2020
DOI: 10.1002/nbm.4292
|View full text |Cite
|
Sign up to set email alerts
|

Overview of quantitative susceptibility mapping using deep learning: Current status, challenges and opportunities

Abstract: Quantitative susceptibility mapping (QSM) has gained broad interests in the field by extracting biological tissue properties, predominantly myelin, iron and calcium from magnetic resonance imaging (MRI) phase measurements in vivo. Thereby, QSM can reveal pathological changes of these key components in a variety of diseases. QSM requires multiple processing steps such as phase unwrapping, background field removal and field-to-source-inversion. Current state of the art techniques utilize iterative optimization p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
43
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 55 publications
(44 citation statements)
references
References 101 publications
(141 reference statements)
1
43
0
Order By: Relevance
“…By contrast, another deep learning framework, DeepQSM, 34 also based on the original U‐net, generated local field maps from synthetic susceptibility labels of simple geometric shapes using the forward model so that the training inputs and labels satisfied the exact underpinning equation between susceptibility source and induced field. However, the QSM results degraded noticeably when the test data deviated from the model (eg, noise and error in measurements) in DeepQSM 34,35 and susceptibility underestimation was observed, especially in deep gray matter (DGM) regions.…”
Section: Introductionmentioning
confidence: 99%
“…By contrast, another deep learning framework, DeepQSM, 34 also based on the original U‐net, generated local field maps from synthetic susceptibility labels of simple geometric shapes using the forward model so that the training inputs and labels satisfied the exact underpinning equation between susceptibility source and induced field. However, the QSM results degraded noticeably when the test data deviated from the model (eg, noise and error in measurements) in DeepQSM 34,35 and susceptibility underestimation was observed, especially in deep gray matter (DGM) regions.…”
Section: Introductionmentioning
confidence: 99%
“…A key question is the generalization to data not encountered in the training. Interestingly, also in EPT's sister field of Quantitative Susceptibility Mapping deep learning improves the quality of susceptibility reconstruction over conventional methodology [103,104]. Promising results have been achieved here on the generalization issue.…”
Section: Discussionmentioning
confidence: 92%
“…However, several recent methodical investigations have suggested that study outcomes may depend on the particular processing algorithms chosen for QSM (12)(13)(14). QSM typically involves the following steps in the order of application: coil combination (12); phase unwrapping (14); multi-echo combination (12); background field removal (14); and, finally, the estimation of susceptibility maps (13,(15)(16)(17). Processing artifacts and inaccuracies at any of these five processing stages can propagate into the computed susceptibility maps.…”
Section: Introductionmentioning
confidence: 99%