Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan;66(1):53-62.
doi: 10.3340/jkns.2022.0062. Epub 2022 Jun 2.

Automatically Diagnosing Skull Fractures Using an Object Detection Method and Deep Learning Algorithm in Plain Radiography Images

Tae Seok Jeong  1 , Gi Taek Yee  2 , Kwang Gi Kim  3 , Young Jae Kim  3 , Sang Gu Lee  2 , Woo Kyung Kim  1
Affiliations

Automatically Diagnosing Skull Fractures Using an Object Detection Method and Deep Learning Algorithm in Plain Radiography Images

Tae Seok Jeong et al. J Korean Neurosurg Soc. 2023 Jan.

Abstract

Objective: Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability.

Methods: A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance.

Results: In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anteriorposterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor.

Conclusion: The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

Keywords: Artificial intelligence; Deep learning; Radiography; Skull fractures; Traumatic brain injury.

PubMed Disclaimer

Conflict of interest statement

Conflicts of interest

Gi Taek Yee has been editorial board of JKNS since May 2017. He was not involved in the review process of this original article. No potential conflict of interest relevant to this article was reported.

Figures

Fig. 1.
Fig. 1.
Patient selection.
Fig. 2.
Fig. 2.
RetinaNet architecture with (a) ResNet and (b) feature pyramid network as a feature extractor to (c) classify the probability of the skull fracture and (d) regress the bounding box coordinates.
Fig. 3.
Fig. 3.
Precision-recall curve. The diagnostic performance of object detection using RetinaNet was assessed by the precision-recall curve and the average precision (AP). AP is calculated as the area under the precision-recall curve. AP values for ResNet models and intersection over union (IOU) thresholds were analyzed.
Fig. 4.
Fig. 4.
Analyzed sample images. A : True-positive image detecting parietal bone fracture in lateral view. B : False-positive image detecting vascular groove in lateral view. C : False-negative image not detecting diastatic fracture of left lambdoid suture observed in the left orbit area of anterior-posterior view.
Fig. 5.
Fig. 5.
Pediatric sample images. A : False-positive image detecting lambdoid suture and accessory suture. B : False-positive image detecting vascular groove.
See this image and copyright information in PMC

References

    1. Amyot F, Arciniegas DB, Brazaitis MP, Curley KC, Diaz-Arrastia R, Gandjbakhche A, et al. A review of the effectiveness of neuroimaging modalities for the detection of traumatic brain injury. J Neurotrauma. 2015;32:1693–1721. - PMC - PubMed
    1. Beyaz S, Açıcı K, Sümer E. Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches. Jt Dis Relat Surg. 2020;31:175–183. - PMC - PubMed
    1. Bruns JJ, Jr, Jagoda AS. Mild traumatic brain injury. Mt Sinai J Med. 2009;76:129–137. - PubMed
    1. Chung SW, Han SS, Lee JW, Oh KS, Kim NR, Yoon JP, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta orthop. 2018;89:468–473. - PMC - PubMed
    1. Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A. The pascal visual object classes (voc) challenge. Int J Comput Vis. 2010;88:303–338.

LinkOut - more resources