Author:
Niiya Akifumi,Murakami Kouzou,Kobayashi Rei,Sekimoto Atsuhito,Saeki Miho,Toyofuku Kosuke,Kato Masako,Shinjo Hidenori,Ito Yoshinori,Takei Mizuki,Murata Chiori,Ohgiya Yoshimitsu
Abstract
AbstractArtificial intelligence algorithms utilizing deep learning are helpful tools for diagnostic imaging. A deep learning-based automatic detection algorithm was developed for rib fractures on computed tomography (CT) images of high-energy trauma patients. In this study, the clinical effectiveness of this algorithm was evaluated. A total of 56 cases were retrospectively examined, including 46 rib fractures and 10 control cases from our hospital, between January and June 2019. Two radiologists annotated the fracture lesions (complete or incomplete) for each CT image, which is considered the “ground truth.” Thereafter, the algorithm’s diagnostic results for all cases were compared with the ground truth, and the sensitivity and number of false positive (FP) results per case were assessed. The radiologists identified 199 images with a fracture. The sensitivity of the algorithm was 89.8%, and the number of FPs per case was 2.5. After additional learning, the sensitivity increased to 93.5%, and the number of FPs was 1.9 per case. FP results were found in the trabecular bone with the appearance of fracture, vascular grooves, and artifacts. The sensitivity of the algorithm used in this study was sufficient to aid the rapid detection of rib fractures within the evaluated validation set of CT images.
Publisher
Springer Science and Business Media LLC
Reference22 articles.
1. Miller, L. A. Chest wall, lung, and pleural space trauma. Radiol. Clin. North Am. 44, 213–224 (2006).
2. Ziegler, D. W. & Agarwal, N. N. The morbidity and mortality of rib fractures. J. Trauma 37, 975–979 (1994).
3. Ebina, M. et al. Diagnostic precision of emergency room CT and efforts to improve its quality. [Article in Japanese] JJSEM. 18, 1–4 (2015).
4. Walls, J., Hunter, N., Brasher, P. M. A. & Ho, S. G. F. The DePICTORS Study: discrepancies in preliminary interpretation of CT scans between on-call residents and staff. Emerg. Radiol. 16, 303–308 (2009).
5. Strub, W. M., Vagal, A. A., Tomsick, T. & Moulton, J. S. Overnight resident preliminary interpretations on CT examinations: should the process continue?. Emerg. Radiol. 13, 19–23 (2006).
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献