Hybrid Elmann BiLSTM Based Brain Tumor Classification on Augmented Data with Combination of Variational Auto-encoders and Generative Adversarial Network


Balcı F.

TRAITEMENT DU SIGNAL, vol.41, no.2, pp.1-10, 2024 (SCI-Expanded)

  • Publication Type: Article / Article
  • Volume: 41 Issue: 2
  • Publication Date: 2024
  • Doi Number: 10.18280/ts.410217
  • Journal Name: TRAITEMENT DU SIGNAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, Business Source Elite, Business Source Premier, Compendex, zbMATH
  • Page Numbers: pp.1-10
  • Gazi University Affiliated: Yes

Abstract

For detecting and classifying brain tumors, clinicians use Magnetic Resonance Imaging (MRI) data. Automated AI-powered tools accelerate the diagnostic process for clinicians. However, large amounts of data are needed for these models to achieve high accuracy. Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN) architecture are combined for dataset expansion. The accuracy was improved with the artificial image set created in all tested models. However, since the accuracy rate remained at 92,960% using Long Short Term Memory Algorithm, it was observed that a hybrid method was also needed, and hybrid Elmann Bidirectional Long Short Memory Algorithm (Elmann-BiLSTM) was developed. In this proposed approach based on deep learning, a Guided Bilateral Filter is used to separate skull from images after VAE-GAN structure. The thresholding scheme extracts tumour regions from the original image in parts. Edge features and major texture data are collected from these tumor images produced using the Improved Gabor Wavelet Transform. Random Forest-based feature selection algorithm will select optimal features that increase accuracy from extracted features. These features feed the Elmann-BiLSTM algorithm used as a two-step classifier. The accuracy rate was 98.897% in the one-step classification approach and 100% and 99.313% in the two-step classifier approach, respectively.