DPP : deep phase prior for parallel imaging with wave encoding
© 2024 Institute of Physics and Engineering in Medicine..
OBJECTIVE: In MR parallel imaging with virtual channel-expanded Wave encoding, limitations are imposed on the ability to comprehensively and accurately characterize the background phase. These limitations are primarily attributed to the calibrationprocess relying solely on center low-frequency ACS data for calibration. Approach: To tackle the challenge of accurately estimating the background phase in wave encoding, a novel deep neural network model guided by deep phase priors (DPP) is proposed with integrated virtual conjugate coil (VCC) extension. Concretely, within the proposed framework, the background phase is implicitly characterized by employing a carefully designed decoder convolutional neural network, leveraging the inherent characteristics of phase smoothness and compact support in the transformed domain. Furthermore, the proposed model with wave encoding benefits from additional priors, which incorporate transmission sparsity of the latent image and coil sensitivity smoothness.Main results: Ablation experiments were conducted to ascertain the proposed method's capability to implicitly represent CSM and the background phase. Subsequently, the superiority of the proposed method is demonstrated through confidence comparisons with competing methods, employing 4-fold and 5-fold acceleration experiments. In achieving 4-fold and 5-fold acceleration, the optimalquantitative metrics (PSNR/SSIM/NMSE) are 44.1359 dB/0.9863/0.0008 (4-fold) and 41.2074/0.9846/0.0017 (5-fold), respectively. Furthermore, the generalizability of the proposed method is further validated by conducting acceleration experiments with T1, T2, T2*, and various undersampling patterns. In addition, the DPP delivered much better performance than the conventional methods byexploring accelerated phase-sensitive SWI imaging. In SWI accelerated imaging, it also surpasses the optimal competing method in terms of (PSNR/SSIM/NMSE) with 0.096%/0.009%/0.0017%.Significance: The proposed method enables precise characterization of the background phase in the integrated VCC and wave encoding framework, supported via theoretical analysis and empirical findings. Our code is available at: https://github.com/sober235/DPP.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
|---|---|
| Enthalten in: |
Physics in medicine and biology - (2024) vom: 12. Apr. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Liu, Congcong [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Journal Article |
|---|
| Anmerkungen: |
Date Revised 12.04.2024 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1088/1361-6560/ad3e5d |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM370979567 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM370979567 | ||
| 003 | DE-627 | ||
| 005 | 20240413233039.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240413s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6560/ad3e5d |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1374.xml |
| 035 | |a (DE-627)NLM370979567 | ||
| 035 | |a (NLM)38608645 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Liu, Congcong |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a DPP |b deep phase prior for parallel imaging with wave encoding |
| 264 | 1 | |c 2024 | |
| 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 12.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a © 2024 Institute of Physics and Engineering in Medicine. | ||
| 520 | |a OBJECTIVE: In MR parallel imaging with virtual channel-expanded Wave encoding, limitations are imposed on the ability to comprehensively and accurately characterize the background phase. These limitations are primarily attributed to the calibrationprocess relying solely on center low-frequency ACS data for calibration. Approach: To tackle the challenge of accurately estimating the background phase in wave encoding, a novel deep neural network model guided by deep phase priors (DPP) is proposed with integrated virtual conjugate coil (VCC) extension. Concretely, within the proposed framework, the background phase is implicitly characterized by employing a carefully designed decoder convolutional neural network, leveraging the inherent characteristics of phase smoothness and compact support in the transformed domain. Furthermore, the proposed model with wave encoding benefits from additional priors, which incorporate transmission sparsity of the latent image and coil sensitivity smoothness.Main results: Ablation experiments were conducted to ascertain the proposed method's capability to implicitly represent CSM and the background phase. Subsequently, the superiority of the proposed method is demonstrated through confidence comparisons with competing methods, employing 4-fold and 5-fold acceleration experiments. In achieving 4-fold and 5-fold acceleration, the optimalquantitative metrics (PSNR/SSIM/NMSE) are 44.1359 dB/0.9863/0.0008 (4-fold) and 41.2074/0.9846/0.0017 (5-fold), respectively. Furthermore, the generalizability of the proposed method is further validated by conducting acceleration experiments with T1, T2, T2*, and various undersampling patterns. In addition, the DPP delivered much better performance than the conventional methods byexploring accelerated phase-sensitive SWI imaging. In SWI accelerated imaging, it also surpasses the optimal competing method in terms of (PSNR/SSIM/NMSE) with 0.096%/0.009%/0.0017%.Significance: The proposed method enables precise characterization of the background phase in the integrated VCC and wave encoding framework, supported via theoretical analysis and empirical findings. Our code is available at: https://github.com/sober235/DPP | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a MR Imaging | |
| 650 | 4 | |a Parallel Imaging | |
| 650 | 4 | |a Untrained Neural Network | |
| 700 | 1 | |a Cui, Zhuoxu |e verfasserin |4 aut | |
| 700 | 1 | |a Jia, Sen |e verfasserin |4 aut | |
| 700 | 1 | |a Cheng, Jing |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Yuanyuan |e verfasserin |4 aut | |
| 700 | 1 | |a Lin, Ling |e verfasserin |4 aut | |
| 700 | 1 | |a Hu, Zhanqi |e verfasserin |4 aut | |
| 700 | 1 | |a Xie, Taofeng |e verfasserin |4 aut | |
| 700 | 1 | |a Zhou, Yihang |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Yanjie |e verfasserin |4 aut | |
| 700 | 1 | |a Liang, Dong |e verfasserin |4 aut | |
| 700 | 1 | |a Zeng, Hongwu |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Haifeng |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Physics in medicine and biology |d 1956 |g (2024) vom: 12. Apr. |w (DE-627)NLM000336505 |x 1361-6560 |7 nnns |
| 773 | 1 | 8 | |g year:2024 |g day:12 |g month:04 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1088/1361-6560/ad3e5d |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 12 |c 04 | ||