Echocardiography Segmentation by Fractional Differential and Improved Canny, Analysis by Fourier Descriptor

Abstract

The omnidirectional M-mode echocardiogram provides a new method for human heart functional analyses. In this article, to sharpen object edges, we designed image processing kernel based on Fractional differential for image enhancement. After that, the contour of the left ventricle in a short axis is first extracted using both an improved Canny edge detection algorithm and the gray level searching algorithm in the radial direction as auxiliary. The modified Canny edge detection algorithm with the matching method between adjacent frames then is adopted for the subsequent frames to extract the left ventricular contours. The non-functional movements in the B-ultrasonic plane are determined by using the movement extracting method based on Fourier descriptors and the mass center with the inertia axis method, and the movements are removed from a compound motion. The Fourier descriptors are applied to get a series of image contour curves with the principal translation and rotation. Hence the curve of the cardiac motion can accurately show functional movements in any location of the heart. Using our technique, we can reduce multi-lines and excursion, as well as correct the omnidirectional M-mode echocardiography.

Image Enhancement for the Improved Extraction of Local Image Features Using Image Offsets

“…Spatial frequency based descriptor methods revolve around analyzing the spatial arrangement of frequency content. Common methods of converting images from the spatial domain to the frequency domain include the Discrete Fourier transform [45], Gabor transform [46] and wavelet transform [47]. Equations 2.12 and 2.13 show the conversion of an image into its frequency representation and back to its spatial representation through the Discrete Fourier transform.…”