DeTraC: Transfer Learning of Class Decomposed Medical Images in Convolutional Neural Networks

Abbas, Asmaa and Abdelsamea, Mohammed M. and Gaber, Mohamed Medhat (2020) DeTraC: Transfer Learning of Class Decomposed Medical Images in Convolutional Neural Networks. IEEE Access, 8. pp. 74901-74913. ISSN 2169-3536

[img]
Preview
Text
DeTraC.pdf - Accepted Version

Download (1MB)

Abstract

Due to the high availability of large-scale annotated image datasets, paramount progress has been made in deep convolutional neural networks (CNNs) for image classification tasks. CNNs enable learning highly representative and hierarchical local image features directly from data. However, the availability of annotated data, especially in the medical imaging domain, remains the biggest challenge in the field. Transfer learning can provide a promising and effective solution by transferring knowledge from generic image recognition tasks to the medical image classification. However, due to irregularities in the dataset distribution, transfer learning usually fails to provide a robust solution. Class decomposition facilitates easier to learn class boundaries of a dataset, and consequently can deal with any irregularities in the data distribution. Motivated by this challenging problem, the paper presents Decompose, Transfer, and Compose (DeTraC) approach, a novel CNN architecture based on class decomposition to improve the performance of medical image classification using transfer learning and class decomposition approach. DeTraC enables learning at the subclass level that can be more separable with a prospect to faster convergence.We validated our proposed approach with three different cohorts of chest X-ray images, histological images of human colorectal cancer, and digital mammograms. We compared DeTraC with the state-of-the-art CNN models to demonstrate its high performance in terms of accuracy, sensitivity, and specificity.

Item Type: Article
Identification Number: https://doi.org/10.1109/ACCESS.2020.2989273
Date: 21 April 2020
Uncontrolled Keywords: Biomedical imaging Feature extraction Lung Task analysis Machine learning Computed tomography Training Convolution neural networks class decomposition data irregularity medical image classification transfer learning
Subjects: G700 Artificial Intelligence
Divisions: Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology
Depositing User: Mohamed Gaber
Date Deposited: 23 Apr 2020 15:55
Last Modified: 18 May 2020 13:33
URI: http://www.open-access.bcu.ac.uk/id/eprint/9172

Actions (login required)

View Item View Item

Research

In this section...