Marsilio Luca, Moglia Andrea, Manzotti Alfonso, Cerveri Pietro
Department of Electronics, Information and BioengineeringPolitecnico di Milano I-20133 Milan Italy.
Hospital ASST FBF-Sacco I-20157 Milan Italy.
IEEE Open J Eng Med Biol. 2025 Jan 9;6:269-278. doi: 10.1109/OJEMB.2025.3527877. eCollection 2025.
Effective preoperative planning for shoulder joint replacement requires accurate glenohumeral joint (GH) digital surfaces and reliable clinical staging. xCEL-UNet was designed as a dual-task deep network for humerus and scapula bone reconstruction in CT scans, and assessment of three GH joint clinical conditions, namely osteophyte size (OS), joint space reduction (JS), and humeroscapular alignment (HSA). Trained on a dataset of 571 patients, the model optimized segmentation and classification through transfer learning. It achieved median root mean squared errors of 0.31 and 0.24 mm, and Hausdorff distances of 2.35 and 3.28 mm for the humerus and scapula, respectively. Classification accuracy was 91 for OS, 93 for JS, and 85% for HSA. GradCAM-based activation maps validated the network's interpretability. this framework delivers accurate 3D bone surface reconstructions and dependable clinical assessments of the GH joint, offering robust support for therapeutic decision-making in shoulder arthroplasty.
有效的肩关节置换术前规划需要精确的盂肱关节（GH）数字表面和可靠的临床分期。xCEL-UNet被设计为一种双任务深度网络，用于CT扫描中的肱骨和肩胛骨重建，以及评估三种GH关节临床状况，即骨赘大小（OS）、关节间隙减小（JS）和肩胛肱骨对线（HSA）。该模型在571例患者的数据集上进行训练，通过迁移学习优化分割和分类。它在肱骨和肩胛骨上分别实现了0.31和0.24毫米的中位数均方根误差，以及2.35和3.28毫米的豪斯多夫距离。OS的分类准确率为91%，JS为93%，HSA为85%。基于GradCAM的激活图验证了网络的可解释性。该框架提供了精确的三维骨表面重建和可靠的GH关节临床评估，为肩关节置换术中的治疗决策提供了有力支持。
