Primal and dual Bregman methods with application to optical nanoscopy. (English) Zbl 1235.94016

Summary: Measurements in nanoscopic imaging suffer from blurring effects modeled with different point spread functions (PSF). Some apparatus even have PSFs that are locally dependent on phase shifts. Additionally, raw data are affected by Poisson noise resulting from laser sampling and “photon counts” in fluorescence microscopy. In these applications standard reconstruction methods (EM, filtered backprojection) deliver unsatisfactory and noisy results. Starting from a statistical modeling in terms of a MAP likelihood estimation we combine the iterative EM algorithm with total variation (TV) regularization techniques to make an efficient use of a-priori information. Typically, TV-based methods deliver reconstructed cartoon images suffering from contrast reduction. We propose extensions to EM-TV, based on Bregman iterations and primal and dual inverse scale space methods, in order to obtain improved imaging results by simultaneous contrast enhancement. Besides further generalizations of the primal and dual scale space methods in terms of general, convex variational regularization methods, we provide error estimates and convergence rates for exact and noisy data. We illustrate the performance of our techniques on synthetic and experimental biological data.


94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
49N45 Inverse problems in optimal control
Full Text: DOI


[1] Acar, R., & Vogel, C. R. (1994). Analysis of bounded variation penalty methods for ill-posed problems. Inverse Problems, 10, 1217–1229. · Zbl 0809.35151
[2] Aubert, G., & Aujol, J. F. (2008). A variational approach to remove multiplicative noise. SIAM Journal on Applied Mathematics, 68, 925–946. · Zbl 1151.68713
[3] Bardsley, J., & Goldes, J. (2009). Regularization parameter selection methods for ill-posed Poisson maximum likelihood estimation. Inverse Problems, 25. · Zbl 1176.68225
[4] Bardsley, J., & Luttman, A. (2009). Total variation-penalized Poisson likelihood estimation for ill-posed problems. Advances in Computational Mathematics, 31(1), 35–59. · Zbl 1171.94001
[5] Benning, M., & Burger, M. (2009). Error estimates for variational models with non-Gaussian noise (Tech. Rep. 09-40). UCLA CAM.
[6] Bertero, M., Lantéri, H., & Zanni, L. (2008). Iterative image reconstruction: a point of view. In: CRM series: Vol. 8. Mathematical methods in biomedical imaging and intensity-modulated radiation therapy (IMRT).
[7] Bissantz, N., Hohage, T., Munk, A., & Ruymgaart, F. (2007). Convergence rates of general regularization methods for statistical inverse problems and applications. SIAM Journal on Numerical Analysis, 45, 2610–2636. · Zbl 1234.62062
[8] Bregman, L. M. (1967). The relaxation method for finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Computational Mathematics and Mathematical Physics, 7, 200–217. · Zbl 0186.23807
[9] Brune, C., Sawatzky, A., & Burger, M. (2009a). Bregman-EM-TV methods with application to optical nanoscopy. In Proceedings of the 2nd international conference on scale space and variational methods in computer vision (Vol. 5567, pp. 235–246). doi: 10.1007/978-3-642-02256-2_20 . · Zbl 1235.94016
[10] Brune, C., Sawatzky, A., Wübbeling, F., Kösters, T., & Burger, M. (2010). Forward backward EM-TV methods for inverse problems with Poisson noise. Preprint. · Zbl 1342.94026
[11] Burger, M., & Osher, S. (2004). Convergence rates of convex variational regularization. Inverse Problems, 20, 1411–1421. · Zbl 1068.65085
[12] Burger, M., Gilboa, G., Osher, S., & Xu, J. (2006). Nonlinear inverse scale space methods. Communications in Mathematical Sciences, 4(1), 179–212. · Zbl 1106.68117
[13] Burger, M., Frick, K., Osher, S., & Scherzer, O. (2007a). Inverse total variation flow. SIAM Multiscale Modelling and Simulation, 6(2), 366–395. · Zbl 1147.49026
[14] Burger, M., Resmerita, E., & He, L. (2007b). Error estimation for Bregman iterations and inverse scale space methods. Computing, 81, 109–135. · Zbl 1147.68790
[15] Burger, M., Schönlieb, C., & He, L. (2009). Cahn-Hilliard inpainting and a generalization to gray-value images. SIAM Journal of Imaging Science, 3 · Zbl 1180.49007
[16] Chambolle, A. (2004). An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision, 20, 89–97. · Zbl 1366.94056
[17] Csiszar, I. (1991). Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems. Annals of Statistics, 19, 2032–2066. · Zbl 0753.62003
[18] Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society B, 39, 1–38. · Zbl 0364.62022
[19] Dey, N., Blanc-Feraud, L., Zimmer, C., Kam, Z., Roux, P., Olivo-Marin, J. C., & Zerubia, J. (2006). Richardson-Lucy algorithm with total variation regularization for 3D confocal microscope deconvolution. Microscopy Research Technique, 69, 260–266.
[20] Ekeland, I., & Temam, R. (1999). Convex analysis and variational problems. Philadelphia: SIAM (Corrected Reprint Edition). · Zbl 0281.49001
[21] Engl, H. W., Hanke, M., & Neubauer, A. (1996). Regularization of inverse problems. Dordrecht: Kluwer Academic (Paperback edition 2000). · Zbl 0859.65054
[22] Evans, L. C., & Gariepy, R. F. (1992). Measure theory and fine properties of functions. Studies in advanced mathematics. Boca Raton: CRC Press. · Zbl 0804.28001
[23] Geman, S., & Geman, D. (1984). Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 721–741. · Zbl 0573.62030
[24] Geman, S., & McClure, D. E. (1985). Bayesian image analysis: an application to single photon emission tomography. In Proc. statistical computation section (pp. 12–18). Washington: American Statistical Association.
[25] Giusti, E. (1984). Minimal surfaces and functions of bounded variation. Basel: Birkhäuser. · Zbl 0545.49018
[26] Goldstein, T., & Osher, S. (2009). The split Bregman method for L1-regularized problems. SIAM Journal on Imaging Sciences, 2(2), 323–343. · Zbl 1177.65088
[27] He, L., Marquina, A., & Osher, S. (2005). Blind deconvolution using TV regularization and Bregman iteration. International Journal of Imaging Systems and Technology, 15(1), 74–83.
[28] Hell, S., & Schönle, A. (2006). Nanoscale resolution in far-field fluorescence microscopy. In P. W. Hawkes & J. C. H. Spence (Eds.), Science of microscopy. Berlin: Springer.
[29] Hiriart-Urruty, J. B., & Lemaréchal, C. (1993). Grundlehren der mathematischen Wissenschaften (Fundamental principles of mathematical sciences) : Vol. 305. Convex analysis and minimization algorithms I. Berlin: Springer.
[30] Hofmann, B., Kaltenbacher, B., Pöschl, C., & Scherzer, O. (2007). A Convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators. Inverse Problems, 23, 987–1010. · Zbl 1131.65046
[31] Hohage, T. (2009). Variational regularization of inverse problems with Poisson data. Preprint.
[32] Huang, Y. M., Ng, M. K., & Wen, Y. W. (2009). A new total variation method for multiplicative noise removal. SIAM Journal on Imaging Sciences, 2, 20–40. · Zbl 1187.68655
[33] Iusem, A. N. (1991). Convergence analysis for a multiplicatively relaxed EM algorithm. Mathematical Methods in the Applied Sciences, 14, 573–593. · Zbl 0743.65105
[34] Jonsson, E., Huang, S. C., & Chan, T. (1998). Total variation regularization in positron emission tomography (CAM Report 98-48). UCLA.
[35] Kittel, J., et al. (2006). Bruchpilot promotes active zone assembly, Ca2+ channel clustering, and vesicle release. Science, 312, 1051–1054.
[36] Kiwiel, K. (1997). Proximal minimization methods with generalized Bregman functions. SIAM Journal on Control and Optimization, 35, 1142–1168. · Zbl 0890.65061
[37] Klar, T. A., et al. (2000). Fluorescence microscopy with diffraction resolution barrier broken by stimulated emission. PNAS, 97, 8206–8210.
[38] Le, T., Chartrand, R., & Asaki, T. J. (2007). A variational approach to reconstructing images corrupted by Poisson noise. Journal of Mathematical Imaging and Vision, 27, 257–263.
[39] Liao, H., Li, F., & Ng, M. K. (2009). Selection of regularization parameter in total variation image restoration. Journal of the Optical Society of America A, 26, 2311–2320.
[40] Lorenz, D. A. (2008). Convergence rates and source conditions for Tikhonov regularization with sparsity constraints. Journal of Inverse and Ill-Posed Problems, 16, 463–478. · Zbl 1161.65041
[41] Lorenz, D. A., & Trede, D. (2008). Optimal convergence rates for Tikhonov regularization in Besov scales. Inverse Problems, 24, 055010. · Zbl 1147.49030
[42] Lucy, L. B. (1974). An iterative technique for the rectification of observed distributions. The Astronomical Journal, 79, 745–754.
[43] Marquina, A. (2009). Nonlinear inverse scale space methods for total variation blind deconvolution. SIAM Journal on Imaging Sciences, 2(1), 64–83. · Zbl 1177.65193
[44] Natterer, F., & Wübbeling, F. (2001). Mathematical methods in image reconstruction. SIAM monographs on mathematical modeling and computation. · Zbl 0974.92016
[45] Osher, S., Burger, M., Goldfarb, D., Xu, J., & Yin, W. (2005). An iterative regularization method for total variation based image restoration. Multiscale Modelling and Simulation, 4, 460–489. · Zbl 1090.94003
[46] Panin, V. Y., Zeng, G. L., & Gullberg, G. T. (1999). Total variation regulated EM algorithm. IEEE Transactions on Nuclear Sciences, NS-46, 2202–2010.
[47] Perona, P., & Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 629–639. · Zbl 05111848
[48] Remmele, S., Seeland, M., & Hesser, J. (2008). Fluorescence microscopy deconvolution based on Bregman iteration and Richardson-Lucy algorithm with TV regularization. In T. Tolxdorff, J. Braun, T. M. Deserno, H. Handels, A. Horsch, & H.-P. Meinzer (Eds.), Informatik aktuell. Proceedings of the workshop bildverarbeitung für die Medizin 2008 (pp. 72–76). Berlin: Springer. doi: 10.1007/978-3-540-78640-5_15 .
[49] Resmerita, E., & Anderssen, S. (2007). Joint additive Kullback-Leibler residual minimization and regularization for linear inverse problems. Mathematical Methods in the Applied Sciences, 30, 1527–1544. · Zbl 1132.47008
[50] Resmerita, E., & Scherzer, O. (2006). Error estimates for non-quadratic regularization and the relation to enhancing. Inverse Problems, 22, 801–814. · Zbl 1103.65062
[51] Resmerita, E., et al. (2007). The expectation-maximization algorithm for ill-posed integral equations: a convergence analysis. Inverse Problems, 23, 2575–2588. · Zbl 1282.65173
[52] Richardson, W. H. (1972). Bayesian-based iterative method of image restoration. Journal of the Optical Society of America, 62, 55–59.
[53] Rudin, L. I., Osher, S., & Fatemi, E. (1992). Nonlinear total variation based noise removal algorithms. Physica D, 60, 259–268. · Zbl 0780.49028
[54] Rudin, L., Lions, P. L., & Osher, S. (2003). Multiplicative denoising and debluring: theory and algorithms. In S. Osher & N. Paragios (Eds.), Geometric level sets in imaging, vision, and graphics (pp. 103–119). New York: Springer.
[55] Sawatzky, A., Brune, C., Wübbeling, F., Kösters, T., & Schäfers, K. M. B. (2008). Accurate EM-TV algorithm in PET with low SNR. In IEEE nuclear science symposium.
[56] Scherzer, O., & Groetsch, C. (2001). Inverse scale space theory for inverse problems. In M. Kerckhove (Ed.), Scale-space and morphology in computer vision. Proc. 3rd int. conf. scale-space (pp. 317–325). Berlin: Springer. · Zbl 0991.68132
[57] Shepp, L. A., & Vardi, Y. (1982). Maximum likelihood reconstruction for emission tomography. IEEE Transactions on Medical Imaging, 1(2), 113–122.
[58] Shi, J., & Osher, S. (2008). A nonlinear inverse scale space method for a convex multiplicative noise model. SIAM Journal on Imaging Sciences, 1(3), 294–321. · Zbl 1185.94018
[59] Strong, D. M., Aujol, J.-F., & Chan, T. F. (2006). Scale recognition, regularization parameter selection, and Meyer’s G norm in total variation regularization. Multiscale Modeling & Simulation, 5(1), 273–303. · Zbl 1161.68830
[60] Snyder, D. L., Helstrom, C. W., Lanterman, A. D., Faisal, M., & White, R. L. (1995). Compensation for readout noise in CCD images. Journal of the Optical Society of America A, 12, 272–283.
[61] Vardi, Y., Shepp, L. A., & Kaufman, L. (1985). A statistical model for positron emission tomography. Journal of the American Statistical Association, 80(389), 8–20. · Zbl 0561.62094
[62] Vogel, C. (2002). Computational methods for inverse problems. Philadelphia: SIAM. · Zbl 1008.65103
[63] Wernick, M. N., & Aarsvold, J. N. (Eds.) (2004). Emission tomography: the fundamentals of PET and SPECT. San Diego: Academic Press.
[64] Willig, K. I., Harke, B., Medda, R., & Hell, S. W. (2007). STED microscopy with continuous wave beams. Nature Methods, 4(11), 915–918.
[65] Witkin, A. P. (1983). Scale-space filtering. In Proc. int. joint conf. on artificial intelligence (pp. 1019–1023). Karlsruhe.
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.