Ritter Daniel, Denard Patrick J, Raiss Patric, Wijdicks Coen A, Werner Brian C, Bedi Asheesh, Müller Peter E, Bachmaier Samuel
Department of Orthopedic Research, Arthrex, Munich, Germany; Department of Orthopaedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), University Hospital, LMU, Munich, Germany.
Southern Oregon Orthopedics, Medford, OR, USA.
J Shoulder Elbow Surg. 2025 Mar;34(3):e141-e151. doi: 10.1016/j.jse.2024.07.006. Epub 2024 Aug 16.
Reduced bone density is recognized as a predictor for potential complications in reverse shoulder arthroplasty (RSA). While humeral and glenoid planning based on preoperative computed tomography (CT) scans assist in implant selection and position, reproducible methods for quantifying the patients' bone density are currently not available. The purpose of this study was to perform bone density analyses including patient-specific calibration in an RSA cohort based on preoperative CT imaging. It was hypothesized that preoperative CT bone density measures would provide objective quantification of the patients' humeral bone quality.
This study consisted of 3 parts, (1) analysis of a patient-specific calibration method in cadaveric CT scans, (2) retrospective application in a clinical RSA cohort, and (3) clustering and classification with machine learning (ML) models. Forty cadaveric shoulders were scanned in a clinical CT and compared regarding calibration with density phantoms, air muscle, and fat (patient-specific) or standard Hounsfield unit. Postscan patient-specific calibration was used to improve the extraction of 3-dimensional regions of interest for retrospective bone density analysis in a clinical RSA cohort (n = 345). ML models were used to improve the clustering (Hierarchical Ward) and classification (support vector machine) of low bone densities in the respective patients.
The patient-specific calibration method demonstrated improved accuracy with excellent intraclass correlation coefficients for cylindrical cancellous bone densities (intraclass correlation coefficient >0.75). Clustering partitioned the training data set into a high-density subgroup consisting of 96 patients and a low-density subgroup consisting of 146 patients, showing significant differences between these groups. The support vector machine showed optimized prediction accuracy of low and high bone densities compared to conventional statistics in the training (accuracy = 91.2%; area under curve = 0.967) and testing (accuracy = 90.5%; area under curve = 0.958) data set.
Preoperative CT scans can be used to quantify the proximal humeral bone quality in patients undergoing RSA. The use of ML models and patient-specific calibration on bone mineral density demonstrated that multiple three-dimensional bone density scores improved the accuracy of objective preoperative bone quality assessment. The trained model could provide preoperative information to surgeons treating patients with potentially poor bone quality.
骨密度降低被认为是反肩关节置换术（RSA）潜在并发症的一个预测指标。虽然基于术前计算机断层扫描（CT）的肱骨和关节盂规划有助于植入物的选择和定位，但目前尚无用于量化患者骨密度的可重复方法。本研究的目的是基于术前CT成像对RSA队列进行骨密度分析，包括患者特异性校准。研究假设术前CT骨密度测量将为患者的肱骨骨质提供客观量化。
本研究包括3个部分：（1）尸体CT扫描中患者特异性校准方法的分析；（2）在临床RSA队列中的回顾性应用；（3）使用机器学习（ML）模型进行聚类和分类。对40个尸体肩部进行临床CT扫描，并将其与密度体模、空气、肌肉和脂肪（患者特异性）或标准亨氏单位的校准情况进行比较。扫描后采用患者特异性校准来改进临床RSA队列（n = 345）中用于回顾性骨密度分析的三维感兴趣区域的提取。ML模型用于改进各患者低骨密度的聚类（分层沃德法）和分类（支持向量机）。
患者特异性校准方法显示出更高的准确性，圆柱形松质骨密度的组内相关系数优异（组内相关系数>0.75）。聚类将训练数据集分为一个由96名患者组成的高密度亚组和一个由146名患者组成的低密度亚组，显示出这些组之间存在显著差异。与训练（准确率 = 91.2%；曲线下面积 = 0.967）和测试（准确率 = 90.5%；曲线下面积 = 0.958）数据集中的传统统计方法相比，支持向量机显示出对低骨密度和高骨密度的优化预测准确率。
术前CT扫描可用于量化接受RSA治疗患者的近端肱骨骨质。在骨密度上使用ML模型和患者特异性校准表明，多个三维骨密度评分提高了术前客观骨质评估的准确性。经过训练的模型可为治疗骨质可能较差患者的外科医生提供术前信息。
