An attention-based context-informed deep framework for infant brain subcortical segmentation

Precise segmentation of subcortical structures from infant brain magnetic resonance (MR) images plays an essen-tial 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 struc-tures. 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 tar-get 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.

Automated summary

In this study, a context-guided, attention-based, coarse-to-fine deep framework is proposed to accurately segment subcortical structures from infant brain magnetic resonance (MR) images. The framework utilizes a SDM-Unet to predict signed distance maps (SDMs) at the coarse stage, which are then integrated with multi-modal intensity images to refine the segmentation using a multi-source and multi-path attention Unet (M2A-Unet) at the fine stage. The proposed framework achieves higher segmentation accuracy and exhibits good generalizability in both qualitative and quantitative evaluations.