Improvement of the diagnostic accuracy for intracranial haemorrhage using deep learning-based computer-assisted detection
Improvement of the diagnostic accuracy for intracranial haemorrhage using deep learning-based computer-assisted detection
复制标题
DOI：
10.1007/s00234-020-02566-x
复制
发表时间：
2020-10-06
期刊：
影响因子：
2.8
通讯作者：
Yoshiya, Kazuhisa
中科院分区：
文献类型：
--
作者：
Watanabe, Yoshiyuki;Tanaka, Takahiro;Yoshiya, Kazuhisa
目的 阐明基于深度学习的计算机辅助检测（CAD）对不同级别医生利用 CT 检测颅内出血表现的影响。方法 15 名医生（5 名委员会认证的放射科医生、5 名放射科住院医师和 5 名医学实习生）对总共 40 个头部 CT 数据集（正常 16 个；出血 24 个）进行了评估。医生们参加了 2 次阅读课程，无论是否患有 CAD。所有医生都以一定程度的置信度对出血区域进行注释，并记录每个病例的阅读时间。我们的 CAD 系统是使用 433 名患者的头部 CT 图像（正常，203；出血，230）开发的，并使用 U-Net 和基于机器学习的假阳性去除方法将出血率显示为相应的概率热图。根据注释和置信水平计算灵敏度、特异性、准确性和品质因数 (FOM)。结果 在基于患者的评估中，使用 CAD 后，所有医生的平均准确率从 83.7% 显着提高到 89.7% (p< 0.001)。此外，委员会认证的放射科医生、放射科住院医师和实习生在没有 CAD 的情况下的准确率分别为 92.5%、82.5 和 76.0%，在患有 CAD 的情况下分别为 97.5%、90.5 和 81.0%。使用 CAD 后，所有医生的平均 FOM 从 0.78 增加到 0.82 (p= 0.004)。对于所有医生来说，使用 CAD 时（43 秒）的阅读时间明显低于未使用 CAD 时的阅读时间（68 秒，p < 0.001）。结论 使用深度学习开发的 CAD 系统显着提高了所有医生检测颅内出血的诊断性能并减少了阅读时间。
Purpose To elucidate the effect of deep learning-based computer-assisted detection (CAD) on the performance of different-level physicians in detecting intracranial haemorrhage using CT. Methods A total of 40 head CT datasets (normal, 16; haemorrhagic, 24) were evaluated by 15 physicians (5 board-certificated radiologists, 5 radiology residents, and 5 medical interns). The physicians attended 2 reading sessions without and with CAD. All physicians annotated the haemorrhagic regions with a degree of confidence, and the reading time was recorded in each case. Our CAD system was developed using 433 patients' head CT images (normal, 203; haemorrhagic, 230), and haemorrhage rates were displayed as corresponding probability heat maps using U-Net and a machine learning-based false-positive removal method. Sensitivity, specificity, accuracy, and figure of merit (FOM) were calculated based on the annotations and confidence levels. Results In patient-based evaluation, the mean accuracy of all physicians significantly increased from 83.7 to 89.7% (p< 0.001) after using CAD. Additionally, accuracies of board-certificated radiologists, radiology residents, and interns were 92.5, 82.5, and 76.0% without CAD and 97.5, 90.5, and 81.0% with CAD, respectively. The mean FOM of all physicians increased from 0.78 to 0.82 (p= 0.004) after using CAD. The reading time was significantly lower when CAD (43 s) was used than when it was not (68 s,p< 0.001) for all physicians. Conclusion The CAD system developed using deep learning significantly improved the diagnostic performance and reduced the reading time among all physicians in detecting intracranial haemorrhage.