DocumentCode :
3442078
Title :
Pixel position regression - application to medical image segmentation
Author :
Van Ginneken, Bram ; Loog, Marco
Author_Institution :
Inst. of Image Sci., Univ. Med. Center, Utrecht, Netherlands
Volume :
3
fYear :
2004
fDate :
23-26 Aug. 2004
Firstpage :
718
Abstract :
Pixel position regression (PPR), an automatic supervised method for image segmentation, is presented. The method uses a set of corresponding points indicated in each train image. For each point in this set, the mean position in all train images is determined. By warping the set of corresponding points to their mean positions, one can associate with each position in each train image a reference position. PPR estimates the reference position from a rich set of local image features through k-nearest-neighbor regression. The deformation field thus obtained determines the segmentation. It is demonstrated that the deformation field estimate can be improved by (weighted) blurring and more sophisticated methods such as global modeling of the deformation field through principal component analysis and iterated regression. The method is evaluated on a set of chest radiographs in which the lung fields, heart and clavicles are segmented.
Keywords :
diagnostic radiography; feature extraction; image classification; image restoration; image segmentation; iterative methods; medical image processing; principal component analysis; regression analysis; automatic supervised method; chest radiographs; image blurring; image classification; iterated regression; k-nearest neighbor regression; local image features; medical image segmentation; pixel position regression estimation; principal component analysis; Active appearance model; Active shape model; Biomedical imaging; Filter bank; Heart; Image segmentation; Lungs; Pattern recognition; Pixel; Radiography;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN :
1051-4651
Print_ISBN :
0-7695-2128-2
Type :
conf
DOI :
10.1109/ICPR.2004.1334629
Filename :
1334629
Link To Document :
بازگشت