Whole-body magnetic resonance imaging at 0.05 Tesla

19 min read Original article ↗

Editor’s summary

Magnetic resonance imaging (MRI) was invented more than 50 years ago and has continued to improve in resolution and image quality. These improvements are the result of ever more powerful magnets, which make for very heavy and noisy machines that require extensive shielding. These high-power MRI machines are also extremely expensive, which greatly limits patient access. By applying machine learning to the output of a lower-power MRI device, Zhao et al. were able to address these concerns (see the Perspective by Anazodo and du Plessis). The lower-power machine was much cheaper to manufacture and operate, more comfortable and less noisy for patients, and the final images after computational processing were as clear and detailed as those obtained by the high-power devices currently used in the clinical setting. —Yevgeniya Nusinovich

Structured Abstract

INTRODUCTION

Magnetic resonance imaging (MRI) has revolutionized healthcare with its nonionizing, noninvasive, multicontrast, and quantitative capabilities. It also presents a promising platform for future artificial intelligence–driven medical diagnoses. However, after five decades of development, MRI accessibility—especially in low and middle-income countries—remains low and highly uneven due to high costs and specialized settings required for standard superconducting MRI scanners. These scanners are mostly found in specialized radiology departments and large imaging centers, restricting their availability in other medical settings. The need for radio frequency (RF)-shielded rooms and high power consumption further adds to hardware cost and compromises mobility and patient-friendliness.

RATIONALE

We developed a highly simplified whole-body ultra-low-field (ULF) MRI scanner that operates on a standard wall power outlet without RF or magnetic shielding cages. This scanner uses a compact 0.05 Tesla permanent magnet and incorporates active sensing and deep learning to address electromagnetic interference (EMI) signals. We deployed EMI sensing coils positioned around the scanner and implemented a deep learning method to directly predict EMI-free nuclear magnetic resonance signals from acquired data. To enhance image quality and reduce scan time, we also developed a data-driven deep learning image formation method, which integrates image reconstruction and three-dimensional (3D) multiscale super-resolution and leverages the homogeneous human anatomy and image contrasts available in large-scale, high-field, high-resolution MRI data.

RESULTS

We implemented commonly used clinical protocols at 0.05 Tesla, including T1-weighted, T2-weighted, and diffusion-weighted imaging, and optimized their contrasts for different anatomical structures. Each protocol was designed to have a scan time of 8 minutes or less with an image resolution of approximately 2×2×8 mm³. The scanner power consumption during scanning was under 1800W and around 300W when idle. We conducted imaging on healthy volunteers, capturing brain, spine, abdomen, lung, musculoskeletal, and cardiac images. Deep learning signal prediction effectively eliminated EMI signals, enabling clear imaging without shielding. The brain images showed various brain tissues whereas the spine images revealed intervertebral disks, spinal cord, and cerebrospinal fluid. Abdominal images displayed major structures like the liver, kidneys, and spleen. Lung images showed pulmonary vessels and parenchyma. Knee images identified knee structures such as cartilage and meniscus. Cardiac cine images depicted the left ventricle contraction and neck angiography revealed carotid arteries. Furthermore, deep learning image formation greatly improved the 0.05 Tesla image quality for various anatomical structures, including the brain, spine, abdomen, and knee; it also effectively suppressed noise and artifacts and increased image spatial resolution.

CONCLUSION

To address MRI accessibility challenges, we developed a low-power and simplified whole-body 0.05 Tesla MRI scanner that operates without the need for RF or magnetic shielding and that can be manufactured, maintained, and operated at a low cost. We experimentally demonstrated the general utility of this scanner for imaging various human anatomical structures at a whole-body level, even in the presence of strong EMI signals, with acceptable scan time. Moreover, we demonstrated the potential of deep learning image formation to substantially augment 0.05 Tesla image quality by exploiting computing and extensive high-field MRI data. These advances pave the way for affordable, patient-centric, and deep learning–powered ULF MRI scanners, addressing unmet clinical needs in diverse healthcare settings worldwide.

Computing-powered whole-body MRI at 0.05 Tesla.

(Top) Prototype of a low-cost, low-power, compact, and shielding-free imaging system using an open 0.05 Tesla permanent magnet. It incorporates active sensing and deep learning to address EMI signals. (Middle) Typical images of various anatomical structures using conventional image reconstruction. (Bottom) High-resolution images using deep learning image formation by harnessing large-scale high-field MRI data.

Abstract

Despite a half-century of advancements, global magnetic resonance imaging (MRI) accessibility remains limited and uneven, hindering its full potential in health care. Initially, MRI development focused on low fields around 0.05 Tesla, but progress halted after the introduction of the 1.5 Tesla whole-body superconducting scanner in 1983. Using a permanent 0.05 Tesla magnet and deep learning for electromagnetic interference elimination, we developed a whole-body scanner that operates using a standard wall power outlet and without radiofrequency and magnetic shielding. We demonstrated its wide-ranging applicability for imaging various anatomical structures. Furthermore, we developed three-dimensional deep learning reconstruction to boost image quality by harnessing extensive high-field MRI data. These advances pave the way for affordable deep learning–powered ultra-low-field MRI scanners, addressing unmet clinical needs in diverse health care settings worldwide.

Register and access this article for free

As a service to the community, this article is available for free.

Access the full article

View all access options to continue reading this article.

Supplementary Materials

This PDF file includes:

Figs. S1 to S5

Tables S1 to S5

Captions for Movies S1 to S10

Other Supplementary Material for this manuscript includes the following:

References and Notes

1

P. C. Lauterbur, Image Formation by Induced Local Interactions - Examples Employing Nuclear Magnetic-Resonance. Nature 242, 190–191 (1973).

2

P. Mansfield, A. A. Maudsley, Medical Imaging by Nmr, Medical imaging by NMR. Br. J. Radiol. 50, 188–194 (1977).

3

V. R. Fuchs, H. C. Sox Jr., Physicians’ views of the relative importance of thirty medical innovations. Health Aff. 20, 30–42 (2001).

4

Magnetic resonance imaging (MRI) exams (OECD, 2024);

5

R. R. Edelman, S. Warach, Magnetic resonance imaging (1). N. Engl. J. Med. 328, 708–716 (1993).

6

Magnetic resonance imaging (MRI) units (OECD, 2024);

7

A. Webb, J. Obungoloch, Five steps to make MRI scanners more affordable to the world. Nature 615, 391–393 (2023).

8

M. Naddaf, One MRI for 4.7 million people: The battle to treat Syria’s earthquake survivors. Nature 615, 193–194 (2023).

9

C. Z. Cooley, P. C. McDaniel, J. P. Stockmann, S. A. Srinivas, S. F. Cauley, M. Śliwiak, C. R. Sappo, C. F. Vaughn, B. Guerin, M. S. Rosen, M. H. Lev, L. L. Wald, A portable scanner for magnetic resonance imaging of the brain. Nat. Biomed. Eng. 5, 229–239 (2021).

10

Y. He, W. He, L. Tan, F. Chen, F. Meng, H. Feng, Z. Xu, Use of 2.1 MHz MRI scanner for brain imaging and its preliminary results in stroke. J. Magn. Reson. 319, 106829 (2020).

11

T. O’Reilly, W. M. Teeuwisse, D. de Gans, K. Koolstra, A. G. Webb, In vivo 3D brain and extremity MRI at 50 mT using a permanent magnet Halbach array. Magn. Reson. Med. 85, 495–505 (2021).

12

Y. Liu, A. T. L. Leong, Y. Zhao, L. Xiao, H. K. F. Mak, A. C. O. Tsang, G. K. K. Lau, G. K. K. Leung, E. X. Wu, A low-cost and shielding-free ultra-low-field brain MRI scanner. Nat. Commun. 12, 7238 (2021).

13

W. T. Kimberly, A. J. Sorby-Adams, A. G. Webb, E. X. Wu, R. Beekman, R. Bowry, S. J. Schiff, A. de Havenon, F. X. Shen, G. Sze, P. Schaefer, J. E. Iglesias, M. S. Rosen, K. N. Sheth, Brain imaging with portable low-field MRI. Nat. Rev. Bioeng. 1, 617–630 (2023).

14

J. Hennig, An evolution of low-field strength MRI. Magn. Reason. Mater. Phy. 36, 335–346 (2023).

15

M. H. Mazurek, B. A. Cahn, M. M. Yuen, A. M. Prabhat, I. R. Chavva, J. T. Shah, A. L. Crawford, E. B. Welch, J. Rothberg, L. Sacolick, M. Poole, C. Wira, C. C. Matouk, A. Ward, N. Timario, A. Leasure, R. Beekman, T. J. Peng, J. Witsch, J. P. Antonios, G. J. Falcone, K. T. Gobeske, N. Petersen, J. Schindler, L. Sansing, E. J. Gilmore, D. Y. Hwang, J. A. Kim, A. Malhotra, G. Sze, M. S. Rosen, W. T. Kimberly, K. N. Sheth, Portable, bedside, low-field magnetic resonance imaging for evaluation of intracerebral hemorrhage. Nat. Commun. 12, 5119 (2021).

16

M. M. Yuen, A. M. Prabhat, M. H. Mazurek, I. R. Chavva, A. Crawford, B. A. Cahn, R. Beekman, J. A. Kim, K. T. Gobeske, N. H. Petersen, G. J. Falcone, E. J. Gilmore, D. Y. Hwang, A. S. Jasne, H. Amin, R. Sharma, C. Matouk, A. Ward, J. Schindler, L. Sansing, A. de Havenon, A. Aydin, C. Wira, G. Sze, M. S. Rosen, W. T. Kimberly, K. N. Sheth, Portable, low-field magnetic resonance imaging enables highly accessible and dynamic bedside evaluation of ischemic stroke.Sci. Adv. 8, eabm3952 (2022).

17

S. A. Srinivas, S. F. Cauley, J. P. Stockmann, C. R. Sappo, C. E. Vaughn, L. L. Wald, W. A. Grissom, C. Z. Cooley, External Dynamic InTerference Estimation and Removal (EDITER) for low field MRI. Magn. Reson. Med. 87, 614–628 (2022).

18

Y. Zhao, L. Xiao, Y. Liu, A. T. Leong, E. X. Wu, Electromagnetic interference elimination via active sensing and deep learning prediction for radiofrequency shielding-free MRI. NMR Biomed.e4956 (2023).

19

K. N. Sheth, M. H. Mazurek, M. M. Yuen, B. A. Cahn, J. T. Shah, A. Ward, J. A. Kim, E. J. Gilmore, G. J. Falcone, N. Petersen, K. T. Gobeske, F. Kaddouh, D. Y. Hwang, J. Schindler, L. Sansing, C. Matouk, J. Rothberg, G. Sze, J. Siner, M. S. Rosen, S. Spudich, W. T. Kimberly, Assessment of Brain Injury Using Portable, Low-Field Magnetic Resonance Imaging at the Bedside of Critically Ill Patients. JAMA Neurol. 78, 41–47 (2020).

20

Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature 521, 436–444 (2015).

21

E. J. Topol, As artificial intelligence goes multimodal, medical applications multiply. Science 381, adk6139 (2023).

22

J. E. Iglesias, R. Schleicher, S. Laguna, B. Billot, P. Schaefer, B. McKaig, J. N. Goldstein, K. N. Sheth, M. S. Rosen, W. T. Kimberly, Quantitative Brain Morphometry of Portable Low-Field-Strength MRI Using Super-Resolution Machine Learning. Radiology 306, e220522 (2023).

23

V. Lau, L. Xiao, Y. Zhao, S. Su, Y. Ding, C. Man, X. Wang, A. Tsang, P. Cao, G. K. K. Lau, G. K. K. Leung, A. T. L. Leong, E. X. Wu, Pushing the limits of low-cost ultra-low-field MRI by dual-acquisition deep learning 3D superresolution. Magn. Reson. Med. 90, 400–416 (2023).

24

T. Guallart-Naval, J. M. Algarín, R. Pellicer-Guridi, F. Galve, Y. Vives-Gilabert, R. Bosch, E. Pallás, J. M. González, J. P. Rigla, P. Martínez, F. J. Lloris, J. Borreguero, Á. Marcos-Perucho, V. Negnevitsky, L. Martí-Bonmatí, A. Ríos, J. M. Benlloch, J. Alonso, Portable magnetic resonance imaging of patients indoors, outdoors and at home. Sci. Rep. 12, 13147 (2022).

25

Y. Zhao, L. Xiao, J. Hu, E. X. Wu, Robust EMI elimination for RF shielding-free MRI through deep learning direct MR signal prediction. Magn. Reson. Med.mrm.30046 (2024).

26

C. Man, V. Lau, S. Su, Y. Zhao, L. Xiao, Y. Ding, G. K. K. Leung, A. T. L. Leong, E. X. Wu, Deep learning enabled fast 3D brain MRI at 0.055 tesla.Sci. Adv. 9, eadi9327 (2023).

27

P. Börnert, D. G. Norris, A half-century of innovation in technology-preparing MRI for the 21st century. Br. J. Radiol. 93, 20200113 (2020).

28

L. Feng, R. Grimm, K. T. Block, H. Chandarana, S. Kim, J. Xu, L. Axel, D. K. Sodickson, R. Otazo, Golden-angle radial sparse parallel MRI: Combination of compressed sensing, parallel imaging, and golden-angle radial sampling for fast and flexible dynamic volumetric MRI. Magn. Reson. Med. 72, 707–717 (2014).

29

P. A. Bottomley, T. H. Foster, R. E. Argersinger, L. M. Pfeifer, A review of normal tissue hydrogen NMR relaxation times and relaxation mechanisms from 1-100 MHz: Dependence on tissue type, NMR frequency, temperature, species, excision, and age. Med. Phys. 11, 425–448 (1984).

30

T. O’Reilly, A. G. Webb, In vivo T1 and T2 relaxation time maps of brain tissue, skeletal muscle, and lipid measured in healthy volunteers at 50 mT. Magn. Reson. Med. 87, 884–895 (2022).

31

N. Kawel-Boehm, S. J. Hetzel, B. Ambale-Venkatesh, G. Captur, C. J. Francois, M. Jerosch-Herold, M. Salerno, S. D. Teague, E. Valsangiacomo-Buechel, R. J. van der Geest, D. A. Bluemke, Reference ranges (“normal values”) for cardiovascular magnetic resonance (CMR) in adults and children: 2020 update. J. Cardiovasc. Magn. Reson. 22, 87 (2020).

32

D. I. Hoult, R. Richards, The signal-to-noise ratio of the nuclear magnetic resonance experiment. Journal of Magnetic Resonance (1969) 24, 71–85 (1976).

33

R. Damadian, M. Goldsmith, L. Minkoff, NMR in cancer: XVI. FONAR image of the live human body. Physiol. Chem. Phys. 9, 97–100, 108 (1977).

34

W. A. Edelstein, J. M. Hutchison, G. Johnson, T. Redpath, Spin warp NMR imaging and applications to human whole-body imaging. Phys. Med. Biol. 25, 751–756 (1980).

35

J. P. Marques, F. F. J. Simonis, A. G. Webb, M. R. I. Low-field, M. R. I. Low-field, An MR physics perspective. J. Magn. Reson. Imaging 49, 1528–1542 (2019).

36

L. L. Wald, P. C. McDaniel, T. Witzel, J. P. Stockmann, C. Z. Cooley, Low-cost and portable MRI. J. Magn. Reson. Imaging 52, 686–696 (2020).

37

M. Sarracanie, N. Salameh, M. R. I. Low-Field, How Low Can We Go? A Fresh View on an Old Debate. Front. Phys. 8, 172 (2020).

38

M. Dewey, T. Schink, C. F. Dewey, Claustrophobia during magnetic resonance imaging: Cohort study in over 55,000 patients. J. Magn. Reson. Imaging 26, 1322–1327 (2007).

39

D. M. Hudson, C. Heales, R. Meertens, Review of claustrophobia incidence in MRI: A service evaluation of current rates across a multi-centre service. Radiography (Lond.) 28, 780–787 (2022).

40

C. Jin, H. Li, X. Li, M. Wang, C. Liu, J. Guo, J. Yang, Temporary Hearing Threshold Shift in Healthy Volunteers with Hearing Protection Caused by Acoustic Noise Exposure during 3-T Multisequence MR Neuroimaging. Radiology 286, 602–608 (2018).

41

M. J. McJury, Acoustic Noise and Magnetic Resonance Imaging: A Narrative/Descriptive Review. J. Magn. Reson. Imaging 55, 337–346 (2022).

42

T. C. Arnold, D. Tu, S. V. Okar, G. Nair, S. By, K. D. Kawatra, T. E. Robert-Fitzgerald, L. M. Desiderio, M. K. Schindler, R. T. Shinohara, D. S. Reich, J. M. Stein, Sensitivity of portable low-field magnetic resonance imaging for multiple sclerosis lesions. Neuroimage Clin. 35, 103101 (2022).

43

R. R. Edelman, S. Warach, Magnetic resonance imaging (2). N. Engl. J. Med. 328, 785–791 (1993).

44

R. N. Low, Abdominal MRI advances in the detection of liver tumours and characterisation. Lancet Oncol. 8, 525–535 (2007).

45

W. A. Curtis, T. J. Fraum, H. An, Y. Chen, A. S. Shetty, K. J. Fowler, Quantitative MRI of Diffuse Liver Disease: Current Applications and Future Directions. Radiology 290, 23–30 (2019).

46

A. Stabile, F. Giganti, A. B. Rosenkrantz, S. S. Taneja, G. Villeirs, I. S. Gill, C. Allen, M. Emberton, C. M. Moore, V. Kasivisvanathan, Multiparametric MRI for prostate cancer diagnosis: Current status and future directions. Nat. Rev. Urol. 17, 41–61 (2020).

47

T. Kamisawa, L. D. Wood, T. Itoi, K. Takaori, Pancreatic cancer. Lancet 388, 73–85 (2016).

48

K. A. Harrington, A. Shukla-Dave, R. Paudyal, R. K. G. Do, MRI of the Pancreas. J. Magn. Reson. Imaging 53, 347–359 (2021).

49

J. M. Llovet, R. K. Kelley, A. Villanueva, A. G. Singal, E. Pikarsky, S. Roayaie, R. Lencioni, K. Koike, J. Zucman-Rossi, R. S. Finn, Hepatocellular carcinoma. Nat. Rev. Dis. Primers 7, 6 (2021).

50

P. Gupta, R. Soundararajan, A. Patel, P. Kumar-M, V. Sharma, N. Kalra, Abbreviated MRI for hepatocellular carcinoma screening: A systematic review and meta-analysis. J. Hepatol. 75, 108–119 (2021).

51

R. Girardet, M. Dubois, G. Manasseh, M. Jreige, C. Du Pasquier, E. Canniff, M. Gulizia, M. Bonvin, Y. Aleman, B. Taouli, M. Fraga, C. Dromain, N. Vietti Violi, The combination of non-contrast abbreviated MRI and alpha foetoprotein has high performance for hepatocellular carcinoma screening. Eur. Radiol. 33, 6929–6938 (2023).

52

J. Chen, J. A. Talwalkar, M. Yin, K. J. Glaser, S. O. Sanderson, R. L. Ehman, Early detection of nonalcoholic steatohepatitis in patients with nonalcoholic fatty liver disease by using MR elastography. Radiology 259, 749–756 (2011).

53

R. Loomba, T. Wolfson, B. Ang, J. Hooker, C. Behling, M. Peterson, M. Valasek, G. Lin, D. Brenner, A. Gamst, R. Ehman, C. Sirlin, Magnetic resonance elastography predicts advanced fibrosis in patients with nonalcoholic fatty liver disease: A prospective study. Hepatology 60, 1920–1928 (2014).

54

M. Yushchenko, M. Sarracanie, N. Salameh, Fast acquisition of propagating waves in humans with low-field MRI: Toward accessible MR elastography. Sci. Adv. 8, eabo5739 (2022).

55

A. Bashyam, C. J. Frangieh, S. Raigani, J. Sogo, R. T. Bronson, K. Uygun, H. Yeh, D. A. Ausiello, M. J. Cima, A portable single-sided magnetic-resonance sensor for the grading of liver steatosis and fibrosis. Nat. Biomed. Eng. 5, 240–251 (2021).

56

K. Shan, G. Constantine, M. Sivananthan, S. D. Flamm, Role of cardiac magnetic resonance imaging in the assessment of myocardial viability. Circulation 109, 1328–1334 (2004).

57

M. P. Gannon, E. Schaub, C. L. Grines, S. G. Saba, State of the art: Evaluation and prognostication of myocarditis using cardiac MRI. J. Magn. Reson. Imaging 49, e122–e131 (2019).

58

J. S. Witt, S. A. Rosenberg, M. F. Bassetti, MRI-guided adaptive radiotherapy for liver tumours: Visualising the future. Lancet Oncol. 21, e74–e82 (2020).

59

S. Verma, P. L. Choyke, S. C. Eberhardt, A. Oto, C. M. Tempany, B. Turkbey, A. B. Rosenkrantz, The Current State of MR Imaging-targeted Biopsy Techniques for Detection of Prostate Cancer. Radiology 285, 343–356 (2017).

60

M. Kobayashi, A. Pascual-Leone, Transcranial magnetic stimulation in neurology. Lancet Neurol. 2, 145–156 (2003).

61

J. K. Krauss, N. Lipsman, T. Aziz, A. Boutet, P. Brown, J. W. Chang, B. Davidson, W. M. Grill, M. I. Hariz, A. Horn, M. Schulder, A. Mammis, P. A. Tass, J. Volkmann, A. M. Lozano, Technology of deep brain stimulation: Current status and future directions. Nat. Rev. Neurol. 17, 75–87 (2021).

62

P. J. Keall, C. Brighi, C. Glide-Hurst, G. Liney, P. Z. Y. Liu, S. Lydiard, C. Paganelli, T. Pham, S. Shan, A. C. Tree, U. A. van der Heide, D. E. J. Waddington, B. Whelan, Integrated MRI-guided radiotherapy - opportunities and challenges. Nat. Rev. Clin. Oncol. 19, 458–470 (2022).

63

B. Zhu, J. Z. Liu, S. F. Cauley, B. R. Rosen, M. S. Rosen, Image reconstruction by domain-transform manifold learning. Nature 555, 487–492 (2018).

64

P. M. Johnson, Y. W. Lui, The deep route to low-field MRI with high potential. Nature 623, 700–701 (2023).

65

A. M. Coffey, M. L. Truong, E. Y. Chekmenev, Low-field MRI can be more sensitive than high-field MRI. J. Magn. Reson. 237, 169–174 (2013).

66

F. Resmer, H. C. Seton, J. M. Hutchison, Cryogenic receive coil and low noise preamplifier for MRI at 0.01T. J. Magn. Reson. 203, 57–65 (2010).

67

J. D. Sánchez-Heredia, R. Baron, E. S. S. Hansen, C. Laustsen, V. Zhurbenko, J. H. Ardenkjaer-Larsen, Autonomous cryogenic RF receive coil for 13 C imaging of rodents at 3 T. Magn. Reson. Med. 84, 497–508 (2020).

68

S. Wei, Z. Wei, Z. Wang, H. Wang, Q. He, H. He, L. Li, W. Yang, Optimization design of a permanent magnet used for a low field (0.2 T) movable MRI system. Magn. Reson. Mater. Biol. Phys. Med. 36, 409–418 (2023).

69

P. Campbell, Permanent Magnet Materials and their Application, P. Campbell, Ed. (Cambridge Univ. Press, 1994), chap. 3, pp. 57–81.

70

M. Sagawa, S. Fujimura, N. Togawa, H. Yamamoto, Y. Matsuura, New material for permanent magnets on a base of Nd and Fe (invited). J. Appl. Phys. 55, 2083–2087 (1984).

71

B. Gruber, M. Froeling, T. Leiner, D. W. J. Klomp, RF coils: A practical guide for nonphysicists. J. Magn. Reson. Imaging 48, 590–604 (2018).

72

D. P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs.LG] (2015).

73

E. M. Haacke, E. D. Lindskogj, W. Lin, A fast, iterative, partial-fourier technique capable of local phase recovery. Journal of Magnetic Resonance (1969) 92, 126–145 (1991).

74

M. Maggioni, V. Katkovnik, K. Egiazarian, A. Foi, Nonlocal transform-domain filter for volumetric data denoising and reconstruction. IEEE Trans. Image Process. 22, 119–133 (2013).

75

Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, Y. Fu, Image Super-Resolution Using Very Deep Residual Channel Attention Networks. arXiv:1807.02758 [cs.CV] (2018).

76

O. Ronneberger, P. Fischer, T. Brox, “U-net: Convolutional networks for biomedical image segmentation” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 18th International Conference (Springer, 2015), pp. 234–241.

77

Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, O. Ronneberger, “3D U-Net: learning dense volumetric segmentation from sparse annotation” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 19th International Conference (Springer, 2016), pp. 424–432.

78

T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, “Feature pyramid networks for object detection” in Proceedings of the IEEE conference on computer vision and pattern recognition (IEEE, 2017), pp. 2117–2125.

79

S. Woo, J. Park, J.-Y. Lee, I. S. Kweon, CBAM: Convolutional Block Attention Module. arXiv:1807.06521 [cs.CV] (2018).

80

D. C. Van Essen, S. M. Smith, D. M. Barch, T. E. J. Behrens, E. Yacoub, K. Ugurbil, WU-Minn HCP Consortium, The WU-Minn Human Connectome Project: An overview. Neuroimage 80, 62–79 (2013).

81

C. G. Peterfy, E. Schneider, M. Nevitt, The osteoarthritis initiative: Report on the design rationale for the magnetic resonance imaging protocol for the knee. Osteoarthritis Cartilage 16, 1433–1441 (2008).

82

J. Cohen-Adad, E. Alonso-Ortiz, M. Abramovic, C. Arneitz, N. Atcheson, L. Barlow, R. L. Barry, M. Barth, M. Battiston, C. Büchel, M. Budde, V. Callot, A. J. E. Combes, B. De Leener, M. Descoteaux, P. L. de Sousa, M. Dostál, J. Doyon, A. Dvorak, F. Eippert, K. R. Epperson, K. S. Epperson, P. Freund, J. Finsterbusch, A. Foias, M. Fratini, I. Fukunaga, C. A. M. Gandini Wheeler-Kingshott, G. Germani, G. Gilbert, F. Giove, C. Gros, F. Grussu, A. Hagiwara, P.-G. Henry, T. Horák, M. Hori, J. Joers, K. Kamiya, H. Karbasforoushan, M. Keřkovský, A. Khatibi, J.-W. Kim, N. Kinany, H. H. Kitzler, S. Kolind, Y. Kong, P. Kudlička, P. Kuntke, N. D. Kurniawan, S. Kusmia, R. Labounek, M. M. Laganà, C. Laule, C. S. Law, C. Lenglet, T. Leutritz, Y. Liu, S. Llufriu, S. Mackey, E. Martinez-Heras, L. Mattera, I. Nestrasil, K. P. O’Grady, N. Papinutto, D. Papp, D. Pareto, T. B. Parrish, A. Pichiecchio, F. Prados, À. Rovira, M. J. Ruitenberg, R. S. Samson, G. Savini, M. Seif, A. C. Seifert, A. K. Smith, S. A. Smith, Z. A. Smith, E. Solana, Y. Suzuki, G. Tackley, A. Tinnermann, J. Valošek, D. Van De Ville, M. C. Yiannakas, K. A. Weber Ii, N. Weiskopf, R. G. Wise, P. O. Wyss, J. Xu, Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers. Sci. Data 8, 219 (2021).

83

G. McGibney, M. R. Smith, S. T. Nichols, A. Crawley, Quantitative evaluation of several partial Fourier reconstruction algorithms used in MRI. Magn. Reson. Med. 30, 51–59 (1993).

84

Z. Wang, A. C. Bovik, H. R. Sheikh, E. P. Simoncelli, Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004).

85

Y. Zhao, Y. Ding, V. Lau, C. Man, S. Su, L. Xiao, A. T. L. Leong, E. Wu, Whole-body Magnetic Resonance Imaging at 0.05 Tesla, v1, Zenodo; https://zenodo.org/records/10612819 (2024).