Purpose anterior cervical decompression and fusion is a common surgical procedure. Traditionally, experienced doctors observe X-ray films regularly examined by patients to determine postoperative conditions by observing the tiny movements between the limited vertebral bodies. But it is not accurate. This may lead to error diagnostics and serious deterioration of the condition and secondary injury to the patient and will also put a greater financial burden on them. Doctors need a quantitative standard to determine small motion with limited vertebral landmarks after surgery. Computer vision technology is needed to match the over-extension and over-flexion cervical vertebral body to provide objective measurement data for further quantification of intervertebral activity. Based on conventional scheme, the point mean square error is used as the evaluation criterion of the matching effect, and the iterative matching scheme is proposed to improve the stability of the original scheme. The cervical X-ray films of patients from the China–Japan Friendship Hospital were collected as samples to verify the reliability of the scheme. Compared with the existing image matching schemes based on feature points, our scheme is superior in matching effect, matching speed and stability. This scheme can provide a solid foundation for further assisting doctors in the study of rehabilitation after anterior cervical fusion.

中文翻译：

---

一种新的基于X射线图像同源摄影方法的迭代匹配方案

目的颈前路减压融合术是一种常见的外科手术方法。传统上，经验丰富的医生会定期观察患者检查的 X 光片，通过观察有限椎体之间的微小运动来确定术后状况。但这并不准确。这可能导致错误诊断和病情严重恶化，对患者造成二次伤害，也会给他们带来更大的经济负担。医生需要一个定量标准来确定手术后椎体标志有限的小运动。需要计算机视觉技术来匹配颈椎过伸和过屈，为进一步量化椎间活动提供客观的测量数据。在常规方案的基础上，以点均方误差作为匹配效果的评价标准，提出迭代匹配方案以提高原方案的稳定性。采集中日友好医院患者颈部X线片作为样本，验证方案的可靠性。与现有的基于特征点的图像匹配方案相比，我们的方案在匹配效果、匹配速度和稳定性上均具有优势。该方案可为进一步协助医生开展颈前路融合术后康复研究提供坚实的基础。采集中日友好医院患者颈部X线片作为样本，验证方案的可靠性。与现有的基于特征点的图像匹配方案相比，我们的方案在匹配效果、匹配速度和稳定性上均具有优势。该方案可为进一步协助医生开展颈前路融合术后康复研究提供坚实的基础。采集中日友好医院患者颈部X线片作为样本，验证方案的可靠性。与现有的基于特征点的图像匹配方案相比，我们的方案在匹配效果、匹配速度和稳定性上均具有优势。该方案可为进一步协助医生开展颈前路融合术后康复研究提供坚实的基础。