VIOS (pronounced vEEOs) means life (Βίος) in Greek; its common English equivalent bio abounds in science as the word denoting everything about life (biology, biomedicine, bioimaging…). Life is central to our mission. With advances in artificial intelligence (AI), computer vision and inverse problems, our mission is to address societal problems by solving key challenges in the life and natural sciences. This mission inspires our drive in interdisciplinary AI, where we use motivating applications to propose new AI-driven solutions.

News

  • VIOS leads AI Hub: We are delighted that Sotos from VIOS will be the director of CHAI: the new national UK hub on Causal AI and Healthcare (see the UKRI announcement and the governments’s release). See also the University and School of Engineering’s news .

  • 2023 in review: 2023 has been a great year for VIOS. We welcomed Steven as a new academic and Valerio has joined Nottingham. We saw students graduating (Xiao, Victor) landing excellent jobs. We continue to expand. We welcomed 5 new postdocs, 7 new PhD students (3 with Archimedes RC in Greece), 3 visitors, and 2 software engineers. We will continue to expand. This growth has been fueled by impressive success in new grants tackling problems across several applications. From pure theory (representation learning), to computer assisted surgery, to digital research infrastructure aided by AI, to using AI for molecule design, to AI for netzero and many more. We are extremely grateful to our collaborators and the funding agencies for the continued support. Importantly though this success has also led to considerable research output. It is not possible to list it all, but here are some highlights: new patents with Canon, papers at ICLR, best paper awards at DART, papers to soon appear in Nature Methods and Scientific Reports and so much more. We cannot wait to see what 2024 will bring.

  • VIOS is Recruiting PhD Students: VIOS is expanding with new PhD students (at least 3 with fully funding available). Descriptions of the positions will be made available at the join us page.

Read More

Highlighted Publications

1. Understanding metric-related pitfalls in image analysis validation
Reinke, Annika and Tizabi, Minu D and Baumgartner and others
Nature Methods, 1--13
Full Text Preprint

2. Compositionally Equivariant Representation Learning
Liu, Xiao and Sanchez, Pedro and Thermos, Spyridon and O’Neil, Alison Q and Tsaftaris, Sotirios A
IEEE Transactions on Medical Imaging, 1-1
Full Text Preprint

3. Metrics reloaded: recommendations for image analysis validation
Maier-Hein, Lena and Reinke, Annika and Godau, Patrick and others
Nature Methods, 1--18
Full Text Preprint

4. Neural Networks Memorise Personal Information from One Sample
J. Hartley, P.P. Sanchez, F. Haider, S.A. Tsaftaris
Scientific Reports, vol. 13, no. 1, pp. 21366, 2023
Full Text Preprint

5. The role of noise in denoising models for anomaly detection in medical images
A. Kascenas, P. Sanchez, P. Schrempf, C. Wang, W. Clackett, S.S. Mikhael, J.P. Voisey, K. Goatman, A. Weir, N. Pugeault, S.A. Tsaftaris, A.Q. O'Neil
Medical Image Analysis, Volume 90, December 2023
Full Text Preprint

6. Adapting Vision Foundation Models for Plant Phenotyping
F. Chen, M.V. Giuffrida, S.A. Tsaftaris
IEEE/CVF International Conference on Computer Vision 2023
Full Text

7. Diffusion Models for Causal Discovery via Topological Ordering
P. Sanchez, X. Liu, A.Q. O'Neil, S.A. Tsaftaris
ICLR 2023
Preprint Code

Twitter