Mammographic image restoration using maximum entropy deconvolution

Abstract

Abstract. An image restoration approach based on a Bayesian maximum entropy method (MEM) has been applied to a radiological image deconvolution problem, that of reduction of geometric blurring in magnification mammography. The aim of the work is to demonstrate an improvement in image spatial resolution in realistic noisy radiological images with no associated penalty in terms of reduction in the signalto-noise ratio perceived by the observer. Images of the TORMAM mammographic image quality phantom were recorded using the standard magnification settings of 1.8 magnification/fine focus and also at 1.8 magnification/broad focus and 3.0 magnification/fine focus; the latter two arrangements would normally give rise to unacceptable geometric blurring. Measured point-spread functions were used in conjunction with the MEM image processing to de-blur these images. The results are presented as comparative images of phantom test features and as observer scores for the raw and processed images. Visualization of high resolution features and the total image scores for the test phantom were improved by the application of the MEM processing. It is argued that this successful demonstration of image de-blurring in noisy radiological images offers the possibility of weakening the link between focal spot size and geometric blurring in radiology, thus opening up new approaches to system optimization.

Feature extraction from mammograms by using a'priory information

“…This ill-posed problem should be regularized to make the computation of a meaningful approximate solution possible [7][8][9]. It refers to a process of introducing minimum additional infonnation about solution, such as restriction of smoothness, to get it to be stable.…”

A Review on MR Image Intensity Inhomogeneity Correction

“…As a frequently used criterion to characterize the intensity distribution of an image, entropy has been employed to design algorithms for image restoration, thresholding, or classification [64,65]. Also, it has been utilized to quantify the image property with IIH present and guide the parameter searching for IIH removal [54][55][56][57].…”

Digital Image Restoration Based on Pixel Simultaneous Detection Probabilities

“…The restoration in the spatial frequency domain that requires MTF evaluation (on the base of PSF) is also not an easy task due to aliasing [4] and noise amplification in higher spatial frequencies [2].…”

“…The influence of the additive noise on the restoration process in pixel domain in radiography has been studied for a long time [2]. Here, the minimization procedure is used to The general theoretical limitations [7] are very rough and difficult to use for the estimation of the expected precisions.…”