Three-Dimensional Permeability Inversion Using Convolutional Neural Networks and Positron Emission Tomography

2021 ◽  
Author(s):  
Zitong Huang ◽  
Takeshi Kurotori ◽  
Ronny Pini ◽  
Sally Benson ◽  
Christopher Zahasky
Keyword(s):  
Neural Networks ◽  
Positron Emission Tomography ◽  
Convolutional Neural Networks ◽  
Three Dimensional ◽  
Emission Tomography ◽  
Positron Emission

Scaled Subprofile Modeling and Convolutional Neural Networks for the Identification of Parkinson’s Disease in 3D Nuclear Imaging Data

2019 ◽  
Vol 29 (09) ◽  
pp. 1950010 ◽  
Author(s):  
Octavio Martinez Manzanera ◽  
Sanne K. Meles ◽  
Klaus L. Leenders ◽  
Remco J. Renken ◽  
Marco Pagani ◽  
...  
Keyword(s):  
Neural Networks ◽  
Parkinson’S Disease ◽  
Positron Emission Tomography ◽  
Parkinson's Disease ◽  
Convolutional Neural Networks ◽  
Fdg Pet ◽  
Characteristic Curve ◽  
Emission Tomography ◽  
Imaging Data ◽  
Positron Emission

Over the last years convolutional neural networks (CNNs) have shown remarkable results in different image classification tasks, including medical imaging. One area that has been less explored with CNNs is Positron Emission Tomography (PET). Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a PET technique employed to obtain a representation of brain metabolic function. In this study we employed 3D CNNs in FDG-PET brain images with the purpose of discriminating patients diagnosed with Parkinson’s disease (PD) from controls. We employed Scaled Subprofile Modeling using Principal Component Analysis as a preprocessing step to focus on specific brain regions and limit the number of voxels that are used as input for the CNNs, thereby increasing the signal-to-noise ratio in our data. We performed hyperparameter optimization on three CNN architectures to estimate the classification accuracy of the networks on new data. The best performance that we obtained was [Formula: see text] and area under the receiver operating characteristic curve [Formula: see text] on the test set. We believe that, with larger datasets, PD patients could be reliably distinguished from controls by FDG-PET scans alone and that this technique could be applied to more clinically challenging tasks, like the differential diagnosis of neurological disorders with similar symptoms, such as PD, Progressive Supranuclear Palsy (PSP) and Multiple System Atrophy (MSA).

Positron Emission Tomography (PET) for Flow Measurement

2011 ◽  
Vol 301-303 ◽  
pp. 1316-1321 ◽  
Author(s):  
Arthur E. Ruggles ◽  
Bi Yao Zhang ◽  
Spero M. Peters
Keyword(s):  
Positron Emission Tomography ◽  
Pet Imaging ◽  
Three Dimensional ◽  
Bulk Water ◽  
Emission Tomography ◽  
Optical Methods ◽  
Imaging Method ◽  
Analysis And Design ◽  
Pet Tracer ◽  
Positron Emission

Positron Emission Tomography (PET) produces a three dimensional spatial distribution of positron-electron annihilations within an image volume. Various positron emitters are available for use in aqueous, organic and liquid metal flows. Preliminary experiments at the University of Tennessee at Knoxville (UTK) injected small flows of PET tracer into a bulk water flow in a four rod bundle. The trajectory and diffusion of the tracer in the bulk flow were then mapped using a PET scanner. A spatial resolution of 1.4 mm is achieved with current preclinical Micro-PET imaging equipment resulting in 200 MB 3D activity fields. A time resolved 3-D spatial activity profile was also measured. The PET imaging method is especially well suited to complex geometries where traditional optical methods such as LDV and PIV are difficult to apply. PET methods are uniquely useful for imaging in opaque fluids, opaque pressure boundaries, and multiphase studies. Several commercial and shareware Computational Fluid Dynamics (CFD) codes are currently used for science and engineering analysis and design. These codes produce detailed three dimensional flow predictions. The models produced by these codes are often difficult to validate. The development of this experimental technique offers a modality for the comparison of CFD outcomes with experimental data. Developed data sets from PET can be used in verification and validation exercises of simulation outcomes.

Positron Emission Tomography: Clinical Applications and Pharmaceutical Care

1994 ◽  
Vol 7 (3) ◽  
pp. 124-139 ◽  
Author(s):  
Richard J. Hammes ◽  
John W. Babich
Keyword(s):  
Positron Emission Tomography ◽  
Imaging Technique ◽  
Three Dimensional ◽  
Building Blocks ◽  
Emission Tomography ◽  
Pharmacokinetic Parameters ◽  
Nuclear Medicine Imaging ◽  
Receptor Ligands ◽  
Positron Emission

Positron emission tomography {PET) is a nuclear medicine imaging technique which exploits the unique physical characteristics of radionuclides that decay by positron emission. These characteristics allow for in vivo quantitative measurement of three-dimensional distributions of radioactivity with a spatial resolution of 5 mm using current detector technology. In addition to these physical advantages, PET is the only imaging technique that can use the short-lived positron emitting radionuclides of the so-called “organic” elements: carbon (C-11), nitrogen (N-13), and oxygen (0–15). These elements are the building blocks of physiological compounds and can be used to study most enzymes, receptors, and other metabolically important compounds and their associated reactions. PET allows for the study of a variety of physiological and biochemical processes through the application of particular radiopharmaceuticals. PET has also been used to study the interaction of receptor-specific ligands in several receptor systems including dopaminergic, adrenergic, serotinergic, and opiod. C-11 and F-18 labeled receptor ligands have been used to study receptor selectivity and receptor concentrations in vivo. Recently, PET has been used to measure the pharmacokinetics of several novel antibiotics in humans allowing the direct measurement of tissue concentrations and correlation with classical pharmacokinetic parameters. This review discusses some of the current applications of PET in more detail.

Sign in / Sign up

Export Citation Format

Share Document