Rao Vishwanatha M, Wan Zihan, Arabshahi Soroush, Ma David J, Lee Pin-Yu, Tian Ye, Zhang Xuzhe, Laine Andrew F, Guo Jia
Department of Biomedical Engineering, Columbia University, New York, NY, United States.
Department of Applied Mathematics, Columbia University, New York, NY, United States.
Front Neuroimaging. 2022 Nov 21;1:1023481. doi: 10.3389/fnimg.2022.1023481. eCollection 2022.
Brain tissue segmentation has demonstrated great utility in quantifying MRI data by serving as a precursor to further post-processing analysis. However, manual segmentation is highly labor-intensive, and automated approaches, including convolutional neural networks (CNNs), have struggled to generalize well due to properties inherent to MRI acquisition, leaving a great need for an effective segmentation tool. This study introduces a novel CNN-Transformer hybrid architecture designed to improve brain tissue segmentation by taking advantage of the increased performance and generality conferred by Transformers for 3D medical image segmentation tasks. We first demonstrate the superior performance of our model on various T1w MRI datasets. Then, we rigorously validate our model's generality applied across four multi-site T1w MRI datasets, covering different vendors, field strengths, scan parameters, and neuropsychiatric conditions. Finally, we highlight the reliability of our model on test-retest scans taken in different time points. In all situations, our model achieved the greatest generality and reliability compared to the benchmarks. As such, our method is inherently robust and can serve as a valuable tool for brain related T1w MRI studies. The code for the TABS network is available at: https://github.com/raovish6/TABS.
脑组织分割作为进一步后处理分析的预处理步骤，在量化MRI数据方面已展现出巨大效用。然而，手动分割劳动强度极大，而包括卷积神经网络（CNN）在内的自动化方法，由于MRI采集的固有特性，在泛化方面存在困难，因此迫切需要一种有效的分割工具。本研究引入了一种新颖的CNN-Transformer混合架构，旨在利用Transformer在3D医学图像分割任务中带来的更高性能和泛化能力，改进脑组织分割。我们首先展示了我们的模型在各种T1加权MRI数据集上的卓越性能。然后，我们严格验证了我们的模型在四个多站点T1加权MRI数据集上的泛化能力，这些数据集涵盖了不同的供应商、场强、扫描参数和神经精神疾病。最后，我们强调了我们的模型在不同时间点进行的重测扫描中的可靠性。在所有情况下，与基准相比，我们的模型都实现了最佳的泛化能力和可靠性。因此，我们的方法本质上具有鲁棒性，可作为脑相关T1加权MRI研究的宝贵工具。TABS网络的代码可在以下网址获取：https://github.com/raovish6/TABS 。
