Ben Glocker

TL;DR: In this paper, a progressive generative adversarial network (GAN) was used to create high-resolution synthetic mammograms that are not easily distinguishable from real images, which can be used to generate high resolution synthetic images.

TL;DR: In this article, a graph convolutional network (GCN) was proposed for brain analysis in populations, combining imaging and non-imaging data. But GCN models focus on pairwise similarities without modelling the subjects' individual characteristics and features, which can reduce performance.

TL;DR: It is shown that the local Gaussian approximator can be applied to several auto-encoding models to perform image restoration and unsupervised lesion detection and achieves state-of-the-art results.

TL;DR: The UK National Screening Committee's assessments of the use of AI systems to examine screening mammograms continues to focus on maximising benefits and minimising harms to women screened, when deciding whether to recommend the implementation of AI into the Breast Screening Programme in the UK as discussed by the authors .

TL;DR: The quality of automatically generated segmentations of cardiovascular MR (CMR) scans from the UK Biobank (UKBB) Imaging Study is assessed using the Dice Similarity Coefficient (DSC) to be a measure of segmentation quality.