학술논문

Detection of Steatosis Disease using Region Based Segmentation of Growcut Algorithm and Comparing with Random Walker Algorithm to Enhance the Accuracy
Document Type
Conference
Source
2023 Eighth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) Science Technology Engineering and Mathematics (ICONSTEM), 2023 Eighth International Conference on. :1-5 Apr, 2023
Subject
Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Nuclear Engineering
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Image segmentation
Digital images
Software algorithms
Liver
Software
Mathematics
Diseases
Steatosis
Fatty liver disease
Grow cut algorithm
Random walker algorithm
Fatty liver images
Language
Abstract
To detect steatosis disease using region-based segmentation of GrowCut Algorithm and comparing with Random Walker Algorithm. Materials and Methods: It includes steatosis disease images, GrowCut algorithm and Random Walker Algorithm. The images were segmented using the GrowCut Algorithm and the accuracy of the segmentation was compared with the Random Walker algorithm. In the digital image processing lab, the segmentation procedure was carried out using MATLAB software, with a total sample size of 40 for the two groups and a sample quantity of 20. Results: It showed that the GrowCut Algorithm was more accurate than the Random Walker Algorithm for segmenting the steatosis disease images. Conclusion: The GrowCut Algorithm is a better method for segmenting the steatosis images than the Random Walker Algorithm. The GrowCut algorithm was more accurate than the Random Walker algorithm. As a result, the GrowCut Algorithm is suggested as a superior segmentation technique for pictures with steatosis.