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, computer vision and inverse problems, our mission is to address societal problems by solving key challenges in the life and natural sciences.
News
Sotos becomes an ELLIS Fellow: Sotos has been recognised as a Fellow of the European Lab for Learning and Intelligent Systems (ELLIS) of Edinburgh’s ELLIS Unit.
We are expanding!: We are looking for PostDocs and PhD students, visit our join us page for more information. See this link for an opening on Causal Machine Learning in healthcare .
VIOS at MICCAI 2021: VIOS has strong presence in MICCAI presenting 5 papers, and organizing one tutorial, and co-organising one workshop.
New Surveys!: Two new monster surveys from our group: on disentangled representations and on privacy and ML.
Sotos’ Keynote: Sotos will be keynote speaker for MIUA 2022.
Highlighted Publications
1. Why patient data cannot be easily forgotten?
R. Su, X. Liu, S.A. Tsaftaris
2022, submitted
Preprint
2. Diffusion Causal Models for Counterfactual Estimation
P. Sanchez, S.A. Tsaftaris
CLeaR 2022
Preprint Code
3. Measuring Unintended Memorisation of Unique Private Features in Neural Networks.
J. Hartley, S.A. Tsaftaris
2022
Preprint Code
4. Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation
X. Liu, S. Thermos, A. O'Neil, S.A. Tsaftaris
MICCAI 2021
Preprint Code
5. Controllable cardiac synthesis via disentangled anatomy arithmetic
S. Thermos, X. Liu, A. O'Neil, S.A. Tsaftaris
MICCAI 2021
Preprint Code
6. Cohort Bias Adaptation in Aggregated Datasets for Lesion Segmentation
B. Nichyporuk, J. Cardinell, J. Szeto, R. Mehta, S.A. Tsaftaris, D.L. Arnold, T. Arbel
MICCAI workshop, 2021, DART
Preprint
7. Stop Throwing Away Discriminators! Re-using Adversaries for Test-Time Training
G. Valvano, A. Leo, S.A. Tsaftaris
MICCAI workshop, 2021, DART
Preprint Code
8. Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning
G. Valvano, A. Leo, S.A. Tsaftaris
MICCAI workshop, 2021, DART
Preprint Code
9. Have you forgotten? A method to assess if machine learning models have forgotten data
X. Liu, S.A. Tsaftaris
MICCAI 2020
Preprint
10. INSIDE: Steering Spatial Attention with Non-Imaging Information in CNNs
G. Jacenków, A.Q. O'Neil, B. Mohr, S.A. Tsaftaris
MICCAI 2020
Full Text Preprint Code
11. Disentangled Representations for Domain-generalized Cardiac Segmentation
X. Liu, S. Thermos, A. Chartsias, A.Q. O'Neil, S.A. Tsaftaris
MICCAI 2020, STACOM: Statistical Atlases and Computational Modelling of the Heart
Preprint Code
12. Max-Fusion U-Net for Multi-Modal Pathology Segmentation with Attention and Dynamic Resampling
H. Jiang, C. Wang, A. Chartsias, S.A. Tsaftaris
MICCAI 2020, MyoPS: Multi-sequence CMR based Mycardial Pathology Segmentation Challenge
Preprint Code
13. Semi-supervised Pathology Segmentation with Disentangled Representations
H. Jiang, A. Chartsias, X. Zhang, G. Panastasiou, S. Semple, M. Dweck, D. Semple, R. Dharmakumar, S.A. Tsaftaris
MICCAI 2020, DART: Domain Adaptation and Representation Transfer
Preprint Code