Learning to Decode 7T-like MR Image Reconstruction from 3T MR Images

@inproceedings{Sharma2018LearningTD,
  title={Learning to Decode 7T-like MR Image Reconstruction from 3T MR Images},
  author={Aditya Sharma and Prabhjot Kaur and A. Nigam and A. Bhavsar},
  booktitle={DLMIA/ML-CDS@MICCAI},
  year={2018}
}
Increasing demand for high field magnetic resonance (MR) scanner indicates the need for high-quality MR images for accurate medical diagnosis. However, cost constraints, instead, motivate a need for algorithms to enhance images from low field scanners. We propose an approach to process the given low field (3T) MR image slices to reconstruct the corresponding high field (7T-like) slices. Our framework involves a novel architecture of a merged convolutional autoencoder with a single encoder and… Expand
Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings
TLDR
This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar. Expand
Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network
TLDR
An approach to reduce the model’s uncertainty for an input image, and it helps to defend the adversarial attacks on the image superresolution model to be the first to propose an adversarial defense mechanism in any image reconstruction domain. Expand
Fast Bayesian Uncertainty Estimation of Batch Normalized Single Image Super-Resolution Network
TLDR
A Bayesian approach for uncertainty estimation in super-resolution network is introduced and Monte Carlo samples from a posterior distribution are generated by using batch mean and variance as a stochastic parameter in the batch-normalization layer during test time. Expand

References

SHOWING 1-10 OF 15 REFERENCES
Reconstruction of 7T-Like Images From 3T MRI
TLDR
A hierarchical reconstruction based on group sparsity in a novel multi-level Canonical Correlation Analysis (CCA) space is proposed, to improve the quality of 3T MR image to be 7T-like MRI and is able to recover better structural details. Expand
Convolutional Neural Network for Reconstruction of 7T-like Images from 3T MRI Using Appearance and Anatomical Features
TLDR
A deep architecture for Convolutional Neural Network is proposed, which uses the appearance (intensity) and anatomical (labels of brain tissues) features as input to non-linearly map 3T MRI to 7T MRI. Expand
Joint Reconstruction and Segmentation of 7T-like MR Images from 3T MRI Based on Cascaded Convolutional Neural Networks
TLDR
The experimental results show that the estimated 7T-like images have richer anatomical details and better segmentation results, compared to the 3T MRI, and the proposed image post-processing framework achieved better results in both reconstruction and segmentation tasks,Compared to the state-of-the-art methods. Expand
Magnetic Resonance Image Example-Based Contrast Synthesis
TLDR
This paper introduces an image restoration technique that recovers images with both the desired tissue contrast and a normalized intensity profile using patches in the acquired images and an atlas containing patches of the acquired and desired tissue contrasts. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
LABEL: Pediatric brain extraction using learning-based meta-algorithm
TLDR
A novel Learning Algorithm for Brain Extraction and Labeling (LABEL) specially for the pediatric MR brain images and develops a level-set based fusion method to combine multiple brain extractions together with a closed smooth surface for obtaining the final extraction. Expand
Super‐resolution methods in MRI: Can they improve the trade‐off between resolution, signal‐to‐noise ratio, and acquisition time?
TLDR
The results show that super‐resolution reconstruction can indeed improve the resolution, signal‐to‐noise ratio and acquisition time trade‐offs compared with direct high‐resolution acquisition. Expand
No-reference blur assessment based on edge modeling
TLDR
A no-reference objective blur metric based on edge model (EMBM) is presented to address the image blur assessment problem and advocate using only the salient edge pixels to simulate the blur assessment in Human Visual System (HVS). Expand
Image Super-Resolution Via Sparse Representation
TLDR
This paper presents a new approach to single-image superresolution, based upon sparse signal representation, which generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. Expand
and D
  • Shen, “Convolutional neural network for reconstruction of 7t-like images from 3t mri using appearance and anatomical features,” in Deep Learning and Data Labeling for Medical Applications,
  • 2016
...
1
2
...