Department of Biomedical Data Science, Stanford University, Stanford, CA, USA.
Cardiff University Brain Research Imaging Centre, Cardiff University, Cardiff, Wales, UK.
Cartilage. 2021 Dec;13(1_suppl):747S-756S. doi: 10.1177/19476035211042406. Epub 2021 Sep 8.
We evaluated a fully automated femoral cartilage segmentation model for measuring T2 relaxation values and longitudinal changes using multi-echo spin-echo (MESE) magnetic resonance imaging (MRI). We open sourced this model and developed a web app available at https://kl.stanford.edu into which users can drag and drop images to segment them automatically.
We trained a neural network to segment femoral cartilage from MESE MRIs. Cartilage was divided into 12 subregions along medial-lateral, superficial-deep, and anterior-central-posterior boundaries. Subregional T2 values and four-year changes were calculated using a radiologist's segmentations (Reader 1) and the model's segmentations. These were compared using 28 held-out images. A subset of 14 images were also evaluated by a second expert (Reader 2) for comparison.
Model segmentations agreed with Reader 1 segmentations with a Dice score of 0.85 ± 0.03. The model's estimated T2 values for individual subregions agreed with those of Reader 1 with an average Spearman correlation of 0.89 and average mean absolute error (MAE) of 1.34 ms. The model's estimated four-year change in T2 for individual subregions agreed with Reader 1 with an average correlation of 0.80 and average MAE of 1.72 ms. The model agreed with Reader 1 at least as closely as Reader 2 agreed with Reader 1 in terms of Dice score (0.85 vs. 0.75) and subregional T2 values.
Assessments of cartilage health using our fully automated segmentation model agreed with those of an expert as closely as experts agreed with one another. This has the potential to accelerate osteoarthritis research.
我们评估了一种完全自动化的股骨软骨分割模型，该模型使用多回波自旋回波（MESE）磁共振成像（MRI）来测量 T2 弛豫值和纵向变化。我们开源了这个模型，并开发了一个网络应用程序，可在 https://kl.stanford.edu/ 上访问，用户可以将图像拖放到该应用程序中以自动分割。
我们训练了一个神经网络来从 MESE MRI 中分割股骨软骨。软骨沿内侧-外侧、浅层-深层和前-中-后边界分为 12 个亚区。使用放射科医生的分割（Reader 1）和模型的分割计算亚区 T2 值和四年变化。使用 28 个保留图像进行比较。还通过第二位专家（Reader 2）评估了 14 个图像的子集进行比较。
模型分割与 Reader 1 分割的 Dice 评分一致，为 0.85±0.03。模型对各个亚区的估计 T2 值与 Reader 1 的平均 Spearman 相关系数为 0.89，平均平均绝对误差（MAE）为 1.34ms。模型对各个亚区的四年 T2 变化估计与 Reader 1 的平均相关性为 0.80，平均 MAE 为 1.72ms。就 Dice 评分（0.85 对 0.75）和亚区 T2 值而言，模型与 Reader 1 的一致性至少与 Reader 2 与 Reader 1 的一致性一样紧密。
使用我们的全自动分割模型评估软骨健康状况与专家评估的一致性与专家之间的一致性一样紧密。这有可能加速骨关节炎的研究。
