Deep learning for fast low-field MRI acquisitions.
Ontology highlight
ABSTRACT:
SUBMITTER: Ayde R
PROVIDER: S-EPMC9259619 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Recent years have seen a resurgence of interest in inexpensive low magnetic field (< 0.3 T) MRI systems mainly due to advances in magnet, coil and gradient set designs. Most of these advances have focused on improving hardware and signal acquisition strategies, and far less on the use of advanced image reconstruction methods to improve attainable image quality at low field. We describe here the use of our end-to-end deep neural network approach (AUTOMAP) to improve the image quality of highly noise-corrupted low-field MRI data. We compare the performance of this approach to two additional state-of-the-art denoising pipelines. We find that AUTOMAP improves image reconstruction of data acquired on two very different low-field MRI systems: human brain data acquired at 6.5 mT, and plant root data acquired at 47 mT, demonstrating SNR gains above Fourier reconstruction by factors of 1.5- to 4.5-fold, and 3-fold, respectively. In these applications, AUTOMAP outperformed two different contemporary image-based denoising algorithms, and suppressed noise-like spike artifacts in the reconstructed images. The impact of domain-specific training corpora on the reconstruction performance is discussed. The AUTOMAP approach to image reconstruction will enable significant image quality improvements at low-field, especially in highly noise-corrupted environments.
| S-EPMC8050246 | biostudies-literature
Project description:Reconstructing cortical surfaces from structural magnetic resonance imaging (MRI) is a prerequisite for surface-based functional and anatomical image analyses. Conventional algorithms for cortical surface reconstruction are computationally inefficient and typically take several hours for each subject, causing a bottleneck in applications when a fast turnaround time is needed. To address this challenge, we propose a fast cortical surface reconstruction (FastCSR) pipeline by leveraging deep machine learning. We trained our model to learn an implicit representation of the cortical surface in volumetric space, termed the "level set representation". A fast volumetric topology correction method and a topology-preserving surface mesh extraction procedure were employed to reconstruct the cortical surface based on the level set representation. Using 1-mm isotropic T1-weighted images, the FastCSR pipeline was able to reconstruct a subject's cortical surfaces within 5 min with comparable surface quality, which is approximately 47 times faster than the traditional FreeSurfer pipeline. The advantage of FastCSR becomes even more apparent when processing high-resolution images. Importantly, the model demonstrated good generalizability in previously unseen data and showed high test-retest reliability in cortical morphometrics and anatomical parcellations. Finally, FastCSR was robust to images with compromised quality or with distortions caused by lesions. This fast and robust pipeline for cortical surface reconstruction may facilitate large-scale neuroimaging studies and has potential in clinical applications wherein brain images may be compromised.
| S-EPMC8907118 | biostudies-literature
Project description:PurposeThis study aimed to investigate the impact of a deep learning (DL)-based denoising method on the image quality and lesion detectability of 18F-FDG positron emission tomography (PET) images.MethodsFifty-two oncological patients undergoing an 18F-FDG PET/CT imaging with an acquisition of 180 s per bed position were retrospectively included. The list-mode data were rebinned into four datasets: 100% (reference), 75%, 50%, and 33.3% of the total counts, and then reconstructed by OSEM algorithm and post-processed with the DL and Gaussian filter (GS). The image quality was assessed using a 5-point Likert scale, and FDG-avid lesions were counted to measure lesion detectability. Standardized uptake values (SUVs) in livers and lesions, liver signal-to-noise ratio (SNR) and target-to-background ratio (TBR) values were compared between the methods. Subgroup analyses compared TBRs after categorizing lesions based on parameters like lesion diameter, uptake or patient habitus.ResultsThe DL method showed superior performance regarding image noise and inferior performance regarding lesion contrast in the qualitative assessment. More than 96.8% of the lesions were successfully identified in DL images. Excellent agreements on SUV in livers and lesions were found. The DL method significantly improved the liver SNR for count reduction down to 33.3% (p < 0.001). Lesion TBR was not significantly different between DL and reference images of the 75% dataset; furthermore, there was no significant difference either for lesions of > 10 mm or lesions in BMIs of > 25. For the 50% dataset, there was no significant difference between DL and reference images for TBR of lesion with > 15 mm or higher uptake than liver.ConclusionsThe developed DL method improved both liver SNR and lesion TBR indicating better image quality and lesion conspicuousness compared to GS method. Compared with the reference, it showed non-inferior image quality with reduced counts by 25-50% under various conditions.
| S-EPMC8816983 | biostudies-literature
Project description:Microscopic evaluation of resected tissue plays a central role in the surgical management of cancer. Because optical microscopes have a limited depth-of-field (DOF), resected tissue is either frozen or preserved with chemical fixatives, sliced into thin sections placed on microscope slides, stained, and imaged to determine whether surgical margins are free of tumor cells-a costly and time- and labor-intensive procedure. Here, we introduce a deep-learning extended DOF (DeepDOF) microscope to quickly image large areas of freshly resected tissue to provide histologic-quality images of surgical margins without physical sectioning. The DeepDOF microscope consists of a conventional fluorescence microscope with the simple addition of an inexpensive (less than $10) phase mask inserted in the pupil plane to encode the light field and enhance the depth-invariance of the point-spread function. When used with a jointly optimized image-reconstruction algorithm, diffraction-limited optical performance to resolve subcellular features can be maintained while significantly extending the DOF (200 µm). Data from resected oral surgical specimens show that the DeepDOF microscope can consistently visualize nuclear morphology and other important diagnostic features across highly irregular resected tissue surfaces without serial refocusing. With the capability to quickly scan intact samples with subcellular detail, the DeepDOF microscope can improve tissue sampling during intraoperative tumor-margin assessment, while offering an affordable tool to provide histological information from resected tissue specimens in resource-limited settings.
| S-EPMC7776814 | biostudies-literature
Project description:We present a deep learning tractography segmentation method that allows fast and consistent white matter fiber tract identification across healthy and disease populations and across multiple diffusion MRI (dMRI) acquisitions. We create a large-scale training tractography dataset of 1 million labeled fiber samples (54 anatomical tracts are included). To discriminate between fibers from different tracts, we propose a novel 2D multi-channel feature descriptor (FiberMap) that encodes spatial coordinates of points along each fiber. We learn a CNN tract classification model based on FiberMap and obtain a high tract classification accuracy of 90.99%. The method is evaluated on a test dataset of 374 dMRI scans from three independently acquired populations across health conditions (healthy control, neuropsychiatric disorders, and brain tumor patients). We perform comparisons with two state-of-the-art white matter tract segmentation methods. Experimental results show that our method obtains a highly consistent segmentation result, where over 99% of the fiber tracts are successfully detected across all subjects under study, most importantly, including patients with space occupying brain tumors. The proposed method leverages deep learning techniques and provides a much faster and more efficient tool for large data analysis than methods using traditional machine learning techniques.
| S-EPMC7301958 | biostudies-literature
Project description:This work presents a deep learning approach for rapid and accurate muscle water T2 with subject-specific fat T2 calibration using multi-spin-echo acquisitions. This method addresses the computational limitations of conventional bi-component Extended Phase Graph fitting methods (nonlinear-least-squares and dictionary-based) by leveraging fully connected neural networks for fast processing with minimal computational resources. We validated the approach through in vivo experiments using two different MRI vendors. The results showed strong agreement of our deep learning approach with reference methods, summarized by Lin's concordance correlation coefficients ranging from 0.89 to 0.97. Further, the deep learning method achieved a significant computational time improvement, processing data 116 and 33 times faster than the nonlinear least squares and dictionary methods, respectively. In conclusion, the proposed approach demonstrated significant time and resource efficiency improvements over conventional methods while maintaining similar accuracy. This methodology makes the processing of water T2 data faster and easier for the user and will facilitate the utilization of the use of a quantitative water T2 map of muscle in clinical and research studies.
| S-EPMC11002020 | biostudies-literature
Project description:PurposeTendency is to moderate the injected activity and/or reduce acquisition time in PET examinations to minimize potential radiation hazards and increase patient comfort. This work aims to assess the performance of regular full-dose (FD) synthesis from fast/low-dose (LD) whole-body (WB) PET images using deep learning techniques.MethodsInstead of using synthetic LD scans, two separate clinical WB 18F-Fluorodeoxyglucose (18F-FDG) PET/CT studies of 100 patients were acquired: one regular FD (~ 27 min) and one fast or LD (~ 3 min) consisting of 1/8th of the standard acquisition time. A modified cycle-consistent generative adversarial network (CycleGAN) and residual neural network (ResNET) models, denoted as CGAN and RNET, respectively, were implemented to predict FD PET images. The quality of the predicted PET images was assessed by two nuclear medicine physicians. Moreover, the diagnostic quality of the predicted PET images was evaluated using a pass/fail scheme for lesion detectability task. Quantitative analysis using established metrics including standardized uptake value (SUV) bias was performed for the liver, left/right lung, brain, and 400 malignant lesions from the test and evaluation datasets.ResultsCGAN scored 4.92 and 3.88 (out of 5) (adequate to good) for brain and neck + trunk, respectively. The average SUV bias calculated over normal tissues was 3.39 ± 0.71% and - 3.83 ± 1.25% for CGAN and RNET, respectively. Bland-Altman analysis reported the lowest SUV bias (0.01%) and 95% confidence interval of - 0.36, + 0.47 for CGAN compared with the reference FD images for malignant lesions.ConclusionCycleGAN is able to synthesize clinical FD WB PET images from LD images with 1/8th of standard injected activity or acquisition time. The predicted FD images present almost similar performance in terms of lesion detectability, qualitative scores, and quantification bias and variance.
| S-EPMC8241799 | biostudies-literature
Project description:Most commonly used at clinical magnetic fields (1.5 to 3 T), magnetic resonance elastography (MRE) captures mechanical wave propagation to reconstruct the mechanical properties of soft tissue with MRI. However, in terms of noninvasively assessing disease progression in a broad range of organs (e.g., liver, breast, skeletal muscle, and brain), its accessibility is limited and its robustness is challenged when magnetic susceptibility differences are encountered. Low-field MRE offers an opportunity to overcome these issues, and yet it has never been demonstrated in vivo in humans with magnetic fields <1.5 T mainly because of the long acquisition times required to achieve a sufficient signal-to-noise ratio. Here, we describe a method to accelerate 3D motion-sensitized MR scans at 0.1 T using only 10% k-space sampling combined with a high-performance detector and an efficient encoding acquisition strategy. Its application is demonstrated in vivo in the human forearm for a single motion-encoding direction in less than 1 min.
| S-EPMC9462689 | biostudies-literature
Project description:PurposeWe aimed to evaluate the performance of deep learning-based generalization of ultra-low-count amyloid PET/MRI enhancement when applied to studies acquired with different scanning hardware and protocols.MethodsEighty simultaneous [18F]florbetaben PET/MRI studies were acquired, split equally between two sites (site 1: Signa PET/MRI, GE Healthcare, 39 participants, 67 ± 8 years, 23 females; site 2: mMR, Siemens Healthineers, 64 ± 11 years, 23 females) with different MRI protocols. Twenty minutes of list-mode PET data (90-110 min post-injection) were reconstructed as ground-truth. Ultra-low-count data obtained from undersampling by a factor of 100 (site 1) or the first minute of PET acquisition (site 2) were reconstructed for ultra-low-dose/ultra-short-time (1% dose and 5% time, respectively) PET images. A deep convolution neural network was pre-trained with site 1 data and either (A) directly applied or (B) trained further on site 2 data using transfer learning. Networks were also trained from scratch based on (C) site 2 data or (D) all data. Certified physicians determined amyloid uptake (+/-) status for accuracy and scored the image quality. The peak signal-to-noise ratio, structural similarity, and root-mean-squared error were calculated between images and their ground-truth counterparts. Mean regional standardized uptake value ratios (SUVR, reference region: cerebellar cortex) from 37 successful site 2 FreeSurfer segmentations were analyzed.ResultsAll network-synthesized images had reduced noise than their ultra-low-count reconstructions. Quantitatively, image metrics improved the most using method B, where SUVRs had the least variability from the ground-truth and the highest effect size to differentiate between positive and negative images. Method A images had lower accuracy and image quality than other methods; images synthesized from methods B-D scored similarly or better than the ground-truth images.ConclusionsDeep learning can successfully produce diagnostic amyloid PET images from short frame reconstructions. Data bias should be considered when applying pre-trained deep ultra-low-count amyloid PET/MRI networks for generalization.
| S-EPMC7680289 | biostudies-literature
Project description:MRI signal-to-noise ratio (SNR) is the key factor for image quality. Conventionally, SNR is proportional to nuclear spin polarization, which scales linearly with magnetic field strength. Yet ever-stronger magnets present numerous technical and financial limitations. Low-field MRI can mitigate these constraints with equivalent SNR from non-equilibrium 'hyperpolarization' schemes, which increase polarization by orders of magnitude independently of the magnetic field. Here, theory and experimental validation demonstrate that combination of field independent polarization (e.g. hyperpolarization) with frequency optimized MRI detection coils (i.e. multi-turn coils using the maximum allowed conductor length) results in low-field MRI sensitivity approaching and even rivaling that of high-field MRI. Four read-out frequencies were tested using samples with identical numbers of (1)H and (13)C spins. Experimental SNRs at 0.0475T were ?40% of those obtained at 4.7T. Conservatively, theoretical SNRs at 0.0475T 1.13-fold higher than those at 4.7T were possible despite an ?100-fold lower detection frequency, indicating feasibility of high-sensitivity MRI without technically challenging, expensive high-field magnets. The data at 4.7T and 0.0475T was obtained from different spectrometers with different RF probes. The SNR comparison between the two field strengths accounted for many differences in parameters such as system noise figures and variations in the probe detection coils including Q factors and coil diameters.
| S-EPMC3897717 | biostudies-literature