AI-driven longitudinal image analysis for early melanoma diagnosis

Overview

Melanoma is one of the most aggressive forms of skin cancer, yet it is highly treatable when detected early. With the increasing use of smartphones and teledermatology, patients can regularly capture images of their skin lesions, creating valuable longitudinal records that reveal subtle changes over time. However, current artificial intelligence (AI) systems typically analyse individual images in isolation, overlooking important temporal information.

This PhD project will investigate how AI can analyse sequences of skin images collected over time to improve the early diagnosis of melanoma. The research will develop novel deep learning methods for longitudinal image analysis, enabling AI models to identify patterns of disease progression over time. The project will also explore explainable and trustworthy AI techniques to ensure that predictions are transparent, robust, and clinically reliable.

The PhD student will collaborate with clinicians and medical researchers in the School of Medicine at the University of Dundee and Ninewells Hospital, ensuring that their innovations are grounded in real clinical needs. This unique opportunity combines technical excellence with meaningful societal impact, enabling the successful candidate to contribute to the development of next-generation AI technologies that support earlier melanoma diagnosis and help shape the future of AI-driven healthcare.

Diversity statement

Our research community thrives on the diversity of students and staff which helps to make the University of Dundee a UK university of choice for postgraduate research. We welcome applications from all talented individuals and are committed to widening access to those who have the ability and potential to benefit from higher education.