Detection of Medial Epicondyle Avulsion in Elbow Ultrasound Images via Bone Structure Reconstruction

2025-07-26

AI Summary

This study addresses medial epicondyle avulsion injuries—common among baseball players—by proposing a weakly supervised detection method relying solely on normal ultrasound images. Methodologically, it introduces mask autoencoders (MAEs) to bone structure reconstruction for the first time, incorporating a bone-structure-aware loss function that models the continuity of normal bone contours; anomalies are localized via reconstruction errors in discontinuous regions, eliminating the need for any annotated abnormal samples. The approach enables dual-granularity (pixel-level and image-level) anomaly detection. Evaluated on a publicly available, self-collected dataset, it achieves AUCs of 0.965 (pixel-level) and 0.967 (image-level), significantly outperforming both supervised and unsupervised baselines. This work establishes a novel, interpretable, and annotation-efficient paradigm for early screening of sports-related musculoskeletal injuries.

Technology Category

• Computer Vision: Segmentation
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Unsupervised & Self-Supervised Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

This study proposes a reconstruction-based framework for detecting medial epicondyle avulsion in elbow ultrasound images, trained exclusively on normal cases. Medial epicondyle avulsion, commonly observed in baseball players, involves bone detachment and deformity, often appearing as discontinuities in bone contour. Therefore, learning the structure and continuity of normal bone is essential for detecting such abnormalities. To achieve this, we propose a masked autoencoder-based, structure-aware reconstruction framework that learns the continuity of normal bone structures. Even in the presence of avulsion, the model attempts to reconstruct the normal structure, resulting in large reconstruction errors at the avulsion site. For evaluation, we constructed a novel dataset comprising normal and avulsion ultrasound images from 16 baseball players, with pixel-level annotations under orthopedic supervision. Our method outperformed existing approaches, achieving a pixel-wise AUC of 0.965 and an image-wise AUC of 0.967. The dataset is publicly available at: https://github.com/Akahori000/Ultrasound-Medial-Epicondyle-Avulsion-Dataset.

Problem

• Detects medial epicondyle avulsion in elbow ultrasound images
• Reconstructs normal bone structure to identify abnormalities
• Improves accuracy in diagnosing bone detachment in athletes

Innovation

• Masked autoencoder reconstructs normal bone structure
• Trained exclusively on normal ultrasound cases
• Detects avulsion via large reconstruction errors