Lauge Sørensen from the eScience Center defended his PhD "Pattern Recognition-Based Analysis of COPD in CT"
Research in medical diagnosis by means of image processing is facing a big breakthrough. PhD student Lauge Sørensen and his research colleagues from the eScience Centre at DIKU have developed a new efficient method of diagnosis of the lung disease COPD - also known as smoker's lungs.
Lauge defended his PhD "Pattern Recognition-Based Analysis of COPD in CT" which describes various aspects of the new method at DIKU on October 11th, 2010.
The thesis presents several methods for texture-based quantification of emphysema and/or COPD in CT images of the lungs.
The methods rely on image processing and pattern recognition.
The dark areas of the lungs appearing in the CT-scans indicate a high possibility of COPD.
The image processing part deals with characterizing the lung tissue texture using a suitable texture descriptor. Two types of descriptors are considered, the local binary pattern histogram and histograms of filter responses from a multi-scale Gaussian derivative filter bank. The pattern recognition part is used to turn the texture measures into a quantitative measure of disease. Different classification systems are considered, and the pattern recognition concepts of supervised learning, multiple instance learning, and dissimilarity representation-based classification were used in particular.
The PhD has been made in collaboration with computer scientists at the University of Copenhagen (DIKU and the eScience Centre) and medical researchers among others from Gentofte University Hospital and AstraZeneca in Lund, Sverige.
In Denmark about 430.000 people suffer from COPD. In about 80 percent of the cases the disease is caused by smoking, but the disease can also be brought on by exposure to lung damaging materials - for example at the workplace. Treatment possibilities are limited because the disease often is not discovered until it is relatively serious. WHO expects that worldwide COPD will be the third most common cause of death before 2020.
PhD student Lauge Sørensen
Tel: 35 32 07 39 / mobile: 61 68 71 08
For an electronic copy of the thesis, please contact Dina Riis Johannessen, email@example.com.