Ischemic Segment Detection using the Support Vector Domain Description

Michael Sass Hansen; Hildur Ólafsdóttir; Karl Sjöstrand; Henrik B. Larsson; Mikkel Bille Stegmann; Rasmus Larsen; The International Society for Optical Engineering (SPIE)

Ischemic Segment Detection using the Support Vector Domain Description

Michael Sass Hansen
, Hildur Ólafsdóttir
, Karl Sjöstrand
, Henrik B. Larsson
, Mikkel Bille Stegmann
, Rasmus Larsen
, The International Society for Optical Engineering (SPIE) (Editor)

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Myocardial perfusion Magnetic Resonance (MR) imaging has proven to be a powerful method to assess coronary artery diseases. The current work presents a novel approach to the analysis of registered sequences of myocardial perfusion MR images. A previously reported AAM-based segmentation and registration of the myocardium provided pixel-wise signal intensity curves that were analyzed using the Support Vector Domain Description (SVDD). In contrast to normal SVDD, the entire regularization path was calculated and used to calculate a generalized distance. The results corresponded well to the ischemic segments found by assessment of the three common perfusion parameters; maximum upslope, peak and time-to-peak obtained pixel-wise.

Original language	English
Title of host publication	International Symposium on Medical Imaging
Publication date	2007
Publication status	Published - 2007
Event	SPIE Medical Imaging 2007 - Town & Country Hotel, San Diego, United States Duration: 17 Feb 2007 → 22 Feb 2007

Conference

Conference	SPIE Medical Imaging 2007
Location	Town & Country Hotel
Country/Territory	United States
City	San Diego
Period	17/02/2007 → 22/02/2007

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{35c346eef1f84a10bac344fa8e97ac52,

title = "Ischemic Segment Detection using the Support Vector Domain Description",

abstract = "Myocardial perfusion Magnetic Resonance (MR) imaging has proven to be a powerful method to assess coronary artery diseases. The current work presents a novel approach to the analysis of registered sequences of myocardial perfusion MR images. A previously reported AAM-based segmentation and registration of the myocardium provided pixel-wise signal intensity curves that were analyzed using the Support Vector Domain Description (SVDD). In contrast to normal SVDD, the entire regularization path was calculated and used to calculate a generalized distance. The results corresponded well to the ischemic segments found by assessment of the three common perfusion parameters; maximum upslope, peak and time-to-peak obtained pixel-wise.",

author = "Hansen, \{Michael Sass\} and Hildur {\'O}lafsd{\'o}ttir and Karl Sj{\"o}strand and Larsson, \{Henrik B.\} and Stegmann, \{Mikkel Bille\} and Rasmus Larsen and (SPIE), \{The International Society for Optical Engineering\}",

year = "2007",

language = "English",

booktitle = "International Symposium on Medical Imaging",

note = "SPIE Medical Imaging 2007 ; Conference date: 17-02-2007 Through 22-02-2007",

}

TY - GEN

T1 - Ischemic Segment Detection using the Support Vector Domain Description

AU - Hansen, Michael Sass

AU - Ólafsdóttir, Hildur

AU - Sjöstrand, Karl

AU - Larsson, Henrik B.

AU - Stegmann, Mikkel Bille

AU - Larsen, Rasmus

A2 - (SPIE), The International Society for Optical Engineering

PY - 2007

Y1 - 2007

N2 - Myocardial perfusion Magnetic Resonance (MR) imaging has proven to be a powerful method to assess coronary artery diseases. The current work presents a novel approach to the analysis of registered sequences of myocardial perfusion MR images. A previously reported AAM-based segmentation and registration of the myocardium provided pixel-wise signal intensity curves that were analyzed using the Support Vector Domain Description (SVDD). In contrast to normal SVDD, the entire regularization path was calculated and used to calculate a generalized distance. The results corresponded well to the ischemic segments found by assessment of the three common perfusion parameters; maximum upslope, peak and time-to-peak obtained pixel-wise.

AB - Myocardial perfusion Magnetic Resonance (MR) imaging has proven to be a powerful method to assess coronary artery diseases. The current work presents a novel approach to the analysis of registered sequences of myocardial perfusion MR images. A previously reported AAM-based segmentation and registration of the myocardium provided pixel-wise signal intensity curves that were analyzed using the Support Vector Domain Description (SVDD). In contrast to normal SVDD, the entire regularization path was calculated and used to calculate a generalized distance. The results corresponded well to the ischemic segments found by assessment of the three common perfusion parameters; maximum upslope, peak and time-to-peak obtained pixel-wise.

M3 - Article in proceedings

BT - International Symposium on Medical Imaging

T2 - SPIE Medical Imaging 2007

Y2 - 17 February 2007 through 22 February 2007

ER -

Ischemic Segment Detection using the Support Vector Domain Description

Abstract

Conference

OpenUrl availability

Fingerprint

Cite this