Skip to main content

Retinal image analysis

We perform the analysis of retinal images by detecting the eye structures such as the blood vessels and optic disc first. Then the retinal image is analysed to detect the suspicious lesion regions if any. The segmentation of blood vessel is based on the Graph Cut technique. In opposed to the traditional formulation of the graph which is normally ineffective for long, thin structures like the blood vessel, we have included the flux vectors in the graph construction and achieved better results on a number of public datasets. We have addressed the problem of optic disc segmentation based on prior blood vessel segmentation. Two different methods have been developed and evaluated: a direct extension of the Graph Cut method with a compensation factor to eliminate the interference of blood vessels, and the background reconstruction on the blood vessels using Markov Random Field. Based on the results of blood vessels and optic disc, a further detection and classification of suspicious lesion areas in the retinal is performed.


  • Dodo, B., Li, Y., Eltayef, K., & Liu, X. Graph-Cut Segmentation of Retinal Layers from OCT Images. In International Conference on Bioimaging. Portugal, 2018. Best Student Paper Award.
  • Wang, C., Wang, Y., & Li, Y. Automatic Choroidal Layer Segmentation Using Markov Random Field And Level Set Method. IEEE Journal of Biomedical and Health Informatics, volume 21, issue 6, pages 1694-1702, 2017.
  • Djibril Kaba, Yaxing Wang, Chuang Wang, Xiaohui Liu, Haogang Zhu, Ana G. Salazar-Gonzalez and Yongmin Li. Retina Layer Segmentation Using Kernel Graph Cuts and Continuous Max-Flow. Optics Express, volume 23, issue 6, pages 7366-7384, 2015.
  • Ana Salazar-Gonzalez, Djibril Kaba, Yongmin Li and Xiaohui Liu. Segmentation of blood vessels and optic disc in retinal images. IEEE Journal of Biomedical and Health Informatics, volume 18, number 6, page 1874-1886, 2014.
  • A. Salazar-Gonzalez, D. Kaba and Y. Li. MRF Reconstruction of Retinal Images for the Optic Disc Segmentation. In Proc. International Conference on Health Information Science (HIS 2012), Beijing, China, 2012. Best Paper Award.
  • A. Salazar-Gonzalez, Y. Li and X. Liu. Optic Disc Segmentation by Incorporating Blood Vessel Compensation. In Proc. International Workshop on Computational Intelligence in Medical Imaging, Paris, France, 2011.
  • A. Salazar-Gonzalez, Y. Li and X. Liu. Retinal blood vessel segmentation via graph cut. In Proc. International Conference on Control, Automation, Robotics and Vision, Singapore, December 2010

Meet the Principal Investigator(s) for the project

Dr Yongmin Li
Dr Yongmin Li - Please visit my personal website where you may find more details of my work. Dr. Yongmin Li received his PhD from Queen Mary, University of London, MEng and BEng from Tsinghua University, China. Before joining Brunel University, he worked as a research scientist in the British Telecom Laboratories. Dr. Li is a Senior Member of the IEEE, and Senior Fellow of the Higher Education Academy. He was ranked in the world's top 2% scientists by the Standardized Citation Indicators (Elsevier) every year over the past four years ( 2020, 2021, 2022, and 2023). His research interest covers the areas of data science, machine learning, artificial intelligence, image processing, computer vision, video analysis, medical imaging, bio-imaging, biomedical engineering, healthcare technologies, automatic control and nonlinear filtering. Together with his colleagues, their work has won the following awards: 1st Place, RETOUCH Challenge (Online), MICCAI 2023 (with Ndipenoch, Miron and Wang). 2nd Place, FeTA Challenge, MICCAI 2022 (with McConnell, Ndipenoch and Miron). Most Influential Paper over the Decade Award, MVA, 2019 (with Ruta, Porikli, et al). Best Student Paper Award, Bioimaging, 2018 (with Dodo, Eltayef and Liu). VC Prize, Brunel University, 2015 (with Kaba and Liu). Best Paper Award, HIS, 2012 (with Salazar-Gonzalez and Kaba). Best Poster Prize, BMVC, 2007 (with Ruta and Liu). Best Scientific Paper Award, BMVC, 2001 (with Gong and Liddell). Best Paper Prize, RATFG, 2001 (with Gong and Liddell). Prospective PhD Students: We invite talented and hard-working students to join us for their PhD study. From time to time, we may have studentships available, which include an annual bursary (about £18,000 this year) plus payment of tuition fees for three years. Currently we have several projects on-going, for example, Deep Learning for Medical Imaging, Natural Language Processing for Business Intelligence, Natural Language Processing for Tax Assessment, and Image/Video Content Generation for Personalised Remarketing. But any other topics within the area of artificial intelligence and data science would also be welcome.  Contact me for details if interested. Master of Science in Artificial Intelligence 2023/24: Built on our strong international research profile (consistently ranked in the top 100 in the world, 1st in UK for H-index and Highly Cited Papers for 3 years in a row from 2018-2020, and 3rd in UK for overall performance in "the NTU Performance Ranking of Scientific Papers for World Universities", Subject: Computer Science, 2020),  we offer the MSc Artificial Intelligence course with great flexibility (1 year full-time, 2 year part-time or 3 year staged study). If you are interested, apply here. 15 Scholarships available for applicants from under-represented groups, £10,000 of each. Research & Development Collaboration: Developing downstream applications of large AI models is a focused area of my group in the upcoming years. Contact me if you have a collaboration project. We can assist in securing funding from sources like UKRI, EU, or Innovate UK, potentially cutting your costs in the project significantly (e.g. by 1/3 or more), plus the university's input.

Related Research Group(s)


Intelligent Data Analysis - Concerned with effective analysis of data involving artificial intelligence, dynamic systems, image and signal processing, optimisation, pattern recognition, statistics and visualisation.

Partnering with confidence

Organisations interested in our research can partner with us with confidence backed by an external and independent benchmark: The Knowledge Exchange Framework. Read more.

Project last modified 22/11/2023