Conference PaperPDF Available

Abstract and Figures

The trade-off between spatial and temporal resolution in dynamic MRI is a hindrance for MR-guided interventions, which require high temporal resolution while visualizing details. Deep learning based super-resolution (SR) has shown promising results in dealing with this trade-off. Nevertheless, the available temporal information of dynamic MRI has not been exploited in this prior work. The potential of improving the reconstruction quality of dynamic MRIs by incorporating the temporal information has been demonstrated recently. This work extends the previous work by ameliorating the previous model a the dual-channel (static+dynamic images) super-resolution approach, termed DDoS (Dynamic Dual-channel of SuperRes).
Content may be subject to copyright.
118
DDoS: Dynamic Dual-Channel U-Net for Improving Deep Learning Based Super-Resolution of Abdominal
Dynamic MRI
SarasaenC.1,2, ChatterjeeS.1,3,4, NürnbergerA.3,4,5, SpeckO.1,5,6,7
1Otto von Guericke University Magdeburg, Biomedical Magnetic Resonance, Magdeburg, Germany 2Otto von Guericke University Magdeburg, Institute for Medical Engineering, Magdeburg, Germany 3Otto von Guericke University Magdeburg, Faculty of Computer Science, Magdeburg, Germany 4Otto von Guericke University Magdeburg, Data and Knowledge Engineering Group, Magdeburg, Germany 5Center for Behavioral Brain Sciences, Magdeburg, Germany 6German Center for Neurodegenerative Disease, Magdeburg, Germany 7Leibniz Institute for Neurobiology, Magdeburg, Germany
Introduction:
The trade-off between spatial and temporal resolution in dynamic MRI is a hindrance for MR-guided
interventions, which require high temporal resolution while visualizing details. Deep learning based super-
resolution (SR) has shown promising results in dealing with this trade-off[1]. Nevertheless, the available
temporal information of dynamic MRI has not been exploited in this prior work. The potential of improving
the reconstruction quality of dynamic MRIs by incorporating the temporal information has been
demonstrated recently[2-4]. This work extends the previous work by ameliorating the previous model[1] a
the dual-channel (static+dynamic images) super-resolution approach, termed DDoS (Dynamic Dual-channel
of SuperRes).
Methods:
An artificial dynamic dataset was generated by applying random elastic deformations[5] to the publicly
available CHAOS dataset (T1 in- and opposed phase)[6]. Then, a low resolution dataset was simulated by
performing in-plane undersampling[7,8] taking only the centre of the k-space of each slice. A modified U-
Net model[1] was trained with dual-channel input, consisting of the low-resolution image of the current time
point (LR_TPn) and the high resolution image of the previous time point (HR_Tpn-1), see Fig.1. This
training strategy tries to let the network learn the spatio-temporal relationship over time points, with the help
of perceptual loss[9] using a perceptual loss network[10], and was minimised using Adam optimiser for 18
epochs. 3D patches of the volumes were created for training with a patch size of 243, and with a stride of 6
for the slice dimension and 12 for the rest. For testing, a stride of 3 was used for all dimensions with the
same patch size. A 3D abdominal dynamic MRI data was acquired at 3T Siemens Magnetom Skyra [GRE,
T1w Flash 3D, TR: 2.23ms, TE: 10.93ms, voxel size: 1.09x1.09x4.0mm] and was also undersampled in the
same manner and were used for testing.
Results and Discussion:
The highest undersampling (only 6.25% of centre k-space per slice) explored in the former work[1], was
applied to evaluate the improvements with the proposed approach. Fig.2 shows the comparison of low-
resolution input (for the lowest resolution examined), SR result after subject specific fine-tuning[1], DDoS
results and its corresponding ground-truth images. The average SSIM value while comparing the results
against the ground-truth improved from 0.949±0.003 (for SR result after fine-tuning[1]) to 0.979±0.004 and
the average PSNR value improved from 34.647±0.240 to 39.411±0.536. One can observe qualitatively that
the results of the DDoS model are more similar to the ground-truth compared to the result of SR after fine-
tuning. In conclusion, this research illustrates that by incorporating the temporal information in a super-
resolution approach[2] using the DDoS model can improve the reconstruction quality, and may be extended
for application during real-time interventions due to the fast inference speed.
Fig. 1
Fig. 2
Fig. 3
... The control electronics are based on MaRCoS, an open-source, high-performance Magnetic Resonance Control System [40][41][42] . ...
... The receive chain consists of an analog stage (RF coil, passive Tx/Rx switch and lownoise amplifier) followed by a digital stage. The digitization is performed at 122.88 Ms/s by an analog-to-digital converter in the Red Pitaya Stemlab board [40][41][42] . The digital signal is mixed down by complex multiplication with a numerically-controlled oscillator set to the Larmor frequency. ...
Article
Full-text available
Mobile medical imaging devices are invaluable for clinical diagnostic purposes both in and outside healthcare institutions. Among the various imaging modalities, only a few are readily portable. Magnetic resonance imaging (MRI), the gold standard for numerous healthcare conditions, does not traditionally belong to this group. Recently, low-field MRI technology companies have demonstrated the first decisive steps towards portability within medical facilities and vehicles. However, these scanners’ weight and dimensions are incompatible with more demanding use cases such as in remote and developing regions, sports facilities and events, medical and military camps, or home healthcare. Here we present in vivo images taken with a light, small footprint, low-field extremity MRI scanner outside the controlled environment provided by medical facilities. To demonstrate the true portability of the system and benchmark its performance in various relevant scenarios, we have acquired images of a volunteer’s knee in: (i) an MRI physics laboratory; (ii) an office room; (iii) outside a campus building, connected to a nearby power outlet; (iv) in open air, powered from a small fuel-based generator; and (v) at the volunteer’s home. All images have been acquired within clinically viable times, and signal-to-noise ratios and tissue contrast suffice for 2D and 3D reconstructions with diagnostic value. Furthermore, the volunteer carries a fixation metallic implant screwed to the femur, which leads to strong artifacts in standard clinical systems but appears sharp in our low-field acquisitions. Altogether, this work opens a path towards highly accessible MRI under circumstances previously unrealistic.
... All the below images are taken with a single RF coil used for both transmission and reception (Tx/Rx), tuned and impedancematched to ≈ 3 MHz, the proton resonance (Larmor) frequency at our field strength. The control electronics are based on MaRCoS, an open-source, highperformance Magnetic Resonance Control System 35,36 . The diameter and length of the scanner are around 53 and 51 cm respectively, excluding electronics and the mobile structure, with a bore opening ≈ 20 cm and a weight of ≈ 200 kg. ...
Preprint
Full-text available
Mobile medical imaging devices are invaluable for clinical diagnostic purposes both in and outside healthcare institutions. Among the various imaging modalities, only a few are readily portable. Magnetic resonance imaging (MRI), the gold standard for numerous healthcare conditions, does not traditionally belong to this group. Recently, low-field MRI start-up companies have demonstrated the first decisive steps towards portability within medical facilities, but these are so far incompatible with more demanding use cases such as in remote and developing regions, sports facilities and events, medical and military camps, or home healthcare. Here we present in vivo images taken with a light, home-made, low-field extremity MRI scanner outside the controlled environment provided by medical facilities. To demonstrate the true portability of the system and benchmark its performance in various relevant scenarios, we have acquired images of a volunteer's knee in: i) an MRI physics laboratory; ii) an office room; iii) outside a campus building, connected to a nearby power outlet; iv) in open air, powered from a small fuel-based generator; and v) at the volunteer's home. All images have been acquired within clinically viable times, and signal-to-noise ratios (SNR) and tissue contrast suffice for 2D and 3D reconstructions with diagnostic value, with comparable overall image quality across all five situations. Furthermore, the volunteer carries a fixation metallic implant screwed to the femur, which leads to strong artifacts in standard clinical systems but appears sharp in our low-field acquisitions. Altogether, this work opens a path towards highly accessible MRI under circumstances previously unrealistic.
Article
Full-text available
We present a comprehensive study on the non-invasive measurement of hippocampal perfusion. Using high-resolution 7 tesla arterial spin labeling (ASL) data, we generated robust perfusion maps and observed significant variations in perfusion among hippocampal subfields, with CA1 exhibiting the lowest perfusion levels. Notably, these perfusion differences were robust and already detectable with 50 perfusion-weighted images per subject, acquired in 5 min. To understand the underlying factors, we examined the influence of image quality metrics, various tissue microstructure and morphometric properties, macrovasculature, and cytoarchitecture. We observed higher perfusion in regions located closer to arteries, demonstrating the influence of vascular proximity on hippocampal perfusion. Moreover, ex vivo cytoarchitectonic features based on neuronal density differences appeared to correlate stronger with hippocampal perfusion than morphometric measures like gray matter thickness. These findings emphasize the interplay between microvasculature, macrovasculature, and metabolic demand in shaping hippocampal perfusion. Our study expands the current understanding of hippocampal physiology and its relevance to neurological disorders. By providing in vivo evidence of perfusion differences between hippocampal subfields, our findings have implications for diagnosis and potential therapeutic interventions. In conclusion, our study provides a valuable resource for extensively characterizing hippocampal perfusion.
Article
Although hyperpolarized (HP) ¹²⁹ Xe ventilation MRI can be carried out within a breath hold, it is still challenging for many sick patients. Compressed sensing (CS) is a viable alternative to accelerate this approach. However, undersampled images with identical sampling ratios differ from one another. Twenty subjects ( n = 10 healthy and n = 10 patients with asthma) were scanned using a GE MR750 3 T scanner, acquiring fully sampled 2D multi‐slice HP ¹²⁹ Xe lung ventilation images (10 s breath hold, 128 × 80 (FE × PE—frequency encoding × phase encoding) and 16 slices). Using fully sampled data, 500 variable‐density Cartesian random undersampling patterns were generated, each at eight different sampling ratios from 10% to 80%. The parallel imaging and compressed sensing (PICS) command from BART was employed to reconstruct undersampled data. The signal to noise ratio (SNR), structural similarity index measurement (SSIM) and sidelobe to peak ratio of each were subsequently compared. There was a high degree of variation in both SNR and SSIM results from each of the 500 masks of each sampling rate. As the undersampling increases, there is more variation in the quantifying metrics, for both healthy and asthmatic individuals. Our study shows that random undersampling poses a significant challenge when applied at sampling ratios less than 60%, despite fulfilling CS's incoherency criteria. Such low sampling ratios will result in a large variety of undersampling patterns. Therefore, skipped segments of k ‐space cannot be allowed to happen randomly at low sampling rates. By optimizing the sampling pattern, CS will reach its full potential and be able to be applied to a highly undersampled ¹²⁹ Xe lung dataset.
Article
Full-text available
Purpose: To describe the current properties and capabilities of an open-source hardware and software package that is being developed by many sites internationally with the aim of providing an inexpensive yet flexible platform for low-cost MRI. Methods: This paper describes three different setups from 50 to 360mT in different settings, all of which used the MaRCoS console for acquiring data, and different types of software interfaces (custombuilt GUI or PulSeq overlay) to acquire it. Results: Images are presented from both phantoms and in vivo from healthy volunteers to demonstrate the image quality that can be obtained from the MaRCoS hardware/software interfaced to different low-field magnets. Conclusions: The results presented here show that a number of different sequences commonly used in the clinic can be programmed into an open-source system relatively quickly and easily, and can produce good quality images even at this early stage of development. Both the hardware and software will continue to develop, and it is an aim of this paper to encourage other groups to join this international consortium.
ResearchGate has not been able to resolve any references for this publication.