Detection of Medial Epicondyle Avulsion in Elbow Ultrasound Images via Bone Structure Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916975606759424 |
|---|---|
| author | Akahori, Shizuka Teruya, Shotaro Shrestha, Pragyan Yoshii, Yuichi Iizuka, Satoshi Ikumi, Akira Tsuge, Hiromitsu Kitahara, Itaru |
| author_facet | Akahori, Shizuka Teruya, Shotaro Shrestha, Pragyan Yoshii, Yuichi Iizuka, Satoshi Ikumi, Akira Tsuge, Hiromitsu Kitahara, Itaru |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20104 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Detection of Medial Epicondyle Avulsion in Elbow Ultrasound Images via Bone Structure Reconstruction Akahori, Shizuka Teruya, Shotaro Shrestha, Pragyan Yoshii, Yuichi Iizuka, Satoshi Ikumi, Akira Tsuge, Hiromitsu Kitahara, Itaru Computer Vision and Pattern Recognition 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. |
| title | Detection of Medial Epicondyle Avulsion in Elbow Ultrasound Images via Bone Structure Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.20104 |