Software: Concentric tube robot optimization from task and anatomical constraints

This repository contains matlab software pertaining to the design of concentric tube robots based on task and anatomical constraints. The software was developed as part of our 2015 IEEE Trans. Robotics publication, titled “Concentric tube robot optimization based on task and anatomical constraints”.

Github link:

Presenting the team’s research at 2ccOCT

Christos was invited to give a talk at the 2nd International Canterbury Conference on OCT, taking place at University of Kent. Christos will present the team’s advances in micro-precise delivery of retinal therapeutics under OCT guidance with flexible robots. More details can be found at the conference’s website:

Grant accepted: Deep learning and neural networks for Adaptive Optics image processing in longitudinal studies

Moorfields Eye Charity has retained for funding our grant titled “Deep learning and neural networks for Adaptive Optics image processing in longitudinal studies”. The investigators of the grant are Prof. Michel Michaelides, Dr. Angelos Kalitzeos, and Dr. Christos Bergeles. The funds will support a dedicated Deep Learning workstation.

Open PhD Position: Computer-Assisted Interventions


Research Area: PhD in Computer-Assisted Interventions

Department: Medical Physics and Biomedical Engineering, Faculty of Engineering

Supervisors: Dr Christos Bergeles, Prof. Lyndon da Cruz

Salary: £16,296 per annum (+ £4,728 for UCL EU/UK fees)

Duration: 4 years

The Wellcome/EPSRC Centre for Interventional and Surgical Sciences invites applications for a PhD Studentship in Computer-Assisted Interventions. This is an exciting opportunity for enthusiastic Engineer with relevant skills in this area to join an internationally leading research group, and conduct patient-centred research.


The PhD Student will be part of a vibrant team that develops robots and algorithms for regenerative medical interventions in confined spaces. More specifically, the funded project pertains to the development of a micro-surgical robot for the implantation of sight-restoring stem cells to the retina. This specific position aims at developing the computer vision tools that enable image-guided delivery of the said stem cells. The student can be involved in the design and development of real-time algorithms for tool segmentation, retinal image analysis, multi-modal image registration, and the overall framework that provides the computer-aided assistance during the robotic intervention. The student will have the opportunity to be involved in all aspects of algorithm development, testing, and deployment to the operating theatre.

The team is highly multidisciplinary, comprising robotics engineers, computer vision specialists, optics engineers, and stem cell biologists under clear clinical guidance.

The project enjoys excellent financial support through a 5-year ERC Starting grant. The project is co-led by the PIs Dr. Christos Bergeles (UCL) and Prof. Lyndon da Cruz (Moorfields Eye Hospital). The student will be employed within the Translational Imaging Group, part of UCL’s Wellcome EPSRC Interventional and Surgical Sciences Centre, and the Centre of Medical Image Computing.

The start date is flexible, but with a strong preference for a start in September 2017. The post is funded for 4 years, and UCL fees at the EU/UK level are covered. Overseas (non-EU/UK) students may apply if they have other means to fund the additional fees.


Applicants are expected to have a first degree (2:1 and above) in computer vision, computer science, medical image computing, biomedical engineering, mathematics or closely related field. Good analytical and communication skills are expected.

If you have queries regarding the vacancy or the application process, please contact Dr. Christos Bergeles, email:

To apply, please apply via UCL’s online application system PRISM, indicating as a degree “Surgical and Interventional Sciences”. For querries regarding the process, please contact Ms. Rebecca Holmes,

Applications will be considered on a rolling basis, until the position is filled. Ideal start date: October 2017

Software: Unsupervised detection of cone photoreceptors in AOSLO images

This repository contains matlab software pertaining to automated cone photoreceptor identification in adaptive optics scanning light ophthalmoscope (AOSLO) images. The software was developed as part of our 2017 Biomedical Optics Express publication, titled “Unsupervised Identification of Cone Photoreceptors in Non-Confocal Adaptive Optics Scanning Light Ophthalmoscope Images”.

Github link:

C. Bergeles, A. M. Dubis, B. Davidson, M. Kasilian, A. Kalitzeos, J. Carroll, A. Dubra, M. Michaelides, and S. Ourselin, “Unsupervised identification of cone photoreceptors in non-confocal adaptive optics scanning light ophthalmoscope images,” Biomedical Optics Express, vol. 8, no. 6, pp. 4244–4251, 2017 [pdf].