Breast cancer (BC) continues to be a major health challenge for women globally. Early and accurate diagnosis is important for better patient outcomes, but current methods have limitations. When BC is detected in its later stages, then treatment becomes significantly more expensive. This strains already limited healthcare budgets and creates a double burden: for patients facing high treatment costs and for governments struggling to provide adequate care. Conversely, early detection permits more cost-effective treatment options that improve patient outcomes and reduce the economic burden on healthcare systems. Mammography is a gold standard, world-recognised tool that has been proven effective in reducing mortality rates but faces challenges with accuracy. It can fail to identify cancer in women with dense breast tissue (up to 40% of the population) where the tissue can hide abnormalities. Additionally, it can flag benign lesions as suspicious, leading to unnecessary biopsies and anxiety. Furthermore, subjectivity in interpreting mammograms can impact the consistency of malignancy prediction by radiologists. These limitations highlight the requirement for enhanced diagnostic tools. Challenges extend beyond initial diagnosis to classifying breast cancer's molecular subtypes (Luminal A, B, HER2-positive, and triple-negative). These subtypes play a key role in determining prognosis and guiding treatment decisions.

This project aim is to emerge as a response to these limitations by harnessing the power of AI and multimodal medical imaging (i.e., radiology and pathology). This innovative project aims to develop a comprehensive suite of deep learning-based user-friendly tools to empower healthcare professionals in the fight against breast cancer.

Job Responsibility

As a PhD candidate, you will: 

• Develop novel innovative AI models with radiomics and biomarkers based on computer vision and deep learning methods for predicting treatment response and outcomes, tumor staging, and tissue identification from various modalities of images (mammograms, ultrasounds, MRI, and clinical reports) to improve breast cancer detection. 
• Gain expertise in deep learning, machine learning, medical image analysis, Large Language Models (LLMs), and computer vision. 
• Integrate LLMs techniques to analyse patient history and clinical notes for a more comprehensive approach. 
• Work alongside leading researchers in a collaborative and stimulating environment. 
• Leverage deep learning to create intelligent systems that assist doctors in accurate and early diagnosis. 
• Conduct independent validation studies to assess how well these AI (Artificial Intelligence) algorithms generalise to real-world clinical practice. 
• Contribute to the development of groundbreaking AI solutions for breast cancer diagnosis. 
• Publish your research in top scientific artificial intelligence / medical journals and present findings at international conferences such as MICCAI, CVPR, ICCV, and NeurIPS.
• Attend workshops and conferences to stay at the forefront of the field.

Your Profile

We are seeking a highly motivated PhD candidate to join our dynamic, cross-disciplinary team. You will have the chance to develop innovative deep learning models and shape the research direction alongside leading experts.

We Offer

• This 4 years PhD studentship is funded by Barts Charity and comes with a tax-free starting stipend of £24,278. It is open to all students. Those who are not UK Nationals or non-UK nationals with indefinite leave to remain in the UK will need to acquire a visa ahead of the start of the studentship. University tuition fees (at UK levels) will be met by the funding body. 
• The opportunity to work on a project with significant societal implications, directly impacting the lives of cancer patients. 
• Access to state-of-the-art computing resources, including high-performance GPUs and a dedicated research computing cluster. 
• Opportunities to develop your professional network through collaborations with leading researchers and institutions. 

Entry Requirements

The ideal candidate will have: 

• Applicants should hold a First or 2:1 UK honours degree in computer science, Artificial Intelligence, or a related field, or a 2:2 alongside a good Master's degree.
• Experience or interest in machine learning (deep learning) and medical image analysis (radiological and pathological imaging).
• Strong programming skills (preferably Python).
• Experience with deep learning frameworks (e.g., PyTorch, TensorFlow).
• Familiarity with computer vision algorithms and image processing methods.
• Proficiency in deep learning is evidenced by relevant coursework and a strong presence on GitHub.
• Working knowledge of Natural Language Processing (NLP) and LLM.
• Experience or enthusiasm for working with clinicians.
• A passion for research and a desire to make a real-world impact.

English Language Requirements

Applicants for whom English is not a first language will also require a minimum IELTS score of 6.5 (with 6.0 in the written component) or equivalent, unless your undergraduate degree was studied in, and awarded by, an English speaking country. For more information on acceptable English language qualifications please see here.

Fee Status

The funding for this studentship only covers tuition fees at the Home rate, therefore, only those eligible for UK Home fees should apply.

The studentship includes the following funding for 4 years:

• A tax-free annual stipend of £24,278
• Tuition fees at the Home rate*
• Project consumables

*The funding for this studentship only covers tuition fees at the Home rate, therefore, only those eligible for UK Home fees should apply.

To apply you will need to complete an online application form. Please select the 'Non-clinical PhD' option.

The following supporting documents will be required as part of your application:

• Your CV
• Statement of purpose
• Details of 2 referees
• Copy of your transcript(s), including a breakdown of marks
• Copy of your passport
• If applicable, proof of English proficiency

If you have a question about the project, or would like to arrange an informal discussion, please contact the supervisor directly (subject ‘PhD applicant’). For general enquiries about the PhD studentship or application process please contact the Teaching Office.

Successfully shortlisted candidates will be invited to an interview at Barts Cancer Institute.