Use of Deep Convolutional Neural Wavelet Network for Classification of Medical Images: A Novel Approach | Chapter 7 | Research Updates in Mathematics and Computer Science Vol. 3

 This work presents a new solution for medical image classification using the Neural Network (NN) and Wavelet Network (WN) based on the Fast Wavelet Transform (FWT) and the Adaboost algorithm. The deep learning is a set of algorithms of machine learning, seeking to model with the abstractions of top level within the data using the architectures of models composed of multiple not linear transformations. This method is divided in two stages: The learning stage and the classification stage. The first consists to extract the features using the FWT based on the Multi Resolution Analysis (MRA). These features are used to calculate the inputs of the hidden layer. Then, those inputs are filtered by using the Adaboost algorithm to select the best ones corresponding to each image. The second consist to create an Auto Encoder (AE) using the best-selected wavelets of all images. Then, For the classification phase, our Convolutional Deep Neural Wavelet Network (CDNWN) architecture is obtained by applying a pooling for each hidden layer following a succession of Stacked AE. Our approach yielded classification rates that clearly outperform those stated in this publication. Our studies were conducted on two distinct datasets.

Author(s) Details:

Ramzi Ben Ali,
Research Team in Intelligent Machines, University of Gabes, ENIG, Avenue Omar Ibn El Khattab, Zrig 6029, Gabes, Tunisia.

Ridha Ejbali,
Research Team in Intelligent Machines, University of Gabes, ENIG, Avenue Omar Ibn El Khattab, Zrig 6029, Gabes, Tunisia.

Mourad Zaied,
Research Team in Intelligent Machines, University of Gabes, ENIG, Avenue Omar Ibn El Khattab, Zrig 6029, Gabes, Tunisia.

Please see the link here: https://stm.bookpi.org/RUMCS-V3/article/view/14038