Early-Stage Cancer Detection with Lightweight and Robust Machine Learning [SELF-FUNDED STUDENTS ONLY]

This PhD project addresses the challenge of early-stage cancer detection. Artificial intelligence (AI) and machine learning (ML) are transforming medical diagnosis, such as cancer detection. These powerful tools analyze vast amounts of data, uncovering hidden patterns and improving diagnostic accuracy. However, for true impact, we need to develop lightweight and robust ML models.

Lightweight networks are crucial for real-world deployment in resource-constrained settings. They simplify interpretability, making it easier for medical professionals to understand the basis for the model's predictions. Robustness ensures models maintain accuracy even with imperfections in data, a common issue in medical imaging.

Early-stage cancer detection utilising multi-parametric magnetic resonance imaging (MRI) presents a unique challenge. Current ML approaches often struggle due to the subtle nature of these cancers. Diagnosis relies on more than just local features – it requires understanding global relationships between different image regions and incorporating patient context (age, medical history, etc).

This project focuses on developing novel ML architectures specifically designed for early-stage detection of cancers. While initially targeting prostate or brain cancers, findings likely hold promise for early detection of other cancers.

Your research will focus on:

·    Incorporating Global Features and Patient Context: Develop methods that leverage relationships within and across images and patient context, providing a more comprehensive understanding of the cancer's characteristics and a more personalized and accurate diagnosis.

·    Lightweight Network Design: Investigate innovative techniques to create ultra-efficient models capable of accurate diagnosis on standard computing hardware.

·    Explainable AI: Incorporate explainable AI principles to increase trust and adoption by medical professionals, and ensure model transparency and robustness.

This research has the potential to revolutionize early-stage cancer detection. By achieving high accuracy with lightweight and robust models, you can pave the way for widespread adoption in clinical settings, ultimately saving lives:

·    Improved Clinical Workflow: Efficient and accurate AI models can streamline workflows for medical professionals, allowing them to focus on patient care.

·    Earlier Detection, Better Outcomes: Early detection allows for less invasive treatments and improved outcomes.

·    Reduced Healthcare Costs: Early-stage cancer detection allows for less invasive treatment options and improves patient prognosis.

·    Promoting Responsible AI: The project will contribute to the development of robust and transparent AI tools for healthcare, fostering trust and ethical adoption.

To learn more about this project, its requirements, and details please contact Frank Langbein (LangbeinFC@cardiff.ac.uk).

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. A strong background in computer science, mathematics, healthcare technologies or related fields is required. A passion for medical imaging, experience with machine learning, and an eagerness to explore novel approaches are key assets.

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.

This project is accepting applications all year round, for self-funded candidates.

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below.

Please submit your application via Computer Science and Informatics - Study - Cardiff University

In order to be considered candidates must submit the following information:

·       Supporting statement

·       CV

·       In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD

·       In the funding field of your application, please provide details of your funding source.

·       Qualification certificates and Transcripts

·       References x 2

·       Proof of English language (if applicable)

Interview - If the application meets the entrance requirements, you will be invited to an interview. 

If you have any additional questions or need more information, please contact: COMSC-PGR@cardiff.ac.uk