• Publications
  • Influence
Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation
TLDR
We propose a semi-supervised and network-based method for cardiac MR image segmentation, in which a segmentation network is trained from both labelled and unlabelled data. Expand
  • 99
  • 16
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
TLDR
We demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). Expand
  • 188
  • 9
  • PDF
The specification of a consumer design toolkit to support personalised production via additive manufacturing
This thesis stems from the future scenario that as additive manufacturing (AM) technologies become cheaper and more readily available, consumers without formal design training will begin toExpand
  • 6
  • 2
  • PDF
A classification of consumer involvement in new product development
TLDR
A graphical classification of New Product Development strategies is presented, mapped against the commitment of the designer to consumer involvement, and a number of new categories of design. Expand
  • 7
  • 2
  • PDF
3D Fetal Skull Reconstruction from 2DUS via Deep Conditional Generative Networks
TLDR
We present a new deep conditional generative network for the 3D reconstruction of the fetal skull from 2DUS standard planes of the head routinely acquired during the fetal screening process. Expand
  • 16
  • 1
  • PDF
Human-level CMR image analysis with deep fully convolutional networks
TLDR
We demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network and a large-scale annotated dataset. Expand
  • 25
  • 1
  • PDF
A framework for combining a motion atlas with non‐motion information to learn clinically useful biomarkers: Application to cardiac resynchronisation therapy response prediction
TLDR
We present a framework for combining a cardiac motion atlas with non‐motion data that enables CRT response to be predicted with 91.2% accuracy. Expand
  • 21
  • 1
  • PDF
Fast Multiple Landmark Localisation Using a Patch-based Iterative Network
TLDR
We propose a new Patch-based Iterative Network (PIN) for fast and accurate landmark localisation in 3D medical volumes. Expand
  • 16
  • 1
  • PDF
Weakly Supervised Estimation of Shadow Confidence Maps in Fetal Ultrasound Imaging
TLDR
We propose a weakly supervised method to tackle the ill-defined problem of shadow detection for acoustic shadow regions. Expand
  • 16
  • 1
  • PDF
Deep learning with ultrasound physics for fetal skull segmentation
TLDR
We propose a two-stage convolutional neural network (CNN) able to incorporate contextual and structural information into the segmentation process. Expand
  • 11
  • 1
  • PDF