AUTHOR=Bommanapally Vidya , Abeyrathna Dilanga , Chundi Parvathi , Subramaniam Mahadevan 

TITLE=Super resolution-based methodology for self-supervised segmentation of microscopy images

JOURNAL=Frontiers in Microbiology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2024.1255850

DOI=10.3389/fmicb.2024.1255850

ISSN=1664-302X

ABSTRACT=Data-driven Artificial Intelligence (AI)/ Machine learning (ML) image analyses approaches have gained a lot of momentum in analyzing microscopy images in bioengineering, biotechnology, and medicine. The success of these approaches crucially relies on the availability of high-quality microscopy images, which is often a challenge due to the diverse experimental conditions and modes under which these images are obtained. In this paper, we propose the use of recent ML-based image super-resolution (SR) techniques for improving the image quality of microscopy images, incorporating them into multiple ML-based image analyses tasks, and describe a comprehensive study, investigating the impact of SR techniques on the segmentation of microscopy images. The impacts of 4 Generative Adversarial Network (GAN)-and transformer based SR techniques on microscopy image quality are measured using 3 well-established quality metrics. These SR techniques are incorporated into multiple deep network pipelines using supervised, contrastive, and non-contrastive self-supervised methods to semantically segment microscopy images from multiple datasets. Our results show that the image quality of microscopy images has a direct influence on the ML model performance and that both supervised and self-supervised network pipelines using SR images perform better by 2%-6% in comparison to baselines not using SR. Based on our experiments, we also establish that the image quality improvement threshold range  for the complemented Perception based Image Quality Evaluator(PIQE) metric can be used as a pre-condition by domain experts to incorporate SR techniques to significantly improve segmentation performance. A plug-and-play software platform developed to integrate SR techniques with various deep networks using supervised and self-supervised learning methods is also presented.