An Automatic Surgical Decision Support Method for Radial Metaphyseal Fractures in X-Ray

Abstract

Distal Radius Fractures (DRFs) are the most common type of fracture with a high incidence rate, accounting for 17.5% of all adult fractures. The established clinical workflow for patients with a suspicion of DRF calls for the acquisition of two radiographic X-ray images (radiographs) of the wrist in anteroposterior (AP) and lateral (LAT) views [1]. Radiographic parameters (RPs), which are linear angle and distance measurements derived from the AP and LAT radiographs, have been shown to provide objective support for effective decision making in determining clinical treatment of distal radius fractures (DRFs) [2]. Recently, we showed that providing computed RPs to orthopedic surgeons may improve the consistency of the radiographic judgment and influence their clinical decision for the treatment of DRFs [3]. However, calculating the RPs manually from radiographs requires experience, is time consuming, and is subject to observer variability. This paper presents a novel deep learning automatic method for computing the six anatomical RPs associated with DRFs in AP and LAT forearm radiographs.

Ähnliche Arbeiten