A transfer learning approach for automatic segmentation of the surgically treated anterior cruciate ligament.
A transfer learning approach for automatic segmentation of the surgically treated anterior cruciate ligament.
复制标题
DOI：
10.1002/jor.24984
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Fleming BC
中科院分区：
文献类型：
--
作者：
Flannery SW;Kiapour AM;Edgar DJ;Murray MM;Beveridge JE;Fleming BC
定量磁共振成像能够对手术后愈合的前交叉韧带或移植物进行定量评估，但由于需要耗费时间的人工图像分割，其使用受到限制。本研究的目的是验证用于修复和重建前交叉韧带自动分割的深度学习模型。我们假设1)深度学习模型将分割修复的韧带和移植物，其解剖学相似性与完整的韧带相当；2)自动获得的定量特征（即信号强度和体积）与人工分割获得的特征不会有显著差异。ACL修复（n=238）和移植（n=120）获得稳态序列的建设性干扰。先前验证的完整acl模型在两组手术中使用迁移学习进行再训练。用Dice系数、灵敏度和精度来衡量解剖性能。定量特征与地面真值人工分割进行了比较。与完整ACL自动分割相比，两组手术的自动分割导致解剖性能下降（修复/移植：Dice系数= 0.80 / 0.78，精度= 0.79 / 0.78，灵敏度= 0.82 / 0.80），但两者的下降均无统计学意义（Kruskal-Wallis: Dice系数p= 0.02，精度p= 0.09，灵敏度p= 0.17； Dunn随机检验Dice系数：修复/移植p= 0.054 / 0.051）。ground truth与自动分割修复/移植物的定量特征差异无统计学意义（0.82/2.7%信号强度差异，p= 0.57 / 0.26; 1.7/2.7%体积差异，p= 0.68 / 0.72）。定量特征的解剖相似性和统计相似性支持在定量MRI管道中使用该自动分割模型，这将加速研究并为临床应用提供一步。
Quantitative magnetic resonance imaging enables quantitative assessment of the healing anterior cruciate ligament or graft post-surgery, but its use is constrained by the need for time consuming manual image segmentation. The goal of this study was to validate a deep learning model for automatic segmentation of repaired and reconstructed anterior cruciate ligaments. We hypothesized that 1) a deep learning model would segment repaired ligaments and grafts with comparable anatomical similarity to intact ligaments, and 2) automatically derived quantitative features (i.e., signal intensity and volume) would not be significantly different from those obtained by manual segmentation. Constructive Interference in Steady State sequences were acquired of ACL repairs (n=238) and grafts (n=120). A previously validated model for intact ACLs was retrained on both surgical groups using transfer learning. Anatomical performance was measured with Dice coefficient, sensitivity, and precision. Quantitative features were compared to ground truth manual segmentation. Automatic segmentation of both surgical groups resulted in decreased anatomical performance compared to intact ACL automatic segmentation (repairs/grafts: Dice coefficient=.80/.78, precision=.79/.78, sensitivity=.82/.80), but neither decrease was statistically significant (Kruskal-Wallis: Dice coefficient p=.02, precision p=.09, sensitivity p=.17; Dunn post-hoc test for Dice coefficient: repairs/grafts p=.054/.051). There were no significant differences in quantitative features between the ground truth and automatic segmentation of repairs/grafts (0.82/2.7% signal intensity difference, p=.57/.26; 1.7/2.7% volume difference, p=.68/.72). The anatomical similarity performance and statistical similarities of quantitative features supports the use of this automated segmentation model in quantitative MRI pipelines, which will accelerate research and provide a step towards clinical applicability.
登录
查看更多内容
DOI：
10.1002/jor.24926
发表时间：
2021-04
期刊：
Journal of orthopaedic research : official publication of the Orthopaedic Research Society
影响因子：
--
作者：
Flannery SW;Kiapour AM;Edgar DJ;Murray MM;Fleming BC
通讯作者：
Fleming BC
影响因子：
7
作者：
Koff, M. F.;Shah, P.;Pownder, S.;Romero, B.;Williams, R.;Gilbert, S.;Maher, S.;Fortier, L. A.;Rodeo, S. A.;Potter, H. G.
通讯作者：
Potter, H. G.
前交叉韧带的结构和解剖学恢复与手术后1年的软骨损伤有关：愈合韧带的特性会影响软骨损伤。
影响因子：
2.6
作者：
Kiapour AM;Fleming BC;Murray MM
通讯作者：
Murray MM
影响因子：
2.8
作者：
Biercevicz, Alison M.;Proffen, Benedikt L.;Murray, Martha M.;Walsh, Edward G.;Fleming, Braden C.
通讯作者：
Fleming, Braden C.
影响因子：
19.7
作者：
Pauli, Chantal;Bae, Won C.;Du, Jiang
通讯作者：
Du, Jiang