RODEO: Robust DE-aliasing autoencOder for real-time medical image reconstruction

Pattern Recognition

Volumn 63, Issue , 2017, Pages 499-510

  Mehta, Janki ^a   Majumdar, Angshul ^a  

^a INDRAPRASTHA INSTITUTE OF INFORMATION TECHNOLOGY   (India)

Author keywords

Autoencoder; Compressed sensing; CT reconstruction; MRI

Indexed keywords

COMPLEX NETWORKS; COMPRESSED SENSING; COMPUTERIZED TOMOGRAPHY; COST FUNCTIONS; IMAGE PROCESSING; IMAGE RECONSTRUCTION; LEARNING SYSTEMS; MAGNETIC RESONANCE IMAGING; MEDICAL IMAGING; OPTIMIZATION; SIGNAL RECONSTRUCTION;

AUTO ENCODERS; COMPLEX OPTIMIZATION PROBLEMS; CT RECONSTRUCTION; MATRIX-VECTOR PRODUCTS; REAL-TIME RECONSTRUCTION; RECONSTRUCTION SPEED; SPLIT BREGMAN METHODS; UNIVERSAL FUNCTIONS;

MEDICAL IMAGE PROCESSING;

EID: 84999015221     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patcog.2016.09.022     Document Type: Article

References (72)

1. [1] Brenner, D.J., Hall, E.J., Computed tomography - an increasing source of radiation exposure. N. Engl. J. Med. 357 (2007), 2277–2284.
2. [2] A. N. Kolmogorov, On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition, Doklady Akademii Nauk SSSR, 144, 1994, pp. 679–681; American Mathematical Society Translation, 28, 1963, pp. 55–59.
3. [3] Kukrova, V., Kolmogorov's theorem and multilayer neural networks. Neural Netw. 5:3 (1992), 501–506.
4. [4] Hornik, K., Approximation capabilities of multilayer feedforward networks. Neural Netw. 4:2 (1991), 251–257.
5. [5] Cybenko, G., Approximations by superpositions of sigmoidal functions. Math. Control Signals Syst. 2:4 (1989), 303–314.
6. [6] Natarajan, B.K., Sparse approximate solutions to linear systems. SIAM J. Comput. 24 (1995), 227–234.
7. [7] Candes, E., Romberg, J., Tao, T., Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory 52:2 (2006), 489–509.
8. [8] Donoho, D., Compressed sensing. IEEE Trans. Inf. Theory 52:4 (2006), 1289–1306.
9. [9] Lustig, M., Donoho, D., Pauly, J.M., Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn. Reson. Med. 58:6 (2007), 1182–1195.
10. [10] Trzasko, J., Manduca, A., Highly undersampled magnetic resonance image reconstruction via homotopic l0-minimization. IEEE Trans. Med. Imaging 28:1 (2009), 106–121.
11. [11] Majumdar, A., Ward, R.K., On the choice of compressed sensing priors: an experimental study. Signal Process.: Image Commun. 27:9 (2012), 1035–1048.
12. [12] Gamper, U., Boesiger, P., Kozerke, S., Compressed sensing in dynamic MRI. Magn. Reson. Med. 59:2 (2008), 365–373.
13. [13] M.LustigJ.M.SantosD.L.Donoho, J.M Pauly, k-t SPARSE: High Frame Rate Dynamic MRI Exploiting Spatio-Temporal Sparsity, ISMRM '06.
14. [14] Jung, H., Ye, J.C., Kim, E.Y., Improved k-t BLAST and k-t SENSE using FOCUSS. Phys. Med. Biol. 52 (2007), 3201–3226.
15. [15] Jung, H., Park, J., Yoo, J., Ye, J.C., Radial k-t FOCUSS for high-resolution Cardiac Cine MRI. Magn. Reson. Med. 63 (2010), 68–78.
16. [16] Jung, H., Park, J., Yoo, J., Ye, J.C., k-t FOCUSS: a general compressed sensing framework for high resolution dynamic MRI. Magn. Reson. Med. 61 (2009), 103–116.
17. [17] Chen, L., Schabel, M.C., DiBella, E.V.R., Reconstruction of dynamic contrast enhanced magnetic resonance imaging of the breast with temporal constraints. Magn. Reson. Imaging 28:5 (2010), 637–645.
18. [18] Adluru, G., McGann, C., Speier, P., Kholmovski, E.G., Shaaban, A., DiBella, E.V.R., Acquisition and reconstruction of undersampled radial data for myocardial perfusion magnetic resonance imaging. J. Magn. Reson. Imaging 29 (2009), 466–473.
19. [19] B.ZhaoJ.P.HaldarC.BrinegarZ.P.Liang, Low rank matrix recovery for real-time cardiac MRI, International Symposium on Biomedical Imaging, 2010, pp. 996–999.
20. [20] J.P.HaldarZ.-P.Liang, Low-rank approximations for dynamic imaging, in: Proceedings of the IEEE International Symposium on Biomedical Imaging, 2011, pp. 1052–1055.
21. [21] Goud, S., Hu, Y., DiBella, E., Jacob, M., Accelerated dynamic MRI exploiting sparsity and low-rank structure. IEEE Trans. Med. Imaging 30 (2011), 1042–1054.
22. [22] Zhao, B., Haldar, J.P., Christodoulou, A.G., Liang, Z.-P., Image reconstruction from highly undersampled (k,t)-Space data with joint partial separability and sparsity constraints. IEEE Trans. Med. Imaging 31 (2012), 1809–1820.
23. [23] Majumdar, A., Improved dynamic MRI reconstruction by exploiting sparsity and rank-deficiency. Magn. Reson. Imaging 31 (2013), 789–795.
24. [24] Majumdar, A., Ward, R.K., Aboulnasr, T., Non-Convex Algorithm for sparse and low-rank recovery: application to dynamic MRI reconstruction. Magn. Reson. Imaging 31:3 (2012), 448–455.
25. [25] Gleichman, S., Eldar, Y.C., Blind compressed sensing. IEEE Trans. Inf. Theory 57 (2011), 6958–6975.
26. [26] Lingala, S.G., Jacob, M., Blind compressed sensing dynamic MRI. IEEE Trans. Med. Imaging 32 (2013), 1132–1145.
27. [27] Majumdar, A., Improving synthesis and analysis prior blind compressed sensing with low-rank constraints for dynamic MRI reconstruction. Magn. Reson. Imaging 33:1 (2015), 174–179.
28. [28] Sümbül, U., Santos, J.M., Pauly, J.M., A practical acceleration algorithm for real-time imaging. IEEE Trans. Med. Imaging, 28(12), 2009.
29. [29] Sümbül, U., Santos, J.M., Pauly, J.M., Improved time series reconstruction for dynamic magnetic resonance imaging. IEEE Trans. Med. Imaging, 28(7), 2009.
30. [30] Vaswani, N., Lu, W., Modified-CS: modifying compressive sensing for problems with partially known support. IEEE Trans. Signal Process., 58(9), 2010.
31. [31] Majumdar, A., Ward, R.K., Aboulnasr, T., Compressed sensing based near real-time online dynamic MRI reconstruction. IEEE Trans. Med. Imaging 31:2 (2012), 2253–2266.
32. [32] Majumdar, A., Motion predicted online dynamic MRI reconstruction from partially sampled K-Space data. Magn. Reson. Imaging 31:9 (2013), 1578–1586.
33. [33] Majumdar, A., Compressed Sensing for Magnetic Resonance Image Reconstruction, 2015, Cambridge University Press, New Delhi.
34. [34] Majumdar, A., Ward, R.K., MRI: Physics, Reconstruction and Analysis. 2015, CRC Press, New Delhi.
35. [35] Song, J., Liu, Q.H., Johnson, G.A., Badea, C.T., Sparseness prior based iterative image reconstruction for retrospectively gated cardiac micro-ct. Med. Phys. 34 (2007), 4476–4482.
36. [36] Yu, H., Wang, G., Compressed sensing based interior tomography. Phys. Med. Biol. 54 (2009), 2791–2805.
37. [37] Lee, H., Xing, L., Davidi, R., Li, R., Qian, J., Lee, R., Improved compressed sensing-based cone-beam CT reconstruction using adaptive prior image constraints”. Phys. Med. Biol., 57, 2012 (2287-).
38. [38] Chen, G.H., Tang, J., Leng, S., Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. Med. Phys. 35:2 (2008), 660–663.
39. [39] Tang, J., Hsieh, J., Chen, G.H., Temporal resolution improvement in cardiac CT using PICCS (TRI-PICCS): performance studies. Med. Phys. 37:8 (2010), 4377–4388.
40. [40] Ramirez-Giraldo, J.C., Trzasko, J., Leng, S., Yu, L., Manduca, A., McCollough, C.H., Nonconvex prior image constrained compressed sensing (NCPICCS): theory and simulations on perfusion CT. Med. Phys. 38:4 (2011), 2157–2167.
41. [41] Bengio, Y., Learning deep architectures for AI. Found. Trends Mach. Learn. 2:1 (2009), 1–127.
42. [42] Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, Greedy layer-wise training of deep networks, NIPS, 2006.
43. [43] Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A., Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11 (2010), 3371–3408.
44. [44] K.H. Cho, Simple sparsification improves sparse denoising autoencoders in denoising highly noisy images, ICML, 2013.
45. [45] S. Rifai, P. Vincent, X. Muller, X. Glorot, Y. Bengio, Contractive autoencoders: explicit invariance during feature extraction, ICML, 2011.
46. [46] Tropp, J.A., Gilbert, A.C., Signal recovery from random measurements via Orthogonal Matching Pursuit. IEEE Trans. Inf. Theory 53:12 (2007), 4655–4666.
47. [47] Donoho, D., Tsaig, Y., Drori, I., Starck, J.-L., Sparse solution of underdetermined systems of linear equations by Stagewise Orthogonal Matching Pursuit. IEEE Trans. Inf. Theory 58:2 (2012), 1094–1121.
48. [48] Needell, D., Tropp, J.A., CoSaMP: iterative signal recovery from incomplete and inaccurate samples. Appl. Comput. Harmon. Anal. 26:3 (2009), 301–321.
49. [49] Daubechies, I., Defrise, M., Mol, C. De, An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 4:57 (2004), 1413–1457.
50. [50] Donoho, D., De-noising by soft-thresholding. IEEE Trans. Inf. Theory 41:3 (1995), 613–627.
51. [51] Huber, P.J., Robust estimation of a location parameter. Ann. Math. Stat. 35:1 (1964), 73–101.
52. [52] Branham, R.L. Jr., Alternatives to least squares. Astron. J. 87 (1982), 928–937.
53. [53] Shi, M., Lukas, M.A., An L1 estimation algorithm with degeneracy and linear constraints. Comput. Stat. Data Anal. 39:1 (2002), 35–55.
54. [54] L. Wang, M.D. Gordon, J. Zhu, Regularized least absolute deviations regression and an efficient algorithm for parameter tuning, IEEE ICDM, 2006.
55. [55] Barrodale, I., Roberts, F.D.K., An improved algorithm for discrete L1 linear approximation. SIAM J. Numer. Anal. 10:5 (1973), 839–848.
56. [56] Schlossmacher, E.J., An iterative technique for absolute deviations curve fitting. J. Am. Stat. Assoc. 68:344 (1973), 857–859.
57. [57] Wesolowsky, G.O., A new descent algorithm for the least absolute value regression problem. Commun. Stat. – Simul. Comput. Vol. B10:5 (1981), 479–491.
58. [58] Li, Y., Arce, G.R., A maximum likelihood approach to least absolute deviation regression. EURASIP J. Appl. Signal Process. 12 (2004), 1762–1769.
59. [59] Xiao, Y., Zeng, T., Yu, J., Ng, M.K., Pattern Recognit. 44:8 (2011), 1708–1720.
60. [60] Luo, L., Yang, J., Qian, J., Tai, Y., Nuclear-L1 norm joint regression for face reconstruction and recognition with mixed noise. Pattern Recognit. 48:12 (2015), 3811–3824.
61. [61] H.AgarwalA.Majumdar, Generalized synthesis and analysis prior algorithms with application to impulse denoising, ICVGIP, 2014.
62. [62] arXiv:1503.06383.
63. [63] 〈http://home.engineering.iastate.edu/~chenlu/csresidual.htm〉.
64. [64] 〈http://www.sci.utah.edu/bisti.html〉.
65. [65] 〈 http://www.phon.ox.ac.uk/jcoleman/Dynamic_MRI.html〉.
66. [66] Luo, Ying, Ward, R.K., Removing the blocking artifacts of block-based DCT compressed images. IEEE Trans. Image Process. 12:7 (2003), 838–842.
67. [67] 〈 http://nw360.blogspot.in/2007/01/matlab-code-for-luo-and-wards-algorithm.html〉.
68. [68] Dai, X.B., Shu, H.Z., Luo, L.M., Han, G.N., Coatrieux, J.L., Reconstruction of tomographic images from limited range projections using discrete Radon transform and Tchebichef moments. Pattern Recognit. 43:3 (2010), 1152–1164.
69. [69] Wang, T.J., Sze, T.W., The image moment method for the limited range CT image reconstruction and pattern recognition. Pattern Recognit. 34:11 (2001), 2145–2154.
70. [70] 〈 http://isbweb.org/data/vsj〉.
71. [71] 〈 https://www.math.ucdavis.edu/~mpf/spgl1/〉.
72. [72] Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P., Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13:4 (2004), 600–612.