Department of Radiology, Faculty of Medicine, University of Miyazaki, 5200 Kihara, Kiyotake, Miyazaki, 889-1692, Japan.
FUJIFILM Corporation, Tokyo, Japan.
Emerg Radiol. 2022 Apr;29(2):317-328. doi: 10.1007/s10140-021-02000-6. Epub 2021 Dec 2.
The evaluation of all ribs on thin-slice CT images is time consuming and it can be difficult to accurately assess the location and type of rib fracture in an emergency. The aim of our study was to develop and validate a convolutional neural network (CNN) algorithm for the detection of acute rib fractures on thoracic CT images and to investigate the effect of the CNN algorithm on radiologists' performance.
The dataset for development of a CNN consisted of 539 thoracic CT scans with 4906 acute rib fractures. A three-dimensional faster region-based CNN was trained and evaluated by using tenfold cross-validation. For an observer performance study to investigate the effect of CNN outputs on radiologists' performance, 30 thoracic CT scans (28 scans with 90 acute rib fractures and 2 without rib fractures) which were not included in the development dataset were used. Observer performance study involved eight radiologists who evaluated CT images first without and second with CNN outputs. The diagnostic performance was assessed by using figure of merit (FOM) values obtained from the jackknife free-response receiver operating characteristic (JAFROC) analysis.
When radiologists used the CNN output for detection of rib fractures, the mean FOM value significantly increased for all readers (0.759 to 0.819, P = 0.0004) and for displaced (0.925 to 0.995, P = 0.0028) and non-displaced fractures (0.678 to 0.732, P = 0.0116). At all rib levels except for the 1st and 12th ribs, the radiologists' true-positive fraction of the detection became significantly increased by using the CNN outputs.
The CNN specialized for the detection of acute rib fractures on CT images can improve the radiologists' diagnostic performance regardless of the type of fractures and reader's experience. Further studies are needed to clarify the usefulness of the CNN for the detection of acute rib fractures on CT images in actual clinical practice.
在薄层 CT 图像上评估所有肋骨需要花费大量时间，并且在紧急情况下准确评估肋骨骨折的位置和类型可能具有挑战性。我们的研究旨在开发和验证一种用于检测胸部 CT 图像中急性肋骨骨折的卷积神经网络（CNN）算法，并研究该 CNN 算法对放射科医生表现的影响。
用于开发 CNN 的数据集包括 539 例胸部 CT 扫描和 4906 例急性肋骨骨折。使用十折交叉验证训练和评估三维快速区域 CNN。为了进行一项观察者性能研究，以调查 CNN 输出对放射科医生表现的影响，使用了 30 例不包括在开发数据集中的胸部 CT 扫描（28 例有 90 例急性肋骨骨折，2 例无肋骨骨折）。观察者性能研究涉及 8 名放射科医生，他们首先在没有和其次在有 CNN 输出的情况下评估 CT 图像。通过使用来自 Jackknife 自由响应接收器操作特征（JAFROC）分析的优异分数（FOM）值评估诊断性能。
当放射科医生使用 CNN 输出检测肋骨骨折时，所有读者的平均 FOM 值均显著增加（0.759 至 0.819，P=0.0004），并且对于移位（0.925 至 0.995，P=0.0028）和未移位骨折（0.678 至 0.732，P=0.0116）也是如此。除第 1 肋和第 12 肋外，在所有肋骨水平上，使用 CNN 输出后，放射科医生的检测真阳性分数均显著增加。
专门用于检测 CT 图像中急性肋骨骨折的 CNN 可以提高放射科医生的诊断性能，而与骨折类型和读者经验无关。需要进一步的研究来阐明 CNN 在实际临床实践中用于检测 CT 图像中急性肋骨骨折的有用性。
