Comparison of Automatic Vessel Segmentation Techniques for Whole Body Magnetic Resonance Angiography with Limited Ground Truth Data

2017 ◽  
pp. 144-155
Author(s):  
Andrew McNeil ◽  
Giulio Degano ◽  
Ian Poole ◽  
Graeme Houston ◽  
Emanuele Trucco
Keyword(s):  
Magnetic Resonance ◽  
Magnetic Resonance Angiography ◽  
Ground Truth ◽  
Vessel Segmentation ◽  
Whole Body ◽  
Ground Truth Data

Whole-body magnetic resonance angiography of patients using a standard clinical scanner

2005 ◽  
Vol 16 (1) ◽  
pp. 147-153 ◽  
Author(s):  
Tomas Hansen ◽  
Johan Wikström ◽  
Mats-Ola Eriksson ◽  
Anders Lundberg ◽  
Lars Johansson ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Magnetic Resonance Angiography ◽  
Whole Body ◽  
Clinical Scanner

Optimization of Contrast Dosage for Gadobenate Dimeglumine-Enhanced High-Resolution Whole-Body 3D Magnetic Resonance Angiography

2002 ◽  
Vol 37 (5) ◽  
pp. 263-268 ◽  
Author(s):  
MATHIAS GOYEN ◽  
CHRISTOPH U. HERBORN ◽  
THOMAS C. LAUENSTEIN ◽  
JÖRG BARKHAUSEN ◽  
PATRICK VEIT ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
High Resolution ◽  
Magnetic Resonance Angiography ◽  
Gadobenate Dimeglumine ◽  
Whole Body ◽  
Contrast Dosage

scholarly journals Voxel-Wise Adversarial FiboNet for 3D Cerebrovascular Segmentation on Magnetic Resonance Angiography Images

2021 ◽  
Vol 15 ◽  
Author(s):  
Bin Guo ◽  
Fugen Zhou ◽  
Bo Liu ◽  
Xiangzhi Bai
Keyword(s):  
Magnetic Resonance ◽  
Magnetic Resonance Angiography ◽  
Loss Function ◽  
Class Imbalance ◽  
Ground Truth ◽  
Noise Robustness ◽  
Dice Coefficient ◽  
Cerebrovascular Segmentation ◽  
New Feature ◽  
Adversarial Model

Cerebrovascular segmentation is important in various clinical applications, such as surgical planning and computer-aided diagnosis. In order to achieve high segmentation performance, three challenging problems should be taken into consideration: (1) large variations in vascular anatomies and voxel intensities; (2) severe class imbalance between foreground and background voxels; (3) image noise with different magnitudes. Limited accuracy was achieved without considering these challenges in deep learning-based methods for cerebrovascular segmentation. To overcome the limitations, we propose an end-to-end adversarial model called FiboNet-VANGAN. Specifically, our contributions can be summarized as follows: (1) to relieve the first problem mentioned above, a discriminator is proposed to regularize for voxel-wise distribution consistency between the segmentation results and the ground truth; (2) to mitigate the problem of class imbalance, we propose to use the addition of cross-entropy and Dice coefficient as the loss function of the generator. Focal loss is utilized as the loss function of the discriminator; (3) a new feature connection is proposed, based on which a generator called FiboNet is built. By incorporating Dice coefficient in the training of FiboNet, noise robustness can be improved by a large margin. We evaluate our method on a healthy magnetic resonance angiography (MRA) dataset to validate its effectiveness. A brain atrophy MRA dataset is also collected to test the performance of each method on abnormal cases. Results show that the three problems in cerebrovascular segmentation mentioned above can be alleviated and high segmentation accuracy can be achieved on both datasets using our method.

Whole Body Postmortem Magnetic Resonance Angiography

2011 ◽  
Vol 57 (3) ◽  
pp. 778-782 ◽  
Author(s):  
Thomas D. Ruder ◽  
Gary M. Hatch ◽  
Lars C. Ebert ◽  
Patricia M. Flach ◽  
Steffen Ross ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Magnetic Resonance Angiography ◽  
Whole Body

scholarly journals Whole-body magnetic resonance angiography

2019 ◽  
Vol 74 (1) ◽  
pp. 3-12 ◽  
Author(s):  
J.R. Weir-McCall ◽  
M. Bonnici-Mallia ◽  
P.G. Ramkumar ◽  
A.F. Nath ◽  
J.G. Houston
Keyword(s):  
Magnetic Resonance ◽  
Magnetic Resonance Angiography ◽  
Whole Body
Sign in / Sign up

Export Citation Format

Share Document