A Robust Spatial Information-Theoretic GMM Algorithm for Bias Field Estimation and Brain MRI Segmentation

Due to their simplicity and flexibility, the unsupervised statistical models such as Gaussian mixture model (GMM) are powerful tools to address the brain magnetic resonance (MR) images segmentation problems. However, the GMM is based only on the intensity information, which makes it sensitive to noise. Lots of GMM-based segmentation algorithms have the low segmentation accuracy because of the influence caused by noise and intensity inhomogeneity. To further improve the segmentation accuracy, a robust spatial information-theoretic GMM algorithm is proposed in this paper to simultaneously estimate the intensity inhomogeneity and segment brain MR images. First, a novel spatial factor containing the non-local spatial information is incorporated to reduce the impact of noise. The proposed spatial factor not only takes into account the local neighboring information, but also considers the spatial structure information of pixels. Thus, our algorithm can retain more image details while reducing the influence of noise. Second, the mutual information (MI) maximization method is used to identify and eliminate outliers. Finally, to overcome the impact of intensity inhomogeneity, we use a linear combination of a set of orthogonal polynomials to approximate the bias field. The objective function is integrated with the bias field estimation model to segment the images and estimate the bias field simultaneously. The experimental results on both synthetic and clinical brain MR images show that the proposed algorithm can overcome the influence of noise and intensity inhomogeneity, and achieve more accurate segmentation results.

• Publication year

  2020

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1109/ACCESS.2020.2993540
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A scalable region-based level set method using adaptive bilateral filter for noisy image segmentation

  2019cited by this paper
• A matting method based on full feature coverage

  2018cited by this paper
• A novel region-based active contour model via local patch similarity measure for image segmentation

  2018cited by this paper
• A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation

  2018cited by this paper
• Robust generative asymmetric GMM for brain MR image segmentation

  2017cited by this paper
• A modified MRF segmentation of brain MR images

  2017cited by this paper
• A review on brain structures segmentation in magnetic resonance imaging

  2016cited by this paper
• Bounded asymmetric Gaussian mixture model with spatial constraint for image segmentation

  2016cited by this paper
• A unified Bayesian mixture model framework via spatial information for grayscale image segmentation

  2016influential reference
• Non-local-based spatially constrained hierarchical fuzzy C-means method for brain magnetic resonance imaging segmentation

  2016cited by this paper
• A Bayesian Bounded Asymmetric Mixture Model With Segmentation Application

  2014cited by this paper
• Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation.

  2014cited by this paper
• Robust spatially constrained fuzzy c-means algorithm for brain MR image segmentation

  2014cited by this paper
• Fast and Robust Spatially Constrained Gaussian Mixture Model for Image Segmentation

  2013influential reference
• Atlas-Based Segmentation of Degenerated Lumbar Intervertebral Discs From MR Images of the Spine

  2009cited by this paper
• A robust parametric method for bias field estimation and segmentation of MR images

  2009cited by this paper
• Adaptive spatial information-theoretic clustering for image segmentation

  2009cited by this paper
• Finite Mixture Models

  2008cited by this paper
• A Spatially Constrained Generative Model and an EM Algorithm for Image Segmentation

  2007cited by this paper
• A Review of Methods for Correction of Intensity Inhomogeneity in MRI

  2007cited by this paper
• Segmentation of Brain MR Images Using a Charged Fluid Model

  2007cited by this paper
• A Class-Adaptive Spatially Variant Mixture Model for Image Segmentation

  2007influential reference
• A possibilistic fuzzy c-means clustering algorithm

  2005cited by this paper
• A Robust Information Clustering Algorithm

  2005cited by this paper
• Adaptive model initialization and deformation for automatic segmentation of T1-weighted brain MRI data

  2005cited by this paper
• A spatially constrained mixture model for image segmentation

  2005cited by this paper
• Classification of anatomical structures in mr brain images using fuzzy parameters

  2004cited by this paper
• Automated model-based bias field correction of MR images of the brain

  1999influential reference
• Bias field estimation and adaptive segmentation of MRI data using a modified fuzzy C-means algorithm

  1999cited by this paper
• Bayesian pixel classification using spatially variant finite mixtures and the generalized EM algorithm

  1998cited by this paper
• A gaussian-mixture-based image segmentation algorithm

  1998cited by this paper
• The EM algorithm and extensions

  1996cited by this paper
• Adaptive Segmentation of MRI Data

  1995cited by this paper

• Gaussian Mixture Segmentation for Managing Deterioration of Large-Scale Road Networks

  2025cites this paper
• Hybrid Analysis for Detection of Alzheimer Disease Using Computer Aided Diagnostic Tool

  2024cites this paper
• Deep learning models and traditional automated techniques for brain tumor segmentation in MRI: a review

  2022cites this paper
• Brain Tumor Classification for MR Images using Convolution Neural Network with Global Average Pooling

  2021influential citation
• Aided Image Acquisition System for Aerobics Training Based on Motion Recognition Technology

  2020cites this paper