A Modified Deep Convolutional Neural Network for Abnormal Brain Image Classification

Deep learning techniques have gained significant importance among artificial intelligence techniques for any computing applications. Among them, deep convolutional neural networks (DCNNs) is one of the widely used deep learning networks for any practical applications. The accuracy is generally high...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.4275-4283
Main Authors: Hemanth, D. Jude, Anitha, J., Naaji, Antoanela, Geman, Oana, Popescu, Daniela Elena, Hoang Son, Le
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Artificial neural networks
Biomedical imaging
Brain
Brain cancer
brain images
Complexity
Convolution
convolutional neural network
Convolutional neural networks
Deep learning
Feature extraction
Image classification
Machine learning
Magnetic resonance
Neural networks
Parameters
Tumors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning techniques have gained significant importance among artificial intelligence techniques for any computing applications. Among them, deep convolutional neural networks (DCNNs) is one of the widely used deep learning networks for any practical applications. The accuracy is generally high and the manual feature extraction process is not necessary in these networks. However, the high accuracy is achieved at the cost of huge computational complexity. The complexity in DCNN is mainly due to: 1) increased number of layers between input and output layers and 2) two set of parameters (one set of filter coefficients and another set of weights) in the fully connected network need to be adjusted. In this paper, the second aspect is targeted to reduce the computational complexity of conventional DCNN. Suitable modifications are performed in the training algorithm to reduce the number of parameter adjustments. The weight adjustment process in the fully connected layer is completely eliminated in the proposed modified approach. Instead, a simple assignment process is used to find the weights of this fully connected layer. Thus, the computational complexity is significantly reduced in the proposed approach. The application of modified DCNN is explored in the context of magnetic resonance brain tumor image classification. Abnormal brain tumor images from four different classes are used in this paper. The experimental results show promising results for the proposed approach.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2885639