PP-MPI: A deep plug-and-play prior for magnetic particle imaging reconstruction

Simple item page
buir.contributor.authorAşkın, Barış
buir.contributor.authorGüngör, Alper
buir.contributor.authorSarıtaş, Emine Ülkü
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidSarıtaş, Emine Ülkü|0000-0001-8551-1077
buir.contributor.orcidGüngör, Alper|0000-0002-3043-9124
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage114en_US
dc.citation.spage105en_US
dc.citation.volumeNumber13587en_US
dc.contributor.authorAşkın, Barış
dc.contributor.authorGüngör, Alper
dc.contributor.authorAlptekin Soydan, D.
dc.contributor.authorSarıtaş, Emine Ülkü
dc.contributor.authorTop, C. B.
dc.contributor.authorÇukur, Tolga
dc.contributor.editorHaq, Nandinee
dc.contributor.editorMaier, Andreas
dc.contributor.editorQin, Chen
dc.contributor.editorJohnson, Patricia
dc.contributor.editorWürfl, Tobias
dc.contributor.editorYoo, Jaejun
dc.coverage.spatialSingaporeen_US
dc.date.accessioned2023-02-15T13:10:30Z
dc.date.available2023-02-15T13:10:30Z
dc.date.issued2022-09
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionConference Name: 5th International Workshop on Machine Learning for Medical Reconstruction, MLMIR 2022en_US
dc.descriptionDate of Conference: 22 September 2022en_US
dc.description.abstractMagnetic particle imaging (MPI) is a recent modality that enables high contrast and frame-rate imaging of the magnetic nanoparticle (MNP) distribution. Based on a measured system matrix, MPI reconstruction can be cast as an inverse problem that is commonly solved via regularized iterative optimization. Yet, hand-crafted regularization terms can elicit suboptimal performance. Here, we propose a novel MPI reconstruction “PP-MPI” based on a deep plug-and-play (PP) prior embedded in a model-based iterative optimization. We propose to pre-train the PP prior based on a residual dense convolutional neural network (CNN) on an MPI-friendly dataset derived from magnetic resonance angiograms. The PP prior is then embedded into an alternating direction method of multiplier (ADMM) optimizer for reconstruction. A fast implementation is devised for 3D image reconstruction by fusing the predictions from 2D priors in separate rectilinear orientations. Our demonstrations show that PP-MPI outperforms state-of-the-art iterative techniques with hand-crafted regularizers on both simulated and experimental data. In particular, PP-MPI achieves on average 3.10 dB higher peak signal-to-noise ratio than the top-performing baseline under variable noise levels, and can process 12 frames/sec to permit real-time 3D imaging.en_US
dc.description.provenanceSubmitted by Evrim Ergin (eergin@bilkent.edu.tr) on 2023-02-15T13:10:30Z No. of bitstreams: 1 PP_MPI_A_deep_plug_and_play_prior_for_magnetic_particle_imaging_reconstruction.pdf: 785343 bytes, checksum: 62e15aa3ba7630874774b4bfff528476 (MD5)en
dc.description.provenanceMade available in DSpace on 2023-02-15T13:10:30Z (GMT). No. of bitstreams: 1 PP_MPI_A_deep_plug_and_play_prior_for_magnetic_particle_imaging_reconstruction.pdf: 785343 bytes, checksum: 62e15aa3ba7630874774b4bfff528476 (MD5) Previous issue date: 2022-09en
dc.identifier.doi10.1007/978-3-031-17247-2_11en_US
dc.identifier.eisbn978-3-031-17247-2
dc.identifier.isbn978-3-031-17246-5
dc.identifier.urihttp://hdl.handle.net/11693/111367
dc.language.isoEnglishen_US
dc.publisherSpringer Chamen_US
dc.relation.ispartofseriesLecture Notes in Computer Science;
dc.relation.isversionofhttps://doi.org/10.1007/978-3-031-17247-2_11en_US
dc.source.titleMachine Learning for Medical Image Reconstructionen_US
dc.subjectDeep learningen_US
dc.subjectMagnetic particle imagingen_US
dc.subjectPlug and playen_US
dc.subjectReconstructionen_US
dc.titlePP-MPI: A deep plug-and-play prior for magnetic particle imaging reconstructionen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
PP_MPI_A_deep_plug_and_play_prior_for_magnetic_particle_imaging_reconstruction.pdf
Size:
766.94 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering