Cross-Linked Fully Convolution-DenseNet for Volumetric Segmentation of Brain MRI 


Vol. 45,  No. 3, pp. 504-507, Mar.  2020
10.7840/kics.2020.45.3.504


PDF
  Abstract

Automatic brain tissue segmentation in brain MRI is one of challenging issues of segmentation task due to thin sheet structure, intensity inhomogeneity and low contrast between intensity and saturation. Addressing the above problems, this paper introduces cross-linked fully convolution-DenseNet(cross-linked FC-DenseNet) based on the advantages of to models, 3D FC-DenseNet and HyperDenseNet, for the purpose of automatically accurate brain tissue MRI segmentation. As a result of experiments using MRBrainS13, iSeg_2019 dataset, the proposed method performs better in terms of accuracy than existing methods.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

T. L. Phan, S. Ahn, J. Shin, "Cross-Linked Fully Convolution-DenseNet for Volumetric Segmentation of Brain MRI," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 3, pp. 504-507, 2020. DOI: 10.7840/kics.2020.45.3.504.

[ACM Style]

Trung Le Phan, Sangil Ahn, and Jitae Shin. 2020. Cross-Linked Fully Convolution-DenseNet for Volumetric Segmentation of Brain MRI. The Journal of Korean Institute of Communications and Information Sciences, 45, 3, (2020), 504-507. DOI: 10.7840/kics.2020.45.3.504.

[KICS Style]

Trung Le Phan, Sangil Ahn, Jitae Shin, "Cross-Linked Fully Convolution-DenseNet for Volumetric Segmentation of Brain MRI," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 3, pp. 504-507, 3. 2020. (https://doi.org/10.7840/kics.2020.45.3.504)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880