Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/133243
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Classification of medical images in the biomedical literature by jointly using deep and handcrafted visual features |
Author: | Zhang, J. Xia, Y. Xie, Y. Fulham, M. Feng, D.D. |
Citation: | IEEE Journal of Biomedical and Health Informatics, 2018; 22(5):1521-1530 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Issue Date: | 2018 |
ISSN: | 2168-2194 2168-2208 |
Statement of Responsibility: | Jianpeng Zhang, Yong Xia, Yutong Xie, Michael Fulham, David Dagan Feng ... et al. |
Abstract: | The classification of medical images and illustrations from the biomedical literature is important for automated literature review, retrieval, and mining. Although deep learning is effective for large-scale image classification, it may not be the optimal choice for this task as there is only a small training dataset. We propose a combined deep and handcrafted visual feature (CDHVF) based algorithm that uses features learned by three fine-tuned and pretrained deep convolutional neural networks (DCNNs) and two handcrafted descriptors in a joint approach. We evaluated the CDHVF algorithm on the ImageCLEF 2016 Subfigure Classification dataset and it achieved an accuracy of 85.47%, which is higher than the best performance of other purely visual approaches listed in the challenge leaderboard. Our results indicate that handcrafted features complement the image representation learned by DCNNs on small training datasets and improve accuracy in certain medical image classification problems. |
Keywords: | Medical image classification; deep convolutional neural network (DCNN); back-propagation neural network (BPNN); ensemble learning |
Rights: | © 2018, IEEE |
DOI: | 10.1109/JBHI.2017.2775662 |
Grant ID: | ARC |
Published version: | http://dx.doi.org/10.1109/jbhi.2017.2775662 |
Appears in Collections: | Australian Institute for Machine Learning publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.