RESUMO
PURPOSE: Operative management of distal radius fractures (DRFs) has become increasingly common. Age, activity levels, and comorbid conditions are major factors influencing the treatment decision, although operative indications are still controversial. Radiographic parameters (RPs), such as radial inclination, dorsal tilt, and articular step-off, can provide objective support for effective decision making. However, manual measurement of RPs may be imprecise and subject to inconsistency. To address this problem, we developed custom software of an algorithm to automatically detect and compute 6 common RPs associated with DRF in anteroposterior and lateral radiographs. The aim in this study was to assess the effect of this software on radiographic interobserver variability among orthopedic surgeons. Our hypothesis was that precise and consistent measurement of RPs will improve radiographic interpretation variability among surgeons and, consequently, may aid in clinical decision making. METHODS: Thirty-five radiograph series of DRFs were presented to 9 fellowship-trained hand and orthopedic trauma surgeons. Each case was presented with basic clinical information, together with plain anteroposterior and lateral radiographs. One of the 2 possible treatment options was selected: casting or open reduction with a locking plate. The survey was repeated 3 weeks later, this time with computer-generated RP measurements. Data were analyzed for interobserver and intraobserver variability for both surveys, and the interclass coefficient, kappa value, was calculated. RESULTS: The interobserver reliability (interclass coefficient value) improved from poor to moderate, 0.35 to 0.50, with the provided RP. The average intraobserver interclass coefficient was 0.68. When participants were assessed separately according to their subspecialties (trauma and hand), improved interobserver variability was found as well. CONCLUSIONS: Providing computed RPs to orthopedic surgeons may improve the consistency of the radiographic judgment and influence their clinical decision for the treatment of DRFs. CLINICAL RELEVANCE: Orthopedic surgeons' consistency in the radiographic judgment of DRFs slightly improved by providing automatically calculated radiographic measurements to them.
RESUMO
PURPOSE: Radiographic parameters (RPs) provide objective support for effective decision making in determining clinical treatment of distal radius fractures (DRFs). This paper presents a novel automatic RP computation pipeline for computing the six anatomical RPs associated with DRFs in anteroposterior (AP) and lateral (LAT) forearm radiographs. METHODS: The pipeline consists of: (1) segmentation of the distal radius and ulna bones with six 2D Dynamic U-Net deep learning models; (2) landmark points detection and distal radius axis computation from the segmentations with geometric methods; (3) RP computation and generation of a quantitative DRF report and composite AP and LAT radiograph images. This hybrid approach combines the advantages of deep learning and model-based methods. RESULTS: The pipeline was evaluated on 90 AP and 93 LAT radiographs for which ground truth distal radius and ulna segmentations and RP landmarks were manually obtained by expert clinicians. It achieves an accuracy of 94 and 86% on the AP and LAT RPs, within the observer variability, and an RP measurement difference of 1.4 ± 1.2° for the radial angle, 0.5 ± 0.6 mm for the radial length, 0.9 ± 0.7 mm for the radial shift, 0.7 ± 0.5 mm for the ulnar variance, 2.9 ± 3.3° for the palmar tilt and 1.2 ± 1.0 mm for the dorsal shift. CONCLUSION: Our pipeline is the first fully automatic method that accurately and robustly computes the RPs for a wide variety of clinical forearm radiographs from different sources, hand orientations, with and without cast. The computed accurate and reliable RF measurements may support fracture severity assessment and clinical management.