1
|
Kobler E, Effland A, Kunisch K, Pock T. Total Deep Variation: A Stable Regularization Method for Inverse Problems. IEEE Trans Pattern Anal Mach Intell 2022; 44:9163-9180. [PMID: 34727026 DOI: 10.1109/tpami.2021.3124086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
Various problems in computer vision and medical imaging can be cast as inverse problems. A frequent method for solving inverse problems is the variational approach, which amounts to minimizing an energy composed of a data fidelity term and a regularizer. Classically, handcrafted regularizers are used, which are commonly outperformed by state-of-the-art deep learning approaches. In this work, we combine the variational formulation of inverse problems with deep learning by introducing the data-driven general-purpose total deep variation regularizer. In its core, a convolutional neural network extracts local features on multiple scales and in successive blocks. This combination allows for a rigorous mathematical analysis including an optimal control formulation of the training problem in a mean-field setting and a stability analysis with respect to the initial values and the parameters of the regularizer. In addition, we experimentally verify the robustness against adversarial attacks and numerically derive upper bounds for the generalization error. Finally, we achieve state-of-the-art results for several imaging tasks.
Collapse
|
2
|
Kunisch K, Priyasad B. Continuous Differentiability of the Value Function of Semilinear Parabolic Infinite Time Horizon Optimal Control Problems on L 2 ( Ω ) Under Control Constraints. Appl Math Optim 2022; 85:10. [PMID: 35535171 PMCID: PMC9018668 DOI: 10.1007/s00245-022-09840-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 12/16/2021] [Indexed: 06/14/2023]
Abstract
An abstract framework guaranteeing the local continuous differentiability of the value function associated with optimal stabilization problems subject to abstract semilinear parabolic equations subject to a norm constraint on the controls is established. It guarantees that the value function satisfies the associated Hamilton-Jacobi-Bellman equation in the classical sense. The applicability of the developed framework is demonstrated for specific semilinear parabolic equations.
Collapse
Affiliation(s)
- Karl Kunisch
- Institute for Mathematics and Scientific Computing, University of Graz, Heinrichstrasse 36, 8010 Graz, Austria
- Radon Institute, Austrian Academy of Science, Linz, Austria
| | - Buddhika Priyasad
- Institute for Mathematics and Scientific Computing, University of Graz, Heinrichstrasse 36, 8010 Graz, Austria
| |
Collapse
|
3
|
Kunisch K, Trautmann P. An Inverse Problem Involving a Viscous Eikonal Equation with Applications in Electrophysiology. Vietnam J Math 2021; 50:301-317. [PMID: 34901261 PMCID: PMC8632858 DOI: 10.1007/s10013-021-00509-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/09/2020] [Accepted: 02/24/2021] [Indexed: 06/14/2023]
Abstract
In this work we discuss the reconstruction of cardiac activation instants based on a viscous Eikonal equation from boundary observations. The problem is formulated as a least squares problem and solved by a projected version of the Levenberg-Marquardt method. Moreover, we analyze the well-posedness of the state equation and derive the gradient of the least squares functional with respect to the activation instants. In the numerical examples we also conduct an experiment in which the location of the activation sites and the activation instants are reconstructed jointly based on an adapted version of the shape gradient method from (J. Math. Biol. 79, 2033-2068, 2019). We are able to reconstruct the activation instants as well as the locations of the activations with high accuracy relative to the noise level.
Collapse
Affiliation(s)
- Karl Kunisch
- Institute for Mathematics and Scientific Computing, University of Graz, Heinrichstrasse 36, A-8010 Graz, Austria
- Johann Radon Institute for Computational and Applied Mathematics, Austrian Academy of Science, Linz, Austria
| | - Philip Trautmann
- Institute for Mathematics and Scientific Computing, University of Graz, Heinrichstrasse 36, A-8010 Graz, Austria
| |
Collapse
|
4
|
Effland A, Kobler E, Kunisch K, Pock T. Variational Networks: An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration. J Math Imaging Vis 2020; 62:396-416. [PMID: 32300264 PMCID: PMC7138785 DOI: 10.1007/s10851-019-00926-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/17/2019] [Accepted: 10/29/2019] [Indexed: 06/11/2023]
Abstract
We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point. This paradox originates from a tradeoff between optimization and modeling errors of the underlying variational model and holds true even if deep learning methods are used to learn highly expressive regularizers from data. In this paper, we take advantage of this paradox and introduce an optimal stopping time into the gradient flow process, which in turn is learned from data by means of an optimal control approach. After a time discretization, we obtain variational networks, which can be interpreted as a particular type of recurrent neural networks. The learned variational networks achieve competitive results for image denoising and image deblurring on a standard benchmark data set. One of the key theoretical results is the development of first- and second-order conditions to verify optimal stopping time. A nonlinear spectral analysis of the gradient of the learned regularizer gives enlightening insights into the different regularization properties.
Collapse
Affiliation(s)
- Alexander Effland
- Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria
| | - Erich Kobler
- Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria
| | - Karl Kunisch
- Institute of Mathematics and Scientific Computing, University of Graz, Graz, Austria
| | - Thomas Pock
- Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria
| |
Collapse
|
5
|
Kunisch K, Neic A, Plank G, Trautmann P. Inverse localization of earliest cardiac activation sites from activation maps based on the viscous Eikonal equation. J Math Biol 2019; 79:2033-2068. [PMID: 31473798 PMCID: PMC6858910 DOI: 10.1007/s00285-019-01419-3] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2018] [Revised: 05/30/2019] [Indexed: 01/25/2023]
Abstract
In this study we propose a novel method for identifying the locations of earliest activation in the human left ventricle from activation maps measured at the epicardial surface. Electrical activation is modeled based on the viscous Eikonal equation. The sites of earliest activation are identified by solving a minimization problem. Arbitrary initial locations are assumed, which are then modified based on a shape derivative based perturbation field until a minimal mismatch between the computed and the given activation maps on the epicardial surface is achieved. The proposed method is tested in two numerical benchmarks, a generic 2D unit-square benchmark, and an anatomically accurate MRI-derived 3D human left ventricle benchmark to demonstrate potential utility in a clinical context. For unperturbed input data, our localization method is able to accurately reconstruct the earliest activation sites in both benchmarks with deviations of only a fraction of the used spatial discretization size. Further, with the quality of the input data reduced by spatial undersampling and addition of noise, we demonstrate that an accurate identification of the sites of earliest activation is still feasible.
Collapse
Affiliation(s)
| | - Aurel Neic
- , Auenbruggerplatz 2, 8036, Graz, Austria
| | | | | |
Collapse
|
6
|
Aigner CS, Rund A, Abo Seada S, Price AN, Hajnal JV, Malik SJ, Kunisch K, Stollberger R. Time optimal control-based RF pulse design under gradient imperfections. Magn Reson Med 2019; 83:561-574. [PMID: 31441536 PMCID: PMC6899978 DOI: 10.1002/mrm.27955] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2019] [Revised: 07/25/2019] [Accepted: 07/29/2019] [Indexed: 12/15/2022]
Abstract
Purpose This study incorporates a gradient system imperfection model into an optimal control framework for radio frequency (RF) pulse design. Theory and Methods The joint design of minimum‐time RF and slice selective gradient shapes is posed as an optimal control problem. Hardware limitations such as maximal amplitudes for RF and slice selective gradient or its slew rate are included as hard constraints to assure practical applicability of the optimized waveforms. In order to guarantee the performance of the optimized waveform with possible gradient system disturbances such as limited system bandwidth and eddy currents, a measured gradient impulse response function (GIRF) for a specific system is integrated into the optimization. Results The method generates optimized RF and pre‐distorted slice selective gradient shapes for refocusing that are able to fully compensate the modeled imperfections of the gradient system under investigation. The results nearly regenerate the optimal results of an idealized gradient system. The numerical Bloch simulations are validated by phantom and in‐vivo experiments on 2 3T scanners. Conclusions The presented design approach demonstrates the successful correction of gradient system imperfections within an optimal control framework for RF pulse design.
Collapse
Affiliation(s)
- Christoph S Aigner
- Institute of Medical Engineering, Graz University of Technology, Graz, Austria
| | - Armin Rund
- Institute for Mathematics and Scientific Computing, University of Graz, Graz, Austria
| | - Samy Abo Seada
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Anthony N Price
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Joseph V Hajnal
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Shaihan J Malik
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Karl Kunisch
- Institute for Mathematics and Scientific Computing, University of Graz, Graz, Austria.,Johann Radon Institute for Computational and Applied Mathematics (RICAM), Austrian Academy of Sciences, Linz, Austria.,BioTechMed-Graz, Graz, Austria
| | - Rudolf Stollberger
- Institute of Medical Engineering, Graz University of Technology, Graz, Austria.,BioTechMed-Graz, Graz, Austria
| |
Collapse
|
7
|
Ghilli D, Kunisch K. On a Monotone Scheme for Nonconvex Nonsmooth Optimization with Applications to Fracture Mechanics. J Optim Theory Appl 2019; 183:609-641. [PMID: 31975742 PMCID: PMC6944259 DOI: 10.1007/s10957-019-01545-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/20/2018] [Accepted: 05/15/2019] [Indexed: 06/10/2023]
Abstract
A general class of nonconvex optimization problems is considered, where the penalty is the composition of a linear operator with a nonsmooth nonconvex mapping, which is concave on the positive real line. The necessary optimality condition of a regularized version of the original problem is solved by means of a monotonically convergent scheme. Such problems arise in continuum mechanics, as for instance cohesive fractures, where singular behaviour is usually modelled by nonsmooth nonconvex energies. The proposed algorithm is successfully tested for fracture mechanics problems. Its performance is also compared to two alternative algorithms for nonsmooth nonconvex optimization arising in optimal control and mathematical imaging.
Collapse
Affiliation(s)
- Daria Ghilli
- Institute for Mathematics and Scientific Computing, Karl-Franzens University, Graz, Austria
| | - Karl Kunisch
- Institute for Mathematics and Scientific Computing, Karl-Franzens University, Graz, Austria
- Johann Radon Institute, Linz, Austria
| |
Collapse
|
8
|
Rund A, Aigner CS, Kunisch K, Stollberger R. Simultaneous multislice refocusing via time optimal control. Magn Reson Med 2018; 80:1416-1428. [DOI: 10.1002/mrm.27124] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2017] [Revised: 01/17/2018] [Accepted: 01/17/2018] [Indexed: 12/26/2022]
Affiliation(s)
- Armin Rund
- Institute for Mathematics and Scientific Computing, University of Graz; Graz Austria
- BioTechMed-Graz; Graz Austria
| | | | - Karl Kunisch
- Institute for Mathematics and Scientific Computing, University of Graz; Graz Austria
- BioTechMed-Graz; Graz Austria
- Johann Radon Institute for Computational and Applied Mathematics (RICAM), Austrian Academy of Sciences; Linz Austria
| | - Rudolf Stollberger
- BioTechMed-Graz; Graz Austria
- Institute of Medical Engineering, Graz University of Technology; Graz Austria
| |
Collapse
|
9
|
Rund A, Aigner CS, Kunisch K, Stollberger R. Magnetic Resonance RF Pulse Design by Optimal Control With Physical Constraints. IEEE Trans Med Imaging 2018; 37:461-472. [PMID: 28981407 DOI: 10.1109/tmi.2017.2758391] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
Optimal control approaches have proved useful in designing RF pulses for large tip-angle applications. A typical challenge for optimal control design is the inclusion of constraints resulting from physiological or technical limitations that assure the realizability of the optimized pulses. In this paper, we show how to treat such inequality constraints, in particular, amplitude constraints on the B1 field, the slice-selective gradient, and its slew rate, as well as constraints on the slice profile accuracy. For the latter, a pointwise profile error and additional phase constraints are prescribed. Here, a penalization method is introduced that corresponds to a higher order tracking instead of the common quadratic tracking. The order is driven to infinity in the course of the optimization. We jointly optimize for the RF and slice-selective gradient waveform. The amplitude constraints on these control variables are treated efficiently by semismooth Newton or quasi-Newton methods. The method is flexible, adapting to many optimization goals. As an application, we reduce the power of refocusing pulses, which is important for spin echo-based applications with a short echo spacing. Here, the optimization method is tested in numerical experiments for reducing the pulse power of simultaneous multislice refocusing pulses. The results are validated by phantom and in-vivo experiments.
Collapse
|
10
|
Chamakuri N, Kunisch K, Plank G. PDE constrained optimization of electrical defibrillation in a 3D ventricular slice geometry. Int J Numer Method Biomed Eng 2016; 32:e02742. [PMID: 26249168 DOI: 10.1002/cnm.2742] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/26/2015] [Revised: 07/04/2015] [Accepted: 08/04/2015] [Indexed: 06/04/2023]
Abstract
A computational study of an optimal control approach for cardiac defibrillation in a 3D geometry is presented. The cardiac bioelectric activity at the tissue and bath volumes is modeled by the bidomain model equations. The model includes intramural fiber rotation, axially symmetric around the fiber direction, and anisotropic conductivity coefficients, which are extracted from a histological image. The dynamics of the ionic currents are based on the regularized Mitchell-Schaeffer model. The controls enter in the form of electrodes, which are placed at the boundary of the bath volume with the goal of dampening undesired arrhythmias. The numerical optimization is based on Newton techniques. We demonstrated the parallel architecture environment for the computation of potentials on multidomains and for the higher order optimization techniques.
Collapse
Affiliation(s)
- Nagaiah Chamakuri
- Radon Institute for Computational Applied Mathematics, Austrian Academy of Sciences, Altenbergerstr. 69, Linz, A-4040, Austria
| | - Karl Kunisch
- Radon Institute for Computational Applied Mathematics, Austrian Academy of Sciences, Altenbergerstr. 69, Linz, A-4040, Austria
- Institute of Mathematics Scientific Computing, University of Graz, Heinrichstr. 36, Graz, A-8010, Austria
| | - Gernot Plank
- Institute of Biophysics, Medical University of Graz, Harrachgasse 21, Graz, A-8010, Austria
| |
Collapse
|
11
|
Keeling SL, Kunisch K. Robust [Formula: see text] Approaches to Computing the Geometric Median and Principal and Independent Components. J Math Imaging Vis 2016; 56:99-124. [PMID: 27471346 PMCID: PMC4946825 DOI: 10.1007/s10851-016-0637-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2014] [Accepted: 01/18/2016] [Indexed: 06/06/2023]
Abstract
Robust measures are introduced for methods to determine statistically uncorrelated or also statistically independent components spanning data measured in a way that does not permit direct separation of these underlying components. Because of the nonlinear nature of the proposed methods, iterative methods are presented for the optimization of merit functions, and local convergence of these methods is proved. Illustrative examples are presented to demonstrate the benefits of the robust approaches, including an application to the processing of dynamic medical imaging.
Collapse
Affiliation(s)
- Stephen L. Keeling
- Institut für Mathematik und Wissenschaftliches Rechnen, Karl-Franzens-Universität Graz, Heinrichstraße 36, 8010 Graz, Austria
| | - Karl Kunisch
- Institut für Mathematik und Wissenschaftliches Rechnen, Karl-Franzens-Universität Graz, Heinrichstraße 36, 8010 Graz, Austria
| |
Collapse
|
12
|
Chamakuri N, Kunisch K, Plank G. On boundary stimulation and optimal boundary control of the bidomain equations. Math Biosci 2013; 245:206-15. [PMID: 23856647 DOI: 10.1016/j.mbs.2013.07.004] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2012] [Revised: 07/02/2013] [Accepted: 07/04/2013] [Indexed: 11/30/2022]
Abstract
The bidomain equations with Neumann boundary stimulation and optimal control of these stimuli are investigated. First an analytical framework for boundary control is provided. Then a parallel finite element based algorithm is devised and its efficiency is demonstrated not only for the direct problem but also for the optimal control problem. The computations realize a model configuration corresponding to optimal boundary defibrillation of a reentry phenomenon by applying current density stimuli.
Collapse
Affiliation(s)
- Nagaiah Chamakuri
- Radon Institute for Computational and Applied Mathematics, Altenbergerstr. 69, Linz A-4040, Austria.
| | | | | |
Collapse
|
13
|
Kunisch K, Wang L. Time optimal controls of the linear Fitzhugh-Nagumo equation with pointwise control constraints. J Math Anal Appl 2012; 395:114-130. [PMID: 23576818 PMCID: PMC3617911 DOI: 10.1016/j.jmaa.2012.05.028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/19/2011] [Indexed: 06/02/2023]
Abstract
Time optimal control governed by the internally controlled linear Fitzhugh-Nagumo equation with pointwise control constraint is considered. Making use of Ekeland's variational principle, we obtain Pontryagin's maximum principle for a time optimal control problem. Using the maximum principle, the bang-bang property of the optimal controls is established under appropriate assumptions.
Collapse
Affiliation(s)
- Karl Kunisch
- Institut für Mathematik, Karl-Franzens-Universität Graz, A-8010 Graz, Austria
| | - Lijuan Wang
- School of Mathematics and Statistics, Wuhan University, Wuhan 430072, China
| |
Collapse
|
14
|
Nagaiah C, Kunisch K, Plank G. Optimal control approach to termination of re-entry waves in cardiac electrophysiology. J Math Biol 2012; 67:359-88. [PMID: 22684847 DOI: 10.1007/s00285-012-0557-2] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2011] [Revised: 02/28/2012] [Indexed: 10/28/2022]
Abstract
This work proposes an optimal control approach for the termination of re-entry waves in cardiac electrophysiology. The control enters as an extracellular current density into the bidomain equations which are well established model equations in the literature to describe the electrical behavior of the cardiac tissue. The optimal control formulation is inspired, in part, by the dynamical systems behavior of the underlying system of differential equations. Existence of optimal controls is established and the optimality system is derived formally. The numerical realization is described in detail and numerical experiments, which demonstrate the capability of influencing and terminating reentry phenomena, are presented.
Collapse
Affiliation(s)
- Chamakuri Nagaiah
- Institute of Mathematics and Scientific Computing, University of Graz, Heinrichstr. 36, 8010, Graz, Austria.
| | | | | |
Collapse
|
15
|
|
16
|
Ito K, Kroller M, Kunisch K. A Numerical Study of an Augmented Lagrangian Method for the Estimation of Parameters in Elliptic Systems. ACTA ACUST UNITED AC 1991. [DOI: 10.1137/0912048] [Citation(s) in RCA: 22] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
17
|
Abstract
An approximation scheme for a reaction-diffusion system with distributed feedback through the boundary is developed. It is used to estimate the strength of the feedback mechanisms from measurements of the states. The results are illustrated by numerical examples.
Collapse
Affiliation(s)
- K Kunisch
- Institut für Mathematik, Technische Universität Graz, Austria
| | | |
Collapse
|