Medical Image Classification with Hand-Designed or Machine-Designed Texture Descriptors: A Performance Evaluation

Badejo, J. A. and Adetiba, E. and Akinrinmade, A. and Akanle, M.B. (2018) Medical Image Classification with Hand-Designed or Machine-Designed Texture Descriptors: A Performance Evaluation. In: Bioinformatics and Biomedical Engineering. Springer Verlag, pp. 266-275.

HTML - Published Version Download (98Kb)

Abstract

Accurate diagnosis and early detection of various disease conditions are key to improving living conditions in any community. The existing framework for medical image classification depends largely on advanced digital image processing and machine (deep) learning techniques for significant improvement. In this paper, the performance of traditional hand-designed texture descriptors within the image-based learning paradigm is evaluated in comparison with machine-designed descriptors (extracted from pre-trained Convolution Neural Networks). Performance is evaluated, with respect to speed, accuracy and storage requirements, based on four popular medical image datasets. The experiments reveal an increased accuracy with machine-designed descriptors in most cases, though at a higher computational cost. It is therefore necessary to consider other parameters for tradeoff depending on the application being considered. © Springer International Publishing AG, part of Springer Nature 2018.

Item Type:	Book Section
Additional Information:	cited By 0; Conference of 6th International Work-Conference on Bioinformatics and Biomedical Engineering, IWBBIO 2018 ; Conference Date: 25 April 2018 Through 27 April 2018; Conference Code:213089
Uncontrolled Keywords:	Bioinformatics; Biomedical engineering; Convolution; Deep learning; Diagnosis; Image classification; Image enhancement; Medical imaging, Computational costs; Convolution neural network; Learning paradigms; Learning techniques; Living conditions; Performance evaluations; Storage requirements; Texture descriptors, Image texture
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	UNSPECIFIED
Depositing User:	Dr. Joke Badejo
Date Deposited:	17 Sep 2018 10:13
Last Modified:	03 May 2019 11:43
URI:	http://eprints.covenantuniversity.edu.ng/id/eprint/11665

Actions (login required)

View Item