activity
20172020
most citedFreehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks

77 citations · 112 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2019

Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment

Florin C. Ghesu, Bogdan Georgescu, Eli Gibson +6

The interpretation of chest radiographs is an essential task for the detection of thoracic diseases and abnormalities. However, it is a challenging problem with high inter-rater va…

cs.CV201920 cited

Multi-task Learning for Chest X-ray Abnormality Classification on Noisy Labels

Sebastian Guendel, Florin C. Ghesu, Sasa Grbic +4

Chest X-ray (CXR) is the most common X-ray examination performed in daily clinical practice for the diagnosis of various heart and lung abnormalities. The large amount of data to b…

cs.CV20185 cited

Class-Aware Adversarial Lung Nodule Synthesis in CT Images

Jie Yang, Siqi Liu, Sasa Grbic +7

Though large-scale datasets are essential for training deep learning systems, it is expensive to scale up the collection of medical imaging datasets. Synthesizing the objects of in…

cs.CV2018

Decompose to manipulate: Manipulable Object Synthesis in 3D Medical Images with Structured Image Decomposition

Siqi Liu, Eli Gibson, Sasa Grbic +5

The performance of medical image analysis systems is constrained by the quantity of high-quality image annotations. Such systems require data to be annotated by experts with years…

cs.CV2018

Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration

Yipeng Hu, Marc Modat, Eli Gibson +11

One of the fundamental challenges in supervised learning for multimodal image registration is the lack of ground-truth for voxel-level spatial correspondence. This work describes a…

cs.CV201710 cited

Intraoperative Organ Motion Models with an Ensemble of Conditional Generative Adversarial Networks

Yipeng Hu, Eli Gibson, Tom Vercauteren +5

In this paper, we describe how a patient-specific, ultrasound-probe-induced prostate motion model can be directly generated from a single preoperative MR image. Our motion model al…