Efficient multiāscale 3D CNN with fully connected CRF for accurate brain lesion segmentation
- K. Kamnitsas, C. Ledig, Ben Glocker
- Computer ScienceMedical Image Anal.
- 18 March 2016
Domain Generalization via Model-Agnostic Learning of Semantic Features
- Q. Dou, Daniel Coelho de Castro, K. Kamnitsas, B. Glocker
- Computer ScienceNeural Information Processing Systems
- 29 October 2019
This work investigates the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that it can directly generalize to target domains with unknown statistics, and adopts a model-agnostic learning paradigm with gradient-based meta-train and meta-test procedures to expose the optimization to domain shift.
Traumatic brain injury: integrated approaches to improve prevention, clinical care, and research
- A. Maas, D. Menon, Fabrizio Zumbo
- MedicineLancet Neurology
- 1 December 2017
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation
- O. Oktay, Enzo Ferrante, D. Rueckert
- Computer ScienceIEEE Transactions on Medical Imaging
- 22 May 2017
This work proposes a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end and demonstrates how the learnt deep models of 3-D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation
- K. Kamnitsas, Wenjia Bai, Ben Glocker
- Computer ScienceBrainLes@MICCAI
- 14 September 2017
This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods to reduce the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database.
Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
- K. Kamnitsas, Christian F. Baumgartner, Ben Glocker
- Computer ScienceInformation Processing in Medical Imaging
- 28 December 2016
This work investigates unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more robust to differences in the input data, and which does not require any annotations on the test domain.
DeepMedic for Brain Tumor Segmentation
- K. Kamnitsas, Enzo Ferrante, Ben Glocker
- Computer ScienceBrainLes@MICCAI
- 17 October 2016
DeepMedic, a 3D CNN architecture previously presented for lesion segmentation, is employed, which is further improved by adding residual connections, aiming to shed some light on requirements for employing such a system.
SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound
- Christian F. Baumgartner, K. Kamnitsas, D. Rueckert
- Computer ScienceIEEE Transactions on Medical Imaging
- 16 December 2016
A novel method based on convolutional neural networks is proposed, which can automatically detect 13 fetal standard views in freehand 2-D ultrasound data as well as provide a localization of the fetal structures via a bounding box while providing optimal output for the localization task.
DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks
- Martin Rajchl, M. J. Lee, D. Rueckert
- Computer ScienceIEEE Transactions on Medical Imaging
- 25 May 2016
This paper proposes a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in this case bounding boxes, and test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset.
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
- M. Monteiro, L. L. Folgoc, B. Glocker
- Computer ScienceNeural Information Processing Systems
- 1 June 2020
Stochastic segmentation networks (SSNs) are introduced, an efficient probabilistic method for modelling aleatoric uncertainty with any image segmentation network architecture and outperform state-of-the-art for modelling correlated uncertainty in ambiguous images while being much simpler, more flexible, and more efficient.
...
...