Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, United States of America.
Department of Medical Imaging, University of Arizona, Tucson, AZ, United States of America; Siemens Healthcare, Tucson, AZ, USA.
Magn Reson Imaging. 2020 Nov;73:45-54. doi: 10.1016/j.mri.2020.08.005. Epub 2020 Aug 21.
To develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei.
A cascaded multi-planar scheme with a modified residual U-Net architecture was used to segment thalamic nuclei on conventional and white-matter-nulled (WMn) magnetization prepared rapid gradient echo (MPRAGE) data. A single network was optimized to work with images from healthy controls and patients with multiple sclerosis (MS) and essential tremor (ET), acquired at both 3 T and 7 T field strengths. WMn-MPRAGE images were manually delineated by a trained neuroradiologist using the Morel histological atlas as a guide to generate reference ground truth labels. Dice similarity coefficient and volume similarity index (VSI) were used to evaluate performance. Clinical utility was demonstrated by applying this method to study the effect of MS on thalamic nuclei atrophy.
Segmentation of each thalamus into twelve nuclei was achieved in under a minute. For 7 T WMn-MPRAGE, the proposed method outperforms current state-of-the-art on patients with ET with statistically significant improvements in Dice for five nuclei (increase in the range of 0.05-0.18) and VSI for four nuclei (increase in the range of 0.05-0.19), while performing comparably for healthy and MS subjects. Dice and VSI achieved using 7 T WMn-MPRAGE data are comparable to those using 3 T WMn-MPRAGE data. For conventional MPRAGE, the proposed method shows a statistically significant Dice improvement in the range of 0.14-0.63 over FreeSurfer for all nuclei and disease types. Effect of noise on network performance shows robustness to images with SNR as low as half the baseline SNR. Atrophy of four thalamic nuclei and whole thalamus was observed for MS patients compared to healthy control subjects, after controlling for the effect of parallel imaging, intracranial volume, gender, and age (p < 0.004).
The proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.
开发一种快速准确的基于卷积神经网络的方法，用于分割丘脑核。
使用级联多平面方案和改进的残差 U-Net 架构，对常规和白质消除（WMn）磁化准备快速梯度回波（MPRAGE）数据中的丘脑核进行分割。优化了一个单一的网络，以便在 3T 和 7T 场强下对健康对照者和多发性硬化症（MS）和特发性震颤（ET）患者的图像进行工作。WMn-MPRAGE 图像由经过培训的神经放射科医生手动描绘，使用莫雷尔组织学图谱作为指导，生成参考地面真实标签。使用 Dice 相似系数和体积相似指数（VSI）来评估性能。通过应用该方法研究 MS 对丘脑核萎缩的影响，证明了该方法的临床实用性。
在不到一分钟的时间内将每个丘脑分为 12 个核。对于 7T WMn-MPRAGE，所提出的方法在 ET 患者中优于当前的最先进方法，在五个核中 Dice 显著提高（提高范围为 0.05-0.18），在四个核中 VSI 提高（提高范围为 0.05-0.19），而在健康和 MS 受试者中表现相当。使用 7T WMn-MPRAGE 数据获得的 Dice 和 VSI 与使用 3T WMn-MPRAGE 数据获得的结果相当。对于常规 MPRAGE，与 FreeSurfer 相比，所提出的方法在所有核和疾病类型中 Dice 均有统计学显著提高，范围为 0.14-0.63。网络性能对噪声的影响表现出对 SNR 低至基线 SNR 一半的图像的鲁棒性。与健康对照者相比，MS 患者的四个丘脑核和整个丘脑出现萎缩，在控制并行成像、颅内体积、性别和年龄的影响后（p<0.004）。
所提出的分割方法快速、准确，在疾病类型和场强上表现良好，并且具有改善我们对神经疾病中丘脑核参与的理解的巨大潜力。
