Dataset Information

Automatic Segmentation of Corpus Callosum in Midsagittal Based on Bayesian Inference Consisting of Sparse Representation Error and Multi-Atlas Voting.

ABSTRACT: In this paper, we introduce a novel automatic method for Corpus Callosum (CC) in midsagittal plane segmentation. The robust segmentation of CC in midsagittal plane is key role for quantitative study of structural features of CC associated with various neurological disorder such as epilepsy, autism, Alzheimer's disease, and so on. Our approach is based on Bayesian inference using sparse representation and multi-atlas voting which both methods are used in various medical imaging, and show outstanding performance. Prior information in the proposed Bayesian inference is obtained from probability map generated from multi-atlas voting. The probability map contains the information of shape and location of CC of target image. Likelihood in the proposed Bayesian inference is obtained from gamma distribution function, generated from reconstruction errors (or sparse representation error), which are calculated in sparse representation of target patch using foreground dictionary and background dictionary each. Unlike the usual sparse representation method, we added gradient magnitude and gradient direction information to the patches of dictionaries and target, which had better segmentation performance than when not added. We compared three main segmentation results as follow: (1) the joint label fusion (JLF) method which is state-of-art method in multi-atlas voting based segmentation for evaluation of our method; (2) prior information estimated from multi-atlas voting only; (3) likelihood estimated from comparison of the reconstruction errors from sparse representation error only; (4) the proposed Bayesian inference. The methods were evaluated using two data sets of T1-weighted images, which one data set consists of 100 normal young subjects and the other data set consist of 25 normal old subjects and 22 old subjects with heavy drinker. In both data sets, the proposed Bayesian inference method has significantly the best segmentation performance than using each method separately.

SUBMITTER: Park G

PROVIDER: S-EPMC6142891 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic Segmentation of Corpus Callosum in Midsagittal Based on Bayesian Inference Consisting of Sparse Representation Error and Multi-Atlas Voting.

Park Gilsoon G Kwak Kichang K Seo Sang Won SW Lee Jong-Min JM

Frontiers in neuroscience 20180911

In this paper, we introduce a novel automatic method for Corpus Callosum (CC) in midsagittal plane segmentation. The robust segmentation of CC in midsagittal plane is key role for quantitative study of structural features of CC associated with various neurological disorder such as epilepsy, autism, Alzheimer's disease, and so on. Our approach is based on Bayesian inference using sparse representation and multi-atlas voting which both methods are used in various medical imaging, and show outstand ...[more]

PMID: 30271320

Similar Datasets

Project description:The Corpus Callosum (CC) is an important structure that includes the majority of fibers connecting the two brain hemispheres. Several neurodegenerative diseases may alter CC size and morphology leading to its atrophy and malfunction which may play a role in the pathological manifestations found in these diseases. The purpose of the current study is to determine any possible changes in CC size in patients suffering from Alzheimer's disease. The Study also investigated the effect of acetylcholinesterase inhibitors (AChEIs) on the size of CC and its association with improvement in the Alzheimer disease severity scores. Midsagittal size of CC were recorded prospectively from 439 routine T1-weighted MRI brain images in normal individuals. The internal skull surface was measured to calculate CC/ internal skull surface ratio. Two groups of patients were studied: 300 (150 male / 150 female) were healthy subjects and 130 (55 males / 75 females) had Alzheimer disease. Out of the 130 Alzheimer disease pateints, 70 patients were treated with Donepezil or Rivastigmine or both. The size of the CC was measured based on T1-weighted MRI images after the treatment to investigate any possible improvement in CC size. The mean surface area of CC in controls was 6.53±1.105 cm2. There was no significant difference between males and females (P < 0.627), and CC/ internal skull surface ratio was 4.41±0.77%. Patients with mild or severe Alzheimer disease showed a significant reduction in CC size compared to healthy controls. Treating mild Alzheimer patients with either Donepezil or Rivastigmine exerts a comparable therapeutic effect in improving the CC size. There was more improvement in the size of CC in patients with severe Alzheimer disease by using combined therapy of Donepezil and Rivastigmine than using single a medication. we measured the mean size of the various portions of the corpus callosum in normal individuals and Alzheimer patients before and after taking Donepezil and Rivastigmine. Alzheimer patients have pronounced reduction in CC which is corrected after taking Donepezil and Rivastigmine leading to remarkable improvement in Alzheimer disease severity scores.

Dataset Information

Automatic Segmentation of Corpus Callosum in Midsagittal Based on Bayesian Inference Consisting of Sparse Representation Error and Multi-Atlas Voting.

Publications

Automatic Segmentation of Corpus Callosum in Midsagittal Based on Bayesian Inference Consisting of Sparse Representation Error and Multi-Atlas Voting.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets