Deng Minghui, Yu Renping, Wang Li, Shi Feng, Yap Pew-Thian, Shen Dinggang
College of Electrical and Information, Northeast Agricultural University, Harbin 150030, China and Department of Radiology and BRIC, University of North Carolina, Chapel Hill, North Carolina 27599.
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China and Department of Radiology and BRIC, University of North Carolina, Chapel Hill, North Carolina 27599.
Med Phys. 2016 Dec;43(12):6588-6597. doi: 10.1118/1.4967487.
Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio.
In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation.
The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods.
The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.
将脑磁共振（MR）图像分割为白质（WM）、灰质（GM）和脑脊液（CSF）对于脑结构测量和疾病诊断至关重要。基于学习的分割方法在很大程度上依赖于良好的训练真值。然而，常用的3T MR图像质量不足，WM、GM和CSF之间的强度对比度通常较差。因此，它们并非为基于学习的方法提供良好真值标签数据的理想选择。超高场7T成像的最新进展使得获取具有出色强度对比度和信噪比的图像成为可能。
在本文中，作者提出了一种基于随机森林的算法，通过基于从7T MR图像半自动获得的可靠标签训练一系列分类器来分割3T MR图像。所提出的算法通过一系列随机森林分类器迭代地细化WM、GM和CSF的概率图，以改进组织分割。
所提出的方法在两个数据集上得到了验证，即该机构收集的10名受试者以及来自阿尔茨海默病神经影像学倡议（ADNI）数据集的797张3T MR图像。具体而言，对于所有10名受试者的平均骰子系数，所提出的方法在WM、GM和CSF上分别达到了94.52%±0.9%、89.49%±1.83%和79.97%±4.32%，显著优于现有方法（p值<0.021）。对于ADNI数据集，组间差异比较表明所提出的算法优于现有分割方法。
作者开发并验证了一种用于3T脑MR图像分割的新型全自动方法。
