Deep image prior for 3D magnetic particle imaging: A quantitative comparison of regularization techniques on Open MPI dataset

Magnetic particle imaging (MPI) is an imaging modality exploiting the nonlinear magnetization behavior of (super-)paramagnetic nanoparticles to obtain a space- and often also time-dependent concentration of a tracer consisting of these nanoparticles. MPI has a continuously increasing number of potential medical applications. One prerequisite for successful performance in these applications is a proper solution to the image reconstruction problem. More classical methods from inverse problems theory, as well as novel approaches from the field of machine learning, have the potential to deliver high-quality reconstructions in MPI. We investigate a novel reconstruction approach based on a deep image prior, which builds on representing the solution by a deep neural network. Novel approaches, as well as variational and iterative regularization techniques, are compared quantitatively in terms of peak signal-to-noise ratios and structural similarity indices on the publicly available Open MPI dataset.

[1]  Tobias Kluth,et al.  Model uncertainty in magnetic particle imaging: Nonlinear problem formulation and model-based sparse reconstruction , 2017 .

[2]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .

[3]  B Gleich,et al.  Three-dimensional real-time in vivo magnetic particle imaging , 2009, Physics in medicine and biology.

[4]  Fred L. Drake,et al.  Python 3 Reference Manual , 2009 .

[5]  Andrea Vedaldi,et al.  Deep Image Prior , 2017, International Journal of Computer Vision.

[6]  Matthias Graeser,et al.  Magnetic Particle Imaging for Real-Time Perfusion Imaging in Acute Stroke. , 2017, ACS nano.

[7]  Patrick W. Goodwill,et al.  The X-Space Formulation of the Magnetic Particle Imaging Process: 1-D Signal, Resolution, Bandwidth, SNR, SAR, and Magnetostimulation , 2010, IEEE Transactions on Medical Imaging.

[8]  Bernhard Gleich,et al.  Magnetic Particle imaging : Visualization of Instruments for Cardiovascular Intervention 1 , 2012 .

[9]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[10]  Guanglian Li,et al.  On the degree of ill-posedness of multi-dimensional magnetic particle imaging , 2017, Inverse Problems.

[11]  Carola-Bibiane Schönlieb,et al.  Adversarial Regularizers in Inverse Problems , 2018, NeurIPS.

[12]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[13]  K. M. Krishnan,et al.  Evaluation of PEG-coated iron oxide nanoparticles as blood pool tracers for preclinical magnetic particle imaging. , 2017, Nanoscale.

[14]  Tobias Knopp,et al.  Magnetic particle imaging: from proof of principle to preclinical applications , 2017, Physics in medicine and biology.

[15]  Tobias Knopp,et al.  A Wavelet Based Sparse Row-Action Method for Image Reconstruction in Magnetic Particle Imaging , 2020, Medical Physics (Lancaster).

[16]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[17]  B Gleich,et al.  Weighted iterative reconstruction for magnetic particle imaging , 2010, Physics in medicine and biology.

[18]  Alexandros G. Dimakis,et al.  Compressed Sensing with Deep Image Prior and Learned Regularization , 2018, ArXiv.

[19]  Jonas Adler,et al.  Solving ill-posed inverse problems using iterative deep neural networks , 2017, ArXiv.

[20]  Feng Lin,et al.  Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network , 2017, IEEE Transactions on Medical Imaging.

[21]  Otmar Scherzer,et al.  Handbook of Mathematical Methods in Imaging , 2015, Handbook of Mathematical Methods in Imaging.

[22]  Jianhua Ma,et al.  Radon inversion via deep learning , 2018, Medical Imaging.

[23]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[24]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[25]  Thorsten M. Buzug,et al.  Magnetic Particle Imaging: An Introduction to Imaging Principles and Scanner Instrumentation , 2012 .

[26]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[27]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[28]  Jonas Adler,et al.  Learned Primal-Dual Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[29]  Tobias Kluth,et al.  Regularization by Architecture: A Deep Prior Approach for Inverse Problems , 2019, Journal of Mathematical Imaging and Vision.

[30]  Marcus A. Magnor,et al.  A sparse Kaczmarz solver and a linearized Bregman method for online compressed sensing , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[31]  Achiya Dax,et al.  On Row Relaxation Methods for Large Constrained Least Squares Problems , 1993, SIAM J. Sci. Comput..

[32]  Dimitri P. Bertsekas,et al.  Constrained Optimization and Lagrange Multiplier Methods , 1982 .

[33]  Anselm von Gladiss,et al.  MDF: Magnetic Particle Imaging Data Format , 2016, 1602.06072.

[34]  Tobias Knopp,et al.  OpenMPIData: An initiative for freely accessible magnetic particle imaging data , 2019, Data in brief.

[35]  Tobias Knopp,et al.  Edge Preserving and Noise Reducing Reconstruction for Magnetic Particle Imaging , 2017, IEEE Transactions on Medical Imaging.

[36]  Tobias Kluth,et al.  Mathematical models for magnetic particle imaging , 2018, Inverse Problems.

[37]  Simon R. Arridge,et al.  Solving inverse problems using data-driven models , 2019, Acta Numerica.

[38]  Bernhard Gleich,et al.  Tomographic imaging using the nonlinear response of magnetic particles , 2005, Nature.

[39]  Patrick W. Goodwill,et al.  Multidimensional X-Space Magnetic Particle Imaging , 2011, IEEE Transactions on Medical Imaging.

[40]  Bangti Jin,et al.  Enhanced reconstruction in magnetic particle imaging by whitening and randomized SVD approximation , 2019, Physics in medicine and biology.

[41]  Olaf Kosch,et al.  Concentration Dependent MPI Tracer Performance , 2016 .

[42]  T Knopp,et al.  Human-sized magnetic particle imaging for brain applications , 2018, Nature Communications.

[43]  Sanjiv Kumar,et al.  On the Convergence of Adam and Beyond , 2018 .

[44]  Patrick W. Goodwill,et al.  Magnetic Particle Imaging: A Novel in Vivo Imaging Platform for Cancer Detection. , 2017, Nano letters.

[45]  Bruce R. Rosen,et al.  Image reconstruction by domain-transform manifold learning , 2017, Nature.

[46]  Tobias Kluth,et al.  Improved image reconstruction in magnetic particle imaging using structural a priori information , 2017 .

[47]  Kenya Murase,et al.  Usefulness of Magnetic Particle Imaging for Predicting the Therapeutic Effect of Magnetic Hyperthermia , 2015 .

[48]  Jochen Franke,et al.  MPI Flow Analysis Toolbox exploiting pulsed tracer information – an aneurysm phantom proof , 2017 .

[49]  Gabor T. Herman,et al.  A Storage-Efficient Algorithm for Finding the Regularized Solution of a Large, Inconsistent System of Equations , 1980 .

[50]  T Knopp,et al.  Online reconstruction of 3D magnetic particle imaging data , 2016, Physics in medicine and biology.