Reconstruction of undersampled radial free-breathing 3D abdominal MRI using stacked convolutional auto-encoders.

PURPOSE Free-breathing three-dimensional (3D) abdominal imaging is a challenging task for MRI, as respiratory motion severely degrades image quality. One of the most promising self-navigation techniques is the 3D golden-angle radial stack-of-stars (SOS) sequence, which has advantages in terms of speed, resolution, and allowing free breathing. However, streaking artifacts are still clearly observed in reconstructed images when undersampling is applied. This work presents a novel reconstruction approach based on a stacked convolutional auto-encoder (SCAE) network to solve this problem. METHODS Thirty healthy volunteers participated in our experiment. To build the dataset, reference and artifact-affected images were reconstructed using 451 golden-angle spokes and the first 20, 40, or 90 golden-angle spokes corresponding to acceleration rates of 31.4, 15.7, and 6.98, respectively. In the training step, we trained the SCAE by feeding it with patches from artifact-affected images. The SCAE outputs patches in the corresponding reference images. In the testing step, we applied the trained SCAE to map each input artifact-affected patch to the corresponding reference image patch. RESULT The SCAE-based reconstruction images with acceleration rates of 6.98 and 15.7 show nearly similar quality as the reference images. Additionally, the calculation time is below 1 s. Moreover, the proposed approach preserves important features, such as lesions not presented in the training set. CONCLUSION The preliminary results demonstrate the feasibility of the proposed SCAE-based strategy for correcting the streaking artifacts of undersampled free-breathing 3D abdominal MRI with a negligible reconstruction time.

[1]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[2]  Jacek M. Zurada,et al.  Deep Learning of Part-Based Representation of Data Using Sparse Autoencoders With Nonnegativity Constraints , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Peter I. Corke,et al.  Fine-grained bird species recognition via hierarchical subset learning , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[4]  Leon Axel,et al.  XD‐GRASP: Golden‐angle radial MRI with reconstruction of extra motion‐state dimensions using compressed sensing , 2016, Magnetic resonance in medicine.

[5]  Yaozong Gao,et al.  Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse Patch Matching , 2017, Deep Learning for Medical Image Analysis.

[6]  Ehsan Samei,et al.  A generic framework to simulate realistic lung, liver and renal pathologies in CT imaging , 2014, Physics in medicine and biology.

[7]  Dinggang Shen,et al.  Convolutional Neural Network for Reconstruction of 7T-like Images from 3T MRI Using Appearance and Anatomical Features , 2016, LABELS/DLMIA@MICCAI.

[8]  Daniel Rueckert,et al.  A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[9]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Samy Bengio,et al.  Guest Editors' Introduction: Special Section on Learning Deep Architectures , 2013, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  Dong Yu,et al.  Tensor Deep Stacking Networks , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Lovedeep Gondara,et al.  Medical Image Denoising Using Convolutional Denoising Autoencoders , 2016, 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW).

[14]  David Atkinson,et al.  Accelerated motion corrected three‐dimensional abdominal MRI using total variation regularized SENSE reconstruction , 2015, Magnetic resonance in medicine.

[15]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[16]  David Atkinson,et al.  Dynamic MR Image Reconstruction–Separation From Undersampled (${\bf k},t$)-Space via Low-Rank Plus Sparse Prior , 2014, IEEE Transactions on Medical Imaging.

[17]  Jianzhong Wu,et al.  Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images , 2016, IEEE Transactions on Medical Imaging.

[18]  Li Deng,et al.  A tutorial survey of architectures, algorithms, and applications for deep learning , 2014, APSIPA Transactions on Signal and Information Processing.

[19]  Jong Chul Ye,et al.  Deep learning with domain adaptation for accelerated projection‐reconstruction MR , 2018, Magnetic resonance in medicine.

[20]  Stefan Harmeling,et al.  Image denoising: Can plain neural networks compete with BM3D? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Wei Xiong,et al.  Stacked Convolutional Denoising Auto-Encoders for Feature Representation , 2017, IEEE Transactions on Cybernetics.

[22]  Jürgen Schmidhuber,et al.  Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction , 2011, ICANN.

[23]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[24]  Manojkumar Saranathan,et al.  Composite MR image reconstruction and unaliasing for general trajectories using neural networks. , 2010, Magnetic resonance imaging.

[25]  Daniel K Sodickson,et al.  Low‐rank plus sparse matrix decomposition for accelerated dynamic MRI with separation of background and dynamic components , 2015, Magnetic resonance in medicine.

[26]  Armando Manduca,et al.  Self‐navigated motion correction using moments of spatial projections in radial MRI , 2004 .

[27]  Stephen M. Smith,et al.  Accelerating functional MRI using fixed‐rank approximations and radial‐cartesian sampling , 2016, Magnetic resonance in medicine.

[28]  Sungheon Kim,et al.  Golden‐angle radial sparse parallel MRI: Combination of compressed sensing, parallel imaging, and golden‐angle radial sampling for fast and flexible dynamic volumetric MRI , 2014, Magnetic resonance in medicine.

[29]  H. Hricak,et al.  Magnetic resonance imaging with respiratory gating: techniques and advantages. , 1984, AJR. American journal of roentgenology.

[30]  R. Alfidi,et al.  The effect of motion on two-dimensional Fourier transformation magnetic resonance images. , 1984, Radiology.

[31]  Thorsten Heußer,et al.  4D respiratory motion‐compensated image reconstruction of free‐breathing radial MR data with very high undersampling , 2017, Magnetic resonance in medicine.

[32]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[33]  Hao Chen,et al.  Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[34]  Shuiwang Ji,et al.  Deep convolutional neural networks for multi-modality isointense infant brain image segmentation , 2015, NeuroImage.

[35]  M. Zaitsev,et al.  Motion artifacts in MRI: A complex problem with many partial solutions , 2015, Journal of magnetic resonance imaging : JMRI.

[36]  Sanja Fidler,et al.  Monocular Object Instance Segmentation and Depth Ordering with CNNs , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[37]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[38]  P. Börnert,et al.  Free‐breathing whole‐heart coronary MRA with 3D radial SSFP and self‐navigated image reconstruction , 2005, Magnetic resonance in medicine.