اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدXCloud-VIP: Virtual Peak Enables Highly Accelerated NMR Spectroscopy and Faithful Quantitative Measures
80
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Background: Nuclear Magnetic Resonance (NMR) spectroscopy is an important bio-engineering tool to determine the metabolic concentrations, molecule structures and so on. The data acquisition time, however, is very long in multi-dimensional NMR. To accelerate data acquisition, non-uniformly sampling is an effective way but may encounter severe spectral distortions and unfaithful quantitative measures when the acceleration factor is high. Objective: To reconstruct high fidelity spectra from highly accelerated NMR and achieve much better quantitative measures. Methods: A virtual peak (VIP) approach is proposed to self-learn the prior spectral information, such as the central frequency and peak lineshape, and then feed these information into the reconstruction. The proposed method is further implemented with cloud computing to facilitate online, open, and easy access. Results: Results on synthetic and experimental data demonstrate that, compared with the state-of-the-art method, the new approach provides much better reconstruction of low-intensity peaks and significantly improves the quantitative measures, including the regression of peak intensity, the distances between nuclear pairs, and concentrations of metabolics in mixtures. Conclusion: Self-learning prior peak information can improve the reconstruction and quantitative measures of spectra. Significance: This approach enables highly accelerated NMR and may promote time-consuming applications such as quantitative and time-resolved NMR experiments.
قيم البحث
اقرأ أيضاً
For accelerated multi-dimensional NMR spectroscopy, non-uniform sampling is a powerful approach but requires sophisticated algorithms to reconstruct undersampled data. Here, we first devise a high-performance deep learning framework (MoDern), which s
hows astonishing performance in robust and high-quality reconstruction of challenging multi-dimensional protein NMR spectra and reliable quantitative measure of the metabolite mixture. Remarkably, the few trainable parameters of MoDern allowed the neural network to be trained on solely synthetic data while generalizing well to experimental undersampled data in various scenarios. Then, we develop a novel artificial intelligence cloud computing platform (XCloud-MoDern), as a reliable, widely-available, ultra-fast, and easy-to-use technique for highly accelerated NMR. All results demonstrate that XCloud-MoDern contributes a promising platform for further development of spectra analysis.
Machine learning and artificial intelligence have shown remarkable performance in accelerated magnetic resonance imaging (MRI). Cloud computing technologies have great advantages in building an easily accessible platform to deploy advanced algorithms
. In this work, we develop an open-access, easy-to-use and high-performance medical intelligence cloud computing platform (XCloud-pFISTA) to reconstruct MRI images from undersampled k-space data. Two state-of-the-art approaches of the Projected Fast Iterative Soft-Thresholding Algorithm (pFISTA) family have been successfully implemented on the cloud. This work can be considered as a good example of cloud-based medical image reconstruction and may benefit the future development of integrated reconstruction and online diagnosis system.
T2-Shuffling reconstructs multiple sharp T2-weighted images from a single volumetric fast spin-echo (3D-FSE) scan. Wave-CAIPI is a parallel imaging technique that achieves good reconstruction at high accelerations through additional sinusoidal gradie
nts that induce a voxel spreading effect in the readout direction to better take advantage of coil-sensitivity information. In this work, the Shuffling model in T2-Shuffling is augmented with wave-encoding to achieve higher acceleration capability. The resulting Wave-Shuffling approach is applied to 3D-FSE and Magnetization-Prepared Rapid Gradient-Echo (MPRAGE) to achieve rapid, 1 mm-isotropic resolution, time-resolved structural imaging.
Positron emission tomography, like many other tomographic imaging modalities, relies on an image reconstruction step to produce cross-sectional images from projection data. Detection and localization of the back-to-back annihilation photons produced
by positron-electron annihilation defines the trajectories of these photons, which when combined with tomographic reconstruction algorithms, permits recovery of the distribution of positron-emitting radionuclides. Here we produce cross-sectional images directly from the detected coincident annihilation photons, without using a reconstruction algorithm. Ultra-fast radiation detectors with a resolving time averaging 32 picoseconds measured the difference in arrival time of pairs of annihilation photons, localizing the annihilation site to 4.8 mm. This is sufficient to directly generate an image without reconstruction and without the geometric and sampling constraints that normally present for tomographic imaging systems.
In 2000 V. Lomonosov suggested a counterexample to the complex version of the Bishop-Phelps theorem on modulus support functionals. We discuss the $c_0$-analog of that example and demonstrate that the set of sup-attaining functionals is non-trivial,
thus answering an open question, asked in cite{KLMW}.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
