Open AccessMedical Image Segmentation by Fish Schooling Algorithm and Neural Network
Author(s) -
Kundala Sandeep,
Manoj Dandamudi,
P Dhanusha
Publication year - 2021
Publication title -
international journal of modern trends in science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-3778
DOI - 10.46501/ijmtst0710009
Subject(s) - artificial intelligence , artificial neural network , computer science , segmentation , image segmentation , genetic algorithm , fish <actinopterygii> , focus (optics) , image (mathematics) , feature (linguistics) , feature selection , pattern recognition (psychology) , market segmentation , process (computing) , computer vision , digital image , image processing , machine learning , linguistics , philosophy , physics , marketing , fishery , optics , business , biology , operating system
Medical image diagnosis by machine decrease the doctor load and increases the efficiency of treatment as well. Many of diagnosisprocess depends on chemical data and some are depend on digital images. This work focus on brain tumor medical imagediagnosis by segmenting the tumor region in the image. For tumor detection neural network was trained by the model. Selectedfeatures extract from the image by fish schooling genetic algorithm for training of neural network It was obtained that fishschooling based genetic feature selection has increases the detection accuracy of trained model. Experiment was done on realdataset and results compared with existing techniques of tumor detection from MRI images.