Optimization of Brain Tumor MR Image Classification Accuracy Using Optimal Threshold, PCA and Training ANFIS with Different Repetitions.

Tahmasebi Birgani, Mohammad Javad and Chegeni, Nahid and Farhadi Birgani, F and Fatehi, Daryoush and Akbarizadeh, Gholamreza and Shams, A (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. ISSN 2251-7200

[img]
Preview
Text
JBPE-9-189.pdf - Published Version

Download (1MB) | Preview

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. KEYWORDS: ANFIS ; Brain Tumor Detection ; PCA ; Training Repetition; MRI

Item Type: Article
Subjects: WN Radiology . Diagnostic Imaging
Divisions: Faculty of Medicine > Basic Sciences Academic Groups > Department of Medical Physics
Depositing User: marzieye nazari .
Date Deposited: 24 Sep 2019 07:35
Last Modified: 24 Sep 2019 07:35
URI: http://eprints.skums.ac.ir/id/eprint/7940

Actions (login required)

View Item View Item