Yao Yu-Cheng, Lin Cheng-Li, Chen Hung-Hsun, Lin Hsi-Hsien, Hsiung Wei, Wang Shih-Tien, Sun Ying-Chou, Tang Yu-Hsuan, Chou Po-Hsin
School of Medicine National Yang Ming Chiao Tung University Taipei Taiwan.
Department of Orthopedics and Traumatology Taipei Veterans General Hospital Taipei Taiwan.
JOR Spine. 2024 Sep 17;7(3):e70001. doi: 10.1002/jsp2.70001. eCollection 2024 Sep.
In spinal revision surgery, previous pedicle screws (PS) may need to be replaced with new implants. Failure to accurately identify the brand of PS-based instrumentation preoperatively may increase the risk of perioperative complications. This study aimed to develop and validate an optimal deep learning (DL) model to identify the brand of PS-based instrumentation on plain radiographs of spine (PRS) using anteroposterior (AP) and lateral images.
A total of 529 patients who received PS-based instrumentation from seven manufacturers were enrolled in this retrospective study. The postoperative PRS were gathered as ground truths. The training, validation, and testing datasets contained 338, 85, and 106 patients, respectively. YOLOv5 was used to crop out the screws' trajectory, and the EfficientNet-b0 model was used to develop single models (AP, Lateral, Merge, and Concatenated) based on the different PRS images. The ensemble models were different combinations of the single models. Primary outcomes were the models' performance in accuracy, sensitivity, precision, F1-score, kappa value, and area under the curve (AUC). Secondary outcomes were the relative performance of models versus human readers and external validation of the DL models.
The Lateral model had the most stable performance among single models. The discriminative performance was improved by the ensemble method. The AP + Lateral ensemble model had the most stable performance, with an accuracy of 0.9434, F1 score of 0.9388, and AUC of 0.9834. The performance of the ensemble models was comparable to that of experienced orthopedic surgeons and superior to that of inexperienced orthopedic surgeons. External validation revealed that the Lat + Concat ensemble model had the best accuracy (0.9412).
The DL models demonstrated stable performance in identifying the brand of PS-based instrumentation based on AP and/or lateral images of PRS, which may assist orthopedic spine surgeons in preoperative revision planning in clinical practice.
在脊柱翻修手术中，先前的椎弓根螺钉（PS）可能需要更换为新的植入物。术前未能准确识别基于PS的器械品牌可能会增加围手术期并发症的风险。本研究旨在开发并验证一种最佳深度学习（DL）模型，以使用前后位（AP）和侧位图像在脊柱平片（PRS）上识别基于PS的器械品牌。
本回顾性研究共纳入了529例接受了来自七个制造商的基于PS的器械的患者。术后PRS被收集作为基本事实。训练、验证和测试数据集分别包含338、85和106例患者。使用YOLOv5裁剪出螺钉轨迹，并使用EfficientNet-b0模型基于不同的PRS图像开发单一模型（AP、侧位、合并和串联）。集成模型是单一模型的不同组合。主要结果是模型在准确性、敏感性、精确性、F1分数、kappa值和曲线下面积（AUC）方面的表现。次要结果是模型相对于人类读者的相对表现以及DL模型的外部验证。
侧位模型在单一模型中表现最稳定。通过集成方法提高了判别性能。AP + 侧位集成模型表现最稳定，准确率为0.9434，F1分数为0.9388，AUC为0.9834。集成模型的表现与经验丰富的骨科医生相当，且优于经验不足的骨科医生。外部验证显示，Lat + Concat集成模型具有最佳准确性（0.9412）。
DL模型在基于PRS的AP和/或侧位图像识别基于PS的器械品牌方面表现出稳定的性能，这可能有助于脊柱骨科医生在临床实践中的术前翻修规划。
