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

Deep learning for bioimaging: case studies in breast cancer and mutant detection with Quorn


   Centre for Digital Innovation

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 Annalisa Occhipinti  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

Bioimaging deep learning methodologies based on microscopy image analysis have recently emerged, e.g. allowing to automatically detect cancer or quantify the number of cancerous cells presents in a sample. However, several methodological challenges remain to be solved. For example, the currently available deep learning algorithms are not optimised to work with the most recent microscopy images for automated nucleus/cell detection, segmentation, and classification. Moreover, object crowding and overlapping, batch effects, and inconsistent data annotations strongly affect the prediction capability of the deep learning architecture.

As well as cancer detection in biomedicine, a key application of bioimaging deep learning methodologies consists in the detection of mutant formation in cultures within the bioprocessing industry. Today, several food industries provide “meat-free” alternatives with the final aim of tackling climate change and supporting the transition to a Net-Zero future. This includes Quorn™, which has been a successful “meat-alternative” provider since the 1980s with massive production capacity plants to fulfil its global demand.

However, the achievement of a Net-Zero future is hindered by several challenges in the production cycle. For example, the production cycle of Quorn™ mycoprotein must be terminated after about 30 days because of the appearance of mutant strains (C-variant) with altered morphology and function. Monitoring the rise in the C-variant mutant remains challenging, and the appearance of colonials causes premature termination of the fermentation and consequent loss of productivity, with a big impact on the production costs, energy waste, and carbon emissions.

Methodology

 The project will focus on building customised deep learning architectures based on convolutional neural networks (CNNs) for bioimaging. CNNs are designed to recognise patterns and learn inherent features from the set of images from microscopy. The power of CNNs comes from their ability to learn the representation of the training data (images) and relate it to the output variable that we want to predict (optimal time for terminating the production cycle). Architecture optimisation and feature analysis will also be performed as part of the training phase.

Hence, the proposal aims at developing advanced deep learning techniques (multi-modal and transfer learning) to identify hidden patterns in multi-modal architectures, merging imaging and other omic and/or bioreactor data.

This methodological framework will be validated through two case studies:

(i) Designing, implementing and training an AI-based architecture for early detection of breast cancer in publicly available bioimaging data, while investigating the molecular causes of this appearance. Strong emphasis will be given to feature analysis and interpretation methods for the architecture, which will be first attempted using the state-of-the-art SHAP methodology.

(ii) Refining and applying the pipeline in collaboration with Quorn to predict the rise in the C-variant mutant. This will leverage in-kind support from Quorn to provide mycelia samples, sample preparation, access to 50L fermenter, metadata support. We aim to predict the formation of the C-variant in order to reduce wastage and carbon emissions in the production process. The final deep learning model will be trained and tested on the images provided by Quorn™, and it will be subsequentially tested for additional pharmaceutical and food-industry applications.

The developed architecture will be made publicly available allowing other researchers and industrial partners to adapt it for their applications. 

Entry Requirements

Applicants should hold or expect to obtain a good honours degree (2:1 or above) in a relevant discipline. A masters level qualification in a relevant discipline is desirable, but not essential, as well as a demonstrable understanding of the research area. Further details of the expected background may appear in the specific project details. International students will be subject to the standard entry criteria relating to English language ability, ATAS clearance and, when relevant, UK visa requirements and procedures.

How to Apply

Applicants should apply online for this opportunity at: https://e-vision.tees.ac.uk/si_prod/userdocs/web/apply.html?CourseID=1191

Please use the Online Application (Funded PHD) application form for the year starting ‘October 2021’. When asked to specify funding select “other” and enter ‘RDS’ and the title of the PhD project that you are applying for. You should ensure that you clearly indicate that you are applying for a Funded Studentship and the title of the topic or project on the proposal that you will need to upload when applying. If you would like to apply for more than one project, you will need to complete a further application form and specify the relevant title for each application to a topic or project.

Applications for studentships that do not clearly indicate that the application is for a Funded Studentship and state the title of the project applied for on the proposal may mean that your application may not be considered for the appropriate funding.

For academic enquiries, please contact Dr Annalisa Occhipinti [Email Address Removed].

For administrative enquiries before or when making your application, contact [Email Address Removed]


Funding Notes

The Fees-Paid PhD studentship will cover all tuition fees for the period of a full-time PhD Registration of up to four years. Successful applicants who are eligible will be able to access the UK Doctoral Loan scheme https://www.gov.uk/doctoral-loan to support with living costs. The Fully Funded PhD Studentship covers tuition fees for the period of a full-time PhD Registration of up to four years and provide an annual tax-free stipend of £15,000 for three years, subject to satisfactory progress. Applicants who are employed and their employer is interested in funding a PhD, can apply for a Collaborative Studentship
Search Suggestions
Search suggestions

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

PhD saved successfully
View saved PhDs