Search Results for author: Agisilaos Chartsias

Found 13 papers, 10 papers with code

Contrastive Learning for View Classification of Echocardiograms

no code implementations6 Aug 2021 Agisilaos Chartsias, Shan Gao, Angela Mumith, Jorge Oliveira, Kanwal Bhatia, Bernhard Kainz, Arian Beqiri

Analysis of cardiac ultrasound images is commonly performed in routine clinical practice for quantification of cardiac function.

Classification Contrastive Learning

Semi-supervised Pathology Segmentation with Disentangled Representations

1 code implementation5 Sep 2020 Haochuan Jiang, Agisilaos Chartsias, Xinheng Zhang, Giorgos Papanastasiou, Scott Semple, Mark Dweck, David Semple, Rohan Dharmakumar, Sotirios A. Tsaftaris

The model is trained in a semi-supervised fashion with new reconstruction losses directly aiming to improve pathology segmentation with limited annotations.

Anatomy Disentanglement +1

Max-Fusion U-Net for Multi-Modal Pathology Segmentation with Attention and Dynamic Resampling

1 code implementation5 Sep 2020 Haochuan Jiang, Chengjia Wang, Agisilaos Chartsias, Sotirios A. Tsaftaris

Together with the corresponding encoding features, these representations are propagated to decoding layers with U-Net skip-connections.

Management Segmentation

Measuring the Biases and Effectiveness of Content-Style Disentanglement

4 code implementations27 Aug 2020 Xiao Liu, Spyridon Thermos, Gabriele Valvano, Agisilaos Chartsias, Alison O'Neil, Sotirios A. Tsaftaris

In this paper, we conduct an empirical study to investigate the role of different biases in content-style disentanglement settings and unveil the relationship between the degree of disentanglement and task performance.

Disentanglement Image-to-Image Translation

Disentangled Representations for Domain-generalized Cardiac Segmentation

1 code implementation26 Aug 2020 Xiao Liu, Spyridon Thermos, Agisilaos Chartsias, Alison O'Neil, Sotirios A. Tsaftaris

Robust cardiac image segmentation is still an open challenge due to the inability of the existing methods to achieve satisfactory performance on unseen data of different domains.

Anatomy Cardiac Segmentation +5

Pseudo-healthy synthesis with pathology disentanglement and adversarial learning

1 code implementation20 Apr 2020 Tian Xia, Agisilaos Chartsias, Sotirios A. Tsaftaris

In this paper, we present a model that is encouraged to disentangle the information of pathology from what seems to be healthy.

Anomaly Detection Disentanglement

Learning to synthesise the ageing brain without longitudinal data

1 code implementation4 Dec 2019 Tian Xia, Agisilaos Chartsias, Chengjia Wang, Sotirios A. Tsaftaris

Our method synthesises images conditioned on two factors: age (a continuous variable), and status of Alzheimer's Disease (AD, an ordinal variable).

Anatomy

Temporal Consistency Objectives Regularize the Learning of Disentangled Representations

1 code implementation29 Aug 2019 Gabriele Valvano, Agisilaos Chartsias, Andrea Leo, Sotirios A. Tsaftaris

There has been an increasing focus in learning interpretable feature representations, particularly in applications such as medical image analysis that require explainability, whilst relying less on annotated data (since annotations can be tedious and costly).

Anatomy Disentanglement

Disentangled Representation Learning in Cardiac Image Analysis

4 code implementations22 Mar 2019 Agisilaos Chartsias, Thomas Joyce, Giorgos Papanastasiou, Michelle Williams, David Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris

We can venture further and consider that a medical image naturally factors into some spatial factors depicting anatomy and factors that denote the imaging characteristics.

Anatomy Computed Tomography (CT) +3

Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization

no code implementations10 Jan 2019 Tian Xia, Agisilaos Chartsias, Sotirios A. Tsaftaris

Pseudo healthy synthesis, i. e. the creation of a subject-specific `healthy' image from a pathological one, could be helpful in tasks such as anomaly detection, understanding changes induced by pathology and disease or even as data augmentation.

Anomaly Detection Data Augmentation +2

Factorised spatial representation learning: application in semi-supervised myocardial segmentation

1 code implementation19 Mar 2018 Agisilaos Chartsias, Thomas Joyce, Giorgos Papanastasiou, Scott Semple, Michelle Williams, David Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris

Specifically, we achieve comparable performance to fully supervised networks using a fraction of labelled images in experiments on ACDC and a dataset from Edinburgh Imaging Facility QMRI.

Medical Image Segmentation Myocardium Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.