Nam Ju Gang, Hwang Eui Jin, Kim Da Som, Yoo Seung-Jin, Choi Hyewon, Goo Jin Mo, Park Chang Min
Department of Radiology, Seoul National University Hospital and College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea (J.G.N., E.J.H., D.S.K., S.J.Y., H.C., J.M.G., C.M.P.); and Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea (J.M.G., C.M.P.).
Radiol Cardiothorac Imaging. 2020 Dec 10;2(6):e190222. doi: 10.1148/ryct.2020190222. eCollection 2020 Dec.
To evaluate the performance of a deep learning-based algorithm in detecting lung cancers not reported on posteroanterior chest radiographs during routine practice.
The retrospective test dataset included 168 posteroanterior chest radiographs acquired between March 2017 and December 2018 (168 patients; mean age, 71.9 years ± 9.5 [standard deviation]; age range, 42-91 years) with 187 lung cancers (mean size, 2.3 cm ± 1.2) undetected during initial clinical evaluation, and 50 normal chest radiographs. CT served as the reference standard for ground truth. Four thoracic radiologists independently reevaluated the chest radiographs for lung nodules both without and with the aid of the algorithm. The performances of the algorithm and the radiologists were evaluated and compared on a per-chest radiograph basis and a per-lesion basis, according to the area under the receiver operating characteristic curve (AUROC) and area under the jackknife free-response ROC curve (AUFROC).
The algorithm showed excellent diagnostic performances both in terms of per-chest radiograph classification (AUROC, 0.899) and per-lesion localization (AUFROC, 0.744); both of these values were significantly higher than those of the radiologists (AUROC, 0.634-0.663; AUFROC, 0.619-0.651; < .001 for all). The algorithm also demonstrated higher sensitivity (69.6% [117 of 168] vs 47.0% [316 of 672]; < .001) and specificity (94.0% [47 of 50] vs 78.0% [156 of 200]; = .01). When assisted by the algorithm, the radiologists' AUROC (0.634-0.663 vs 0.685-0.724; < 0.01 for all) and pooled AUFROC (0.636 vs 0.688; = .03) substantially improved. The false-positive rate of the algorithm, that is, the total number of false-positive nodules divided by the total number of chest radiographs, was similar to that of pooled radiologists (21.1% [46 of 218] vs 19.0% [166 of 872]; > .05).
A deep learning-based nodule detection algorithm showed excellent detection performance of lung cancers that were not reported on chest radiographs during routine practice and significantly reduced reading errors when used as a second reader.© RSNA, 2020See also commentary by White in this issue.
评估一种基于深度学习的算法在检测常规实践中后前位胸片未报告的肺癌方面的性能。
回顾性测试数据集包括2017年3月至2018年12月期间获取的168张后前位胸片（168例患者；平均年龄71.9岁±9.5[标准差]；年龄范围42 - 91岁），其中有187个肺癌（平均大小2.3 cm±1.2）在初始临床评估中未被检测到，以及50张正常胸片。CT作为真实情况的参考标准。四名胸部放射科医生分别在不借助和借助该算法的情况下对胸片进行肺结节重新评估。根据受试者操作特征曲线下面积（AUROC）和留一法自由反应ROC曲线下面积（AUFROC），在每张胸片基础和每个病灶基础上评估并比较该算法和放射科医生的性能。
该算法在每张胸片分类（AUROC，0.899）和每个病灶定位（AUFROC，0.744）方面均表现出优异的诊断性能；这两个值均显著高于放射科医生的（AUROC，0.634 - 0.663；AUFROC，0.619 - 0.651；所有P <.001）。该算法还表现出更高的敏感性（69.6%[168例中的117例]对47.0%[672例中的316例]；P <.001）和特异性（94.0%[50例中的47例]对78.0%[200例中的156例]；P =.01）。在该算法辅助下，放射科医生的AUROC（0.634 - 0.663对0.685 - 0.724；所有P < 0.01）和合并的AUFROC（0.636对0.688；P =.03）有显著改善。该算法的假阳性率，即假阳性结节总数除以胸片总数，与合并的放射科医生的相似（21.1%[218例中的46例]对19.0%[872例中的166例]；P >.05）。
一种基于深度学习的结节检测算法在检测常规实践中胸片未报告的肺癌方面表现出优异的检测性能，并且用作第二阅片者时显著减少了阅片误差。©RSNA，2020另见本期White的评论。
