Naslov
Disease Quantification by Automatic Segmentation of Lung CT Image

Autori
Mešanović, Nihad ; Huseinagić, Haris ; Kamenjaković, Samir

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, ostalo

Izvornik
4th Congress of Radiology of Bosnia and Herzegovina with International Participation Abstract Book / Vegar, Sandra - Sarajevo, 2011, 61-61

Skup
4th Congress of Radiology of Bosnia and Herzegovina with International Participation

Mjesto i datum
Sarajevo, Bosna i Hercegovina, 30.09.2011. - 02.10.2011

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Domaća recenzija

Ključne riječi
Disease Quantification; Region Growing Segmentation; Affine Registration; Non-rigid Registration

Sažetak
Lung segmentation from CT images is a powerful tool in medical imaging. It can be used in quantification of the lung disease progression, regression or stagnation, and in this work we presented comparison of two approaches, that we applied on the baseline and follow-up lung CT images. The system compares the segmented area that is not affected by the disease inside the parenchyma of the original and the registered follow up exam of the same patient. Preprocessing of the images was done by two approaches: First approach includes rigid registration of the image and second method includes registration of the image by affine and B-spline method. Novel region growing algorithm is used for segmentation, and the results was compared to manual segmentation, and by comparison of segmented structures resulted in determining of disease progression in mathematical terms, which we compared to visual observers. Visual inspectors are 2 radiologists’ specialists, ranging from 20 – 25 years in clinical practice. Both of these approaches showed good results in clinical practice.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Temeljne medicinske znanosti

POVEZANOST RADA