Abstract
Computer-aided analysis for cell images acquired by an electron microscope involves a range of image processing steps including edge detection and thresholding. The major problem encountered in automatic cell analysis is the possible presence of incomplete boundaries of cell features, which prevent the generation of cell feature details including all measurements as the boundaries include very tiny gaps. This paper presents a novel edge-linking technique based on an artificial neural process, which uses directional sensitivity derivatives from an edged image. The input signals applied to the neural layer are integrated with direction-sensitive information produced by an auxiliary algorithm, which interrogates all the pixels in the 2-D image in order to designate the specified direction in which each edge-end pixel should propagate. The proposed edge-linking technique, implemented as an image-processing algorithm for direction-sensitive selectiveness, provides an effective solution to the problem of porous boundaries encountered in biological cell image analysis.
Highlights
Computer-aided analysis performed on cell images acquired from electron microscopes used in conjunction with sensing modalities is of increasing importance to researchers in the biomedical field because it offers many advantages, especially in the remote analysis of medical images
A previous study matching a brain atlas to medical images found that completely connected contours could not be produced despite the application of a number of steps [1]
Gaussian filtering, Sobel edge detection, a thinning operation to obtain one-pixel edges and a heuristic search technique to link the edge gaps were all used, open segments remained, which had to be connected manually. To overcome such difficulties experienced in the automatic or semi-automatic image processing systems, we present here a novel technique for the process of edge-linking which is based on the concept of direction-sensitive cells present in the early stages of the physiology of visual development
Summary
Computer-aided analysis performed on cell images acquired from electron microscopes used in conjunction with sensing modalities is of increasing importance to researchers in the biomedical field because it offers many advantages, especially in the remote analysis of medical images. Despite employing the processing steps prevalent in the contemporary practice of image-processing, the existence of even the tiniest of gaps present in the extracted edges impedes the continuation of the automatic processing steps This problem of gaps is common to many other types of medical image application. Gaussian filtering, Sobel edge detection, a thinning operation to obtain one-pixel edges and a heuristic search technique to link the edge gaps were all used, open segments remained, which had to be connected manually To overcome such difficulties experienced in the automatic or semi-automatic image processing systems, we present here a novel technique for the process of edge-linking which is based on the concept of direction-sensitive cells present in the early stages of the physiology of visual development
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
