FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Variational approaches for imaging tasks in cell biology


   Centre for Accountable, Responsible and Transparent AI

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr Vinay Namboodiri, Dr Julia Sero  Applications accepted all year round  Competition Funded PhD Project (UK Students Only)

About the Project

The goal of this project is to develop strategies for cell segmentation, classification and tracking through variational deep learning techniques approaches that enable estimation of uncertainties in achieving these tasks. These tools will be applied to investigating biological mechanisms of cell growth and tumorigenesis. Working together with cell biologists, the student will also have the opportunity to generate and test hypotheses on new datasets produced with their input.

Time-lapse microscopy is a powerful tool for investigating the dynamic changes in cell proliferation, migration, and survival that underlie cancer biology. Automating data analysis is critical for exploiting the wealth of data contained in time-lapse movies. Fluorescent labels are commonly used to facilitate object identification and tracking, but label-free imaging using transmitted light (brightfield) reduces phototoxicity and cell perturbation. However, brightfield images pose significant technical challenges compared with fluorescent images. Humans can easily recognise low-contrast objects on irregular backgrounds, but computers have historically struggled with this type of task. Recent developments in AI show promise for improving computer vision to the level of a trained human observer, for example using convolutional neural networks to identify cell division events [1]. But challenges remain for optimising cell tracking and classification in complex conditions observed in tumour cells, such as overgrowth, irregular morphology, and rapid movement.

The method will combine probabilistic deep learning techniques to ensure that if required human intervention can be sought based on calibrated uncertainties. The methods would incorporate temporal recurrence models combined with attention-based methods to ensure dense estimation of cells can be reliably identified and tracked and would be invariant to the variations of resolution and contrast that are prevalent in these imaging techniques.

These approaches would lead to progress through explainable machine learning techniques for a number of applications in cell biology imaging.

This project is associated with the UKRI Centre for Doctoral Training (CDT) in Accountable, Responsible and Transparent AI (ART-AI). We value people from different life experiences with a passion for research. The CDT's mission is to graduate diverse specialists with perspectives who can go out in the world and make a difference.

Applicants should hold, or expect to receive, a first or upper-second class honours degree in a relevant subject. Applicants should have taken a mathematics unit or a quantitative methods course at university or have at least grade B in A level maths or international equivalent.

Informal enquiries about the project should be directed to Dr Vinay Namboodiri.

Formal applications should be accompanied by a research proposal and made via the University of Bath’s online application form. Enquiries about the application process should be sent to [Email Address Removed].

Start date: 3 October 2022.


Funding Notes

ART-AI CDT studentships are available on a competition basis and applicants are advised to apply early as offers are made from January onwards. Funding will cover tuition fees and maintenance at the UKRI doctoral stipend rate (£16,062 per annum in 2022/23, increased annually in line with the GDP deflator) for up to 4 years.
We also welcome applications from candidates who can source their own funding.

References

[1] Liu Z. et al., "A survey on applications of deep learning in microscopy image analysis", Computers in Biology and Medicine. 134:104523. 2021. https://doi.org/10.1016/j.compbiomed.2021.104523
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs