通过重建正常骨结构，精准识别肘部超声中的内上髁撕脱伤
Detection of Medial Epicondyle Avulsion in Elbow Ultrasound Images via Bone Structure Reconstruction
- 用掩码自编码器学习正常骨连续性，异常处重建误差大
- 像素级AUC达0.965，图像级AUC达0.967，性能领先
- 专为运动员肘部损伤设计，适合骨科影像辅助诊断
本研究提出一种基于重建的框架，用于检测肘部超声图像中的内上髁撕脱伤，仅在正常病例上训练。内上髁撕脱常见于棒球运动员，表现为骨质分离与形态异常，常体现为骨轮廓不连续。因此，学习正常骨结构的连续性对识别异常至关重要。为此，我们设计了一种基于掩码自编码器、结构感知的重建框架，学习正常骨结构的连续性。即使存在撕脱，模型仍尝试重建正常结构，导致撕脱区域出现显著重建误差。为评估性能，我们构建了一个新数据集，包含16名棒球运动员的正常与撕脱超声图像，并由骨科医生提供像素级标注。所提方法优于现有方法，在像素级和图像级分别达到0.965和0.967的AUC。数据集已公开：https://github.com/Akahori000/Ultrasound-Medial-Epicondyle-Avulsion-Dataset。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。