Gopinath Karthik, Desrosiers Christian, Lombaert Herve
ETS Montreal, Canada.
ETS Montreal, Canada.
Med Image Anal. 2023 Dec;90:102974. doi: 10.1016/j.media.2023.102974. Epub 2023 Sep 22.
Reconstructing and segmenting cortical surfaces from MRI is essential to a wide range of brain analyses. However, most approaches follow a multi-step slow process, such as a sequential spherical inflation and registration, which requires considerable computation times. To overcome the limitations arising from these multi-steps, we propose SegRecon, an integrated end-to-end deep learning method to jointly reconstruct and segment cortical surfaces directly from an MRI volume in one single step. We train a volume-based neural network to predict, for each voxel, the signed distances to multiple nested surfaces and their corresponding spherical representation in atlas space. This is, for instance, useful for jointly reconstructing and segmenting the white-to-gray-matter interface and the gray-matter-to-CSF (pial) surface. We evaluate the performance of our surface reconstruction and segmentation method with a comprehensive set of experiments on the MindBoggle, ABIDE and OASIS datasets. Our reconstruction error is found to be less than 0.52 mm and 0.97 mm in terms of average Hausdorff distance to the FreeSurfer generated surfaces. Likewise, the parcellation results show over 4% improvements in average Dice with respect to FreeSurfer, in addition to an observed drastic speed-up from hours to seconds of computation on a standard desktop station.
从磁共振成像（MRI）中重建和分割皮质表面对于广泛的脑分析至关重要。然而，大多数方法都遵循多步骤的缓慢过程，例如顺序球面膨胀和配准，这需要相当长的计算时间。为了克服这些多步骤带来的局限性，我们提出了SegRecon，这是一种集成的端到端深度学习方法，可在单个步骤中直接从MRI体积中联合重建和分割皮质表面。我们训练了一个基于体积的神经网络，以预测每个体素到多个嵌套表面的有符号距离及其在图谱空间中的相应球面表示。例如，这对于联合重建和分割白质与灰质界面以及灰质与脑脊液（软脑膜）表面很有用。我们在MindBoggle、ABIDE和OASIS数据集上进行了一系列全面的实验，以评估我们的表面重建和分割方法的性能。我们发现，相对于FreeSurfer生成的表面，我们的重建误差在平均豪斯多夫距离方面小于0.52毫米和0.97毫米。同样，与FreeSurfer相比，分割结果在平均骰子系数方面提高了4%以上，此外，在标准台式机上的计算时间从数小时大幅缩短至数秒。
