My name is Adrian Galdran, and I was appointed as a Senior Lecturer in Data Science for Medical Imaging last November, in the context of BU’s Academic Targeted Research Scheme. Although I am particularly interested in medical image analysis, I have a broad interest in medical data taking any shape and nature, be it text, imaging, video, or even big tables filled with numbers!
I have been working on computer vision with medical applications for a while now. After earning my PhD in the Basque Country University (northern Spain), I headed to the beautiful Porto, where I spent two years as a postdoctoral fellow at INESC-TEC. In those years I focused a lot on the automatic analysis of images of the eye fundus. These are images acquired by projecting light into the back of the eye and capturing a picture of the retina, and they are useful for the early detection of diseases like Diabetic Retinopathy or Age-Related Diabetic Maculopathy.
An image of the eye fundus – the retina
When a person suffers from this kind of diabetes, retinal vessels start to hemorrhage and leak blood into the retina, which at first starts as micro-aneurysms, but later develops into larger lesions and leads to sight-threatening situations. I find it fascinating that we can diagnose diseases like diabetes by looking into the human retina.
After my stay in Portugal, I moved for a second postdoctoral experience to Montréal, Canada, where I worked on deep learning for medical image classification and segmentation, again with a focus on retinal imaging. I spent one year in Canada, with its rough winter and a wonderful summer. It was then that I received the offer to pursue my research within BU, in the context of the new Medical Imaging and Visualisation Institute (IMIV). I am very excited to collaborate with this new institution, which houses an MRI scanner and ultrasound devices. I expect that the privilege of having access to these advanced facilities will trigger research in medical image analysis at BU, and I am hoping to be part of it.
If you are interested in collaborating in any aspect of medical image analysis, please contact me to discuss any common project we may build.
The SIAM Journal on Imaging Sciences (“SIIMS – a broad authoritative source for fundamental results in imaging sciences, with a unique combination of mathematics and applications”), an influential Q1-journal with a significant Impact Factor and SJR indicator, has just published the paper “Automatically Controlled Morphing of 2D Shapes with Textures” authored by NCCA academics and students. This multidisciplinary paper proposes a novel theoretical and practical framework resulting in a suite of mathematically substantiated techniques important in the context of 2D imagery, artistic design, computer animation, and emerging streaming and interactive applications.
The paper has a rather long and non-trivial history related to the fusion of academic and student research. Initially, NCCA UG student Felix Marrington-Reeve (“Computer Visualisation and Animation” course, Level 6) undertook his R&D project within the “Innovations” unit and got some interesting results. The 8-page paper written on the basis of his project and co-authored with his supervisors Dr Valery Adzhiev and Prof Alexander Pasko, was, however, rejected in 2017 by two international conferences (they were prepared to accept a short version but the authors thought the work deserved a better fate).
After Felix’s graduation (he started working in a leading production company Framestore) Dr Oleg Fryazinov and PhD student Alexander Tereshin joined the project team. A lot of additional theoretical and practical work had been done, and in February 2019 the radically modified and extended 30-page version was submitted to SIIMS. After two-stage rigorous peer-reviewing process, in October 2019 the paper was accepted by this prestigious journal.
- Tereshin, A., Adzhiev, V., Fryazinov, O., Marrington-Reeve, F., Pasko, A. (2020). “Automatically Controlled Morphing of 2D Shapes with Textures”, The SIAM Journal on Imaging Sciences, Vol. 13, No. 1, pp. 78-107. DOI: 10.1137/19M1241581
- Full text of the paper: http://eprints.bournemouth.ac.uk/33366/
Innovate UK and the Engineering and Physical Sciences Research Council (EPSRC) are to invest a total of £19.5 million to support projects in Quantum Technologies. Projects may involve technologies belonging to one of the core groups defined in the UK’s roadmap for quantum technologies: clocks, sensors, imaging, communications or computing.
The call is now open, the registration deadline is 28th September and the call closes at noon on the 5th October.
Projects must be industry-led, but projects involving academics as partners are welcome, provided academic costs do not exceed 50% of the total.
Up to £6 million will be available for Feasibility Studies, which will fund the development of early stage devices, component technologies and for marketing studies. Projects will last up to 12 months and have total costs of £50k- £400k.
The Collaborative R&D call will seek to connect the supply chain, to deliver a demonstrator technology and must include an end user. A fund of £13.5 million is available. Total project values should be £500k – £2 million, but an addition 10% is available which can only be used for capital equipment, taking the maximum project value to £2.2 million.
The call brief is available here: https://www.gov.uk/government/publications/funding-competition-commercialisation-of-quantum-technologies
Networking and briefing events – click on the links for more information as dates, times, venues and content of the events do vary.
If you are interested in this call you must contact RKEO with adequate notice before the deadline. Please note that some funding bodies specify a time for submission as well as a date. Please confirm this with your RKEO Funding Development Officer.
You can set up your own personalised alerts on Research Professional. If you need help setting these up, just ask your School’s/Faculty’s Funding Development Officer in RKEO or view the recent blog post here. If you are thinking of applying, why not add an expression of interest on Research Professional so that BU colleagues can see your intention to bid and contact you to collaborate.