Optimization of brain tumor MR image classification accuracy using optimal threshold, PCA and training ANFIS with different Repetitions

Tahmasebi Birgani, M and Chegeni, Nahid. and Farhadi Birgani, F and Fatehi, D and Akbarizadeh, G and Azin, S (2019) Optimization of brain tumor MR image classification accuracy using optimal threshold, PCA and training ANFIS with different Repetitions. Journal of Biomedical Physics and Engineering, 9 (2).

[img] Text
790-2540-6-PB_2.pdf

Download (1MB)
Official URL: https://www.scopus.com/record/display.uri?eid=2-s2...

Abstract

Background: One of the leading causes of death is brain tumors. Accurate tumor classification leads to appropriate decision making and providing the most efficient treatment to the patients. This study aims to optimize brain tumor MR images classification accuracy using optimal threshold, PCA and training Adaptive Neuro Fuzzy Inference System (ANFIS) with different repetitions. Material and Methods: The procedure used in this study consists of five steps: (1) T1, T2 weighted images collection, (2) tumor separation with different threshold levels, (3) feature extraction, (4) presence and absence of feature reduction applying principal component analysis (PCA) and (5) ANFIS classification with 0, 20 and 200 training repetitions. Results: ANFIS accuracy was 40%, 80% and 97% for all features and 97%, 98.5% and 100% for the 6 selected features by PCA in 0, 20 and 200 training repetitions, respectively. Conclusion: The findings of the present study demonstrated that accuracy can be raised up to 100% by using an optimized threshold method, PCA and increasing training repetitions

Item Type: Article
Uncontrolled Keywords: ANFIS, Brain Tumor Detection, MRI, PCA, Training Repetition
Subjects: WB Practice of Medicine
WL Nervous system
QZ pathology-Neoplasms
Divisions: Faculty of Medicine
Depositing User: Unnamed user with email zamani.m@skums.ac.ir
Date Deposited: 12 Jun 2019 07:49
Last Modified: 07 Jul 2019 09:35
URI: http://eprints.skums.ac.ir/id/eprint/7778

Actions (login required)

View Item View Item