Multiscale brain MRI super-resolution using deep 3D convolutional networks

[Display omitted] •A residual-based deep 3D CNN architecture for super-resolution.•Comprehensive performance analysis of key elements of neural networks.•Multi-scale training approach to handle arbitrary scale factors.•Multimodal CNN for super-resolution. The purpose of super-resolution approaches i...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computerized medical imaging and graphics Ročník 77; s. 101647
Hlavní autori: Pham, Chi-Hieu, Tor-Díez, Carlos, Meunier, Hélène, Bednarek, Nathalie, Fablet, Ronan, Passat, Nicolas, Rousseau, François
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Elsevier Ltd 01.10.2019
Elsevier Science Ltd
Elsevier
Predmet:
3D convolutional neural network
Artificial neural networks
Brain
Brain MRI
Computer Science
Computer Vision and Pattern Recognition
Convolution
Cortex
Image acquisition
Image enhancement
Image Processing
Image reconstruction
Image resolution
Internal Medicine
Learning
Magnetic resonance imaging
Medical Imaging
Neural networks
Neuroimaging
NMR
Nuclear magnetic resonance
Optimization
Other
Post-processing
Resonance
Scaling factors
Structural analysis
Super-resolution
Training
Transfer learning
Super-resolution
3D convolutional neural network
Brain MRI
brain MRI
super-resolution
ISSN:0895-6111, 1879-0771, 1879-0771
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:[Display omitted] •A residual-based deep 3D CNN architecture for super-resolution.•Comprehensive performance analysis of key elements of neural networks.•Multi-scale training approach to handle arbitrary scale factors.•Multimodal CNN for super-resolution. The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0895-6111
1879-0771
1879-0771
DOI:10.1016/j.compmedimag.2019.101647