Department of Orthopedic Surgery, Keio University School of Medicine, Shinanomachi 35, Shinjuku, Tokyo, 160-8582, Japan.
Sci Rep. 2024 Aug 3;14(1):17989. doi: 10.1038/s41598-024-68937-z.
Spinal deformities, including adolescent idiopathic scoliosis (AIS) and adult spinal deformity (ASD), affect many patients. The measurement of the Cobb angle on coronal radiographs is essential for their diagnosis and treatment planning. To enhance the precision of Cobb angle measurements for both AIS and ASD, we developed three distinct artificial intelligence (AI) algorithms: AIS/ASD-trained AI (trained with both AIS and ASD cases); AIS-trained AI (trained solely on AIS cases); ASD-trained AI (trained solely on ASD cases). We used 1612 whole-spine radiographs, including 1029 AIS and 583 ASD cases with variable postures, as teaching data. We measured the major and two minor curves. To assess the accuracy, we used 285 radiographs (159 AIS and 126 ASD) as a test set and calculated the mean absolute error (MAE) and intraclass correlation coefficient (ICC) between each AI algorithm and the average of manual measurements by four spine experts. The AIS/ASD-trained AI showed the highest accuracy among the three AI algorithms. This result suggested that learning across multiple diseases rather than disease-specific training may be an efficient AI learning method. The presented AI algorithm has the potential to reduce errors in Cobb angle measurements and improve the quality of clinical practice.
脊柱畸形，包括青少年特发性脊柱侧凸（AIS）和成人脊柱畸形（ASD），影响着许多患者。冠状位 X 光片上 Cobb 角的测量对于其诊断和治疗计划至关重要。为了提高 AIS 和 ASD 的 Cobb 角测量精度，我们开发了三种不同的人工智能（AI）算法：AIS/ASD 训练的 AI（同时使用 AIS 和 ASD 病例进行训练）；AIS 训练的 AI（仅使用 AIS 病例进行训练）；ASD 训练的 AI（仅使用 ASD 病例进行训练）。我们使用了 1612 张全脊柱 X 光片，包括 1029 例 AIS 和 583 例 ASD 病例，具有不同的姿势，作为教学数据。我们测量了主要曲线和两个次要曲线。为了评估准确性，我们使用了 285 张 X 光片（159 例 AIS 和 126 例 ASD）作为测试集，并计算了每个 AI 算法与四位脊柱专家手动测量平均值之间的平均绝对误差（MAE）和组内相关系数（ICC）。AIS/ASD 训练的 AI 在三种 AI 算法中表现出最高的准确性。这一结果表明，跨多种疾病学习而不是针对特定疾病的训练可能是一种有效的 AI 学习方法。所提出的 AI 算法有可能减少 Cobb 角测量中的误差，并提高临床实践的质量。
