3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study

TL;DR

This paper presents a novel 3D fully convolutional neural network for efficient, accurate, and robust subcortical brain structure segmentation in MRI, validated on large-scale multi-site datasets with diverse demographics.

Contribution

It introduces a deep 3D CNN architecture with small kernels and multi-scale context modeling, enabling end-to-end training and superior performance on large, heterogeneous datasets.

Findings

Achieved state-of-the-art segmentation accuracy on ISBR dataset.

Demonstrated robustness across 1112 subjects from 17 sites with diverse demographics.

Provided faster segmentation compared to traditional atlas-based methods.

Abstract

This study investigates a 3D and fully convolutional neural network (CNN) for subcortical brain structure segmentation in MRI. 3D CNN architectures have been generally avoided due to their computational and memory requirements during inference. We address the problem via small kernels, allowing deeper architectures. We further model both local and global context by embedding intermediate-layer outputs in the final prediction, which encourages consistency between features extracted at different scales and embeds fine-grained information directly in the segmentation process. Our model is efficiently trained end-to-end on a graphics processing unit (GPU), in a single stage, exploiting the dense inference capabilities of fully CNNs. We performed comprehensive experiments over two publicly available datasets. First, we demonstrate a state-of-the-art performance on the ISBR dataset. Then, we report a {\em large-scale} multi-site evaluation over 1112 unregistered subject datasets acquired from 17 different sites (ABIDE dataset), with ages ranging from 7 to 64 years, showing that our method is robust to various acquisition protocols, demographics and clinical factors. Our method yielded segmentations that are highly consistent with a standard atlas-based approach, while running in a fraction of the time needed by atlas-based methods and avoiding registration/normalization steps. This makes it convenient for massive multi-site neuroanatomical imaging studies. To the best of our knowledge, our work is the first to study subcortical structure segmentation on such large-scale and heterogeneous data.