Identification of human papillomavirus from super resolution microscopic images generated using deep learning architectures

Gao, Xiaohong W. ORCID logoORCID: https://orcid.org/0000-0002-8103-6624, Wen, Xuesong ORCID logoORCID: https://orcid.org/0000-0001-6518-8962, Li, Dong ORCID logoORCID: https://orcid.org/0000-0001-9240-4173 and Liu, Xuefeng (2022) Identification of human papillomavirus from super resolution microscopic images generated using deep learning architectures. In: Deep Learning Applications, Volume 4. Wani, M. Arif and Palade, Vasile, eds. Advances in Intelligent Systems and Computing (AISC), 1434 . Springer. ISBN 9789811961526. [Book Section] (Accepted/In press)

[img] PDF - Final accepted version (with author's formatting)
Restricted to Repository staff and depositor only until 30 November 2024.

Download (1MB)

Abstract

This chapter presents five deep learning architectures for identification of Human papillomavirus (HPV) through generation of super resolution (SR) images by 4 folds. Specifically, generative adversarial deep learning networks (GAN) and a texture-based vision transformer (TTSR) architec-ture are applied and evaluated. As such, the generated SR images are able to display the same way a high-resolution image offers in identification of HPV like structures. In comparison, TTSR appears to perform the best with PSNR and SSIM being 28.70 and 0.8778 respectively whereas 25.80/0.7910, 18.35/0.5059. 30.31/0.8013, and 28.07/0.6074 are observed for the methods of RCAN, Pix2Pix, CycleGAN, and ESRGAN respective-ly. With regard to sensitivity and specificity when detecting HPV clus-ters, TTSR also leads with 83.6% and 83.33% respectively. It appears the computational SR images are capable to differentiate distinguishing fea-tures of HPV like particles and to determine the effectiveness of anti-HPV agents, holding promise providing insights into the formation stage of a cancer from HPV in the near future.

Item Type: Book Section
Sustainable Development Goals:
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 35224
Useful Links:
Depositing User: Xiaohong Gao
Date Deposited: 07 Jun 2022 15:45
Last Modified: 04 Oct 2022 10:31
URI: https://eprints.mdx.ac.uk/id/eprint/35224

Actions (login required)

View Item View Item

Statistics

Activity Overview
6 month trend
1Download
6 month trend
15Hits

Additional statistics are available via IRStats2.