Generative Interpretation of Medical Images

Publication: ResearchPh.D. thesis – Annual report year: 2004

Standard

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@book{8c819fe7dba54d97b211d94aec772b95,
title = "Generative Interpretation of Medical Images",
author = "Stegmann, {Mikkel Bille} and Ersbøll, {Bjarne Kjær} and Rasmus Larsen",
year = "2004",

}

RIS

TY - BOOK

T1 - Generative Interpretation of Medical Images

A1 - Stegmann,Mikkel Bille

AU - Stegmann,Mikkel Bille

A2 - Ersbøll,Bjarne Kjær

A2 - Larsen,Rasmus

ED - Ersbøll,Bjarne Kjær

ED - Larsen,Rasmus

PY - 2004/6

Y1 - 2004/6

N2 - This thesis describes, proposes and evaluates methods for automated analysis and quantification of medical images. A common theme is the usage of generative methods, which draw inference from unknown images by synthesising new images having shape, pose and appearance similar to the analysed images. The theoretical framework for fulfilling these goals is based on the class of Active Appearance Models, which has been explored and extended in case studies involving cardiac and brain magnetic resonance images (MRI), and chest radiographs. Topics treated include model truncation, model compression using wavelets, handling of non-Gaussian variation by means of cluster analysis, correction of respiratory noise in cardiac MRI, and the extensions to multi-slice two-dimensional time-series and bi-temporal three-dimensional models. The medical applications include automated estimation of: left ventricular ejection fraction from 4D cardiac cine MRI, myocardial perfusion in bolus passage cardiac perfusion MRI, corpus callosum shape and area in mid-sagittal brain MRI, and finally, lung, heart, clavicle location and cardiothoracic ratio in anterior-posterior chest radiographs.

AB - This thesis describes, proposes and evaluates methods for automated analysis and quantification of medical images. A common theme is the usage of generative methods, which draw inference from unknown images by synthesising new images having shape, pose and appearance similar to the analysed images. The theoretical framework for fulfilling these goals is based on the class of Active Appearance Models, which has been explored and extended in case studies involving cardiac and brain magnetic resonance images (MRI), and chest radiographs. Topics treated include model truncation, model compression using wavelets, handling of non-Gaussian variation by means of cluster analysis, correction of respiratory noise in cardiac MRI, and the extensions to multi-slice two-dimensional time-series and bi-temporal three-dimensional models. The medical applications include automated estimation of: left ventricular ejection fraction from 4D cardiac cine MRI, myocardial perfusion in bolus passage cardiac perfusion MRI, corpus callosum shape and area in mid-sagittal brain MRI, and finally, lung, heart, clavicle location and cardiothoracic ratio in anterior-posterior chest radiographs.

UR - http://www.imm.dtu.dk/pubdb/p.php?3126

BT - Generative Interpretation of Medical Images

ER -