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

TL;DR

This paper introduces a structure-aware reconstruction method using masked autoencoders to detect medial epicondyle avulsion in elbow ultrasound images, trained only on normal cases, and achieves high accuracy in identifying abnormalities.

Contribution

The study presents a novel reconstruction-based framework that learns normal bone structure to detect avulsion, with a new dataset and superior performance over existing methods.

Findings

Achieved pixel-wise AUC of 0.965

Achieved image-wise AUC of 0.967

Outperformed existing approaches

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.