Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Classifying and localising future cancerous lesions from medical image data using longitudinal data

   Faculty of Engineering and Physical Sciences

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof Gustavo Carnerio  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

Many types of cancer [1] follow complex disease progression processes, where the main tool to reduce the mortality from these cancers depends on their early detection via population-wide health screening programs [2]. In these programs, medical imaging data are collected from asymptomatic patients and analysed by clinicians to localise and classify cancerous lesions, where the earlier the detection, the better the treatment outcome [2]. A natural question is: can we improve treatment outcomes by detecting cancerous signs that appear before the first lesions are visible? 

Modern medical image analysis methods are developed to localise and classify cancerous lesions [3], but methods that can classify medical images in terms of future cancer risk are still rare. Some examples can classify but not localise future cancerous lesions without using longitudinal data [4]. Others use longitudinal data but cannot localise future lesions because they aim to detect visible disease signs [5]. 

In this project, we will propose a method to analyse longitudinal medical image data from asymptomatic patients from population-wise health screening programs to predict the risk of developing cancer and to localise future cancerous lesions. For the longitudinal analysis, we will develop new machine learning approaches to analyse time-series data, where risk prediction will be based on survival models, and future cancerous lesion localisation will depend on explainable artificial intelligence methods. This project will provide numerous contributions to the medical image analysis community and introduce innovative clinical analysis techniques.

Studentship group name

Surrey Institute for People-Centred AI


School of Computer Science and Electrical Engineering

Research group(s)

Centre for Vision, Speech and Signal Processing

How to Apply

Open to UK and International students starting in October 2023.

Applications should be submitted via the Vision, Speech and Signal Processsing PhD programme page. In place of a research proposal you should upload a document stating the title of the projects (up to 2) that you wish to apply for and the name(s) of the relevant supervisor. You must upload your full CV and any transcripts of previous academic qualifications. You should enter ’Faculty Funded Competition’ under funding type.


The studentship will provide a stipend at UKRI rates (currently £17,668 for 2022/23) and tuition fees for 3.5 years. An additional bursary of £1700 per annum for the duration of the studentship will be offered to exceptional candidates.

Biological Sciences (4) Computer Science (8) Engineering (12)


[1] Bray, F. et al. "GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries." CA: a Cancer Journal for Clinicians 71, no. 2021 (2020): 209-249.
[2] Coleman, Cathy. "Early detection and screening for breast cancer." In Seminars in oncology nursing, vol. 33, no. 2, pp. 141-155. WB Saunders, 2017.
[3] Frazer, Helen ML, et al. "Evaluation of deep learning‐based artificial intelligence techniques for breast cancer detection on mammograms: Results from a retrospective study using a BreastScreen Victoria dataset." Journal of medical imaging and radiation oncology 65, no. 5 (2021): 529-537.
[4] Wanders, Alexander JT, et al. "Interval Cancer Detection Using a Neural Network and Breast Density in Women with Negative Screening Mammograms." Radiology 303, no. 2 (2022): 269-275.
[5] Shu, Michelle, et al. "Deep survival analysis with longitudinal X-rays for COVID-19." In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4046-4055. 2021.

 About the Project