Assessment of a Deep Learning Algorithm for the Detection of Rib Fractures on Whole-Body Trauma Computed Tomography

• Published in: Korean journal of radiology Vol. 21; no. 7; pp. 891 - 899
• Main Authors: Weikert, Thomas, Noordtzij, Luca Andre, Bremerich, Jens, Stieltjes, Bram, Parmar, Victor, Cyriac, Joshy, Sommer, Gregor, Sauter, Alexander Walter
• Format: Journal Article
• Language: English
• Published: Korea (South) The Korean Society of Radiology 01.07.2020; 대한영상의학회
• Subjects: Adult; Aged; Algorithms; Deep Learning; Female; Fractures; Humans; Image Interpretation, Computer-Assisted; Male; Medical imaging; Middle Aged; Neural networks; Retrospective Studies; Rib Fractures - diagnosis; Thoracic Imaging; Tomography; Tomography, X-Ray Computed - methods; Trauma; Trauma centers; Whole Body Imaging; Wounds and Injuries - diagnostic imaging; 방사선과학; United States > US; Deep learning; Rib fractures; Computed tomography; Trauma; Computer-assisted image interpretation
• ISSN: 1229-6929; 2005-8330; 2005-8330
• DOI: 10.3348/kjr.2019.0653

To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.