Department of Radiology, University of California San Diego, 9452 Medical Center Drive, La Jolla, CA, 92037, USA.
Department of Radiology, Beijing Chao-Yang Hospital, Capital Medical University, 8 Gongren Tiyuchang Nanlu, Chaoyang District, Beijing, 100020, China.
Eur Radiol. 2021 Oct;31(10):7653-7663. doi: 10.1007/s00330-021-07853-6. Epub 2021 Mar 30.
To develop a fully automated full-thickness cartilage segmentation and mapping of T1, T1ρ, and T2*, as well as macromolecular fraction (MMF) by combining a series of quantitative 3D ultrashort echo time (UTE) cones MR imaging with a transfer learning-based U-Net convolutional neural networks (CNN) model.
Sixty-five participants (20 normal, 29 doubtful-minimal osteoarthritis (OA), and 16 moderate-severe OA) were scanned using 3D UTE cones T1 (Cones-T1), adiabatic T1ρ (Cones-AdiabT1ρ), T2* (Cones-T2*), and magnetization transfer (Cones-MT) sequences at 3 T. Manual segmentation was performed by two experienced radiologists, and automatic segmentation was completed using the proposed U-Net CNN model. The accuracy of cartilage segmentation was evaluated using the Dice score and volumetric overlap error (VOE). Pearson correlation coefficient and intraclass correlation coefficient (ICC) were calculated to evaluate the consistency of quantitative MR parameters extracted from automatic and manual segmentations. UTE biomarkers were compared among different subject groups using one-way ANOVA.
The U-Net CNN model provided reliable cartilage segmentation with a mean Dice score of 0.82 and a mean VOE of 29.86%. The consistency of Cones-T1, Cones-AdiabT1ρ, Cones-T2*, and MMF calculated using automatic and manual segmentations ranged from 0.91 to 0.99 for Pearson correlation coefficients, and from 0.91 to 0.96 for ICCs, respectively. Significant increases in Cones-T1, Cones-AdiabT1ρ, and Cones-T2* (p < 0.05) and a decrease in MMF (p < 0.001) were observed in doubtful-minimal OA and/or moderate-severe OA over normal controls.
Quantitative 3D UTE cones MR imaging combined with the proposed U-Net CNN model allows a fully automated comprehensive assessment of articular cartilage.
• 3D UTE cones imaging combined with U-Net CNN model was able to provide fully automated cartilage segmentation. • UTE parameters obtained from automatic segmentation were able to reliably provide a quantitative assessment of cartilage.
通过结合一系列定量 3D 超短回波时间（UTE）锥形磁共振成像与基于迁移学习的 U-Net 卷积神经网络（CNN）模型，开发一种全自动全层软骨分割和 T1、T1ρ、T2* 以及大分子分数（MMF）的映射方法。
65 名参与者（20 名正常、29 名可疑-轻度骨关节炎（OA）和 16 名中重度 OA）在 3T 下接受 3D UTE 锥形 T1（Cones-T1）、各向异性 T1ρ（Cones-AdiabT1ρ）、T2*（Cones-T2*）和磁化传递（Cones-MT）序列扫描。两名有经验的放射科医生进行手动分割，使用所提出的 U-Net CNN 模型完成自动分割。使用 Dice 评分和体积重叠误差（VOE）评估软骨分割的准确性。计算 Pearson 相关系数和组内相关系数（ICC），以评估从自动和手动分割提取的定量 MR 参数的一致性。使用单因素方差分析比较不同组别的 UTE 生物标志物。
U-Net CNN 模型提供了可靠的软骨分割，平均 Dice 评分为 0.82，平均 VOE 为 29.86%。使用自动和手动分割计算的 Cones-T1、Cones-AdiabT1ρ、Cones-T2* 和 MMF 的 Pearson 相关系数范围为 0.91 至 0.99，ICC 范围为 0.91 至 0.96。可疑-轻度 OA 和/或中重度 OA 与正常对照组相比，Cones-T1、Cones-AdiabT1ρ 和 Cones-T2*（p<0.05）显著增加，MMF 显著降低（p<0.001）。
定量 3D UTE 锥形磁共振成像结合所提出的 U-Net CNN 模型可实现关节软骨的全自动综合评估。
• 3D UTE 锥形成像结合 U-Net CNN 模型能够提供全自动的软骨分割。• 自动分割获得的 UTE 参数能够可靠地提供软骨的定量评估。
