Glomeruli segmentation based on neural network with fault tolerance analysis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Image segmentation, which is the first essential and fundamental issue in the image analysis and pattern recognition, is a classical difficult problem in image processing. In the computer-aided diagnosis system of the renal biopsy images in microscope, the correct segmentation of glomerulus is an important step for automatic analysis. Complex characteristics of renal biopsy images lead to the difficulty in boundary features description. A kind of feature operator based on the definition of the cavum boundary is proposed in this paper. According to this operator, a nonlinear thresholding surface can be constructed by neural network, and the appropriate surface can be selected to enhance the cavum boundary by the fault tolerance analysis. After denoising, the segmentation results can be obtained. Experimental results indicate that this method can enhance the boundary and suppress noises at the same time; it can obtain good segmented results and has a fine adaptability to various sample images.

Original languageEnglish
Title of host publicationProceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008
Pages401-404
Number of pages4
Volume1
DOIs
Publication statusPublished - 2008
Event2008 International Symposium on Computational Intelligence and Design, ISCID 2008 - Wuhan
Duration: 2008 Oct 172008 Oct 17

Other

Other2008 International Symposium on Computational Intelligence and Design, ISCID 2008
CityWuhan
Period08/10/1708/10/17

Fingerprint

Biopsy
Fault tolerance
Neural networks
Computer aided diagnosis
Image segmentation
Image analysis
Pattern recognition
Image processing
Microscopes

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Zhang, J., & Furuzuki, T. (2008). Glomeruli segmentation based on neural network with fault tolerance analysis. In Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008 (Vol. 1, pp. 401-404). [4725636] https://doi.org/10.1109/ISCID.2008.222

Glomeruli segmentation based on neural network with fault tolerance analysis. / Zhang, Jun; Furuzuki, Takayuki.

Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008. Vol. 1 2008. p. 401-404 4725636.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, J & Furuzuki, T 2008, Glomeruli segmentation based on neural network with fault tolerance analysis. in Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008. vol. 1, 4725636, pp. 401-404, 2008 International Symposium on Computational Intelligence and Design, ISCID 2008, Wuhan, 08/10/17. https://doi.org/10.1109/ISCID.2008.222
Zhang J, Furuzuki T. Glomeruli segmentation based on neural network with fault tolerance analysis. In Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008. Vol. 1. 2008. p. 401-404. 4725636 https://doi.org/10.1109/ISCID.2008.222
Zhang, Jun ; Furuzuki, Takayuki. / Glomeruli segmentation based on neural network with fault tolerance analysis. Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008. Vol. 1 2008. pp. 401-404
@inproceedings{6e1f44010f7542149263b662264f4a20,
title = "Glomeruli segmentation based on neural network with fault tolerance analysis",
abstract = "Image segmentation, which is the first essential and fundamental issue in the image analysis and pattern recognition, is a classical difficult problem in image processing. In the computer-aided diagnosis system of the renal biopsy images in microscope, the correct segmentation of glomerulus is an important step for automatic analysis. Complex characteristics of renal biopsy images lead to the difficulty in boundary features description. A kind of feature operator based on the definition of the cavum boundary is proposed in this paper. According to this operator, a nonlinear thresholding surface can be constructed by neural network, and the appropriate surface can be selected to enhance the cavum boundary by the fault tolerance analysis. After denoising, the segmentation results can be obtained. Experimental results indicate that this method can enhance the boundary and suppress noises at the same time; it can obtain good segmented results and has a fine adaptability to various sample images.",
author = "Jun Zhang and Takayuki Furuzuki",
year = "2008",
doi = "10.1109/ISCID.2008.222",
language = "English",
isbn = "9780769533117",
volume = "1",
pages = "401--404",
booktitle = "Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008",

}

TY - GEN

T1 - Glomeruli segmentation based on neural network with fault tolerance analysis

AU - Zhang, Jun

AU - Furuzuki, Takayuki

PY - 2008

Y1 - 2008

N2 - Image segmentation, which is the first essential and fundamental issue in the image analysis and pattern recognition, is a classical difficult problem in image processing. In the computer-aided diagnosis system of the renal biopsy images in microscope, the correct segmentation of glomerulus is an important step for automatic analysis. Complex characteristics of renal biopsy images lead to the difficulty in boundary features description. A kind of feature operator based on the definition of the cavum boundary is proposed in this paper. According to this operator, a nonlinear thresholding surface can be constructed by neural network, and the appropriate surface can be selected to enhance the cavum boundary by the fault tolerance analysis. After denoising, the segmentation results can be obtained. Experimental results indicate that this method can enhance the boundary and suppress noises at the same time; it can obtain good segmented results and has a fine adaptability to various sample images.

AB - Image segmentation, which is the first essential and fundamental issue in the image analysis and pattern recognition, is a classical difficult problem in image processing. In the computer-aided diagnosis system of the renal biopsy images in microscope, the correct segmentation of glomerulus is an important step for automatic analysis. Complex characteristics of renal biopsy images lead to the difficulty in boundary features description. A kind of feature operator based on the definition of the cavum boundary is proposed in this paper. According to this operator, a nonlinear thresholding surface can be constructed by neural network, and the appropriate surface can be selected to enhance the cavum boundary by the fault tolerance analysis. After denoising, the segmentation results can be obtained. Experimental results indicate that this method can enhance the boundary and suppress noises at the same time; it can obtain good segmented results and has a fine adaptability to various sample images.

UR - http://www.scopus.com/inward/record.url?scp=61349095432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61349095432&partnerID=8YFLogxK

U2 - 10.1109/ISCID.2008.222

DO - 10.1109/ISCID.2008.222

M3 - Conference contribution

AN - SCOPUS:61349095432

SN - 9780769533117

VL - 1

SP - 401

EP - 404

BT - Proceedings of the 2008 International Symposium on Computational Intelligence and Design, ISCID 2008

ER -