Automatic recognition of corpus callosum from sagittal brain MR images

Chulhee Lee; Michael A. Unser; Terence A. Ketter

Automatic recognition of corpus callosum from sagittal brain MR images

Chulhee Lee, Michael A. Unser, Terence A. Ketter

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose a new method to find the corpus callosum from sagittal brain MR images automatically. First, we calculate the statistical characteristics of the corpus callosum and obtain shape information. The recognition algorithm consists of two stages: extracting regions satisfying the statistical characteristics (gray level distributions) of the corpus callosum, and finding a region matching the shape information. An innovative feature of the algorithm is that we adaptively relax the statistical requirement until we find a region matching the shape information. In order to match the shape information, we propose a new directed window region growing algorithm instead of using conventional contour matching. Experiments show promising results.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	Andrew G. Tescher
Pages	528-534
Number of pages	7
Volume	2564
Publication status	Published - 1995 Dec 1
Event	Applications of Digital Image Processing XVIII - San Diego, CA, USA Duration: 1995 Jul 12 → 1995 Jul 14

Other

Other	Applications of Digital Image Processing XVIII
City	San Diego, CA, USA
Period	95/7/12 → 95/7/14

Fingerprint

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Condensed Matter Physics

Cite this

Lee, C., Unser, M. A., & Ketter, T. A. (1995). Automatic recognition of corpus callosum from sagittal brain MR images. In A. G. Tescher (Ed.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2564, pp. 528-534)

@inproceedings{a762ed05f6ba4704aa1bb981fcf4fd60,

title = "Automatic recognition of corpus callosum from sagittal brain MR images",

abstract = "We propose a new method to find the corpus callosum from sagittal brain MR images automatically. First, we calculate the statistical characteristics of the corpus callosum and obtain shape information. The recognition algorithm consists of two stages: extracting regions satisfying the statistical characteristics (gray level distributions) of the corpus callosum, and finding a region matching the shape information. An innovative feature of the algorithm is that we adaptively relax the statistical requirement until we find a region matching the shape information. In order to match the shape information, we propose a new directed window region growing algorithm instead of using conventional contour matching. Experiments show promising results.",

author = "Chulhee Lee and Unser, {Michael A.} and Ketter, {Terence A.}",

year = "1995",

month = dec

day = "1",

language = "English",

isbn = "0819419230",

volume = "2564",

pages = "528--534",

editor = "Tescher, {Andrew G.}",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Applications of Digital Image Processing XVIII ; Conference date: 12-07-1995 Through 14-07-1995",

}

TY - GEN

T1 - Automatic recognition of corpus callosum from sagittal brain MR images

AU - Lee, Chulhee

AU - Unser, Michael A.

AU - Ketter, Terence A.

PY - 1995/12/1

Y1 - 1995/12/1

N2 - We propose a new method to find the corpus callosum from sagittal brain MR images automatically. First, we calculate the statistical characteristics of the corpus callosum and obtain shape information. The recognition algorithm consists of two stages: extracting regions satisfying the statistical characteristics (gray level distributions) of the corpus callosum, and finding a region matching the shape information. An innovative feature of the algorithm is that we adaptively relax the statistical requirement until we find a region matching the shape information. In order to match the shape information, we propose a new directed window region growing algorithm instead of using conventional contour matching. Experiments show promising results.

AB - We propose a new method to find the corpus callosum from sagittal brain MR images automatically. First, we calculate the statistical characteristics of the corpus callosum and obtain shape information. The recognition algorithm consists of two stages: extracting regions satisfying the statistical characteristics (gray level distributions) of the corpus callosum, and finding a region matching the shape information. An innovative feature of the algorithm is that we adaptively relax the statistical requirement until we find a region matching the shape information. In order to match the shape information, we propose a new directed window region growing algorithm instead of using conventional contour matching. Experiments show promising results.

UR - http://www.scopus.com/inward/record.url?scp=0029518130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029518130&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029518130

SN - 0819419230

SN - 9780819419231

VL - 2564

SP - 528

EP - 534

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Tescher, Andrew G.

T2 - Applications of Digital Image Processing XVIII

Y2 - 12 July 1995 through 14 July 1995

ER -

Automatic recognition of corpus callosum from sagittal brain MR images

Abstract

Other

Fingerprint

All Science Journal Classification (ASJC) codes

Cite this

Access to Document