发表机构
Pohang Stroke and Spine Hospital; Handong Global University; Pohang University of Science and Technology; Kyungpook National University Hospital（浦项中风与脊柱医院; 韩东全球大学; 浦项科技大学; 庆北国立大学医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出RSM框架，包含基于自编码与修复的ARNAI网络，用于去除脊柱植入物伪影，提升术后X光片的分割与脊柱骨盆参数测量精度，L4–L5节段Cobb角误差平均降低约70%。
AI 中文摘要
目的：本研究旨在开发一种适用于术后影像的人工智能框架，用于在存在脊柱植入物的情况下，对X光片上的脊柱骨盆参数进行自动化测量，并具备对植入物伪影的稳健性。材料与方法：我们回顾性审查了两家机构的腰椎侧位X光片（内部：2017年1月至2024年12月；外部：2021年10月至2025年9月）。我们开发了恢复、分割与测量（RSM）框架，其中包含一种新颖的基于自编码与修复的伪影去除网络（ARNAI），以减轻术后X光片中与植入物相关的伪影。使用Wilcoxon符号秩检验和组内相关系数评估分割和脊柱骨盆参数（PT、LL、SS、SCA）的测量性能。结果：当将ARNAI添加到最新的基于Transformer的分割模型FCBFormer中时，平均DSC从0.814增加到0.870，在L3–L5节段有显著提升，在L1–L2节段有较小改善。在91张带有植入物的X光片中，L4–L5节段Cobb角的平均误差从15.6–16.2°降低到4.7°，平均误差减少了70%。L4–L5节段Cobb角的ICC从0.18提高到0.54（评估者1）和0.59（评估者2），而骨盆倾斜、腰椎前凸和骶骨倾斜的ICC均超过0.70。在内部含植入物队列中，经过多重比较校正后，L4–L5节段Cobb角误差的改善具有统计学显著性。结论：所提出的RSM框架改善了含植入物的术后X光片中脊柱骨盆参数的自动化测量。通过减轻植入物相关伪影，ARNAI提高了分割和下游测量的准确性，其中对L4–L5节段Cobb角估计的益处最大，平均误差减少了约70%。
英文摘要
Purpose: This study aims to develop an AI framework applicable for postoperative imaging for automated measurement of spinopelvic parameters on radiographs with robustness to the presence of spinal implants. Materials and Methods: We retrospectively reviewed lateral lumbar spine radiographs from two institutions (Internal: January 2017--December 2024; External: October 2021--September 2025). We developed the Restore, Segment, and Measure (RSM) framework, incorporating a novel Artifact Removal Network based on Autoencoding and Inpainting (ARNAI) to mitigate implant-related artifacts in postoperative radiographs. Segmentation and spinopelvic parameter (PT, LL, SS, SCA) measurement performance were assessed using Wilcoxon signed-rank tests and intraclass correlation coefficients. Results: When ARNAI was added to a recent Transformer-based segmentation model, FCBFormer, the mean DSC increased to 0.870 from 0.814, with marked gains at L3--L5 and smaller improvements at L1--L2. On 91 radiographs with implants, the mean L4--L5 segmental Cobb angle error decreased to 4.7 ° from 15.6--16.2 °, an average error reduction of 70%. The ICC for L4--L5 segmental Cobb angle improved to 0.54 (Rater 1) and 0.59 (Rater 2) from 0.18, and ICCs for pelvic tilt, lumbar lordosis, and sacral slope all exceeded 0.70. The improvement in L4--L5 segmental Cobb angle error was statistically significant in the internal implant-containing cohort after correction for multiple comparisons. Conclusion: The proposed RSM framework improved automated spinopelvic parameter measurement in implant-containing postoperative radiographs. By mitigating implant-related artifacts, ARNAI improved segmentation and downstream measurement accuracy, with the greatest benefit observed for L4--L5 segmental Cobb angle estimation, where the mean error was reduced by approximately 70%.
Comments12 pages 4 figures
