Automatic detection of rib fractures: Are we there yet?

Development and evaluation of a deep learning-based model for simultaneous detection and localization of rib and clavicle fractures in trauma patients' chest radiographs

Purpose

To develop a rib and clavicle fracture detection model for chest radiographs in trauma patients using a deep learning (DL) algorithm.

Materials and methods

We retrospectively collected 56 145 chest X-rays (CXRs) from trauma patients in a trauma center between August 2008 and December 2016. A rib/clavicle fracture detection DL algorithm was trained using this data set with 991 (1.8%) images labeled by experts with fracture site locations. The algorithm was tested on independently collected 300 CXRs in 2017. An external test set was also collected from hospitalized trauma patients in a regional hospital for evaluation. The receiver operating characteristic curve with area under the curve (AUC), accuracy, sensitivity, specificity, precision, and negative predictive value of the model on each test set was evaluated. The prediction probability on the images was visualized as heatmaps.

Results

The trained DL model achieved an AUC of 0.912 (95% CI 87.8 to 94.7) on the independent test set. The accuracy, sensitivity, and specificity on the given cut-off value are 83.7, 86.8, and 80.4, respectively. On the external test set, the model had a sensitivity of 88.0 and an accuracy of 72.5. While the model exhibited a slight decrease in accuracy on the external test set, it maintained its sensitivity in detecting fractures.

Conclusion

The algorithm detects rib and clavicle fractures concomitantly in the CXR of trauma patients with high accuracy in locating lesions through heatmap visualization.

Oblique Axis Rib Stretch and Curved Planar Reformats in Patients for Rib Fracture Detection and Characterization: Feasibility and Clinical Application

Objective

To assess the use of CT with oblique axis rib stretch (OARS) and curved planar reformats (CPRs) for rib fracture detection and characterization.

Methods

A total of 108 forensically diagnosed patients with rib fractures were evaluated retrospectively. OARS and CPRs were independently used during the diagnosis in two groups. In each group, the final diagnosis was made after a junior radiologist's initial diagnosis was reviewed by a senior radiologist. The images were evaluated for the presence and characterization of rib fractures.

Results

A total of 2,592 ribs were analyzed, and 326 fractured ribs and 345 fracture sites were diagnosed using reference standard. Two groups of radiologists identified 331 and 333 fracture sites using the OARS method, 291 and 288 fracture sites using the CPRs method, and 274 fracture sites in forensically diagnosed patients (CR: conventional reconstruction), respectively; and all missed diagnoses were nondisplaced rib fractures. The ROC Az value of OARS1,2 was 0.98, which is higher than CPRs1,2 0.91, and CR 0.90 (all p < 0.01). The Az value for detecting rib fractures using CPRs1,2 and CR has no statistical difference (p = 0.14 and 0.29). More misdiagnosed patients were found using CPRs1,2 (42 and 44 cases) than OARS1,2 (1 and 2 cases) and CR (2 cases). The displaced fracture detection ratio of all methods showed no difference.

Conclusions

Doctors using the OARS method could improve diagnostic performance for detecting rib fractures without the requirement of specialized software and workstation when compared with CPRs.

Development of an artificial intelligence-assisted computed tomography diagnosis technology for rib fracture and evaluation of its clinical usefulness

Artificial 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.

An Interpretable Approach to Automated Severity Scoring in Pelvic Trauma

Pelvic ring disruptions result from blunt injury mechanisms and are often found in patients with multi-system trauma. To grade pelvic fracture severity in trauma victims based on whole-body CT, the Tile AO/OTA classification is frequently used. Due to the high volume of whole-body trauma CTs generated in busy trauma centers, an automated approach to Tile classification would provide substantial value, e. g., to prioritize the reading queue of the attending trauma radiologist. In such scenario, an automated method should perform grading based on a transparent process and based on interpretable features to enable interaction with human readers and lower their workload by offering insights from a first automated read of the scan. This paper introduces an automated yet interpretable pelvic trauma decision support system to assist radiologists in fracture detection and Tile grade classification. The method operates similarly to human interpretation of CT scans and first detects distinct pelvic fractures on CT with high specificity using a Faster-RCNN model that are then interpreted using a structural causal model based on clinical best practices to infer an initial Tile grade. The Bayesian causal model and finally, the object detector are then queried for likely co-occurring fractures that may have been rejected initially due to the highly specific operating point of the detector, resulting in an updated list of detected fractures and corresponding final Tile grade. Our method is transparent in that it provides finding location and type using the object detector, as well as information on important counterfactuals that would invalidate the system's recommendation and achieves an AUC of 83.3%/85.1% for translational/rotational instability. Despite being designed for human-machine teaming, our approach does not compromise on performance compared to previous black-box approaches.