Novel Bayesian multiscale methods for image denoising using alpha-stable distributions

Before launching into ultrasound research, it is important to recall that the ultimate goal is to provide the clinician with the best possible information needed to make an accurate diagnosis. Ultrasound images are inherently affected by speckle noise, which is due to image formation under coher...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριος συγγραφέας: Achim, Alin
Άλλοι συγγραφείς: Μπεζεριάνος, Αναστάσιος
Μορφή: Βιβλίο
Γλώσσα:English
Έκδοση: 2009
Θέματα:
Διαθέσιμο Online:http://nemertes.lis.upatras.gr/jspui/handle/10889/1265
Περιγραφή
Περίληψη:Before launching into ultrasound research, it is important to recall that the ultimate goal is to provide the clinician with the best possible information needed to make an accurate diagnosis. Ultrasound images are inherently affected by speckle noise, which is due to image formation under coherent waves. Thus, it appears to be sensible to reduce speckle artifacts before performing image analysis, provided that image texture that might distinguish one tissue from another is preserved. The main goal of this thesis was the development of novel speckle suppression methods from medical ultrasound images in the multiscale wavelet domain. We started by showing, through extensive modeling, that the subband decompositions of ultrasound images have significantly non-Gaussian statistics that are best described by families of heavy-tailed distributions such as the alpha-stable. Then, we developed Bayesian estimators that exploit these statistics. We used the alpha-stable model to design both the minimum absolute error (MAE) and the maximum a posteriori (MAP) estimators for alpha-stable signal mixed in Gaussian noise. The resulting noise-removal processors perform non-linear operations on the data and we relate this non-linearity to the degree of non-Gaussianity of the data. We compared our techniques to classical speckle filters and current state-of-the-art soft and hard thresholding methods applied on actual ultrasound medical images and we quantified the achieved performance improvement. Finally, we have shown that our proposed processors can find application in other areas of interest as well, and we have chosen as an illustrative example the case of synthetic aperture radar (SAR) images.