Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina.
Trinity College of Arts & Sciences, Duke University, Durham, North Carolina.
J Arthroplasty. 2024 Sep;39(9):2225-2233. doi: 10.1016/j.arth.2024.04.062. Epub 2024 Apr 27.
Increasing deformity of the lower extremities, as measured by the hip-knee-ankle angle (HKAA), is associated with poor patient outcomes after total hip and knee arthroplasty (THA, TKA). Automated calculation of HKAA is imperative to reduce the burden on orthopaedic surgeons. We proposed a detection-based deep learning (DL) model to calculate HKAA in THA and TKA patients and assessed the agreement between DL-derived HKAAs and manual measurement.
We retrospectively identified 1,379 long-leg radiographs (LLRs) from patients scheduled for THA or TKA within an academic medical center. There were 1,221 LLRs used to develop the model (randomly split into 70% training, 20% validation, and 10% held-out test sets); 158 LLRs were considered "difficult," as the femoral head was difficult to distinguish from surrounding tissue. There were 2 raters who annotated the HKAA of both lower extremities, and inter-rater reliability was calculated to compare the DL-derived HKAAs with manual measurement within the test set.
The DL model achieved a mean average precision of 0.985 on the test set. The average HKAA of the operative leg was 173.05 ± 4.54°; the nonoperative leg was 175.55 ± 3.56°. The inter-rater reliability between manual and DL-derived HKAA measurements on the operative leg and nonoperative leg indicated excellent reliability (intraclass correlation (2,k) = 0.987 [0.96, 0.99], intraclass correlation (2, k) = 0.987 [0.98, 0.99, respectively]). The standard error of measurement for the DL-derived HKAA for the operative and nonoperative legs was 0.515° and 0.403°, respectively.
A detection-based DL algorithm can calculate the HKAA in LLRs and is comparable to that calculated by manual measurement. The algorithm can detect the bilateral femoral head, knee, and ankle joints with high precision, even in patients where the femoral head is difficult to visualize.
下肢畸形程度的增加，以髋膝踝角（HKAA）来衡量，与全髋关节和膝关节置换术（THA、TKA）后的患者预后不良有关。HKAA 的自动计算对于减轻矫形外科医生的负担至关重要。我们提出了一种基于检测的深度学习（DL）模型来计算 THA 和 TKA 患者的 HKAA，并评估了 DL 衍生的 HKAAs 与手动测量之间的一致性。
我们回顾性地从学术医疗中心计划接受 THA 或 TKA 的患者中确定了 1379 张长腿 X 线片（LLR）。其中 1221 张 LLR 用于模型开发（随机分为 70%的训练集、20%的验证集和 10%的保留测试集）；158 张 LLR 被认为是“困难的”，因为股骨头难以与周围组织区分开来。有 2 名评估者对双侧下肢的 HKAA 进行了注释，并计算了组内相关系数（2，k）以比较测试集中的 DL 衍生 HKAAs 与手动测量值。
DL 模型在测试集上的平均平均精度为 0.985。手术侧的平均 HKAA 为 173.05±4.54°；非手术侧为 175.55±3.56°。手术侧和非手术侧手动和 DL 衍生 HKAA 测量值之间的组内相关系数（2，k）表示具有极好的可靠性（（2，k）=0.987[0.96，0.99]，（2，k）=0.987[0.98，0.99]）。DL 衍生的 HKAA 的测量误差标准分别为手术侧和非手术侧的 0.515°和 0.403°。
基于检测的 DL 算法可以计算 LLR 中的 HKAA，并且与手动测量相当。该算法可以高精度地检测双侧股骨头、膝关节和踝关节，即使在股骨头难以可视化的患者中也是如此。
