3d-SMRnet: Achieving a New Quality of MPI System Matrix Recovery by Deep Learning

Baltruschat, Ivo M.; Szwargulski, Patryk; Griese, Florian; Grosser, Malte; Werner, René; Knopp, Tobias

doi:10.1007/978-3-030-59713-9_8

Cited by 21 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MPI images the spatial concentration distribution of SPIONs, and the reconstruction of MPI is done to solve the spatial concentration distribution of SPIONs. The image reconstruction based on SM is performed in frequency space [ 6 , 44 ]. A discrete Fourier transformation is performed on the recorded voltage signal u ( t ) directly after the data acquisition, expressed as

.…”

Section: The Theory Of Sm-based Mpimentioning

confidence: 99%

The Reconstruction of Magnetic Particle Imaging: Current Approaches Based on the System Matrix

et al. 2021

View full text Add to dashboard Cite

Magnetic particle imaging (MPI) is a novel non-invasive molecular imaging technology that images the distribution of superparamagnetic iron oxide nanoparticles (SPIONs). It is not affected by imaging depth, with high sensitivity, high resolution, and no radiation. The MPI reconstruction with high precision and high quality is of enormous practical importance, and many studies have been conducted to improve the reconstruction accuracy and quality. MPI reconstruction based on the system matrix (SM) is an important part of MPI reconstruction. In this review, the principle of MPI, current construction methods of SM and the theory of SM-based MPI are discussed. For SM-based approaches, MPI reconstruction mainly has the following problems: the reconstruction problem is an inverse and ill-posed problem, the complex background signals seriously affect the reconstruction results, the field of view cannot cover the entire object, and the available 3D datasets are of relatively large volume. In this review, we compared and grouped different studies on the above issues, including SM-based MPI reconstruction based on the state-of-the-art Tikhonov regularization, SM-based MPI reconstruction based on the improved methods, SM-based MPI reconstruction methods to subtract the background signal, SM-based MPI reconstruction approaches to expand the spatial coverage, and matrix transformations to accelerate SM-based MPI reconstruction. In addition, the current phantoms and performance indicators used for SM-based reconstruction are listed. Finally, certain research suggestions for MPI reconstruction are proposed, expecting that this review will provide a certain reference for researchers in MPI reconstruction and will promote the future applications of MPI in clinical medicine.

show abstract

.…”

Section: The Theory Of Sm-based Mpimentioning

confidence: 99%

The Reconstruction of Magnetic Particle Imaging: Current Approaches Based on the System Matrix

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, DL approaches have also been considered for MPI calibration [22]. A previous study has proposed to perform LR SM measurements, and then to recover an HR SM by upsampling the SM rows.…”

Section: Related Workmentioning

confidence: 99%

“…Super-resolution of LR SM measurements in MPI is closely related to the single-image SR problem in computer vision [21,22,25]. The de facto gold standard in SR problems are CNN models that comprise small, translation-invariant filters to extract localized image features [26].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Güngör¹,

Askin²,

Soydan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Magnetic particle imaging (MPI) is a recent modality that offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to setup an inverse problem to reconstruct images of the particle distribution during subsequent scans. This calibration enables the reconstruction to sensitively account for various system imperfections. Yet time-consuming SM measurements have to be repeated under notable drifts or changes in system properties. Here, we introduce a novel deep learning approach for accelerated MPI calibration based on transformers for SM super-resolution (TranSMS). Low-resolution SM measurements are performed using large MNP samples for improved signal-to-noise ratio efficiency, and the high-resolution SM is super-resolved via a model-based deep network. TranSMS leverages a vision transformer module to capture contextual relationships in low-resolution input images, a dense convolutional module for localizing highresolution image features, and a data-consistency module to ensure consistency to measurements. Demonstrations on simulated and experimental data indicate that TranSMS achieves significantly improved SM recovery and image reconstruction in MPI, while enabling acceleration up to 64-fold during two-dimensional calibration.

show abstract

“…Also of value are convolutional neural networks 126 , which have been successfully used in data classification, pattern recognition and inverse problems such as image reconstruction. Only a very recent attempt of applying convolu-tional networks in MNP-based applications by Baltruschat et al 127 can be found. In this work, super-resolution convolutional neural networks are employed to retrieve a highresolution system function to be used in MPI reconstruction starting from measurements of a low-resolution system function.…”

Section: Introducing (Hybrid) Data-driven Models In Theranosticsmentioning

confidence: 99%

Perspective: magnetic nanoparticles in theranostic applications

Coene,

Leliaert

2022

Preprint

View full text Add to dashboard Cite

3d-SMRnet: Achieving a New Quality of MPI System Matrix Recovery by Deep Learning

Cited by 21 publications

References 13 publications

The Reconstruction of Magnetic Particle Imaging: Current Approaches Based on the System Matrix

The Reconstruction of Magnetic Particle Imaging: Current Approaches Based on the System Matrix

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Perspective: magnetic nanoparticles in theranostic applications

Contact Info

Product

Resources

About