Abstract

Hand X-Rays are used for tasks such as detecting fractures and investigating joint pain. The choice of the X-Ray view plays a crucial role in a medical expert's ability to make an accurate diagnosis. In particular, this choice is essential for the hand, where small and overlapping bones of the carpals can make it challenging to view structures even with correct positioning. In this study, we develop a prototype that uses deep learning models, iterative methods and a depth sensor to estimate hand and X-Ray machine parameters. We then use these parameters to generate feedback that ensures proper positioning according to radiographic positioning standards.

The method of this study consists of five steps: detector plane parameter estimation, 2D hand keypoint prediction, landmark depth estimation, positioning parameter extraction, and protocol constraint verification. Detector plane parameter estimation is achieved by fitting a plane to randomly queried depth points using RANSAC. Google's MediaPipe HandPose model is used for 2D hand keypoint estimation, and depth coordinates are determined using the OAK-D Pro's depth sensor. Finally, hand positioning parameters are extracted and evaluated with respect to the selected viewing protocol. We focus on three commonly used hand positioning protocols: posterior-anterior, oblique, and lateral view. The prototype also has a user interface and a feedback system designed for practical use in the X-Ray room.

Two evaluations are undertaken to validate our prototype. First, with the help of a radiology technician, we rate the quality of the suggested positioning by the device. Second, using a bespoke left-hand X-ray phantom and an X-Ray machine, we generate images with and without the prototype guidance for a double-blind study rated by a radiologist.