Document Zbl 1457.92089

Akbar, Ridho; Feng, Yuanjing; Zhang, Fan; He, Jianzhong; Zeng, Qingrun; Ning, Lipeng; Westin, Carl-Fredrik; O’Donnell, Lauren J.

Spatial sparse estimation of fiber orientation distribution using deep alternating directions method of multipliers network. (English) Zbl 1457.92089

Bonet-Carne, Elisenda (ed.) et al., Computational diffusion MRI. MICCAI workshop, Shenzhen, China, October 17, 2019. Cham: Springer. Math. Vis., 79-89 (2020).

Summary: Sparse prior information is introduced to improve the accuracy of (FOD) estimation. Spatial continuity is another important aspect of prior information, but it is difficult to directly consider in sparse FODs estimation. First, we proposed a model based on adaptive group-patch and \(l_1\)-norm regularization. Second, in order to solve the FOD estimation problem of complex spherical deconvolution optimization using alternating directions method of multipliers (ADMM), a deep ADMM network is proposed to learn the optimal model parameters from training data. In order to obtain the qualitative and quantitative evaluation of the proposed method and the state-of-the-art constrained spherical deconvolution (CSD): first, ISBI 2013 phantom with known ground truth will be used to evaluate the local accuracy of the fiber configuration. Second, the global impact of FOD accuracy on real brain datasets was assessed using standard tractography and automatic white matter analysis algorithms. Compared with the comparison method, the proposed method has good consistency in sparse fiber reconstruction and fiber continuity.
For the entire collection see [Zbl 1455.92001].

MSC:

92C55	Biomedical imaging and signal processing
92B20	Neural networks for/in biological studies, artificial life and related topics
92-08	Computational methods for problems pertaining to biology

Keywords:

diffusion MRI; fiber orientation distributions; sparse spatial deconvolution model; deep ADMM network

Software:

Dipy

Cite Review PDF

Full Text: DOI

References:

[1]	Tournier, J.D., Calamante, F., Connelly, A.: Robust determination of the fibre orientation distribution in diffusion MRI: non-negativity constrained super-resolved spherical deconvolution. Neuroimage 35(4), 1459-1472 (2007). https://doi.org/10.1016/j.neuroimage.2007.02.016
[2]	Tournier, J.D., Calamante, F., Gadian, D.G., Connelly, A.: Direct estimation of the fiber orientation density function from diffusion-weighted MRI data using spherical deconvolution. NeuroImage 23(3), 1176-1185 (2004). https://doi.org/10.1016/j.neuroimage.2004.07.037
[3]	Jeurissen, B., Tournier, J.D., Dhollander, T., Connelly, A., Sijbers, J.: Multi-tissue constrained spherical deconvolution for improved analysis of multi-shell diffusion MRI data. NeuroImage 103, 411-426 (2014). https://doi.org/10.1016/j.neuroimage.2014.07.061
[4]	Landman, B.A., Bogovic, J.A., Wan, H., ElShahaby, F.E.Z., Bazin, P.L., Prince, J.L.: Resolution of crossing fibers with constrained compressed sensing using diffusion tensor MRI. NeuroImage 59(3), 2175-2186 (2012). https://doi.org/10.1016/j.neuroimage.2011.10.011
[5]	Daducci, A., Canales-Rodrı, E.J., Descoteaux, M., Garyfallidis, E., Gur, Y., Lin, Y.C., Mani, M., Merlet, S., Paquette, M., Ramirez-Manzanares, A., Reisert, M.: Quantitative comparison of reconstruction methods for intra-voxel fiber recovery from diffusion MRI. IEEE Trans. Med. Imaging 33(2), 384-399 (2013). https://doi.org/10.1109/TMI.2013.2285500
[6]	Daducci, A., Van De Ville, D., Thiran, J.P., Wiaux, Y.: Sparse regularization for fiber ODF reconstruction: From the suboptimality of \(\ell 2\) and \(\ell 1\) priors to \(\ell 0\). Med. Image Anal. 18(6), 820-833 (2014). https://doi.org/10.1016/j.media.2014.01.011
[7]	Auría, A., Daducci, A., Thiran, J.P., Wiaux, Y.: Structured sparsity for spatially coherent fibre orientation estimation in diffusion MRI. NeuroImage 115, 245-255 (2015). https://doi.org/10.1016/j.neuroimage.2015.04.049
[8]	Rathi, Y., Michailovich, O., Laun, F., Setsompop, K., Grant, P.E., Westin, C.F.: Multi-shell diffusion signal recovery from sparse measurements. Med. Image Anal. 18(7), 1143-1156 (2014). https://doi.org/10.1016/j.media.2014.06.003
[9]	Lin, Z., Gong, T., Wang, K., Li, Z., He, H., Tong, Q., Yu, F., Zhong, J.: Fast learning of fiber orientation distribution function for MR tractography using convolutional neural network. Med. Phys. (2019). https://doi.org/10.1002/mp.13555
[10]	Garyfallidis, E., Brett, M., Amirbekian, B., Rokem, A., Van Der Walt, S., Descoteaux, M., Nimmo-Smith, I.: Dipy, a library for the analysis of diffusion MRI data. Frontiers Neuroinform. 8, 8 (2014). https://doi.org/10.3389/fninf.2014.00008
[11]	Zhang, F., Wu, Y., Norton, I., Rigolo, L., Rathi, Y., Makris, N., O’Donnell, L.J.: An anatomically curated fiber clustering white matter atlas for consistent white matter tract parcellation across the lifespan. NeuroImage 179, 429-447 (2018). https://doi.org/10.1016/j.neuroimage.2018.06.027
[12]	Wu, Y., Feng, Y., Li, F., Westin, C.F.: Global consistency spatial model for fiber orientation distribution estimation. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 1180-1183. IEEE (2015). https://doi.org/10.1109/ISBI.2015.7164083
[13]	Elden, L.: Algorithms for the regularization of ill-conditioned least squares problems. BIT Numer. Math. 17(2), 134-145 (1977). https://doi.org/10.1007/BF01932285 · Zbl 0362.65105
[14]	Canales-Rodríguez, E.J., Legarreta, J.H., Pizzolato, M., Rensonnet, G., Girard, G., Rafael-Patino, J., Barakovic, M., Romascano, D., Aleman-Gomez, Y., Radua, J., Pomarol-Clotet, E.: Sparse wars: A survey and comparative study of spherical deconvolution algorithms for diffusion MRI. NeuroImage 184, 140-160 (2019). https://doi.org/10.1016/j.neuroimage.2018.08.071
[15]	Kottath, R.

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.