Evaluation of GAN architectures for visualisation of HPV viruses from microscopic images
Conference paper
Gao, X., Wen, S., Li, D., Liu, W., Xiong, J., Xu, B., Liu, J., Zhang, H. and Liu, X. 2021. Evaluation of GAN architectures for visualisation of HPV viruses from microscopic images. 20th IEEE ICMLA 2021. Virtual online 13 - 16 Dec 2021 IEEE. pp. 829-833 https://doi.org/10.1109/ICMLA52953.2021.00137
Type | Conference paper |
---|---|
Title | Evaluation of GAN architectures for visualisation of HPV viruses from microscopic images |
Authors | Gao, X., Wen, S., Li, D., Liu, W., Xiong, J., Xu, B., Liu, J., Zhang, H. and Liu, X. |
Abstract | Human papillomavirus (HPV) remains a leading cause of virus-induced cancers and has a typical size of 52 to 55nm in diameter. Hence conventional light microscopy that usually sustains a resolution at ~100nm per pixel falls short of detecting it. This study explores four state of the art generative adversarial networks (GANs) for visualising HPV. The evaluation is achieved by counting the HPV clusters that are corrected identified as well as drug treated cultured cells, i.e. no HPVs. The average sensitivity and specificity are 78.81%, 76.37%, 76.62% and 84.71% for CycleGAN, Pix2pix, ESRGAN and Pix2pixHD respectively. For ESRGAN, the training takes place by matching pairs between low and high resolution (x4) images. For the other three networks, the translation is performed from original raw images to their coloured maps that have undertaken Gaussian filtering in order to discern HPV clusters visually. Pix2pixHD appears to perform the best. |
Keywords | Generative adversarial network (GAN); super resolution; Human papilloma virus like particles (HPVLPs); Pix2pixHD; CycleGAN |
Conference | 20th IEEE ICMLA 2021 |
Page range | 829-833 |
Proceedings Title | 2021 20th IEEE International Conference On Machine Learning And Applications (ICMLA) |
ISBN | |
Electronic | 9781665443371 |
Paperback | 9781665443388 |
Publisher | IEEE |
Publication dates | |
14 Dec 2021 | |
Online | 25 Jan 2022 |
Publication process dates | |
Deposited | 18 Nov 2021 |
Accepted | 01 Oct 2021 |
Output status | Published |
Accepted author manuscript | |
Copyright Statement | © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICMLA52953.2021.00137 |
Web of Science identifier | WOS:000779208200129 |
Language | English |
https://repository.mdx.ac.uk/item/8990y
Download files
72
total views19
total downloads3
views this month2
downloads this month