A Tree-based Approach Towards Edge Detection of Medical Image using MDT

Abstract

To develop any autonomous computerized algorithm for abnormality detection based on medical image analysis essentially requires a robust segmentation algorithm. To achieve this goal of accurate segmentation of medical image it requires an effective edge detection algorithm. Generalized edge detection algorithms like Sobel, Canny, though effective in normal images but often fails in case of medical images. Medical images obtained from devices such as Ultrasonography, X-Ray, CT and MRI exhibit diverse image characteristics but are essentially collection of intensity variations from which specific abnormalities are needed to be isolated. Homogeneity enhancement, followed by edge detection and resulting segmentation is essential prerequisite for all medical image analysis system. This paper proposes a robust medical image enhancement and edge detection algorithm that is equally effective with most medical images that are popular now-a-days yielding excellent segmentation results in all cases.