意外瘤的组织学类型。该方法可为肾上腺肿瘤患者的诊断与个性化诊疗提供辅助支持。