论文部分内容阅读
摘要目的分析计算机辅助诊断(CAD)的附加价值,即对前列腺影像报告和数据系统指南(PIRADS)报告的诊断准确性和癌症侵袭性的评估能力。方法 130例病人进行多参数MRI,在MRI引导下行组织活检得到病理结果,所有病例均有前瞻性的PIRADS报告,所有的病灶同时经过CAD辅助分析。采用Logistic回归将CAD的预测和放射医生PIRADS评分合成一个分。采用受试者操作特征(ROC)曲线分析和Spearman’s相关系数评估诊断的准确性,与肿瘤分级
Abstract Objective To analyze the added value of computer-aided diagnosis (CAD), the diagnostic accuracy of the Pilot Imaging Report and Data System Guide (PIRADS) report and the assessment of cancer aggressiveness. Methods A total of 130 patients underwent multiparametric MRI. Biopsy specimens were obtained under MRI guidance. All cases were prospectively reported with PIRADS. All the lesions were simultaneously analyzed by CAD. Logistic regression was used to combine CAD predictions with radiologist PIRADS scores. The accuracy of the diagnosis was evaluated using the receiver operating characteristic (ROC) curve analysis and Spearman’s correlation coefficient, and the tumor grade