no code implementations • 19 Apr 2024 • Konstantinos Vilouras, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris
In this work, we use a publicly available Foundation Model, namely the Latent Diffusion Model, to solve this challenging task.
no code implementations • 1 Nov 2023 • Konstantinos Vilouras, Xiao Liu, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris
Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one.
no code implementations • 10 Oct 2023 • Xiao Liu, Antanas Kascenas, Hannah Watson, Sotirios A. Tsaftaris, Alison Q. O'Neil
For brain tumour segmentation, deep learning models can achieve human expert-level performance given a large amount of data and pixel-level annotations.
no code implementations • 10 Oct 2023 • Joseph S. Boyle, Antanas Kascenas, Pat Lok, Maria Liakata, Alison Q. O'Neil
The task of assigning diagnostic ICD codes to patient hospital admissions is typically performed by expert human coders.
no code implementations • 30 Aug 2023 • Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni, Jeffrey Dalton, Alison Q. O'Neil
Automated approaches to radiology reporting require the image to be encoded into a suitable token representation for input to the language model.
no code implementations • 13 Jun 2023 • Xiao Liu, Pedro Sanchez, Spyridon Thermos, Alison Q. O'Neil, Sotirios A. Tsaftaris
By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings.
1 code implementation • 19 Jan 2023 • Antanas Kascenas, Pedro Sanchez, Patrick Schrempf, Chaoyang Wang, William Clackett, Shadia S. Mikhael, Jeremy P. Voisey, Keith Goatman, Alexander Weir, Nicolas Pugeault, Sotirios A. Tsaftaris, Alison Q. O'Neil
Denoising methods, for instance classical denoising autoencoders (DAEs) and more recently emerging diffusion models, are a promising approach, however naive application of pixelwise noise leads to poor anomaly detection performance.
1 code implementation • 6 Aug 2022 • Xiao Liu, Spyridon Thermos, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris
Maximisation of mutual information is achieved by introducing an auxiliary network and training with a latent regression loss.
1 code implementation • 25 Jul 2022 • Pedro Sanchez, Antanas Kascenas, Xiao Liu, Alison Q. O'Neil, Sotirios A. Tsaftaris
This requires training with healthy and unhealthy data in DPMs.
1 code implementation • 29 Jun 2022 • Xiao Liu, Spyridon Thermos, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris
Moreover, with a reconstruction module, unlabeled data can also be used to learn the vMF kernels and likelihoods by recombining them to reconstruct the input image.
1 code implementation • 12 Feb 2022 • Grzegorz Jacenków, Alison Q. O'Neil, Sotirios A. Tsaftaris
We use the indication field to drive better image classification, by taking a transformer network which is unimodally pre-trained on text (BERT) and fine-tuning it for multimodal classification of a dual image-text input.
1 code implementation • 26 Aug 2021 • Xiao Liu, Pedro Sanchez, Spyridon Thermos, Alison Q. O'Neil, Sotirios A. Tsaftaris
Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision.
no code implementations • 4 Jul 2021 • Marija Jegorova, Chaitanya Kaul, Charlie Mayor, Alison Q. O'Neil, Alexander Weir, Roderick Murray-Smith, Sotirios A. Tsaftaris
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data.
1 code implementation • 21 Aug 2020 • Grzegorz Jacenków, Alison Q. O'Neil, Brian Mohr, Sotirios A. Tsaftaris
We evaluate the method on two datasets: a new CLEVR-Seg dataset where we segment objects based on location, and the ACDC dataset conditioned on cardiac phase and slice location within the volume.
no code implementations • 31 Jul 2020 • Patrick Schrempf, Hannah Watson, Shadia Mikhael, Maciej Pajak, Matúš Falis, Aneta Lisowska, Keith W. Muir, David Harris-Birtill, Alison Q. O'Neil
Training medical image analysis models requires large amounts of expertly annotated data which is time-consuming and expensive to obtain.
no code implementations • 17 Mar 2020 • Shayne Shaw, Maciej Pajak, Aneta Lisowska, Sotirios A. Tsaftaris, Alison Q. O'Neil
Deep learning shows great potential for the domain of digital pathology.
no code implementations • 10 Oct 2019 • Mattias Appelgren, Patrick Schrempf, Matúš Falis, Satoshi Ikeda, Alison Q. O'Neil
However, the data required to train models for every language may be difficult, expensive and time-consuming to obtain, particularly for low-resource languages.
no code implementations • 14 May 2018 • Alison Q. O'Neil, Antanas Kascenas, Joseph Henry, Daniel Wyeth, Matthew Shepherd, Erin Beveridge, Lauren Clunie, Carrie Sansom, Evelina Šeduikytė, Keith Muir, Ian Poole
We present an efficient neural network method for locating anatomical landmarks in 3D medical CT scans, using atlas location autocontext in order to learn long-range spatial context.