School of Computer Science and Engineering, Beihang University, Beijing, China.
Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, United States of America.
PLoS One. 2022 Aug 15;17(8):e0270339. doi: 10.1371/journal.pone.0270339. eCollection 2022.
MRI brain structure segmentation plays an important role in neuroimaging studies. Existing methods either spend much CPU time, require considerable annotated data, or fail in segmenting volumes with large deformation. In this paper, we develop a novel multi-atlas-based algorithm for 3D MRI brain structure segmentation. It consists of three modules: registration, atlas selection and label fusion. Both registration and label fusion leverage an integrated flow based on grayscale and SIFT features. We introduce an effective and efficient strategy for atlas selection by employing the accompanying energy generated in the registration step. A 3D sequential belief propagation method and a 3D coarse-to-fine flow matching approach are developed in both registration and label fusion modules. The proposed method is evaluated on five public datasets. The results show that it has the best performance in almost all the settings compared to competitive methods such as ANTs, Elastix, Learning to Rank and Joint Label Fusion. Moreover, our registration method is more than 7 times as efficient as that of ANTs SyN, while our label transfer method is 18 times faster than Joint Label Fusion in CPU time. The results on the ADNI dataset demonstrate that our method is applicable to image pairs that require a significant transformation in registration. The performance on a composite dataset suggests that our method succeeds in a cross-modality manner. The results of this study show that the integrated 3D flow-based method is effective and efficient for brain structure segmentation. It also demonstrates the power of SIFT features, multi-atlas segmentation and classical machine learning algorithms for a medical image analysis task. The experimental results on public datasets show the proposed method's potential for general applicability in various brain structures and settings.
MRI 脑结构分割在神经影像学研究中起着重要作用。现有的方法要么花费大量的 CPU 时间，要么需要大量的标注数据，要么无法对变形较大的体积进行分割。在本文中，我们开发了一种新的基于多图谱的 3D MRI 脑结构分割算法。它由三个模块组成：配准、图谱选择和标签融合。配准和标签融合都利用了基于灰度和 SIFT 特征的集成流。我们通过利用配准步骤中产生的伴随能量，提出了一种有效的图谱选择策略。在注册和标签融合模块中，开发了 3D 顺序置信传播方法和 3D 粗到精流匹配方法。在五个公共数据集上对所提出的方法进行了评估。结果表明，与 ANTs、Elastix、Learning to Rank 和 Joint Label Fusion 等竞争方法相比，该方法在几乎所有设置下都具有最佳性能。此外，我们的注册方法的效率比 ANTs SyN 高 7 倍以上，而我们的标签传输方法在 CPU 时间上比 Joint Label Fusion 快 18 倍。在 ADNI 数据集上的结果表明，我们的方法适用于在配准中需要显著变换的图像对。在组合数据集上的结果表明，我们的方法以跨模态的方式取得了成功。该研究的结果表明，基于集成 3D 流的方法对于脑结构分割是有效和高效的。它还证明了 SIFT 特征、多图谱分割和经典机器学习算法在医学图像分析任务中的强大功能。在公共数据集上的实验结果表明，该方法具有在各种脑结构和设置中广泛应用的潜力。
