Search Results for author: Sébastien Ourselin

Found 37 papers, 22 papers with code

Generative Medical Segmentation

1 code implementation27 Mar 2024 Jiayu Huo, Xi Ouyang, Sébastien Ourselin, Rachel Sparks

Concretely, GMS employs a robust pre-trained Variational Autoencoder (VAE) to derive latent representations of both images and masks, followed by a mapping model that learns the transition from image to mask in the latent space.

Domain Generalization Image Segmentation +3

UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation

1 code implementation19 Sep 2023 Jianghao Wu, Guotai Wang, Ran Gu, Tao Lu, Yinan Chen, Wentao Zhu, Tom Vercauteren, Sébastien Ourselin, Shaoting Zhang

The different predictions in these duplicated heads are used to obtain pseudo labels for unlabeled target-domain images and their uncertainty to identify reliable pseudo labels.

Brain Segmentation Image Segmentation +5

Partial supervision for the FeTA challenge 2021

2 code implementations3 Nov 2021 Lucas Fidon, Michael Aertsen, Suprosanna Shit, Philippe Demaerel, Sébastien Ourselin, Jan Deprest, Tom Vercauteren

Label-set loss functions allow to train deep neural networks with partially segmented images, i. e. segmentations in which some classes may be grouped into super-classes.

Brain Segmentation Image Segmentation +2

Homography-based Visual Servoing with Remote Center of Motion for Semi-autonomous Robotic Endoscope Manipulation

1 code implementation25 Oct 2021 Martin Huber, John Bason Mitchell, Ross Henry, Sébastien Ourselin, Tom Vercauteren, Christos Bergeles

Our approach allows a surgeon to build a graph of desired views, from which, once built, views can be manually selected and automatically servoed to irrespective of robot-patient frame transformation changes.

Image Registration

Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction

2 code implementations30 Sep 2021 Martin Huber, Sébastien Ourselin, Christos Bergeles, Tom Vercauteren

We perform an extensive evaluation of state-of-the-art (SOTA) Deep Neural Networks (DNNs) across multiple compute regimes, finding our method transfers from our camera motion free da Vinci surgery dataset to videos of laparoscopic interventions, outperforming classical homography estimation approaches in both, precision by 41%, and runtime on a CPU by 43%.

Homography Estimation Imitation Learning +1

Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures

1 code implementation22 Jun 2021 Fernando Pérez-García, Catherine Scott, Rachel Sparks, Beate Diehl, Sébastien Ourselin

We demonstrate that an STCNN trained on a HAR dataset can be used in combination with an RNN to accurately represent arbitrarily long videos of seizures.

Action Recognition Management +2

An MRF-UNet Product of Experts for Image Segmentation

1 code implementation12 Apr 2021 Mikael Brudfors, Yaël Balbastre, John Ashburner, Geraint Rees, Parashkev Nachev, Sébastien Ourselin, M. Jorge Cardoso

While convolutional neural networks (CNNs) trained by back-propagation have seen unprecedented success at semantic segmentation tasks, they are known to struggle on out-of-distribution data.

Image Segmentation Semantic Segmentation

CARRNN: A Continuous Autoregressive Recurrent Neural Network for Deep Representation Learning from Sporadic Temporal Data

no code implementations8 Apr 2021 Mostafa Mehdipour Ghazi, Lauge Sørensen, Sébastien Ourselin, Mads Nielsen

Learning temporal patterns from multivariate longitudinal data is challenging especially in cases when data is sporadic, as often seen in, e. g., healthcare applications where the data can suffer from irregularity and asynchronicity as the time between consecutive data points can vary across features and samples, hindering the application of existing deep learning models that are constructed for complete, evenly spaced data with fixed sequence lengths.

ICU Mortality Representation Learning +2

Multi-Atlas Based Pathological Stratification of d-TGA Congenital Heart Disease

no code implementations5 Apr 2021 Maria A. Zuluaga, Alex F. Mendelson, M. Jorge Cardoso, Andrew M. Taylor, Sébastien Ourselin

One of the main sources of error in multi-atlas segmentation propagation approaches comes from the use of atlas databases that are morphologically dissimilar to the target image.


CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation

3 code implementations22 Sep 2020 Ran Gu, Guotai Wang, Tao Song, Rui Huang, Michael Aertsen, Jan Deprest, Sébastien Ourselin, Tom Vercauteren, Shaoting Zhang

Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object.

Image Segmentation Lesion Segmentation +3

Automatic Right Ventricle Segmentation using Multi-Label Fusion in Cardiac MRI

no code implementations5 Apr 2020 Maria A. Zuluaga, M. Jorge Cardoso, Sébastien Ourselin

Accurate segmentation of the right ventricle (RV) is a crucial step in the assessment of the ventricular structure and function.

Anatomy Motion Segmentation +2

Let's agree to disagree: learning highly debatable multirater labelling

no code implementations4 Sep 2019 Carole H. Sudre, Beatriz Gomez Anson, Silvia Ingala, Chris D. Lane, Daniel Jimenez, Lukas Haider, Thomas Varsavsky, Ryutaro Tanno, Lorna Smith, Sébastien Ourselin, Rolf H. Jäger, M. Jorge Cardoso

Classification and differentiation of small pathological objects may greatly vary among human raters due to differences in training, expertise and their consistency over time.

object-detection Object Detection

Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning

no code implementations16 Aug 2019 Mauricio Orbes-Arteaga, Thomas Varsavsky, Carole H. Sudre, Zach Eaton-Rosen, Lewis J. Haddow, Lauge Sørensen, Mads Nielsen, Akshay Pai, Sébastien Ourselin, Marc Modat, Parashkev Nachev, M. Jorge Cardoso

Inspired by recent work in semi-supervised learning we introduce a novel method to adapt from one source domain to $n$ target domains (as long as there is paired data covering all domains).

Domain Adaptation

Robust parametric modeling of Alzheimer's disease progression

no code implementations14 Aug 2019 Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai, Marc Modat, M. Jorge Cardoso, Sébastien Ourselin, Lauge Sørensen

Different M-estimators and logistic functions, including a novel type proposed in this study, called modified Stannard, are evaluated on the data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) for robust modeling of volumetric MRI and PET biomarkers, CSF measurements, as well as cognitive tests.

Density Estimation

Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation

1 code implementation25 Jul 2019 Reuben Dorent, Samuel Joutard, Marc Modat, Sébastien Ourselin, Tom Vercauteren

We propose a new deep learning method for tumour segmentation when dealing with missing imaging modalities.


Simultaneous synthesis of FLAIR and segmentation of white matter hypointensities from T1 MRIs

no code implementations20 Aug 2018 Mauricio Orbes-Arteaga, M. Jorge Cardoso, Lauge Sørensen, Marc Modat, Sébastien Ourselin, Mads Nielsen, Akshay Pai

Segmenting vascular pathologies such as white matter lesions in Brain magnetic resonance images (MRIs) require acquisition of multiple sequences such as T1-weighted (T1-w) --on which lesions appear hypointense-- and fluid attenuated inversion recovery (FLAIR) sequence --where lesions appear hyperintense--.

Imputation Segmentation

Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration

no code implementations9 Jul 2018 Yipeng Hu, Marc Modat, Eli Gibson, Wenqi Li, Nooshin Ghavami, Ester Bonmati, Guotai Wang, Steven Bandula, Caroline M. Moore, Mark Emberton, Sébastien Ourselin, J. Alison Noble, Dean C. Barratt, Tom Vercauteren

A median target registration error of 3. 6 mm on landmark centroids and a median Dice of 0. 87 on prostate glands are achieved from cross-validation experiments, in which 108 pairs of multimodal images from 76 patients were tested with high-quality anatomical labels.

Image Registration

Boosted Training of Convolutional Neural Networks for Multi-Class Segmentation

no code implementations13 Jun 2018 Lorenz Berger, Eoin Hyde, Matt Gibb, Nevil Pavithran, Garin Kelly, Faiz Mumtaz, Sébastien Ourselin

Training deep neural networks on large and sparse datasets is still challenging and can require large amounts of computation and memory.

Anatomy Image Segmentation +2

VTrails: Inferring Vessels with Geodesic Connectivity Trees

no code implementations8 Jun 2018 Stefano Moriconi, Maria A. Zuluaga, H. Rolf Jäger, Parashkev Nachev, Sébastien Ourselin, M. Jorge Cardoso

The analysis of vessel morphology and connectivity has an impact on a number of cardiovascular and neurovascular applications by providing patient-specific high-level quantitative features such as spatial location, direction and scale.

Retrieval and Registration of Long-Range Overlapping Frames for Scalable Mosaicking of In Vivo Fetoscopy

no code implementations28 Feb 2018 Loïc Peter, Marcel Tella-Amo, Dzhoshkun Ismail Shakir, George Attilakos, Ruwan Wimalasundera, Jan Deprest, Sébastien Ourselin, Tom Vercauteren

Robustness to visual challenges during registration and long-range temporal consistency are proposed, offering first positive results on in vivo data for which standard mosaicking techniques are not applicable.


NiftyNet: a deep-learning platform for medical imaging

10 code implementations11 Sep 2017 Eli Gibson, Wenqi Li, Carole Sudre, Lucas Fidon, Dzhoshkun I. Shakir, Guotai Wang, Zach Eaton-Rosen, Robert Gray, Tom Doel, Yipeng Hu, Tom Whyntie, Parashkev Nachev, Marc Modat, Dean C. Barratt, Sébastien Ourselin, M. Jorge Cardoso, Tom Vercauteren

NiftyNet provides a modular deep-learning pipeline for a range of medical imaging applications including segmentation, regression, image generation and representation learning applications.

Data Augmentation Image Generation +4

Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations

7 code implementations11 Jul 2017 Carole H. Sudre, Wenqi Li, Tom Vercauteren, Sébastien Ourselin, M. Jorge Cardoso

Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images.


What is the distribution of the number of unique original items in a bootstrap sample?

no code implementations18 Feb 2016 Alex F. Mendelson, Maria A. Zuluaga, Brian F. Hutton, Sébastien Ourselin

The purpose of this report is to present the distribution of the number of unique original items in a bootstrap sample clearly and concisely, with a view to enabling other machine learning researchers to understand and control this quantity in existing and future resampling techniques.

BIG-bench Machine Learning

Automatic structural parcellation of mouse brain MRI using multi-atlas label fusion

1 code implementation27 Jan 2014 Da Ma, Manuel J. Cardoso, Marc Modat, Nick Powell, Jack Wells, Holly Holmes, Frances Wiseman, Victor Tybulewicz, Elizabeth Fisher, Mark F. Lythgoe, Sébastien Ourselin

The segmentation accuracy of the multi-atlas framework was evaluated using publicly available mouse brain atlas databases with pre-segmented manually labelled anatomical structures as the gold standard, and optimised parameters were obtained for the STEPS algorithm in the label fusion to achieve the best segmentation accuracy.


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