University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390, USA.
Baylor, Scott, & White, Dallas, TX, USA.
Skeletal Radiol. 2024 May;53(5):923-933. doi: 10.1007/s00256-023-04502-5. Epub 2023 Nov 15.
Angular and longitudinal deformities of leg alignment create excessive stresses across joints, leading to pain and impaired function. Multiple measurements are used to assess these deformities on anteroposterior (AP) full-length radiographs. An artificial intelligence (AI) software automatically locates anatomical landmarks on AP full-length radiographs and performs 13 measurements to assess knee angular alignment and leg length. The primary aim of this study was to evaluate the agreements in LLD and knee alignment measurements between an AI software and two board-certified radiologists in patients without metal implants. The secondary aim was to assess time savings achieved by AI.
The measurements assessed in the study were hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg length discrepancy (LLD), and mechanical axis deviation (MAD). These measurements were performed by two radiologists and the AI software on 164 legs. Intraclass-correlation-coefficients (ICC) and Bland-Altman analyses were used to assess the AI's performance.
The AI software set incorrect landmarks for 11/164 legs. Excluding these cases, ICCs between the software and radiologists were excellent for 12/13 variables (11/13 with outliers included), and the AI software met performance targets for 11/13 variables (9/13 with outliers included). The mean reading time for the AI algorithm and two readers, respectively, was 38.3, 435.0, and 625.0 s.
This study demonstrated that, with few exceptions, this AI-based software reliably generated measurements for most variables in the study and provided substantial time savings.
腿部对线的角度和纵向畸形会导致关节承受过大的压力,从而引起疼痛和功能障碍。多项测量用于评估前后位(AP)全长射线照片上的这些畸形。人工智能(AI)软件可自动在 AP 全长射线照片上定位解剖学标志,并进行 13 项测量以评估膝关节角度对线和下肢长度。本研究的主要目的是评估在无金属植入物的患者中,AI 软件与两名董事会认证的放射科医生在测量下肢不等长(LLD)和膝关节对线方面的一致性。次要目的是评估 AI 节省的时间。
研究中评估的测量值包括髋膝角(HKA)、解剖胫股角(aTFA)、解剖机械轴角(AMA)、关节线会聚角(JLCA)、机械外侧股骨近端角(mLPFA)、机械外侧股骨远端角(mLDFA)、机械内侧胫骨近端角(mMPTA)、机械外侧胫骨远端角(mLDTA)、股骨长度、胫骨长度、全长、下肢不等长(LLD)和机械轴偏差(MAD)。这些测量值由两名放射科医生和 AI 软件在 164 条腿上进行。使用组内相关系数(ICC)和 Bland-Altman 分析评估 AI 的性能。
AI 软件为 11/164 条腿设置了错误的标志点。排除这些病例后,软件与放射科医生之间的 ICC 在 12/13 个变量中表现出色(包括 11 个带有离群值的变量),并且 AI 软件满足了 11/13 个变量的性能目标(包括 11 个带有离群值的变量)。AI 算法和两位读者的平均阅读时间分别为 38.3、435.0 和 625.0 s。
本研究表明,除少数例外情况外,该基于 AI 的软件能够可靠地生成研究中大多数变量的测量值,并大大节省了时间。