Korean J Radiol.
2022 Mar;23(3):343-354. 10.3348/kjr.2021.0449.
Deep Learning-Assisted Diagnosis of Pediatric Skull Fractures on Plain Radiographs
- Choi JW
1,2 - Choi JW1,2
- Cho YJ1,3
- Ha JY4
- Lee YY5
- Koh SY3
- Seo JY3
- Choi YH1,3
- Cheon JE1,3,6
- Phi JH7
- Kim I8
- Yang J9
- Kim WS1,3,6
- Affiliations
-
- 1Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
- 2Department of Radiology, Armed Forces Yangju Hospital, Yangju, Korea
- 3Department of Radiology, Seoul National University Hospital, Seoul, Korea
- 4Department of Radiology, Gyeongsang National University Changwon Hospital, Changwon, Korea
- 5Department of Radiology, Chonnam National University Hospital, Gwangju, Korea
- 6Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Korea
- 7Division of Pediatric Neurosurgery, Seoul National University Children’s Hospital, Seoul, Korea
- 8Department of Emergency Medicine, Armed Forces Yangju Hospital, Yangju, Korea
- 9Army Aviation Operations Command, Icheon, Korea
- KMID: 2526716
- DOI: http://doi.org/10.3348/kjr.2021.0449
Abstract
Objective
To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children.
Materials and Methods
This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs).
Results
The AI model showed an AUROC of 0.922 (95% CI, 0.842–0.969) in the internal test set and 0.870 (95% CI, 0.785–0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%–92.0%) and specificity of 91.3% (95% CI, 79.2%–97.6%) for the internal test set and 78.9% (95% CI, 54.4%–93.9%) and 88.2% (95% CI, 78.7%– 94.4%), respectively, for the external test set. With the model’s assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020–0.168; p = 0.012) and 0.069 (95% CI, 0.002–0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074–0.090; p = 0.850).
Conclusion
A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Automatically Diagnosing Skull Fractures Using an Object Detection Method and Deep Learning Algorithm in Plain Radiography Images
- Clinical Comparison of the Predictive Value of the Simple Skull X-Ray and 3 Dimensional Computed Tomography for Skull Fractures of Children
- Detection of Proximal Caries Lesions with Deep Learning Algorithm
- Deep Learning in Dental Radiographic Imaging
- Diagnosis of Burst Fracture of the Spine on Plain Radiographs Using the Wintopo(R) Program
