Compressed Sensing : From Research to Clinical Practice with Deep Neural Networks
Compressed sensing (CS) reconstruction methods leverage sparse structure in underlying signals to recover high-resolution images from highly undersampled measurements. When applied to magnetic resonance imaging (MRI), CS has the potential to dramatically shorten MRI scan times, increase diagnostic value, and improve overall patient experience. However, CS has several shortcomings which limit its clinical translation such as: 1) artifacts arising from inaccurate sparse modelling assumptions, 2) extensive parameter tuning required for each clinical application, and 3) clinically infeasible reconstruction times. Recently, CS has been extended to incorporate deep neural networks as a way of learning complex image priors from historical exam data. Commonly referred to as unrolled neural networks, these techniques have proven to be a compelling and practical approach to address the challenges of sparse CS. In this tutorial, we will review the classical compressed sensing formulation and outline steps needed to transform this formulation into a deep learning-based reconstruction framework. Supplementary open source code in Python will be used to demonstrate this approach with open databases. Further, we will discuss considerations in applying unrolled neural networks in the clinical setting.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:37 |
|---|---|
| Enthalten in: |
IEEE signal processing magazine - 37(2020), 1 vom: 13. Jan., Seite 111-127 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Sandino, Christopher M [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Clinical translation |
|---|
| Anmerkungen: |
Date Revised 14.02.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1109/MSP.2019.2950433 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM317594346 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM317594346 | ||
| 003 | DE-627 | ||
| 005 | 20240214232244.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/MSP.2019.2950433 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1292.xml |
| 035 | |a (DE-627)NLM317594346 | ||
| 035 | |a (NLM)33192036 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Sandino, Christopher M |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Compressed Sensing |b From Research to Clinical Practice with Deep Neural Networks |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 14.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Compressed sensing (CS) reconstruction methods leverage sparse structure in underlying signals to recover high-resolution images from highly undersampled measurements. When applied to magnetic resonance imaging (MRI), CS has the potential to dramatically shorten MRI scan times, increase diagnostic value, and improve overall patient experience. However, CS has several shortcomings which limit its clinical translation such as: 1) artifacts arising from inaccurate sparse modelling assumptions, 2) extensive parameter tuning required for each clinical application, and 3) clinically infeasible reconstruction times. Recently, CS has been extended to incorporate deep neural networks as a way of learning complex image priors from historical exam data. Commonly referred to as unrolled neural networks, these techniques have proven to be a compelling and practical approach to address the challenges of sparse CS. In this tutorial, we will review the classical compressed sensing formulation and outline steps needed to transform this formulation into a deep learning-based reconstruction framework. Supplementary open source code in Python will be used to demonstrate this approach with open databases. Further, we will discuss considerations in applying unrolled neural networks in the clinical setting | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a clinical translation | |
| 650 | 4 | |a compressed sensing | |
| 650 | 4 | |a deep learning | |
| 700 | 1 | |a Cheng, Joseph Y |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Feiyu |e verfasserin |4 aut | |
| 700 | 1 | |a Mardani, Morteza |e verfasserin |4 aut | |
| 700 | 1 | |a Pauly, John M |e verfasserin |4 aut | |
| 700 | 1 | |a Vasanawala, Shreyas S |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE signal processing magazine |d 2008 |g 37(2020), 1 vom: 13. Jan., Seite 111-127 |w (DE-627)NLM194100359 |x 1053-5888 |7 nnns |
| 773 | 1 | 8 | |g volume:37 |g year:2020 |g number:1 |g day:13 |g month:01 |g pages:111-127 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/MSP.2019.2950433 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 37 |j 2020 |e 1 |b 13 |c 01 |h 111-127 | ||