Please use this identifier to cite or link to this item: http://repository.li.mahidol.ac.th/dspace/handle/123456789/41984
Title: CNN-based image analysis for malaria diagnosis
Authors: Zhaohui Liang
Andrew Powell
Ilker Ersoy
Mahdieh Poostchi
Kamolrat Silamut
Kannappan Palaniappan
Peng Guo
Md Amir Hossain
Antani Sameer
Richard James Maude
Jimmy Xiangji Huang
Stefan Jaeger
George Thoma
York University
Swarthmore College
University of Missouri School of Medicine
University of Missouri-Columbia
Mahidol University
Electrical and Computer Engineering
Chittagong Medical College Hospital
National Library of Medicine
Keywords: Biochemistry, Genetics and Molecular Biology
Issue Date: 17-Jan-2017
Citation: Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016. (2017), 493-496
Abstract: © 2016 IEEE. Malaria is a major global health threat. The standard way of diagnosing malaria is by visually examining blood smears for parasite-infected red blood cells under the microscope by qualified technicians. This method is inefficient and the diagnosis depends on the experience and the knowledge of the person doing the examination. Automatic image recognition technologies based on machine learning have been applied to malaria blood smears for diagnosis before. However, the practical performance has not been sufficient so far. This study proposes a new and robust machine learning model based on a convolutional neural network (CNN) to automatically classify single cells in thin blood smears on standard microscope slides as either infected or uninfected. In a ten-fold cross-validation based on 27,578 single cell images, the average accuracy of our new 16-layer CNN model is 97.37%. A transfer learning model only achieves 91.99% on the same images. The CNN model shows superiority over the transfer learning model in all performance indicators such as sensitivity (96.99% vs 89.00%), specificity (97.75% vs 94.98%), precision (97.73% vs 95.12%), F1 score (97.36% vs 90.24%), and Matthews correlation coefficient (94.75% vs 85.25%).
URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85013270066&origin=inward
http://repository.li.mahidol.ac.th/dspace/handle/123456789/41984
Appears in Collections:Scopus 2016-2017

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.