nach oben

Erschienen in:

13.07.2021 | Imaging Informatics and Artificial Intelligence

Accelerate gas diffusion-weighted MRI for lung morphometry with deep learning

verfasst von: Caohui Duan, He Deng, Sa Xiao, Junshuai Xie, Haidong Li, Xiuchao Zhao, Dongshan Han, Xianping Sun, Xin Lou, Chaohui Ye, Xin Zhou

Erschienen in: European Radiology | Ausgabe 1/2022

Einloggen, um Zugang zu erhalten

Abstract

Objectives

Multiple b-value gas diffusion-weighted MRI (DW-MRI) enables non-invasive and quantitative assessment of lung morphometry, but its long acquisition time is not well-tolerated by patients. We aimed to accelerate multiple b-value gas DW-MRI for lung morphometry using deep learning.

Methods

A deep cascade of residual dense network (DC-RDN) was developed to reconstruct high-quality DW images from highly undersampled k-space data. Hyperpolarized ¹²⁹Xe lung ventilation images were acquired from 101 participants and were retrospectively collected to generate synthetic DW-MRI data to train the DC-RDN. Afterwards, the performance of the DC-RDN was evaluated on retrospectively and prospectively undersampled multiple b-value ¹²⁹Xe MRI datasets.

Results

Each slice with size of 64 × 64 × 5 could be reconstructed within 7.2 ms. For the retrospective test data, the DC-RDN showed significant improvement on all quantitative metrics compared with the conventional reconstruction methods (p < 0.05). The apparent diffusion coefficient (ADC) and morphometry parameters were not significantly different between the fully sampled and DC-RDN reconstructed images (p > 0.05). For the prospectively accelerated acquisition, the required breath-holding time was reduced from 17.8 to 4.7 s with an acceleration factor of 4. Meanwhile, the prospectively reconstructed results showed good agreement with the fully sampled images, with a mean difference of −0.72% and −0.74% regarding global mean ADC and mean linear intercept (L_m) values.

Conclusions

DC-RDN is effective in accelerating multiple b-value gas DW-MRI while maintaining accurate estimation of lung microstructural morphometry, facilitating the clinical potential of studying lung diseases with hyperpolarized DW-MRI.

Key Points

• The deep cascade of residual dense network allowed fast and high-quality reconstruction of multiple b-value gas diffusion-weighted MRI at an acceleration factor of 4.

• The apparent diffusion coefficient and morphometry parameters were not significantly different between the fully sampled images and the reconstructed results (p > 0.05).

• The required breath-holding time was reduced from 17.8 to 4.7 s and each slice with size of 64 × 64 × 5 could be reconstructed within 7.2 ms.

Nur mit Berechtigung zugänglich

Mugler JP III, Altes TA (2013) Hyperpolarized ¹²⁹Xe MRI of the human lung. J Magn Reson Imaging 37(2):313–331PubMedPubMedCentralCrossRef

Doganay O, Matin T, Chen M et al (2019) Time-series hyperpolarized xenon-129 MRI of lobar lung ventilation of COPD in comparison to V/Q-SPECT/CT and CT. Eur Radiol 29:4058–4067PubMedCrossRef

Kaushik SS, Cleveland ZI, Cofer GP et al (2011) Diffusion-weighted hyperpolarized ¹²⁹Xe MRI in healthy volunteers and subjects with chronic obstructive pulmonary disease. Magn Reson Med 65:1154–1165PubMedCrossRef

Ouriadov A, Farag A, Kirby M, McCormack DG, Parraga G, Santyr GE (2013) Lung morphometry using hyperpolarized ¹²⁹Xe apparent diffusion coefficient anisotropy in chronic obstructive pulmonary disease. Magn Reson Med 70:1699–1706PubMedCrossRef

Tafti S, Garrison WJ, Mugler JP III et al (2020) Emphysema index based on hyperpolarized ³He or ¹²⁹Xe diffusion MRI: performance and comparison with quantitative CT and pulmonary function tests. Radiology 297:201–210PubMedCrossRef

Thomen RP, Quirk JD, Roach D et al (2017) Direct comparison of ¹²⁹Xe diffusion measurements with quantitative histology in human lungs. Magn Reson Med 77:265–272PubMedCrossRef

Chan HF, Weatherley ND, Johns CS et al (2019) Airway microstructure in idiopathic pulmonary fibrosis: assessment at hyperpolarized ³He diffusion-weighted MRI. Radiology 291:223–229PubMedCrossRef

Sukstanskii AL, Yablonskiy DA (2008) In vivo lung morphometry with hyperpolarized ³He diffusion MRI: theoretical background. J Magn Reson 190:200–210PubMedCrossRef

Sukstanskii AL, Yablonskiy DA (2012) Lung morphometry with hyperpolarized ¹²⁹Xe: theoretical background. Magn Reson Med 67:856–866PubMedCrossRef

10.

Chan HF, Collier GJ, Weatherley ND, Wild JM (2019) Comparison of in vivo lung morphometry models from 3D multiple b-value ³He and ¹²⁹Xe diffusion-weighted MRI. Magn Reson Med 81:2959–2971PubMedCrossRef

11.

Zhang H, Xie J, Xiao S et al (2018) Lung morphometry using hyperpolarized ¹²⁹Xe multi-b diffusion MRI with compressed sensing in healthy subjects and patients with COPD. Med Phys 45:3097–3108PubMedCrossRef

12.

Westcott A, Guo F, Parraga G, Ouriadov A (2019) Rapid single-breath hyperpolarized noble gas MRI-based biomarkers of airspace enlargement. J Magn Reson Imaging 49:1713–1722PubMedCrossRef

13.

Chan HF, Stewart NJ, Parra-Robles J, Collier GJ, Wild JM (2017) Whole lung morphometry with 3D multiple b-value hyperpolarized gas MRI and compressed sensing. Magn Reson Med 77:1916–1925PubMedCrossRef

14.

Chan HF, Stewart NJ, Norquay G, Collier GJ, Wild JM (2018) 3D diffusion-weighted ¹²⁹Xe MRI for whole lung morphometry. Magn Reson Med 79:2986–2995PubMedCrossRef

15.

Abascal JFPJ, Desco M, Parra-Robles J (2018) Incorporation of prior knowledge of signal behavior into the reconstruction to accelerate the acquisition of diffusion MRI data. IEEE Trans Med Imaging 37:547–556PubMedCrossRef

16.

Ouriadov A, Guo F, McCormack DG, Parraga G (2019) Accelerated ¹²⁹Xe MRI morphometry of terminal airspace enlargement: feasibility in volunteers and those with alpha-1 antitrypsin deficiency. Magn Reson Med 84:416–426PubMedCrossRef

17.

Lustig M, Donoho D, Pauly JM (2007) Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 58:1182–1195PubMedCrossRef

18.

Ajraoui S, Lee KJ, Deppe MH, Parnell SR, Parra-Robles J, Wild JM (2010) Compressed sensing in hyperpolarized ³He lung MRI. Magn Reson Med 63:1059–1069PubMedCrossRef

19.

Delattre BMA, Boudabbous S, Hansen C, Neroladaki A, Hachulla AL, Vargas MI (2020) Compressed sensing MRI of different organs: ready for clinical daily practice? Eur Radiol 30:308–319PubMedCrossRef

20.

Hammernik K, Klatzer T, Kobler E et al (2018) Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med 79:3055–3071PubMedCrossRef

21.

Yang G, Yu S, Dong H et al (2018) DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans Med Imaging 37:1310–1321PubMedCrossRef

22.

Yang Y, Sun J, Li H et al (2020) ADMM-CSNet: a deep learning approach for image compressive sensing. IEEE Trans Pattern Anal Mach Intell 42:521–538PubMedCrossRef

23.

Chen F, Taviani V, Malkiel I et al (2018) Variable-density single-shot fast spin-echo MRI with deep learning reconstruction by using variational networks. Radiology 289:366–373PubMedCrossRef

24.

Han Y, Yoo J, Kim HH, Shin HJ, Sung K, Ye JC (2018) Deep learning with domain adaptation for accelerated projection-reconstruction MR. Magn Reson Med 80:1189–1205PubMedCrossRef

25.

Hauptmann A, Arridge S, Lucka F, Muthurangu V, Steeden JA (2019) Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning–proof of concept in congenital heart disease. Magn Reson Med 81:1143–1156PubMedCrossRef

26.

Zhu B, Liu JZ, Cauley SF, Rosen BR, Rosen MS (2018) Image reconstruction by domain-transform manifold learning. Nature 555:487–492PubMedCrossRef

27.

Qin C, Schlemper J, Caballero J, Price AN, Hajnal JV, Rueckert D (2019) Convolutional recurrent neural networks for dynamic MR image reconstruction. IEEE Trans Med Imag 38:280–290CrossRef

28.

Duan C, Deng H, Xiao S et al (2019) Fast and accurate reconstruction of human lung gas MRI with deep learning. Magn Reson Med 82:2273–2285PubMedCrossRef

29.

Schlemper J, Caballero J, Hajnal JV, Price AN, Rueckert D (2018) A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging 37:491–503PubMedCrossRef

30.

Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. Proceedings of the IEEE conference on computer vision and pattern recognition 2472-2481.

31.

Huang G, Liu Z, Maaten Lvd, Weinberger KQ (2017) Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition 2261-2269.

32.

Sun L, Fan Z, Fu X, Huang Y, Ding X, Paisley J (2019) A deep information sharing network for multi-contrast compressed sensing MRI reconstruction. IEEE Trans Image Process 28:6141–6153PubMedCrossRef

33.

Xiang L, Chen Y, Chang W et al (2019) Deep learning based multi-modal fusion for fast MR reconstruction. IEEE Trans Biomed Eng 66:2105–2114CrossRef

34.

Wang H, Zheng R, Dai F, Wang Q, Wang C (2019) High-field MR diffusion-weighted image denoising using a joint denoising convolutional neural network. J Magn Reson Imag 50:1937–1947CrossRef

35.

He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision 1026-1034.

36.

Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. https://arxiv.org/abs/1412.6980. .

37.

Hyun CM, Kim HP, Lee SM et al (2018) Deep learning for undersampled MRI reconstruction. Phys Med Biol 63:135007PubMedCrossRef

38.

Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–612PubMedCrossRef

39.

Yaman B, Hosseini SAH, Moeller S et al (2020) Self-supervised learning of physics-guided reconstruction neural networks without fully sampled reference data. Magn Reson Med 84:3172–3191PubMedPubMedCentralCrossRef

40.

Gong K, Catana C, Qi J, Li Q (2019) PET image reconstruction using deep image prior. IEEE Trans Med Imaging 38:1655–1665PubMedCrossRef

41.

Cai C, Wang C, Zeng Y et al (2018) Single-shot T₂ mapping using overlapping-echo detachment planar imaging and a deep convolutional neural network. Magn Reson Med 80:2202–2214PubMedCrossRef

42.

Cohen O, Zhu B, Rosen MS (2018) MR fingerprinting Deep RecOnstruction NEtwork (DRONE). Magn Reson Med 80:885–894PubMedPubMedCentralCrossRef

43.

Knoll F, Hammernik K, Kobler E, Pock T, Recht MP, Sodickson DK (2019) Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magn Reson Med 81:116–128PubMedCrossRef

44.

Guan W, Ni Z, Hu Y et al (2020) Clinical characteristics of coronavirus disease 2019 in China. N Engl J Med 382:1708–1720PubMedCrossRef

45.

Revel MP, Parkar AP, Prosch H et al (2020) COVID-19 patients and the radiology department–advice from the European Society of Radiology (ESR) and the European Society of Thoracic Imaging (ESTI). Eur Radiol 30:4903–4909PubMedCrossRef

46.

Li H, Zhao X, Wang Y et al (2021) Damaged lung gas-exchange function of discharged COVID-19 patients detected by hyperpolarized ¹²⁹Xe MRI. Sci Adv. https://doi.org/10.1126/sciadv.abc8180

Titel: Accelerate gas diffusion-weighted MRI for lung morphometry with deep learning
verfasst von: Caohui Duan
He Deng
Sa Xiao
Junshuai Xie
Haidong Li
Xiuchao Zhao
Dongshan Han
Xianping Sun
Xin Lou
Chaohui Ye
Xin Zhou
Publikationsdatum: 13.07.2021
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 1/2022
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-08126-y

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Live-Webinar "Urologie und Sexualmedizin in der Praxis"

Springer Medizin

Accelerate gas diffusion-weighted MRI for lung morphometry with deep learning