Paper Info
Title
Performance Evaluation Of A Generative Adversarial Network For Deblurring Mobile-Phone Cervical Images
Abstract
Visual examination forms an integral part of cervical cancer screening. With the recent rise in smartphone-based health technologies, capturing cervical images using a smartphone camera for telemedicine and automated screening is gaining popularity. However, such images are highly prone to image corruption, typically out-of-focus target or camera shake blur. In this paper, we applied a generative adversarial network (GAN) to deblur mobile-phone cervical (MC) images, and we evaluate the deblur quality using various measures. Our evaluation process is three-fold: first, we calculate the peak signal to noise ratio (PSNR) and the structural similarity (SSIM) of a test dataset with ground truth availability. Next, we calculate the perception based image quality evaluator (PIQE) score of a test dataset without ground truth availability. Finally, we classify a dataset of blurred and the corresponding deblurred images into normal/abnormal MC images. The resulting change in classification accuracy was our final assessment. Our evaluation experiments show that deblurring of MC images can potentially improve the accuracy of both manual and automated cancerous lesion screening.
Year
DOI
Venue
2019
10.1109/EMBC.2019.8857124
2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)
Keywords
Field
DocType
Generative Adversarial Network, Cervical Image Deblurring, Uterine Cervix Cancer Classification
Kernel (linear algebra),Computer vision,Peak signal-to-noise ratio,Generative adversarial network,Deblurring,Computer science,Image quality,Ground truth,Artificial intelligence,Mobile phone
Conference
Volume
ISSN
Citations 
2019
1557-170X
0
PageRank 
References 
Authors
0.34
0
6
Name
Order
Citations
PageRank
Prasanth Ganesan100.68
Zhiyun Xue224522.97
Sanjana Singh300.34
L. Rodney Long453456.98
Behnaz Ghoraani500.68
Sameer Antani61402134.03