Automated detection and measurement of bacteriophages in electron microscopy images

Project description

Bacteriophages (phages) are viruses that infect bacteria and play important roles in human health, biotechnology, and the environment. Understanding their shapes and sizes helps researchers identify and characterise different types of phages. Transmission Electron Microscopy (TEM) provides detailed images of these tiny viruses, but characterising them is often time-consuming and requires manual measurements (see our web app PhageScale). The challenge is to automatically identify individual phages, distinguish their structural components, such as the head and tail, and accurately measure their dimensions, even when images are noisy or particles overlap. In this project, you will explore how computer vision and deep learning can automate this process. The idea is to develop an AI-based system that detects phage particles in TEM images, segments their structural components (capsid and tail), and measures features such as capsid diameter, tail length, and tail width. You will work on an applied AI problem involving image processing, object detection, image segmentation, deep learning, and quantitative analysis. You do not need advanced biology knowledge. The outcome will be a prototype tool that helps researchers analyse phage images more efficiently, accurately, and consistently.

Co-supervisors

Prof Robert Edwards, Flinders Accelerator for Microbiome Exploration, College of Science & Engineering

Further information

For more information about our research, check out our GitHub profiles Vini2, linsalrob, metagentools, the Edward's lab website and the FAME group's website.

Assumed knowledge

You should have a background in Computer Science, Information Technology, or a related field. A basic understanding of Programming in Python, Computer Vision and AI/ML model training would be awesome. We'll teach you the relevant background in phage biology and provide you with published phage TEM images.

Note: You need to register interest in projects from different supervisors (not a number of projects with the one supervisor).
You must also contact each supervisor directly to discuss both the project details and your suitability to undertake the project.