Brain Tissue Segmentation Using NeuroNet With Different Pre-processing Techniques

TL;DR

This paper presents a NeuroNet-based approach for brain tissue segmentation in MRI images, emphasizing the impact of pre-processing techniques and hyper-parameter tuning on segmentation accuracy, validated on the IBSR18 dataset.

Contribution

It introduces specific pre-processing pipelines and hyper-parameter tuning strategies to enhance NeuroNet's performance in brain tissue segmentation.

Findings

Achieved average DSC of 0.84 for CSF, 0.94 for GM, and 0.94 for WM.

Pre-processing and hyper-parameter tuning improve segmentation accuracy.

Validated on IBSR18 dataset with quantitative metrics.

Abstract

Automatic segmentation of brain Magnetic Resonance Imaging (MRI) images is one of the vital steps for quantitative analysis of brain for further inspection. In this paper, NeuroNet has been adopted to segment the brain tissues (white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF)) which uses Residual Network (ResNet) in encoder and Fully Convolution Network (FCN) in the decoder. To achieve the best performance, various hyper-parameters have been tuned, while, network parameters (kernel and bias) were initialized using the NeuroNet pre-trained model. Different pre-processing pipelines have also been introduced to get a robust trained model. The model has been trained and tested on IBSR18 data-set. To validate the research outcome, performance was measured quantitatively using Dice Similarity Coefficient (DSC) and is reported on average as 0.84 for CSF, 0.94 for GM, and 0.94 for WM. The outcome of the research indicates that for the IBSR18 data-set, pre-processing and proper tuning of hyper-parameters for NeuroNet model have improvement in DSC for the brain tissue segmentation.