Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
Neuroimage. 2023 Apr 1;269:119931. doi: 10.1016/j.neuroimage.2023.119931. Epub 2023 Feb 4.
Precise segmentation of subcortical structures from infant brain magnetic resonance (MR) images plays an essential role in studying early subcortical structural and functional developmental patterns and diagnosis of related brain disorders. However, due to the dynamic appearance changes, low tissue contrast, and tiny subcortical size in infant brain MR images, infant subcortical segmentation is a challenging task. In this paper, we propose a context-guided, attention-based, coarse-to-fine deep framework to precisely segment the infant subcortical structures. At the coarse stage, we aim to directly predict the signed distance maps (SDMs) from multi-modal intensity images, including T1w, T2w, and the ratio of T1w and T2w images, with an SDM-Unet, which can leverage the spatial context information, including the structural position information and the shape information of the target structure, to generate high-quality SDMs. At the fine stage, the predicted SDMs, which encode spatial-context information of each subcortical structure, are integrated with the multi-modal intensity images as the input to a multi-source and multi-path attention Unet (M2A-Unet) for achieving refined segmentation. Both the 3D spatial and channel attention blocks are added to guide the M2A-Unet to focus more on the important subregions and channels. We additionally incorporate the inner and outer subcortical boundaries as extra labels to help precisely estimate the ambiguous boundaries. We validate our method on an infant MR image dataset and on an unrelated neonatal MR image dataset. Compared to eleven state-of-the-art methods, the proposed framework consistently achieves higher segmentation accuracy in both qualitative and quantitative evaluations of infant MR images and also exhibits good generalizability in the neonatal dataset.
精确分割婴儿脑磁共振（MR）图像的皮质下结构对于研究早期皮质下结构和功能发育模式以及诊断相关脑疾病至关重要。然而，由于婴儿脑 MR 图像中的动态外观变化、低组织对比度和微小的皮质下尺寸，婴儿皮质下分割是一项具有挑战性的任务。在本文中，我们提出了一种基于上下文引导、注意力机制的粗到精深度框架，用于精确分割婴儿皮质下结构。在粗阶段，我们旨在直接从多模态强度图像（包括 T1w、T2w 和 T1w 与 T2w 图像的比值）预测符号距离图（SDM），使用 SDM-Unet 可以利用空间上下文信息，包括目标结构的结构位置信息和形状信息，生成高质量的 SDM。在精细阶段，预测的 SDM 编码了每个皮质下结构的空间上下文信息，与多模态强度图像一起作为输入，输入到多源多路径注意力 U 型网络（M2A-Unet）中，以实现精细分割。我们还添加了 3D 空间注意力块和通道注意力块，以引导 M2A-Unet 更加关注重要的子区域和通道。我们还将内外皮质下边界作为额外的标签，以帮助更准确地估计模糊边界。我们在婴儿 MR 图像数据集和不相关的新生儿 MR 图像数据集上验证了我们的方法。与十一种最先进的方法相比，所提出的框架在婴儿 MR 图像的定性和定量评估中始终实现了更高的分割精度，并且在新生儿数据集上也表现出良好的泛化能力。
