Literature DB >> 31009085

Fast learning of fiber orientation distribution function for MR tractography using convolutional neural network.

Zhichao Lin1, Ting Gong2, Kewen Wang3, Zhiwei Li1, Hongjian He2, Qiqi Tong2, Feng Yu1, Jianhui Zhong2,4.   

Abstract

PURPOSE: In diffusion-weighted magnetic resonance imaging (DW-MRI), the fiber orientation distribution function (fODF) is of great importance for solving complex fiber configurations to achieve reliable tractography throughout the brain, which ultimately facilitates the understanding of brain connectivity and exploration of neurological dysfunction. Recently, multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD) method has been explored for reconstructing full fODFs. To achieve a reliable fitting, similar to other model-based approaches, a large number of diffusion measurements is typically required for MSMT-CSD method. The prolonged acquisition is, however, not feasible in practical clinical routine and is prone to motion artifacts. To accelerate the acquisition, we proposed a method to reconstruct the fODF from downsampled diffusion-weighted images (DWIs) by leveraging the strong inference ability of the deep convolutional neural network (CNN).
METHODS: The method treats spherical harmonics (SH)-represented DWI signals and fODF coefficients as inputs and outputs, respectively. To compensate for the reduced gradient directions with reduced number of DWIs in acquisition in each voxel, its surrounding voxels are incorporated by the network for exploiting their spatial continuity. The resulting fODF coefficients are fitted with applying the CNN in a multi-target regression model. The network is composed of two convolutional layers and three fully connected layers. To obtain an initial evaluation of the method, we quantitatively measured its performance on a simulated dataset. Then, for in vivo tests, we employed data from 24 subjects from the Human Connectome Project (HCP) as training set and six subjects as test set. The performance of the proposed method was primarily compared to the super-resolved MSMT-CSD with the decreasing number of DWIs. The fODFs reconstructed by MSMT-CSD from all available 288 DWIs were used as training labels and the reference standard. The performance was quantitatively measured by the angular correlation coefficient (ACC) and the mean angular error (MAE).
RESULTS: For the simulated dataset, the proposed method exhibited the potential advantage over the model reconstruction. For the in vivo dataset, it achieved superior results over the MSMT-CSD in all the investigated cases, with its advantage more obvious when a limited number of DWIs were used. As the number of DWIs was reduced from 95 to 25, the median ACC ranged from 0.96 to 0.91 for the CNN, but 0.93 to 0.77 for the MSMT-CSD (with perfect score of 1). The angular error in the typical regions of interest (ROIs) was also much lower, especially in multi-fiber regions. The average MAE for the CNN method in regions containing one, two, three fibers was, respectively, 1.09°, 2.75°, and 8.35° smaller than the MSMT-CSD method. The visual inception of the fODF further confirmed this superiority. Moreover, the tractography results validated the effectiveness of the learned fODF, in preserving known major branching fibers with only 25 DWIs.
CONCLUSION: Experiments on HCP datasets demonstrated the feasibility of the proposed method in recovering fODFs from up to 11-fold reduced number of DWIs. The proposed method offers a new streamlined reconstruction procedure and exhibits promising potential in acquisition acceleration for the reconstruction of fODFs with good accuracy.
© 2019 American Association of Physicists in Medicine.

Entities:  

Keywords:  constrained spherical deconvolution; convolutional neural network; diffusion-weighted MR imaging; fiber orientation dispersion function; fiber tractography

Year:  2019        PMID: 31009085     DOI: 10.1002/mp.13555

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  9 in total

1.  Deep Learning Estimation of Multi-Tissue Constrained Spherical Deconvolution with Limited Single Shell DW-MRI.

Authors:  Vishwesh Nath; Sudhir K Pathak; Kurt G Schilling; Walt Schneider; Bennett A Landman
Journal:  Proc SPIE Int Soc Opt Eng       Date:  2020-03-10

2.  Performance of orientation distribution function-fingerprinting with a biophysical multicompartment diffusion model.

Authors:  Patryk Filipiak; Timothy Shepherd; Ying-Chia Lin; Dimitris G Placantonakis; Fernando E Boada; Steven H Baete
Journal:  Magn Reson Med       Date:  2022-02-28       Impact factor: 3.737

Review 3.  Recent advances of deep learning in psychiatric disorders.

Authors:  Lu Chen; Chunchao Xia; Huaiqiang Sun
Journal:  Precis Clin Med       Date:  2020-08-28

4.  A machine learning-based method for estimating the number and orientations of major fascicles in diffusion-weighted magnetic resonance imaging.

Authors:  Davood Karimi; Lana Vasung; Camilo Jaimes; Fedel Machado-Rivas; Shadab Khan; Simon K Warfield; Ali Gholipour
Journal:  Med Image Anal       Date:  2021-06-03       Impact factor: 13.828

Review 5.  Diffusion Imaging in the Post HCP Era.

Authors:  Steen Moeller; Pramod Pisharady Kumar; Jesper Andersson; Mehmet Akcakaya; Noam Harel; Ruoyun Emily Ma; Xiaoping Wu; Essa Yacoub; Christophe Lenglet; Kamil Ugurbil
Journal:  J Magn Reson Imaging       Date:  2020-06-20       Impact factor: 5.119

6.  DeepDTI: High-fidelity six-direction diffusion tensor imaging using deep learning.

Authors:  Qiyuan Tian; Berkin Bilgic; Qiuyun Fan; Congyu Liao; Chanon Ngamsombat; Yuxin Hu; Thomas Witzel; Kawin Setsompop; Jonathan R Polimeni; Susie Y Huang
Journal:  Neuroimage       Date:  2020-06-03       Impact factor: 6.556

7.  Deep learning-based parameter estimation in fetal diffusion-weighted MRI.

Authors:  Davood Karimi; Camilo Jaimes; Fedel Machado-Rivas; Lana Vasung; Shadab Khan; Simon K Warfield; Ali Gholipour
Journal:  Neuroimage       Date:  2021-08-26       Impact factor: 6.556

8.  Deep Learning-based Noise Reduction for Fast Volume Diffusion Tensor Imaging: Assessing the Noise Reduction Effect and Reliability of Diffusion Metrics.

Authors:  Hajime Sagawa; Yasutaka Fushimi; Satoshi Nakajima; Koji Fujimoto; Kanae Kawai Miyake; Hitomi Numamoto; Koji Koizumi; Masahito Nambu; Hiroharu Kataoka; Yuji Nakamoto; Tsuneo Saga
Journal:  Magn Reson Med Sci       Date:  2020-09-18       Impact factor: 2.471

Review 9.  Learning to estimate the fiber orientation distribution function from diffusion-weighted MRI.

Authors:  Davood Karimi; Lana Vasung; Camilo Jaimes; Fedel Machado-Rivas; Simon K Warfield; Ali Gholipour
Journal:  Neuroimage       Date:  2021-06-26       Impact factor: 6.556

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.