E
Ester Bonmati
Researcher at University College London
Publications - 38
Citations - 1607
Ester Bonmati is an academic researcher from University College London. The author has contributed to research in topics: Image registration & Convolutional neural network. The author has an hindex of 12, co-authored 35 publications receiving 1008 citations. Previous affiliations of Ester Bonmati include Engineering and Physical Sciences Research Council & University of Girona.
Papers
More filters
Journal ArticleDOI
Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks
Eli Gibson,Francesco Giganti,Yipeng Hu,Ester Bonmati,Steve Bandula,Kurinchi Selvan Gurusamy,Brian R. Davidson,Stephen P. Pereira,Matthew J. Clarkson,Dean C. Barratt +9 more
TL;DR: It is concluded that the deep-learning-based segmentation represents a registration-free method for multi-organ abdominal CT segmentation whose accuracy can surpass current methods, potentially supporting image-guided navigation in gastrointestinal endoscopy procedures.
Journal ArticleDOI
Weakly-supervised convolutional neural networks for multimodal image registration.
Yipeng Hu,Yipeng Hu,Marc Modat,Eli Gibson,Wenqi Li,Nooshin Ghavami,Ester Bonmati,Guotai Wang,Steven Bandula,Caroline M. Moore,Mark Emberton,Sebastien Ourselin,J. Alison Noble,Dean C. Barratt,Tom Vercauteren +14 more
TL;DR: The proposed end‐to‐end convolutional neural network approach aims to predict displacement fields to align multiple labelled corresponding structures for individual image pairs during the training, while only unlabelled image pairs are used as the network input for inference.
Proceedings ArticleDOI
Label-driven weakly-supervised learning for multimodal deformarle image registration
Yipeng Hu,Marc Modat,Eli Gibson,Nooshin Ghavami,Ester Bonmati,Caroline M. Moore,Mark Emberton,J. Alison Noble,Dean C. Barratt,Tom Vercauteren +9 more
TL;DR: A weakly-supervised, label-driven formulation for learning 3D voxel correspondence from higher-level label correspondence is proposed, thereby bypassing classical intensity-based image similarity measures.
Book ChapterDOI
Adversarial deformation regularization for training image registration neural networks
Yipeng Hu,Eli Gibson,Nooshin Ghavami,Ester Bonmati,Caroline M. Moore,Mark Emberton,Tom Vercauteren,J. Alison Noble,Dean C. Barratt +8 more
TL;DR: An adversarial learning approach to constrain convolutional neural network training for image registration, replacing heuristic smoothness measures of displacement fields often used in these tasks, can help predict physically plausible deformation without any other smoothness penalty.
Journal ArticleDOI
The SmartTarget Biopsy Trial: A Prospective, Within-person Randomised, Blinded Trial Comparing the Accuracy of Visual-registration and Magnetic Resonance Imaging/Ultrasound Image-fusion Targeted Biopsies for Prostate Cancer Risk Stratification.
Sami Hamid,Sami Hamid,Ian Donaldson,Ian Donaldson,Yipeng Hu,Rachael Rodell,Barbara Villarini,Ester Bonmati,Pamela Tranter,Shonit Punwani,Shonit Punwani,Harbir S. Sidhu,Harbir S. Sidhu,S Willis,Jan van der Meulen,David J. Hawkes,Neil McCartan,Ingrid Potyka,Norman R. Williams,Chris Brew-Graves,Alex Freeman,Caroline M. Moore,Caroline M. Moore,Dean C. Barratt,Mark Emberton,Mark Emberton,Hashim U. Ahmed +26 more
TL;DR: Visual-registration and image-fusion targeting strategies combined had the highest detection rate for clinically significant cancers and should be used together whenever targeted biopsy is being performed.