G
Greg Slabaugh
Researcher at City University London
Publications - 132
Citations - 3501
Greg Slabaugh is an academic researcher from City University London. The author has contributed to research in topics: Image segmentation & Segmentation. The author has an hindex of 25, co-authored 116 publications receiving 2920 citations. Previous affiliations of Greg Slabaugh include New Jersey Institute of Technology & Siemens.
Papers
More filters
Journal ArticleDOI
DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction
Guang Yang,Simiao Yu,Hao Dong,Greg Slabaugh,Pier Luigi Dragotti,Xujiong Ye,Fangde Liu,Simon R. Arridge,Jennifer Keegan,Yike Guo,David N. Firmin +10 more
TL;DR: This paper provides a deep learning-based strategy for reconstruction of CS-MRI, and bridges a substantial gap between conventional non-learning methods working only on data from a single image, and prior knowledge from large training data sets.
Journal ArticleDOI
Shape-Based Computer-Aided Detection of Lung Nodules in Thoracic CT Images
TL;DR: The proposed computer tomography lung nodule computer-aided detection method has been trained and validated on a clinical dataset of 108 thoracic CT scans using a wide range of tube dose levels and shows much promise for clinical applications.
Proceedings ArticleDOI
A survey of methods for volumetric scene reconstruction from photographs
TL;DR: This paper is a survey of techniques for volumetric scene reconstruction based on geometric intersections, color consistency, and pair-wise matching.
Journal ArticleDOI
Reconstructing surfaces by volumetric regularization using radial basis functions
TL;DR: A new method of surface reconstruction is presented that generates smooth and seamless models from sparse, noisy, nonuniform, and low resolution range data, formulated as a sum of weighted radial basis functions.
Journal ArticleDOI
Shape-Driven Segmentation of the Arterial Wall in Intravascular Ultrasound Images
TL;DR: A shape-driven approach to segmentation of the arterial wall from intravascular ultrasound images in the rectangular domain is presented, which constrain the lumen and media-adventitia contours to a smooth, closed geometry, which increases the segmentation quality without any tradeoff with a regularizer term.