发表机构
Institute for Neuro- and Bioinformatics, University of Lübeck; University Medical Center Schleswig-Holstein; IMAGE Information Systems Europe GmbH; Pattern Recognition Company GmbH（吕贝克大学神经与生物信息学研究所; 石勒苏益格-荷尔斯泰因大学医学中心; IMAGE信息系统欧洲有限公司; 模式识别有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于CT的合成数据生成框架，用于解决放射图像患者姿态评估中真实训练数据获取难的问题，经3077对踝关节图像预训练后，真实踝关节姿态评估性能提升最多11个百分点。
AI 中文摘要
放射图像的诊断质量对可靠诊断和治疗规划至关重要，患者在放射摄影期间的姿态是决定该质量的最重要因素之一。由于患者定位困难且缺乏标准化，采用基于AI的自动化方法，在拍摄放射图像前通过深度图像自动评估患者姿态会很有帮助。但受监管障碍影响，实际中难以获取所需的深度图像及对应的放射图像。本文提出一种可从计算机断层扫描（CT）扫描中合成生成此类训练数据的框架；还表明，在由3077个踝关节上部图像对组成的合成数据集上预训练后，真实踝关节上部的姿态评估性能可提升最多11个百分点。
英文摘要
An adequate diagnostic quality of radiographs is essential for reliable diagnoses and treatment planning. The patient's pose during radiography is one of the most important factors determining the diagnostic quality. Since patient positioning is difficult and not standardized, an automated AI-based approach using depth images to automatically assess the patient's pose before the radiograph has been taken would be helpful. Due to regulatory hurdles, however, it is difficult in practice to acquire the required depth images and corresponding radiographs. In this paper, we present a framework that can generate such training data synthetically from Computed Tomography scans. We further show that by pretraining on our generated synthetic dataset consisting of 3077 image pairs of upper ankle joints, the pose assessment of real upper ankle joints can be improved by up to 11 percentage points.
CommentsAccepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2026:027
Journal refMachine.Learning.for.Biomedical.Imaging. 2026 (2026)
DOI：10.59275/j.melba.2026-c874
