Improving rib fracture detection accuracy and reading efficiency with deep learning-based detection software: a clinical evaluation

Zhang, Bin; Jia, Chunxue; Wu, Runze; Lv, Baotao; Li, Beibei; Li, Fuzhou; Du, Guijin; Sun, Zhenchao; Li, Xiaodong

doi:10.1259/bjr.20200870

Cited by 43 publications

(29 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CNN for the automatic detection of acute rib fractures is expected to detect all types of acute fractures. The diagnostic performance of radiologists in our study was lower for non-displaced fractures than displaced fractures, and this was in line with previous studies [21,22,25]. However, the assistance of CNN significantly improved the performance of radiologists for the detection of non-displaced fractures.…”

Section: Discussionsupporting

confidence: 91%

“…Based on our study, the adoption of CNNs for the detection of acute rib fractures on CT images may not only improve the radiologists' detection accuracy of fractures by using as a second opinion but also reduce the time required for reading CT images. However, in our study, the sequential test method [25] was used in the observer performance study. Therefore, we could not independently compare the reading time with images alone and the reading time with images using the CNN.…”

Section: Discussionmentioning

confidence: 99%

“…Divergent assessment results were re-evaluated by the two radiologists to reach a consensus. When the CT images were annotated by the two radiologists, rib fractures were classified into two types: displaced and non-displaced [3,24,25] (Fig. 1).…”

Section: Image Property and Annotationmentioning

confidence: 99%

“…Displaced rib fractures were defined as fractures with a displacement greater than 2 mm [3,24,25]. Non-displaced rib fractures were defined as fractures with disruption of the cortex without significant displacement, including simple, transverse, oblique, or butterfly fractures [3,24,25]. Buckle fractures and irregularity of one or both cortical margins were included in a non-displaced group in this study [3].…”

Section: Image Property and Annotationmentioning

confidence: 99%

See 3 more Smart Citations

Detection of acute rib fractures on CT images with convolutional neural networks: effect of location and type of fracture and reader’s experience

et al. 2021

View full text Add to dashboard Cite

PurposeThe 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. Methods The dataset for development of a CNN consisted of 539 thoracic CT scans with 4906 acute rib fractures. A threedimensional 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. Results 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. ConclusionThe 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.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Discussionmentioning

confidence: 99%

Section: Image Property and Annotationmentioning

confidence: 99%

Section: Image Property and Annotationmentioning

confidence: 99%

See 2 more Smart Citations

Detection of acute rib fractures on CT images with convolutional neural networks: effect of location and type of fracture and reader’s experience

et al. 2021

View full text Add to dashboard Cite

show abstract

“…To avoid serious consequences, accurate detection of rib fractures is important. Low-dose thoracic computed tomography (CT) scans are commonly used in the assessment and auxiliary diagnosis of rib fractures [ 3 , 4 ], but missed diagnoses are common. Studies have shown that the sensitivity of diagnosis of rib fractures is only about 60% on initial chest CT evaluations [ 5 ], and missed diagnosis may cause severe medical accidents.…”

Section: Introductionmentioning

confidence: 99%

Rib Fracture Detection with Dual-Attention Enhanced U-Net

Zhou

Jia

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Rib fractures are common injuries caused by chest trauma, which may cause serious consequences. It is essential to diagnose rib fractures accurately. Low-dose thoracic computed tomography (CT) is commonly used for rib fracture diagnosis, and convolutional neural network- (CNN-) based methods have assisted doctors in rib fracture diagnosis in recent years. However, due to the lack of rib fracture data and the irregular, various shape of rib fractures, it is difficult for CNN-based methods to extract rib fracture features. As a result, they cannot achieve satisfying results in terms of accuracy and sensitivity in detecting rib fractures. Inspired by the attention mechanism, we proposed the CFSG U-Net for rib fracture detection. The CSFG U-Net uses the U-Net architecture and is enhanced by a dual-attention module, including a channel-wise fusion attention module (CFAM) and a spatial-wise group attention module (SGAM). CFAM uses the channel attention mechanism to reweight the feature map along the channel dimension and refine the U-Net’s skip connections. SGAM uses the group technique to generate spatial attention to adjust feature maps in the spatial dimension, which allows the spatial attention module to capture more fine-grained semantic information. To evaluate the effectiveness of our proposed methods, we established a rib fracture dataset in our research. The experimental results on our dataset show that the maximum sensitivity of our proposed method is 89.58%, and the average FROC score is 81.28%, which outperforms the existing rib fracture detection methods and attention modules.

show abstract