Image Enhancement based Improved Multi-scale Hessian Matrix for Coronary Angiography

Image Enhancement based Improved Multi-scale Hessian Matrix for Coronary Angiography

 The coronary angiography image is easy to be affected by many factors, such as vascular thickness varied huge, complex background noise, uneven illumination intensity and so on. Many vascular image enhancement methods are propose, such as linear filters , morphology filter, anisotropic diffusion filter and so on. The most common method is vascular enhancement filter based on Hessian matrix introduced in paper.

Multi-scale fusion in the multi-scale vessel enhancement filter is used to solve the vascular characteristics that the size of blood vessel images is different.  Multi-scale Hessian matrix method is mentioned through combining Hessian matrix method with other image enhancement methods.

In this paper, a method of image de-noising and enhancement based on the improved multi-scale Hessian matrix that integrate the multi-scale Hessian matrix with morphological top-hat method for coronary angiography images is proposed.

MORPHOLOGICAL TOP-HAT OPERATIONS

Morphological opening operation can be used to smooth the outline of objects, disconnect narrow neck, eliminate thin projections etc

The highlights can be removed by the morphological opening operation, because the area of highlights smaller than the structure element. Background image obtained by the opening operation is subtracted from the original image, the acquired vascular tree have got image enhancement, the process is known as top-hat operation.

MULTI-SCALE HESSIAN MATRIX VESSEL EXTRACTION

Hessian matrix, resulting in a lot of background noise (aperture etc.), and many small tiny blood vessels disappeared at the same time. To be able to solve these problems, an improved method combining multi-scale Hessian matrix with morphological top-hat operation is proposed in this paper.

An improved multi-scale Hessian matrix, combined with morphological top-hat operation for the detection of coronary angiography is presented in the paper.