Magnetic resonance imaging apparatus

The combination of tomographic imaging and deep learning, or machine learning in general, promises to empower not only image analysis but also image reconstruction. The latter aspect is considered in this perspective article with an emphasis on medical imaging to develop a new generation of image reconstruction theories and techniques. This direction might lead to intelligent utilization of domain knowledge from big data, innovative approaches for image reconstruction, and superior performance in clinical and preclinical applications. To realize the full impact of machine learning for tomographic imaging, major theoretical, technical and translational efforts are immediately needed.

pdf/a-perspective-on-deep-imaging-zyboopyb3b.pdf

A Perspective on Deep Imaging

Deep-learning-based tomographic imaging is an important application of artificial intelligence and a new frontier of machine learning. Deep learning has been widely used in computer vision and image analysis, which deal with existing images, improve these images, and produce features from them. Since 2016, deep learning techniques have been actively researched for tomographic imaging, especially in the context of biomedicine, with impressive results and great potential. Tomographic reconstruction produces images of multi-dimensional structures from externally measured ‘encoded’ data in the form of various tomographic transforms (integrals, harmonics, echoes and so on). In this Review, we provide a general background, highlight representative results with an emphasis on medical imaging, and discuss key issues that need to be addressed in this emerging field. In particular, tomographic imaging is an integral part of modern medicine, and will play a key role in personalized, preventive and precision medicine and make it intelligent, inexpensive and indiscriminate. The popularity of deep learning is leading to new areas in biomedical applications. Wang and colleagues summarize in this Review the recent development and future directions of deep neural networks for superior image quality in the tomographic imaging field.

Deep learning for tomographic image reconstruction

Purpose: This study was performed to investigate the accuracies of the synthesized monochromatic images and effective atomic number maps obtained with the new GE Discovery CT750 HD CT scanner. Methods: A Gammex-RMI model 467 tissue characterization phantom and the CT number linearity section of a Phantom Laboratory Catphan 600 phantom were scanned using the dual energy (DE) feature on the GE CT750 HD scanner. Synthesized monochromatic images at various energies between 40 and 120 keV and effective atomic number (Z{sub eff}) maps were generated. Regions of interest were placed within these images/maps to measure the average monochromatic CT numbers and average Z{sub eff} of the materials within these phantoms. The true Z{sub eff} values were either supplied by the phantom manufacturer or computed using Mayneord's equation. The linear attenuation coefficients for the true CT numbers were computed using the NIST XCOM program with the input of manufacturer supplied elemental compositions and densities. The effects of small variations in the assumed true densities of the materials were also investigated. Finally, the effect of body size on the accuracies of the synthesized monochromatic CT numbers was investigated using a custom lumbar section phantom with and without an external fat-mimicking ring. Results: Othermore » than the Z{sub eff} of the simulated lung inserts in the tissue characterization phantom, which could not be measured by DECT, the Z{sub eff} values of all of the other materials in the tissue characterization and Catphan phantoms were accurate to 15%. The accuracies of the synthesized monochromatic CT numbers of the materials in both phantoms varied with energy and material. For the 40-120 keV range, RMS errors between the measured and true CT numbers in the Catphan are 8-25 HU when the true CT numbers were computed using the nominal plastic densities. These RMS errors improve to 3-12 HU for assumed true densities within the nominal density {+-}0.02 g/cc range. The RMS errors between the measured and true CT numbers of the tissue mimicking materials in the tissue characterization phantom over the 40-120 keV range varied from about 6 HU-248 HU and did not improve as dramatically with small changes in assumed true density. Conclusions: Initial tests indicate that the Z{sub eff} values computed with DECT on this scanner are reasonably accurate; however, the synthesized monochromatic CT numbers can be very inaccurate, especially for dense tissue mimicking materials at low energies. Furthermore, the synthesized monochromatic CT numbers of materials still depend on the amount of the surrounding tissues especially at low keV, demonstrating that the numbers are not truly monochromatic. Further research is needed to develop DE methods that produce more accurate synthesized monochromatic CT numbers.« less

/pdf/accuracies-of-the-synthesized-monochromatic-ct-numbers-and-3w1py2fao0.pdf

Accuracies of the synthesized monochromatic CT numbers and effective atomic numbers obtained with a rapid kVp switching dual energy CT scanner

There is an increasing interest in iterative reconstruction (IR) as a key tool to improve quality and increase applicability of x-ray CT imaging. IR has the ability to significantly reduce patient dose; it provides the flexibility to reconstruct images from arbitrary x-ray system geometries and allows one to include detailed models of photon transport and detection physics to accurately correct for a wide variety of image degrading effects. This paper reviews discretization issues and modelling of finite spatial resolution, Compton scatter in the scanned object, data noise and the energy spectrum. The widespread implementation of IR with a highly accurate model-based correction, however, still requires significant effort. In addition, new hardware will provide new opportunities and challenges to improve CT with new modelling.

/pdf/modelling-the-physics-in-the-iterative-reconstruction-for-4h1h7qkdgb.pdf

Modelling the physics in the iterative reconstruction for transmission computed tomography

We present a new simulation environment for X-ray computed tomography, called CatSim. CatSim provides a research platform for GE researchers and collaborators to explore new reconstruction algorithms, CT architectures, and X-ray source or detector technologies. The main requirements for this simulator are accurate physics modeling, low computation times, and geometrical flexibility. CatSim allows simulating complex analytic phantoms, such as the FORBILD phantoms, including boxes, ellipsoids, elliptical cylinders, cones, and cut planes. CatSim incorporates polychromaticity, realistic quantum and electronic noise models, finite focal spot size and shape, finite detector cell size, detector cross-talk, detector lag or afterglow, bowtie filtration, finite detector efficiency, non-linear partial volume, scatter (variance-reduced Monte Carlo), and absorbed dose. We present an overview of CatSim along with a number of validation experiments.

CatSim: a new computer assisted tomography simulation environment

A method and apparatus include acquisition of a view dataset based on x-rays received by a detector corresponding to a energy level, reconstruction of an initial image using the view dataset, the initial image comprising a plurality of metal voxels at respective metal voxel locations, and generation of a metal mask corresponding to the plurality of metal voxels within the initial image. The method and apparatus also include forward projection of the metal mask onto the view dataset to identify metal dexels in the view dataset, performance of a weighted interpolation based on the identified metal dexels to generate a completed view dataset, reconstruction of a final image using the completed view dataset, the final image comprising a plurality of image voxels corresponding to the metal voxel locations, and replacement of a portion of the plurality of image voxels corresponding to the metal voxel locations with smoothed metal values.

Method and apparatus for reduction of metal artifacts in CT images

A data acquisition system includes a charge-sensitive amplifier (CSA) configured to receive a charge from an x-ray detector, the CSA includes a high-gain electronic voltage amplifier, an electrical energy storage device coupled with the amplifier, and an electrical resistor coupled with the amplifier. The data acquisition system includes a baseline sampling circuit configured to receive an output from the CSA and to sample a baseline signal from the CSA, at least one discriminator coupled to an output of the CSA and to an output of the baseline sampling circuit, the at least one discriminator configured to output a voltage if the output of the CSA exceeds a threshold, and a counter coupled to an output of the discriminator and configured to output a digital signal indicative of a photon count received at the x-ray detector and based on the output from the CSA and on the signal from the CSA.

Readout electronics for photon counting and energy discriminating detectors

A method for reducing bandwidth required for transmission of data in a device having two portions rotating with respect to one another. The first portion includes a data acquisition system (DAS) having a charge-to-digital converter and a digital signal processor (DSP) configured to receive and compress digital data from the charge-to-digital processor. The second portion includes a computer configured to receive data from the DAS. The DAS and computer are communicatively coupled via a slip ring having a finite transmission bandwidth. The computer is configured to reconstruct and display an image using compressed data. The method includes using the DAS to compress scan data to a predetermined number of mantissa bits and a predetermined number of exponent bits, transmitting the compressed data from the first portion to the second portion across the slip ring, and using the transmitted compressed data to reconstruct and display an image of an object.

Methods and apparatus for data communication across a slip ring

An imaging system includes an x-ray source that emits a beam of x-rays toward an object, a detector that receives high frequency electromagnetic energy attenuated by the object, a data acquisition system (DAS) operably connected to the detector, and a computer operably connected to the DAS The computer is programmed to compute detector coefficients based on a static low kVp measurement and a static high kVp measurement, capture incident spectra at high and low kVp during fast kVp switching, compute effective X-ray incident spectra at high and low kVp during fast kVp switching using the captured incident spectra, scan a water phantom and normalize the computed detector coefficients to water, adjust the computed effective X-ray incident spectra based on the normalized detector coefficients, compute basis material decomposition functions using the adjusted X-ray incident spectra, and generate one or more basis material density images using the computed basis material decomposition functions

System and method of spectral calibration and basis material decomposition for X-ray CT systems

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Naveen Chandra

Author Tools

Chat about Author