PhD Studentship: Multimodal clinical and imaging learning algorithms for skin lesion analysis

Project contact: Prof Moi Hoon Yap

Funding info:

Home fees (2023/24) included plus an annual stipend paid at the UKRI rate (£17,668 for 2022/23). 

Mode of study: Full time

Eligibility:

Open to home and overseas students.

Eligible overseas students will need to make up the difference in tuition fees. 

Key dates:      

Closing date: 16 October 2023

Expected start: January 2024

Project summary

This research proposes to use multimodal clinical and multi-imaging data to create new skin lesion analysis methods. The International Skin Imaging Collaboration (ISIC) is a world-leading consortium in skin imaging research. The goal is to improve skin cancer diagnosis and enable researchers and clinicians to work collaboratively.

In collaboration with the International Skin Imaging Collaboration (ISIC), we promote knowledge of the possibilities of accurate skin lesion detection and recognition, afforded by recent advances in deep learning and multimodal fusion methods. This project builds on our previous work in curating and recommending the use of ISIC datasets and new methodology in skin lesion segmentation. This research will work directly with ISIC AI Working Group and access to the multimodal dataset (such as clinical data, confocal microscopy and histopathology).

The PhD candidate will receive professional development training from the University and our research partners. Joint supervision will broaden the perspective on the research impact and enrich the student experience as the candidate gains a wider understanding of applied research and interacting with clinicians and international researchers.

Aims and objectives

The proposed research project aims to investigate the ability of deep learning networks to perform automated skin lesion detection using multi-imaging and associated clinical metadata. The objectives are:

• Conduct a comprehensive review on the current state-of-the-art classification networks for use in multi-class skin lesion recognition.
• Create a new mechanism of access to ISIC platform and data curation.
• Propose a novel multimodal skin lesion classification based on clinical and multi-imaging
• Develop early detection algorithms (based on size analysis) and a robust skin cancer detection algorithm for different skin tones.
• Evaluate the efficacy of the new classification model

Specific requirements of the project

Candidates must have a strong motivation for research and excellent programming skills. Expertise of developing computer vision and machine learning algorithms would be desirable, with an interest in image analysis.

Qualifications:

• A high grade undergraduate degree (first class or upper second) in Computer Science or MSc in relevant field

Skills:

• Knowledge of programming and data analysis
• Good communication and writing skills
• Developing image analysis/machine learning algorithms would be beneficial
• Able to work as part of a joint academia and clinical team

How to apply

Interested applicants should contact Prof Moi Hoon Yap for an informal discussion.

To apply you will need to complete the online application form for a full-time PhD in Computing and digital technology (or download the PGR application form), by clicking the 'Apply' button, above.

You should also complete the PGR thesis proposal (supplementary information) form addressing the project’s aims and objectives, demonstrating how the skills you have maps to the area of research and why you see this area as being of importance and interest. 

If applying online, you will need to upload your statement in the supporting documents section, or email the application form and statement to mailto:PGRAdmissions@mmu.ac.uk. Closing date 16 October 2023. Expected start January 2024.

Please quote the reference: SciEng-MHY-2023-skin-lesion-analysis

Advert information