ENHANCING THE MEDICAL IMAGES QUALITY USING ADAPTIVE GENETIC ALGORITHM
Abstract
It is obvious that there is a need for a Medical Decisiveness Determine System (MDDS) should be able to diagnose abnormalities in medical imaging. This is because the medical diagnosis system in health care sectors requires assistants to serve as secondary opinions for medical practitioners. During the process of picture acquisition, it is common practice to adjust the contrast level of medical images in order to prevent image degradation. Contrast enhancement in medical images is typically seen as an optimisation problem, and the Adaptive Genetic Algorithm (AGA) algorithm is utilised in order to arrive at the best possible answer. The findings of the comparison are established between the Adaptive Genetic Algorithm that has been proposed and other algorithms that are already in existence. A number of different performance indicators, including PSNR, SSIM, MSSIM, IFC, VIF, VSNR, MSE, SDME, and NAE, are utilised in order to make comparisons between the results. Methods that have been developed and those that already exist are evaluated using a variety of cancer pictures. As a result, the contrast and quality of medical images can be improved through the utilisation of AGA, which also offers a higher contrast level of medical images, hence facilitating improved decision-making by medical professionals.

Authors
C. Srivenkateswaran1, K. Regin Bose2, Belwin J.Brearley3, D.C. Jullie Josephine4
Rajalakshmi Institute of Technology, India1,2, B.S.Abdur Rahman Crescent Institute of Science and Technology, India3, Saveetha Institute of Medical and Technical Sciences, India4

Keywords
MDDS, AGA, SDME, Medical Images
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
0082290230321
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 14 , Issue: 3 , Pages: 3222 - 3230 )
Date of Publication :
February 2024
Page Views :
415
Full Text Views :
50

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.