Can computer-aided diagnosis assist in the identification of prostate cancer on prostate MRI? a multi-center, multi-reader investigation.
Can computer-aided diagnosis assist in the identification of prostate cancer on prostate MRI? a multi-center, multi-reader investigation.
复制标题
DOI：
10.18632/oncotarget.26100
复制
发表时间：
2018-09-18
期刊：
影响因子：
--
通讯作者：
Turkbey, Baris
中科院分区：
文献类型：
--
作者：
Gaur, Sonia;Lay, Nathan;Turkbey, Baris
对于前列腺多参数MRI（mpMRI）上的前列腺癌检测，前列腺成像报告和数据系统版本2（PI-RADSv 2）和计算机辅助诊断（CAD）系统旨在广泛提高放射科医生和中心的标准化。我们的目标是评价CAD辅助前列腺癌检测与传统mpMRI解释相比，在不同的数据集，从五个机构获得测试的9个不同经验水平的读者，共代表14个全球分布的机构。单独mpMRI的索引病变灵敏度分别为79%（全前列腺（WP））、84%（外周区（PZ））、71%（移行区（TZ）），与CAD相似，分别为76%（WP，p=0.39）、77%（PZ，p=0.07）、79%（TZ，p=0.15）。在PI-RADSv 2中，对于有中等经验的阅片者，TZ中的CAD获益最大
For prostate cancer detection on prostate multiparametric MRI (mpMRI), the Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) and computer-aided diagnosis (CAD) systems aim to widely improve standardization across radiologists and centers. Our goal was to evaluate CAD assistance in prostate cancer detection compared with conventional mpMRI interpretation in a diverse dataset acquired from five institutions tested by nine readers of varying experience levels, in total representing 14 globally spread institutions. Index lesion sensitivities of mpMRI-alone were 79% (whole prostate (WP)), 84% (peripheral zone (PZ)), 71% (transition zone (TZ)), similar to CAD at 76% (WP, p=0.39), 77% (PZ, p=0.07), 79% (TZ, p=0.15). Greatest CAD benefit was in TZ for moderately-experienced readers at PI-RADSv2