Brain MRI classification using discrete wavelet transform and bag-of-words

  • Wadhah Ayadi
  • , Wajdi Elhamzi
  • , Imen Charfi
  • , Bouraoui Ouni
  • , Mohamed Atri

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

Automatic CAD system able to detect correctly the unhealthy brain in magnetic resonance imaging (MRI) scanning is represented in this paper. The new system exploited Discrete Wavelet Transform (DWT) and Bag-of-Words (BoW) to extract image features. Support vector machine (SVM) was used in classification step. We employed 256×256 images from three datasets (DS-66, DS-160, DS-255) provided by Harvard Medical School, to evaluate our method. 10∗k-fold stratified Cross Validation (CV) technique was applied to validate the system performance. The Accuracy reached respectively 100%, 100%, and 99.61% for DS-66, DS-160, and DS-255 datasets. The overall computation time is about 0.027 s for each MR image. A comparative study with several works showed efficiency and robustness of our scheme.

Original languageEnglish
Title of host publication2018 International Conference on Advanced Systems and Electric Technologies, IC_ASET 2018
EditorsNaoufel Machta, Abdessattar Ben Amor, Salwa Elloumi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages45-49
Number of pages5
ISBN (Electronic)9781538644492
DOIs
StatePublished - 11 Jun 2018
Externally publishedYes
Event13th International Conference on Advanced Systems and Electric Technologies, IC_ASET 2018 - Hammamet, Tunisia
Duration: 22 Mar 201825 Mar 2018

Publication series

Name2018 International Conference on Advanced Systems and Electric Technologies, IC_ASET 2018

Conference

Conference13th International Conference on Advanced Systems and Electric Technologies, IC_ASET 2018
Country/TerritoryTunisia
CityHammamet
Period22/03/1825/03/18

Keywords

  • BoW
  • Brain Tumor
  • CAD
  • Classification
  • DWT
  • MRI

Fingerprint

Dive into the research topics of 'Brain MRI classification using discrete wavelet transform and bag-of-words'. Together they form a unique fingerprint.

Cite this