Weill Cornell College of Medicine, New York, New York; Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York.
Department of Orthopaedic Surgery, Massachusetts General Hospital, Boston, Massachusetts.
J Arthroplasty. 2024 May;39(5):1191-1198.e2. doi: 10.1016/j.arth.2023.11.021. Epub 2023 Nov 23.
The radiographic assessment of bone morphology impacts implant selection and fixation type in total hip arthroplasty (THA) and is important to minimize the risk of periprosthetic femur fracture (PFF). We utilized a deep-learning algorithm to automate femoral radiographic parameters and determined which automated parameters were associated with early PFF.
Radiographs from a publicly available database and from patients undergoing primary cementless THA at a high-volume institution (2016 to 2020) were obtained. A U-Net algorithm was trained to segment femoral landmarks for bone morphology parameter automation. Automated parameters were compared against that of a fellowship-trained surgeon and compared in an independent cohort of 100 patients who underwent THA (50 with early PFF and 50 controls matched by femoral component, age, sex, body mass index, and surgical approach).
On the independent cohort, the algorithm generated 1,710 unique measurements for 95 images (5% lesser trochanter identification failure) in 22 minutes. Medullary canal width, femoral cortex width, canal flare index, morphological cortical index, canal bone ratio, and canal calcar ratio had good-to-excellent correlation with surgeon measurements (Pearson's correlation coefficient: 0.76 to 0.96). Canal calcar ratios (0.43 ± 0.08 versus 0.40 ± 0.07) and canal bone ratios (0.39 ± 0.06 versus 0.36 ± 0.06) were higher (P < .05) in the PFF cohort when comparing the automated parameters.
Deep-learning automated parameters demonstrated differences in patients who had and did not have early PFF after cementless primary THA. This algorithm has the potential to complement and improve patient-specific PFF risk-prediction tools.
在全髋关节置换术（THA）中，骨骼形态的放射学评估会影响植入物的选择和固定类型，对于降低假体周围股骨骨折（PFF）的风险非常重要。我们利用深度学习算法实现了股骨放射学参数的自动化，并确定了哪些自动化参数与早期 PFF 相关。
从一个公开数据库和一个高容量机构（2016 年至 2020 年）接受初次非骨水泥 THA 的患者中获取放射照片。使用 U-Net 算法对股骨标志进行分割，实现骨骼形态参数的自动化。将自动化参数与一名经过 fellowship培训的外科医生的参数进行比较，并在 100 名接受 THA 的患者（50 例早期 PFF 和 50 例匹配股骨组件、年龄、性别、体重指数和手术入路的对照）的独立队列中进行比较。
在独立队列中，该算法在 22 分钟内为 95 张图像生成了 1710 个独特的测量值（5%的小转子识别失败）。髓腔宽度、股骨皮质宽度、管腔扩张指数、形态皮质指数、管腔骨比和管腔骺骨比与外科医生的测量值具有良好到极好的相关性（Pearson 相关系数：0.76 至 0.96）。在比较自动化参数时，PFF 组的管腔骺骨比（0.43±0.08 比 0.40±0.07）和管腔骨比（0.39±0.06 比 0.36±0.06）更高（P<0.05）。
在初次非骨水泥 THA 后出现和未出现早期 PFF 的患者中，深度学习自动化参数存在差异。该算法有可能补充和改进针对假体周围股骨骨折的特定患者风险预测工具。
