Attention-based convolutional neural network for perfusion T2-weighted MR images preprocessing

03/04/2023
by   Svitlana Alkhimova, et al.
0

Accurate skull-stripping is crucial preprocessing in dynamic susceptibility contrast-enhanced perfusion magnetic resonance data analysis. The presence of non-brain tissues impacts the perfusion parameters assessment. In this study, we propose different integration strategies for the spatial and channel squeeze and excitation attention mechanism into the baseline U-Net+ResNet neural network architecture to provide automatic skull-striping i.e., Standard scSE, scSE-PRE, scSE-POST, and scSE Identity strategies of plugging of scSE block into the ResNet backbone. We comprehensively investigate the performance of skull-stripping in T2-star weighted MR images with abnormal brain anatomy. The comparison that utilizing any of the proposed strategies provides the robustness of skull-stripping. However, the scSE-POST integration strategy provides the best result with an average Dice Coefficient of 0.9810.

READ FULL TEXT
research
08/04/2021

Automatic hemisphere segmentation in rodent MRI with lesions

We present MedicDeepLabv3+, a convolutional neural network that is the f...
research
04/16/2018

Classifying magnetic resonance image modalities with convolutional neural networks

Magnetic Resonance (MR) imaging allows the acquisition of images with di...
research
10/25/2018

Training of a Skull-Stripping Neural Network with efficient data augmentation

Skull-stripping methods aim to remove the non-brain tissue from acquisit...
research
03/26/2019

CUSUM Filter for Brain Segmentation on DSC Perfusion MR Head Scans with Abnormal Brain Anatomy

This paper presents a new approach for relatively accurate brain region ...
research
04/11/2017

Automatic segmentation of MR brain images with a convolutional neural network

Automatic segmentation in MR brain images is important for quantitative ...
research
07/08/2019

Brain Tissues Segmentation on MR Perfusion Images Using CUSUM Filter for Boundary Pixels

The fully automated and relatively accurate method of brain tissues segm...
research
08/22/2019

Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation

Most MRI liver segmentation methods use a structural 3D scan as input, s...

Please sign up or login with your details

Forgot password? Click here to reset