U-SegNet: Fully Convolutional Neural Network based Automated Brain tissue segmentation Tool
This work addresses the challenge of segmenting thin gray matter structures and smooth tissue boundaries in brain MRI for diagnosing neuro-disorders, representing an incremental improvement.
The paper tackled the problem of automated brain tissue segmentation from MRI by proposing U-SegNet, a hybrid of SegNet and U-Net architectures, which achieved an average dice ratio of 89.74% on the IBSR dataset.
Automated brain tissue segmentation into white matter (WM), gray matter (GM), and cerebro-spinal fluid (CSF) from magnetic resonance images (MRI) is helpful in the diagnosis of neuro-disorders such as epilepsy, Alzheimer's, multiple sclerosis, etc. However, thin GM structures at the periphery of cortex and smooth transitions on tissue boundaries such as between GM and WM, or WM and CSF pose difficulty in building a reliable segmentation tool. This paper proposes a Fully Convolutional Neural Network (FCN) tool, that is a hybrid of two widely used deep learning segmentation architectures SegNet and U-Net, for improved brain tissue segmentation. We propose a skip connection inspired from U-Net, in the SegNet architetcure, to incorporate fine multiscale information for better tissue boundary identification. We show that the proposed U-SegNet architecture, improves segmentation performance, as measured by average dice ratio, to 89.74% on the widely used IBSR dataset consisting of T-1 weighted MRI volumes of 18 subjects.