Zhang Le, Pei Baoqing, Zhang Shijia, Lu Da, Xu Yangyang, Huang Xin, Wu Xueqing
Beijing Key Laboratory for Design and Evaluation Technology of Advanced Implantable & Interventional Medical Devices, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China.
Shenzhen Institute of Beihang University, Shenzhen, China.
Global Spine J. 2025 May;15(4):2062-2074. doi: 10.1177/21925682241282581. Epub 2024 Sep 12.
Study DesignRetrospective observational study.ObjectivesScoliosis is commonly observed in adolescents, with a world0wide prevalence of 0.5%. It is prone to be overlooked by parents during its early stages, as it often lacks overt characteristics. As a result, many individuals are not aware that they may have scoliosis until the symptoms become quite severe, significantly affecting the physical and mental well-being of patients. Traditional screening methods for scoliosis demand significant physician effort and require unnecessary radiography exposure; thus, implementing large-scale screening is challenging. The application of deep learning algorithms has the potential to reduce unnecessary radiation risks as well as the costs of scoliosis screening.MethodsThe data of 247 scoliosis patients observed between 2008 and 2021 were used for training. The dataset included frontal, lateral, and back upright images as well as X-ray images obtained during the same period. We proposed and validated deep learning algorithms for automated scoliosis screening using upright back images. The overall process involved the localization of the back region of interest (ROI), spinal region segmentation, and Cobb angle measurements.ResultsThe results indicated that the accuracy of the Cobb angle measurement was superior to that of the traditional human visual recognition method, providing a concise and convenient scoliosis screening capability without causing any harm to the human body.ConclusionsThe method was automated, accurate, concise, and convenient. It is potentially applicable to a wide range of screening methods for the detection of early scoliosis.
研究设计
回顾性观察研究。
目的
脊柱侧弯在青少年中很常见，全球患病率为0.5%。在其早期阶段，脊柱侧弯很容易被家长忽视，因为它通常没有明显的特征。因此，许多人直到症状非常严重时才意识到自己可能患有脊柱侧弯，这对患者的身心健康有显著影响。传统的脊柱侧弯筛查方法需要医生付出大量精力，且需要进行不必要的X线照射；因此，实施大规模筛查具有挑战性。深度学习算法的应用有可能降低不必要的辐射风险以及脊柱侧弯筛查的成本。
方法
使用2008年至2021年间观察到的247例脊柱侧弯患者的数据进行训练。该数据集包括正位、侧位和背部直立图像以及同期获得的X线图像。我们提出并验证了使用背部直立图像进行脊柱侧弯自动筛查的深度学习算法。整个过程包括背部感兴趣区域（ROI）的定位、脊柱区域分割和Cobb角测量。
结果
结果表明，Cobb角测量的准确性优于传统的人工视觉识别方法，提供了一种简洁方便的脊柱侧弯筛查能力，且不会对人体造成任何伤害。
结论
该方法具有自动化、准确、简洁和方便的特点。它有可能适用于广泛的早期脊柱侧弯检测筛查方法。
