Deep learning for photoacoustic tomography from sparse data

References

• Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge (MA): MIT Press; 2016.
   Google Scholar
• LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–444. doi: 10.1038/nature14539
   PubMed Web of Science ®Google Scholar
• Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv:1409.0473; 2014.
   Google Scholar
• Collobert R, Weston J, Bottou L, et al. Natural language processing (almost) from scratch. J Mach Learn Res. 2011;12:2493–2537.
   Web of Science ®Google Scholar
• Greenspan H, van Ginneken B, Summers RM. Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans Med Imaging. 2016;35(5):1153–1159. doi: 10.1109/TMI.2016.2553401
   Web of Science ®Google Scholar
• Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167; 2015.
   Google Scholar
• Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097–1105.
   Google Scholar
• Litjens G, Kooi T, Ehteshami Bejnordi B, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;41:60–88.
   Google Scholar
• Ma J, Sheridan RP, Liaw A, et al. Deep neural nets as a method for quantitative structure–activity relationships. J Chem Inf Model. 2015;55(2):263–274. doi: 10.1021/ci500747n
   PubMed Web of Science ®Google Scholar
• Wu R, Yan S, Shan Y, et al. Deep image: scaling up image recognition. arXiv:1501.02876; 2015.
   Google Scholar
• Chen H, Zhang Y, Zhang W, et al. Low-dose CT via convolutional neural network. Biomed Opt Express. 2017;8(2):679–694. doi: 10.1364/BOE.8.000679
   PubMed Web of Science ®Google Scholar
• Han Y, Yoo JJ, Ye JC. Deep residual learning for compressed sensing CT reconstruction via persistent homology analysis. Available from: arXiv:1611.06391; 2016.
   Google Scholar
• Jin KH, McCann MT, Froustey E, et al. Deep convolutional neural network for inverse problems in imaging. arXiv:1611.03679; 2016.
   Google Scholar
• Wang G. A perspective on deep imaging. IEEE Access. 2016;4:8914–8924. doi: 10.1109/ACCESS.2016.2624938
   Web of Science ®Google Scholar
• Wang S, Su Z, Ying L, et al. Accelerating magnetic resonance imaging via deep learning. IEEE 13th international symposium on biomedical Imaging (ISBI); 2016. p. 514–517.
   Google Scholar
• Würfl T, Ghesu FC, Christlein V. Deep learning computed tomography. International conference on medical image computing and computer-assisted intervention; Springer: 2016. p. 432–440.
   Google Scholar
• Zhang H, Li L, Qiao K, et al. Image prediction for limited-angle tomography via deep learning with convolutional neural network. arXiv:1607.08707; 2016.
   Google Scholar
• Beard P. Biomedical photoacoustic imaging. Interface Focus. 2011;1(4):602–631. doi: 10.1098/rsfs.2011.0028
   PubMed Web of Science ®Google Scholar
• Kruger RA, Lui P, Fang YR, et al. Photoacoustic ultrasound (paus) – reconstruction tomography. Med Phys. 1995;22(10):1605–1609. doi: 10.1118/1.597429
   PubMed Web of Science ®Google Scholar
• Paltauf G, Nuster R, Haltmeier M, et al. Photoacoustic tomography using a Mach-Zehnder interferometer as an acoustic line detector. Appl Opt. 2007;46(16):3352–3358. doi: 10.1364/AO.46.003352
   PubMed Web of Science ®Google Scholar
• Wang LV. Multiscale photoacoustic microscopy and computed tomography. Nat Photon. 2009;3(9):503–509. doi: 10.1038/nphoton.2009.157
   PubMed Web of Science ®Google Scholar
• Haltmeier M. Sampling conditions for the circular radon transform. IEEE Trans Image Process. 2016;25(6):2910–2919. doi: 10.1109/TIP.2016.2551364
   PubMed Web of Science ®Google Scholar
• Natterer F. The mathematics of computerized tomographytte, volume 32 of Classics in applied mathematics. Philadelphia: SIAM; 2001.
   Google Scholar
• Arridge S, Beard P, Betcke M, et al. Accelerated high-resolution photoacoustic tomography via compressed sensing. Phys Med Biol. 2016;61(24):8908. doi: 10.1088/1361-6560/61/24/8908
   PubMed Web of Science ®Google Scholar
• Bauer-Marschallinger J, Felbermayer K, Bouchal K-D, et al. Photoacoustic projection imaging using a 64-channel fiber optic detector array. Proc. San Francisco (CA): SPIE; 2015. p. 9323.
   Google Scholar
• Gratt S, Nuster R, Wurzinger G, et al. 64-line-sensor array: fast imaging system for photoacoustic tomography. Proc SPIE. 2014;8943: 894365.
   Google Scholar
• Guo Z, Li C, Song L, et al. Compressed sensing in photoacoustic tomography in vivo. J Biomed Opt. 2010;15(2): 021311–021311. doi: 10.1117/1.3381187
   Web of Science ®Google Scholar
• Rosenthal A, Ntziachristos V, Razansky D. Acoustic inversion in optoacoustic tomography: a review. Curr Med Imaging Rev. 2013;9(4):318–336. doi: 10.2174/15734056113096660006
   PubMed Web of Science ®Google Scholar
• Sandbichler M, Krahmer F, Berer T, et al. A novel compressed sensing scheme for photoacoustic tomography. SIAM J Appl Math. 2015;75(6):2475–2494. doi: 10.1137/141001408
   Web of Science ®Google Scholar
• Arridge SR, Betcke MM, Cox BT, et al. On the adjoint operator in photoacoustic tomography. Inverse Problems. 2016;32(11): 115012 (19pp). doi: 10.1088/0266-5611/32/11/115012
   Web of Science ®Google Scholar
• Belhachmi Z, Glatz T, Scherzer O. A direct method for photoacoustic tomography with inhomogeneous sound speed. Inverse Problems. 2016;32(4): 045005. doi: 10.1088/0266-5611/32/4/045005
   Web of Science ®Google Scholar
• Haltmeier M, Nguyen LV. Analysis of iterative methods in photoacoustic tomography with variable sound speed. SIAM J Imaging Sci. 2017;10(2):751–781. doi: 10.1137/16M1104822
   Web of Science ®Google Scholar
• Huang C, Wang K, Nie L, et al. Full-wave iterative image reconstruction in photoacoustic tomography with acoustically inhomogeneous media. IEEE Trans Med Imaging. 2013;32(6):1097–1110. doi: 10.1109/TMI.2013.2254496
   PubMed Web of Science ®Google Scholar
• Javaherian A, Holman S. A multi-grid iterative method for photoacoustic tomography. IEEE Trans Med Imaging. 2017;36(3):696–706. doi: 10.1109/TMI.2016.2625272
   PubMed Web of Science ®Google Scholar
• Schwab J, Pereverzyev Jr S, Haltmeier M. A Galerkin least squares approach for photoacoustic tomography. arXiv:1612.08094; 2016.
   Google Scholar
• Wang K, Su R, Oraevsky AA, et al. Investigation of iterative image reconstruction in three-dimensional optoacoustic tomography. Phys Med Biol. 2012;57(17):5399. doi: 10.1088/0031-9155/57/17/5399
   PubMed Web of Science ®Google Scholar
• Acar R, Vogel CR. Analysis of bounded variation penalty methods for ill-posed problems. Inverse Problems. 1994;10(6):1217–1229. doi: 10.1088/0266-5611/10/6/003
   Web of Science ®Google Scholar
• Daubechies I, Defrise M, De Mol C. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Comm Pure Appl Math. 2004;57(11):1413–1457. doi: 10.1002/cpa.20042
   Web of Science ®Google Scholar
• Frikel J, Haltmeier M. Efficient regularization with wavelet sparsity constraints in photoacoustic tomography. Inverse Prob. 2018; 34:024006(28pp).
   Google Scholar
• Grasmair M, Haltmeier M, Scherzer O. Sparsity in inverse geophysical problems. In Freeden W, Nashed MZ, Sonar T, editors. Handbook of geomathematics. Berlin, Heidelberg: Springer; 2010. p. 763–784.
   Google Scholar
• Provost J, Lesage F. The application of compressed sensing for photo-acoustic tomography. IEEE Trans Med Imaging. 2009;28(4):585–594. doi: 10.1109/TMI.2008.2007825
   PubMed Web of Science ®Google Scholar
• Scherzer O, Grasmair M, Grossauer H, et al. Variational methods in imaging, volume 167 of Applied mathematical sciences. New York: Springer; 2009.
   Google Scholar
• Burgholzer P, Bauer-Marschallinger J, Grün H, et al. Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors. Inverse Problems. 2007;23(6):S65–S80. doi: 10.1088/0266-5611/23/6/S06
   Web of Science ®Google Scholar
• Finch D, Haltmeier M, Rakesh. Inversion of spherical means and the wave equation in even dimensions. SIAM J Appl Math. 2007;68(2):392–412. doi: 10.1137/070682137
   Web of Science ®Google Scholar
• Finch D, Patch SK, Rakesh. Determining a function from its mean values over a family of spheres. SIAM J Math Anal. 2004;35(5):1213–1240. doi: 10.1137/S0036141002417814
   Web of Science ®Google Scholar
• Haltmeier M. Inversion of circular means and the wave equation on convex planar domains. Comput Math Appl. 2013;65(7):1025–1036. doi: 10.1016/j.camwa.2013.01.036
   Web of Science ®Google Scholar
• Haltmeier M. Universal inversion formulas for recovering a function from spherical means. SIAM J Math Anal. 2014;46(1):214–232. doi: 10.1137/120881270
   Web of Science ®Google Scholar
• Kunyansky LA. Explicit inversion formulae for the spherical mean Radon transform. Inverse Problems. 2007;23(1):373–383. doi: 10.1088/0266-5611/23/1/021
   Web of Science ®Google Scholar
• Xu M, Wang LV. Universal back-projection algorithm for photoacoustic computed tomography. Phys Rev E. 2005;71(1): 016706.
   Web of Science ®Google Scholar
• Agranovsky M, Kuchment P. Uniqueness of reconstruction and an inversion procedure for thermoacoustic and photoacoustic tomography with variable sound speed. Inverse Problems. 2007;23(5):2089–2102. doi: 10.1088/0266-5611/23/5/016
   Web of Science ®Google Scholar
• Haltmeier M, Scherzer O, Zangerl G. A reconstruction algorithm for photoacoustic imaging based on the nonuniform FFT. IEEE Trans Med Imaging. 2009;28(11):1727–1735. doi: 10.1109/TMI.2009.2022623
   PubMed Web of Science ®Google Scholar
• Jaeger M, Schüpbach S, Gertsch A, et al. Fourier reconstruction in optoacoustic imaging using truncated regularized inverse k-space interpolation. Inverse Problems. 2007;23:S51–S63. doi: 10.1088/0266-5611/23/6/S05
   Web of Science ®Google Scholar
• Kunyansky LA. A series solution and a fast algorithm for the inversion of the spherical mean Radon transform. Inverse Problems. 2007;23(6):S11–S20. doi: 10.1088/0266-5611/23/6/S02
   Web of Science ®Google Scholar
• Xu Y, Xu M, Wang LV. Exact frequency-domain reconstruction for thermoacoustic tomography–II: cylindrical geometry. IEEE Trans Med Imaging. 2002;21:829–833. doi: 10.1109/TMI.2002.801171
   PubMed Web of Science ®Google Scholar
• Burgholzer P, Matt GJ, Haltmeier M, et al. Exact and approximate imaging methods for photoacoustic tomography using an arbitrary detection surface. Phys Rev E. 2007;75(4): 046706. doi: 10.1103/PhysRevE.75.046706
   Web of Science ®Google Scholar
• Hristova Y, Kuchment P, Nguyen L. Reconstruction and time reversal in thermoacoustic tomography in acoustically homogeneous and inhomogeneous media. Inverse Problems. 2008;24(5): 055006 (25pp). doi: 10.1088/0266-5611/24/5/055006
   Web of Science ®Google Scholar
• Stefanov P, Uhlmann G. Thermoacoustic tomography with variable sound speed. Inverse Problems. 2009;25(7): 075011. 16. doi: 10.1088/0266-5611/25/7/075011
   PubMed Web of Science ®Google Scholar
• Treeby BE, Cox BT. k-wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave-fields. J Biomed Opt. 2010;15: 021314. doi: 10.1117/1.3360308
   PubMed Web of Science ®Google Scholar
• Ronneberge O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. CoRR; 2015.
   Google Scholar
• Dreier F, Haltmeier M, Pereverzyev Jr S. Operator learning approach for the limited view problem in photoacoustic tomography. arXiv:1705.02698; 2017.
   Google Scholar
• Kuchment P, Kunyansky L. Mathematics of photoacoustic and thermoacoustic tomography. In: Otmar S, editor. Handbook math methods imaging. New York: Springer; 2011. p. 817–865.
   Google Scholar
• Xu M, Wang LV. Photoacoustic imaging in biomedicine. Rev Sci Instrum. 2006;77(4): 041101 (22pp). doi: 10.1063/1.2195024
   Web of Science ®Google Scholar
• Çiçek O, Abdulkadir A, Lienkamp SS, et al. 3d u-net: learning dense volumetric segmentation from sparse annotation. arXiv:1606.06650; 2016.
   Google Scholar
• Haltmeier M, Sandbichler M, Berer T, et al. A sparsification and reconstruction strategy for compressed sensing photoacoustic tomography. J Acoust Soc Amer. 2018;141(6):3838(11pp).
   Google Scholar
• Stefanov P, Uhlmann G. Thermoacoustic tomography with variable sound speed. Inverse Problems. 2009;25(7): 075011. 16. doi: 10.1088/0266-5611/25/7/075011
   PubMed Web of Science ®Google Scholar
• Grün H, Berer T, Burgholzer P, et al. Three-dimensional photoacoustic imaging using fiber-based line detectors. J Biomed Opt. 2010;15(2): 021306–021308. doi: 10.1117/1.3381186
   PubMed Web of Science ®Google Scholar
• Nuster R, Holotta M, Kremser C, et al. Photoacoustic microtomography using optical interferometric detection. J Biomed Opt. 2010;15(2): 021307–021307–6. doi: 10.1117/1.3333547
   Web of Science ®Google Scholar
• Meng J, Wang LV, Liang D, et al. In vivo optical-resolution photoacoustic computed tomography with compressed sensing. Opt Lett. 2012;37(22):4573–4575. doi: 10.1364/OL.37.004573
   PubMed Web of Science ®Google Scholar
• Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Netw. 1989;2(3):183–192. doi: 10.1016/0893-6080(89)90003-8
   Web of Science ®Google Scholar
• Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Netw. 1991;4(2):251–257. doi: 10.1016/0893-6080(91)90009-T
   Web of Science ®Google Scholar
• Bishop CM. Pattern recognition and machine learning. New York: Springer; 2006.
   Google Scholar
• De Cezaro A, Haltmeier M, Leitão A, et al. On steepest-descent-Kaczmarz methods for regularizing systems of nonlinear ill-posed equations. Appl Math Comput. 2008;202(2):596–607.
   Web of Science ®Google Scholar
• Gordon R, Bender R, Herman GT. Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography. J Theor Biol. 1970;29(3):471–481. doi: 10.1016/0022-5193(70)90109-8
   PubMed Web of Science ®Google Scholar
• LeCun Y, Boser B, Denker JS, et al. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1989;1(4):541–551. doi: 10.1162/neco.1989.1.4.541
   Web of Science ®Google Scholar
• Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition; Boston, USA; 2015. p. 3431–3440.
   Google Scholar
• Haltmeier M. A mollification approach for inverting the spherical mean Radon transform. SIAM J Appl Math. 2011;71(5):1637–1652. doi: 10.1137/110821561
   Web of Science ®Google Scholar
• Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics. Vol. 9. 2010; p. 249–256.
   Google Scholar
• Vogel CR, Oman ME. Iterative methods for total variation denoising. SIAM J Sci Comput. 1996;17:227–238. doi: 10.1137/0917016
   Web of Science ®Google Scholar
• Paltauf G, Hartmair P, Kovachev G, et al. Piezoelectric line detector array for photoacoustic tomography. Photoacoustics. 2017;8:28–36. doi: 10.1016/j.pacs.2017.09.002
   PubMed Web of Science ®Google Scholar
• Schwab J, Antholzer S, Nuster R, et al. Real-time photoacoustic projection imaging using deep learning. arXiv:1801.06693; 2018.
   Google Scholar