Measurement of Medial Elbow Joint Space Using Landmark Detection

Ultrasound imaging of the medial elbow is crucial for early detection of Ulnar Collateral Ligament (UCL) injuries. Specifically, measuring the elbow joint space on ultrasound images enables the assessment of valgus instability. Automating this measurement requires a precisely annotated dataset to leverage recent advances in deep neural networks; however, no publicly available dataset has been proposed to date. In this work, we introduce a novel medial elbow ultrasound dataset with landmark annotations, facilitating the development of deep neural networks for joint space measurement. The dataset comprises 4,109 medial elbow ultrasound images from 22 participants, with precise landmark annotations on the humerus and ulna, performed under the supervision of three orthopedic surgeons. We evaluate several landmark detection models on our dataset and demonstrate its effectiveness in training models. Additionally, we propose Shape Subspace Refinement (SSR) to refine landmark heatmap peaks, improving the accuracy of heatmap-based landmark detection models. Furthermore, we show that the detected landmarks can be utilized for point-based segmentation of the humerus and ulna. The dataset is publicly available at [dataset link].