Medical Image Analysis with an Innovative Intelligent Computer Program
Loading...
Date
2010
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Uva Wellassa University of Sri Lanka
Abstract
The pre-defined major research objective was uniquely identifying an image captured from a medical instrument such as electronic microscope (microscopic view). It was proposed that, the technique optical patterns recognition, one of the key applications of artificial neural networks (ANN) will be used. Furthermore, also mentioned that the researcher will study the feasibility of using genetic algorithms (GA) to enhance the efficiency of ANN. In brief, the research is developing a computer program (software) with its ultimate objective, analyze a digital image and recognize it. (Optionally —Interpret it.)
Many experiments were carried-out to achieve these objectives, started with implementing an algorithm (a neural network) to recognize optical patterns. Succeeded with the selected software to implement and simulate basic algorithms -`Wolfram Mathematica Version 6.0'.
The prototype-level NN architecture comprised of 3 layers, successfully trained with `Back-propagation algorithm' and was able to recognize some pre-trained images of Sinhala characters (for algorithms testing purposes only). This program was then interfaced with a GUI created from VB.net and worked fine. (A Sinhala OCR-Optical Character Recognizer — a by-product)
In the next step, the training algorithm was optimized with an innovated Genetic Algorithm (GA), tested and obtained reports verifying that the GA works as expected and it significantly reduces the errors of outputs.
Then, after an in-depth study, the type of medical image (from which instrument they
are being captured from) was selected. That was color images from TEM
(Transmission Electron Microscopy)
(http://en.wikipedia.org/wiki/Transmission_electron_microscopy). The images
analyzed by the program are - more specifically, human blood viruses those can be recognized by its specific optical patterns.
Description
Keywords
Computer Science and Technology