College of Electrical and Information, Northeast Agricultural University, Changjiang Road 600, Harbin, China.
School of Astronautics, Harin Institute of Technology, West Direct Street 92, Harbin, China.
Curr Med Imaging. 2021;17(3):342-351. doi: 10.2174/1573405616666200806171509.
The learning-based algorithms provide an ability to automatically estimate and refine GM, WM and CSF. The ground truth manually achieved from the 3T MR image may not be accurate and reliable with poor image intensity contrast. It will seriously influence the classification performance because the supervised learning-based algorithms extremely rely on the ground truth. Recently, the 7T MR images brings about the excellent image intensity contrast, while Structured Random Forest (SRF) performs the pixel-level classification and achieves structural and contextual information in images.
In this paper, a automatic segmentation algorithm is proposed based on ground truth achieved by the corresponding 7T subjects for segmenting the 3T&1.5T brain tissues using SRF classifiers. Through taking advantage of the 7T brain MR images, we can achieve the highly accuracy and reliable ground truth and then implement the training of SRF classifiers. Our proposed algorithm effectively integrates the T1-weighed images along with the probability maps to train the SRF classifiers for brain tissue segmentation.
Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 95.14%±0.9%, 90.17%±1.83%, and 81.96%±4.32% for WM, GM, and CSF. With the experiment results, the proposed algorithm can achieve better performances than other automatic segmentation methods. Further experiments are performed on the 200 3T&1.5T brain MR images of ADNI dataset and our proposed method shows promised performances.
The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.
基于学习的算法提供了自动估计和细化 GM、WM 和 CSF 的能力。从 3T MR 图像手动获得的真值可能由于图像强度对比度差而不准确和不可靠。这将严重影响分类性能，因为基于监督学习的算法极其依赖于真值。最近，7T MR 图像带来了出色的图像强度对比度，而结构化随机森林（SRF）执行像素级分类，并在图像中获得结构和上下文信息。
在本文中，提出了一种基于对应 7T 受试者获得的真值的自动分割算法，用于使用 SRF 分类器对 3T 和 1.5T 大脑组织进行分割。通过利用 7T 大脑 MR 图像，我们可以获得高度准确和可靠的真值，然后对 SRF 分类器进行训练。我们提出的算法有效地将 T1 加权图像与概率图结合起来，用于训练 SRF 分类器进行脑组织分割。
具体来说，对于所有 10 个受试者的平均 Dice 比，所提出的方法分别实现了 95.14%±0.9%、90.17%±1.83%和 81.96%±4.32%的 WM、GM 和 CSF。通过实验结果，所提出的算法可以比其他自动分割方法获得更好的性能。进一步在 ADNI 数据集的 200 个 3T 和 1.5T 大脑 MR 图像上进行实验，所提出的方法表现出有前景的性能。
作者已经开发并验证了一种用于 3T 大脑 MR 图像分割的全新全自动方法。
