Self-attention convolutional neural network for improved MR image reconstruction

Wu, Yan; Ma, Yajun; Liu, Jing; Du, Jiang; Li, Xing

doi:10.1016/j.ins.2019.03.080

Cited by 96 publications

(49 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…neural network (CNN) architecture is a deep learning approach commonly used in theoretical and practical studies on topics such as disease classification, MRI reconstruction, and effector protein prediction. [11][12][13] A common CNN architecture consists of input, convolutional, pooling, and fully connected layers. Additionally, batch normalization, rectified linear unit, and dropout layers can also be used to speed up the process and reduce overfitting.…”

Section: Convolutionalmentioning

confidence: 99%

Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches

2020

View full text Add to dashboard Cite

Results: Performance in terms of sensitivity, specificity, accuracy, F1 score, and Cohen's kappa coefficient were evaluated using five-fold cross validation tests. Best performance was obtained when cropped images were rescaled to 50¥50 pixels. The kappa metric showed more reliable classifier performance when 50¥50 pixels image size was used to feed the CNN. The classifier performance was more reliable according to other image sizes. Sensitivity and specificity rates were computed to be 83% and 73%, respectively. With the inclusion of the GA, this rate increased by 1.6%. The detection rate of fractured bones was found to be 83%. A kappa coefficient of 55% was obtained, indicating an acceptable agreement. Conclusion: This experimental study utilized deep learning techniques in the detection of bone fractures in radiography. Although the dataset was unbalanced, the results can be considered promising. It was observed that use of smaller image size decreases computational cost and provides better results according to evaluation metrics.

show abstract

Section: Convolutionalmentioning

confidence: 99%

Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches

2020

View full text Add to dashboard Cite

show abstract

“…In recent years, convolutional neural networks have been used in many diverse areas, e.g., DNA–Protein binding sites prediction [ 33 ], magnetic resonance image reconstruction [ 34 ], automatic road segmentation [ 32 ], facial verification [ 35 ], music generation [ 36 ], relation extraction (extracting the semantic relationship between the pairs from plain text) [ 37 ], database intrusion detection [ 38 ], arc detection in pantograph–catenary systems [ 39 ] and the time-series classification [ 40 ]. This versatility of the CNNs makes them a reasonable choice to use while building a solution to the considered problem.…”

Section: Preliminaries and Definitions/backgroundmentioning

confidence: 99%

Long-Range Dependent Traffic Classification with Convolutional Neural Networks Based on Hurst Exponent Analysis

Filus

Domański

Domańska

et al. 2020

Entropy

View full text Add to dashboard Cite

The paper examines the ability of neural networks to classify Internet traffic data in terms of self-similarity expressed by the Hurst exponent. Fractional Gaussian noise is used for the generation of synthetic data for modeling the genuine ones. It is presented that the trained model is capable of classifying the synthetic data obtained from the Pareto distribution and the real traffic data. We present the results of training for different optimizers of the cost function and a different number of convolutional layers in the neural network.

show abstract

“…Furthermore, Lv et al [ 18 ] developed a stack of autoencoders to remove streaking artifacts from radial undersampled free-breathing 3D abdominal MRI data. More recent studies [ 19 , 20 ] integrated the attention mechanism into CNN for accelerated MRI reconstruction, which improved the reconstruction outcome by taking advantage of long-range dependencies across images.…”

Section: Introductionmentioning

confidence: 99%

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction

2021

View full text Add to dashboard Cite

In this study, we proposed a model combing parallel imaging (PI) with generative adversarial network (GAN) architecture (PIC-GAN) for accelerated multi-channel magnetic resonance imaging (MRI) reconstruction. This model integrated data fidelity and regularization terms into the generator to benefit from multi-coils information and provide an “end-to-end” reconstruction. Besides, to better preserve image details during reconstruction, we combined the adversarial loss with pixel-wise loss in both image and frequency domains. The proposed PIC-GAN framework was evaluated on abdominal and knee MRI images using 2, 4 and 6-fold accelerations with different undersampling patterns. The performance of the PIC-GAN was compared to the sparsity-based parallel imaging (L1-ESPIRiT), the variational network (VN), and conventional GAN with single-channel images as input (zero-filled (ZF)-GAN). Experimental results show that our PIC-GAN can effectively reconstruct multi-channel MR images at a low noise level and improved structure similarity of the reconstructed images. PIC-GAN has yielded the lowest Normalized Mean Square Error (in ×10−5) (PIC-GAN: 0.58 ± 0.37, ZF-GAN: 1.93 ± 1.41, VN: 1.87 ± 1.28, L1-ESPIRiT: 2.49 ± 1.04 for abdominal MRI data and PIC-GAN: 0.80 ± 0.26, ZF-GAN: 0.93 ± 0.29, VN:1.18 ± 0.31, L1-ESPIRiT: 1.28 ± 0.24 for knee MRI data) and the highest Peak Signal to Noise Ratio (PIC-GAN: 34.43 ± 1.92, ZF-GAN: 31.45 ± 4.0, VN: 29.26 ± 2.98, L1-ESPIRiT: 25.40 ± 1.88 for abdominal MRI data and PIC-GAN: 34.10 ± 1.09, ZF-GAN: 31.47 ± 1.05, VN: 30.01 ± 1.01, L1-ESPIRiT: 28.01 ± 0.98 for knee MRI data) compared to ZF-GAN, VN and L1-ESPIRiT with an under-sampling factor of 6. The proposed PIC-GAN framework has shown superior reconstruction performance in terms of reducing aliasing artifacts and restoring tissue structures as compared to other conventional and state-of-the-art reconstruction methods.

show abstract

Self-attention convolutional neural network for improved MR image reconstruction

Cited by 96 publications

References 37 publications

Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches

Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches

Long-Range Dependent Traffic Classification with Convolutional Neural Networks Based on Hurst Exponent Analysis

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction

Contact Info

Product

Resources

About