4.7 Article

Deep learning with multiresolution handcrafted features for brain MRI segmentation

Journal

ARTIFICIAL INTELLIGENCE IN MEDICINE
Volume 131, Issue -, Pages -

Publisher

ELSEVIER
DOI: 10.1016/j.artmed.2022.102365

Keywords

CNN; Contourlet; Shearlet; Segmentation; MR

Funding

  1. Swiss National Science Foundation, Switzerland [320030_176052]
  2. SNSF
  3. Swiss National Science Foundation (SNF) [320030_176052] Funding Source: Swiss National Science Foundation (SNF)

Ask authors/readers for more resources

This study proposes an approach that combines multiresolution features and CNN-based features to efficiently segment the brain into three tissue classes. The results demonstrate significant improvement in bone class segmentation compared to other methods, and suggest that NSST coefficients provide more useful information than NSCT coefficients.
The segmentation of magnetic resonance (MR) images is a crucial task for creating pseudo computed tomography (CT) images which are used to achieve positron emission tomography (PET) attenuation correction. One of the main challenges of creating pseudo CT images is the difficulty to obtain an accurate segmentation of the bone tissue in brain MR images. Deep convolutional neural networks (CNNs) have been widely and efficiently applied to perform MR image segmentation. The aim of this work is to propose a segmentation approach that combines multiresolution handcrafted features with CNN-based features to add directional properties and enrich the set of features to perform segmentation. The main objective is to efficiently segment the brain into three tissue classes: bone, soft tissue, and air. The proposed method combines non subsampled Contourlet (NSCT) and non subsampled Shearlet (NSST) coefficients with CNN's features using different mechanisms. The entropy value is calculated to select the most useful coefficients and reduce the input's dimensionality. The segmentation results are evaluated using fifty clinical brain MR and CT images by calculating the precision, recall, dice similarity coefficient (DSC), and Jaccard similarity coefficient (JSC). The results are also compared to other methods reported in the literature. The DSC of the bone class is improved from 0.6179 & PLUSMN; 0.0006 to 0.6416 & PLUSMN; 0.0006. The addition of multiresolution features of NSCT and NSST with CNN's features demonstrates promising results. Moreover, NSST coefficients provide more useful information than NSCT coefficients.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available