Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning

Noises, artifacts, and loss of information caused by the magnetic resonance (MR) reconstruction may compromise the final performance of the downstream applications. In this paper, we develop a re-weighted multi-task deep learning method to learn prior knowledge from the existing big dataset and then utilize them to assist simultaneous MR reconstruction and segmentation from the under-sampled k-space data. The multi-task deep learning framework is equipped with two network sub-modules, which are integrated and trained by our designed iterative teacher forcing scheme (ITFS) under the dynamic re-weighted loss constraint (DRLC). The ITFS is designed to avoid error accumulation by injecting the fully-sampled data into the training process. The DRLC is proposed to dynamically balance the contributions from the reconstruction and segmentation sub-modules so as to co-prompt the multi-task accuracy. The proposed method has been evaluated on two open datasets and one in vivo in-house dataset and compared to six state-of-the-art methods. Results show that the proposed method possesses encouraging capabilities for simultaneous and accurate MR reconstruction and segmentation.

[1]  A. Giovagnoni,et al.  New advances in MRI diagnosis of degenerative osteoarthropathy of the peripheral joints , 2019, La radiologia medica.

[2]  Leslie Ying,et al.  Accelerating magnetic resonance imaging via deep learning , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[3]  Steve Halligan,et al.  Diagnostic accuracy of whole-body MRI versus standard imaging pathways for metastatic disease in newly diagnosed non-small-cell lung cancer : the prospective Streamline L trial , 2019 .

[4]  François Lauze,et al.  Simultaneous Reconstruction and Segmentation of CT Scans with Shadowed Data , 2017, SSVM.

[5]  Daniel Rueckert,et al.  Application-Driven MRI: Joint Reconstruction and Segmentation from Undersampled MRI Data , 2014, MICCAI.

[6]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7]  Daniel C. Castro,et al.  Cardiac MR Segmentation from Undersampled k-space Using Deep Latent Representation Learning , 2018, MICCAI.

[8]  Dimitris N. Metaxas,et al.  FR-Net: Joint Reconstruction and Segmentation in Compressed Sensing Cardiac MRI , 2019, FIMH.

[9]  Esther Klann,et al.  A Mumford-Shah-Like Method for Limited Data Tomography with an Application to Electron Tomography , 2011, SIAM J. Imaging Sci..

[10]  Liyan Sun,et al.  Joint CS-MRI Reconstruction and Segmentation with a Unified Deep Network , 2019, IPMI.

[11]  M. Lustig,et al.  Compressed Sensing MRI , 2008, IEEE Signal Processing Magazine.

[12]  Rama Chellappa,et al.  Task-Aware Compressed Sensing with Generative Adversarial Networks , 2018, AAAI.

[13]  S. Larsson,et al.  Clinical Significance of Magnetic Resonance Imaging Markers of Vascular Brain Injury: A Systematic Review and Meta-analysis , 2019, JAMA neurology.

[14]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[15]  Martin Burger,et al.  Simultaneous reconstruction and segmentation for dynamic SPECT imaging , 2016, 1606.03852.

[16]  ZipserDavid,et al.  A learning algorithm for continually running fully recurrent neural networks , 1989 .

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

[18]  Martin Benning,et al.  Enhancing joint reconstruction and segmentation with non-convex Bregman iteration , 2018, Inverse Problems.

[19]  Di Guo,et al.  Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator , 2014, Medical Image Anal..

[20]  Alan C. Evans,et al.  BrainWeb: Online Interface to a 3D MRI Simulated Brain Database , 1997 .

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

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  M. Lustig,et al.  SPIRiT: Iterative self‐consistent parallel imaging reconstruction from arbitrary k‐space , 2010, Magnetic resonance in medicine.

[24]  Carola-Bibiane Schönlieb,et al.  Task adapted reconstruction for inverse problems , 2018, Inverse Problems.

[25]  Lei Ai,et al.  A large, open source dataset of stroke anatomical brain images and manual lesion segmentations , 2017, Scientific Data.

[26]  Ronny Ramlau,et al.  A Mumford-Shah level-set approach for the inversion and segmentation of X-ray tomography data , 2007, J. Comput. Phys..

[27]  R. Ramlau,et al.  A Mumford-Shah level-set approach for the inversion andsegmentation of SPECT/CT data , 2011 .

[28]  Mathews Jacob,et al.  MoDL: Model-Based Deep Learning Architecture for Inverse Problems , 2017, IEEE Transactions on Medical Imaging.

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

[30]  Xiao Chen,et al.  Brain Segmentation from k-Space with End-to-End Recurrent Attention Network , 2018, MICCAI.