Inventory reference ISSN 1812-7231 Klin.inform.telemed. Volume 2, Issue 3, 2005, Pages 51-55
Author(s) Alexander M. Akhmetshin, Lyudmila G. Akhmetshina
Dniepropetrovsk National University, Dniepropetrovsk, Ukraine
Article title Low contrast radiological image segmentation by means of spaceeresonance imaging method
A new method of radiological image analysis is outlined. The one has high sensitivity to detection of low contrast pathological areas and high stability to influence of anatomical noise. The essence of method is comparing to each pixel of analyzed image some virtual digital filter. Coefficients of the one are brightness of analyzed image. Information features for further analysis are magnitude and frequency extremal points of magnitude–frequency andgroup–delay characteristics of that filter. Presented experimental results on examples of X-ray CT and mammogram images analysis had shown high information possibilities of the new method in situation when known methods using did not any give positive results.
Keywords radiological image processing, space resonance, low contrast, segmentation, sensitivity, phase characteristic
Full-text version http://kit-journal.com.ua/en/viewer_en.html?doc/2005_3/10.pdf