scholarly journals A Survey on Artificial Intelligence in Chest Imaging of COVID-19

2020 ◽  
Vol 1 (3) ◽  
pp. 137-146
Author(s):  
Yun Chen ◽  
Gongfa Jiang ◽  
Yue Li ◽  
Yutao Tang ◽  
Yanfang Xu ◽  
...  

Abstract The coronavirus disease 2019 (COVID-19) has infected more than 9.3 million people and has caused over 0.47 million deaths worldwide as of June 24, 2020. Chest imaging techniques including computed tomography and X-ray scans are indispensable tools in COVID-19 diagnosis and its management. The strong infectiousness of this disease brings a huge burden for radiologists. In order to overcome the difficulty and improve accuracy of the diagnosis, artificial intelligence (AI)-based imaging analysis methods are explored. This survey focuses on the development of chest imaging analysis methods based on AI for COVID-19 in the past few months. Specially, we first recall imaging analysis methods of two typical viral pneumonias, which can provide a reference for studying the disease on chest images. We further describe the development of AI-assisted diagnosis and assessment for the disease, and find that AI techniques have great advantage in this application.

Author(s):  
Saadet Sena Egeli ◽  
Yalcin Isler

Discovery of X-Rays is the beginning point of the medical imaging which developed and diversified in years. Since early days of X-Ray discovery they are used in also for imaging of teeth, in 1896, Dr. Otto Walkhoff imaged his mouth with X-Ray exposure. X-Rays helped the dentists to diagnose tooth decays and bone loss, examine dental structures and identify abnormalities of these structures. Today developments in technology resulted in different imaging techniques, X-Rays are used for Projectional Radiography and Computed Tomography, besides there are Nuclear Imaging, Magnetic Resonance Imaging and Ultrasound Imaging that widely used. In this review, imaging techniques for dental applications with the extension of artificial intelligence is examined to provide a brief information.


2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Pasquale Delogu ◽  
Vittorio Di Trapani ◽  
Luca Brombal ◽  
Giovanni Mettivier ◽  
Angelo Taibi ◽  
...  

Abstract The limits of mammography have led to an increasing interest on possible alternatives such as the breast Computed Tomography (bCT). The common goal of all X-ray imaging techniques is to achieve the optimal contrast resolution, measured through the Contrast to Noise Ratio (CNR), while minimizing the radiological risks, quantified by the dose. Both dose and CNR depend on the energy and the intensity of the X-rays employed for the specific imaging technique. Some attempts to determine an optimal energy for bCT have suggested the range 22 keV–34 keV, some others instead suggested the range 50 keV–60 keV depending on the parameters considered in the study. Recent experimental works, based on the use of monochromatic radiation and breast specimens, show that energies around 32 keV give better image quality respect to setups based on higher energies. In this paper we report a systematic study aiming at defining the range of energies that maximizes the CNR at fixed dose in bCT. The study evaluates several compositions and diameters of the breast and includes various reconstruction algorithms as well as different dose levels. The results show that a good compromise between CNR and dose is obtained using energies around 28 keV.


2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Stephanie Kulpe ◽  
Martin Dierolf ◽  
Benedikt Günther ◽  
Madleen Busse ◽  
Klaus Achterhold ◽  
...  

Abstract In clinical diagnosis, X-ray computed tomography (CT) is one of the most important imaging techniques. Yet, this method lacks the ability to differentiate similarly absorbing substances like commonly used iodine contrast agent and calcium which is typically seen in calcifications, kidney stones and bones. K-edge subtraction (KES) imaging can help distinguish these materials by subtracting two CT scans recorded at different X-ray energies. So far, this method mostly relies on monochromatic X-rays produced at large synchrotron facilities. Here, we present the first proof-of-principle experiment of a filter-based KES CT method performed at a compact synchrotron X-ray source based on inverse-Compton scattering, the Munich Compact Light Source (MuCLS). It is shown that iodine contrast agent and calcium can be clearly separated to provide CT volumes only showing one of the two materials. These results demonstrate that KES CT at a compact synchrotron source can become an important tool in pre-clinical research.


2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Márton Szabó ◽  
Robin Kundrata ◽  
Johana Hoffmannova ◽  
Tamás Németh ◽  
Emese Bodor ◽  
...  

AbstractFossil bioinclusions in amber are invaluable source of information on the past evolution and diversity of various organisms, as well as on the paleoecosystems in general. The click-beetles, Elateridae, which originated and greatly diversified during the Mesozoic, are mostly known from the adpression-like fossils, and their diversity in the Cretaceous ambers is only poorly documented. In this study, we describe a new click-beetle based on an incomplete inclusion in ajkaite, an Upper Cretaceous (Santonian) amber from the Ajka Coal Formation from Hungary. We used X-ray micro-computed tomography scanning to reconstruct its morphology because it is deposited in an opaque piece of amber. Our results suggest that the newly described Ajkaelater merkli gen. et sp. nov. belongs to subfamily Elaterinae. It represents the first Mesozoic beetle reported from Hungary, and the first Mesozoic Elateridae formally described from mainland Europe. Our discovery supports an Eurasian distribution and diversification of Elaterinae already in the Cretaceous. The paleoenvironment of the Ajka Coal Formation agrees well with the presumed habitat preference of the new fossil taxon. The discovery of a presumably saproxylic click-beetle shed further light on the yet poorly known paleoecosystem of the Santonian present-day western Hungary.


Author(s):  
Riemer H. J. A. Slart ◽  
Michelle C. Williams ◽  
Luis Eduardo Juarez-Orozco ◽  
Christoph Rischpler ◽  
Marc R. Dweck ◽  
...  

AbstractIn daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.


2021 ◽  
Author(s):  
Konstantin Willer ◽  
Alexander Fingerle ◽  
Wolfgang Noichl ◽  
Fabio De Marco ◽  
Manuela Frank ◽  
...  

SummaryBackgroundDiseases of the respiratory system are leading global causes of chronic morbidity and mortality. While advanced medical imaging technologies of today deliver detailed diagnostic information, a low-dose, fast, and inexpensive option for early detection and/or follow-ups is still lacking. Here, we report on the first human application of a novel modality, namely X-ray dark-field chest imaging, which might fill this gap. Enabling the assessment of microstructural changes in lung parenchyma, this technique presents a more sensitive alternative to conventional chest X-rays, and yet requires only a fraction of the dose applied in computed tomography (CT).MethodsFor this first clinical evaluation, we have built a novel dark-field chest X-ray system, which is also capable of simultaneously acquiring a conventional thorax radiograph (7 seconds, 0·035 mSv effective dose). Representing a major medical condition, we selected chronic obstructive pulmonary disease as study subject to obtain a first impression of potential diagnostic benefits relevant to humans. For a collective of 77 patients with different disease stages, X-ray dark-field- and CT-images were acquired and visually assessed by 5 readers. In addition, pulmonary function tests were performed for every patient. The individual data sets were evaluated in a statistical work-up using correlation testing, rank-based analysis of variance, and pair-wise post-hoc comparison.FindingsCompared to CT-based parameters (quantitative emphysema: ρ=–0·27, p=0·0893 and visual emphysema: ρ=–0·45, p=0·0028), the dark-field signal (ρ=0·62, p<0·0001) yields a stronger correlation with diffusion capacity in the evaluated collective. Emphysema assessment based on dark-field chest X-ray features yields consistent conclusions with findings from visual CT image interpretation and shows improved diagnostic performance in comparison to conventional clinical tests characterizing emphysema.InterpretationX-ray dark-field chest imaging allows the diagnosis of pulmonary emphysema as it provides relevant information representing the structural condition of lung parenchyma. Significant diagnostic benefits are also expected for other lung disorders.FundingEuropean Research Council, Royal Philips, Karlsruhe Nano Micro Facility.Research in contextEvidence before this studyWith a rising number of examinations in the last decades, X-rays play an indispensable role in clinical routine. Contrast formation in medical X-ray imaging such as radiography, fluoroscopy, and computed tomography is based on attenuation, which generally benefits from large differences in atomic number and/or mass density between involved materials. If these conditions are not prevalent, or the resolution of the imaging system is not sufficient, diagnostic capabilities are limited. However, attenuation is not the only physical effect X-rays are subjected to when penetrating matter. Variations in an object’s electron density lead to refraction and coherent small-angle scattering of incident X-rays. Phase-sensitive imaging techniques can detect these wave-optical phenomena, yielding additional object information. The dark-field signal, being a function of small-angle scattering, can provide structural information on the micron scale, generally below the resolution limit of the imaging system. Due to their very stringent requirements to X-ray source coherence, these techniques were originally limited to large-scale synchrotron facilities. The proposal of a three-grating interferometer in 2006, however, enabled the use of low-brilliance sources for X-ray phase-contrast imaging and thereby paved the way into the clinics. Such an apparatus elegantly allows the simultaneous acquisition of the conventional attenuation, differential phase-contrast, and novel dark-field signals. In a compact table-top system suitable for investigating murine disease models, numerous studies on pulmonary disorders such as chronic obstructive pulmonary disease (COPD), pulmonary fibrosis, pneumothorax, ventilator-associated lung injury, lung cancer, and pneumonia have been conducted and demonstrated a broad diagnostic value of the dark-field modality in particular. Adapting the system to enable imaging of the human body is a technical challenge due to limitations of the micrometer-fine, high aspect ratio grating structures in terms of fabricable size and performance at clinically relevant X-ray energies. The first evidences that these limitations are manageable were delivered in 2017 and 2018 by in-vivo porcine and human cadaver studies with an experimental prototype system.Added value of this studyWith this work we present the first X-ray dark-field chest images of human subjects in-vivo and demonstrate the method’s feasibility in a clinical surrounding. To enable this study, we have conceived, constructed, and commissioned a custom-built first demonstrator system suitable for patient use. This includes satisfying clinical demands regarding safety, usability, acquisition time, radiation dose, field of view, and image quality. This study marks the transition from investigating artificially induced disease models to evaluating the modality’s actual diagnostic performance in patients.Implications of all available evidenceOur findings indicate that X-ray dark-field radiography provides image-type information of the lungs’ underlying microstructure in humans. In view of the strong link between alveolar structure and the functional condition of the lung, this capability is highly relevant for respiratory medicine and might help to establish a better understanding of pulmonary disorders. With regard to early detection of COPD, which is generally accompanied by structural impairments of the lung, this novel technique might support resolving the prevalent under-diagnosis reported in literature. With an effective dose significantly lower (about a factor of hundred) compared to thorax computed tomography, dark-field radiography could be used as broadly deployed screening tool.


2021 ◽  
Vol 23 (4) ◽  
pp. 372-381
Author(s):  
Aleksandr A. Melnikov ◽  
◽  
Viktor V. Diachenko ◽  
Igor V. Shubin ◽  
Aleksei E. Nikitin ◽  
...  

The review provides the literature data on the basal issues of bone remodeling and the applied use of medical imaging techniques for the prevention of clinically significant consequences of osteoporosis. The article discusses the role and prospects of using the method of quantitative computed tomography and its modifications for the diagnosis of osteoporosis and osteopenic syndrome. It considers the advantages of quantitative computed tomography over widely used medical techniques for assessing bone mineral density (mono- and dual-energy X-ray absorptiometry, mono- and dual-energy isotope absorptiometry).


2020 ◽  
Author(s):  
Neil Marr ◽  
Mark Hopkinson ◽  
Andrew P. Hibbert ◽  
Andrew A. Pitsillides ◽  
Chavaunne T. Thorpe

ABSTRACTBACKGROUND3-dimensional imaging modalities for optically dense connective tissues such as tendons are limited and typically have a single imaging methodological endpoint. Here, we have developed a bimodal procedure that utilises fluorescence-based confocal microscopy and x-ray micro-computed tomography for the imaging of adult tendons to visualise and analyse extracellular sub-structure and cellular composition in small and large animal species.RESULTSUsing fluorescent immunolabelling and optical clearing, we visualised the expression of the basement membrane protein laminin-α4 in 3D throughout whole rat Achilles tendons and equine superficial digital flexor tendon 5 mm segments. This revealed a complex network of laminin-α4 within the tendon core that predominantly localises to the interfascicular matrix compartment. Furthermore, we implemented a chemical drying process capable of creating contrast densities enabling visualisation and quantification of both fascicular and interfascicular matrix volume and thickness by x-ray micro-computed tomography. We also demonstrated that both modalities can be combined using reverse clarification of fluorescently labelled tissues prior to chemical drying to enable bimodal imaging of a single sample.CONCLUSIONSWhole-mount imaging of tendon allowed us to identify the presence of an extensive network of laminin-α4 within tendon, the complexity of which cannot be appreciated using traditional 2D imaging techniques. Creating contrast for x-ray micro-computed tomography imaging of tendon using chemical drying is not only simple and rapid, but also markedly improves on previously published methods. Combining these methods provides the ability to gain spatio-temporal information and quantify tendon substructures to elucidate the relationship between morphology and function.


Membranes ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 905
Author(s):  
Thomas F. Johnson ◽  
Kyle Jones ◽  
Francesco Iacoviello ◽  
Stephen Turner ◽  
Nigel B. Jackson ◽  
...  

Two high resolution, 3D imaging techniques were applied to visualize and characterize sterilizing grade dual-layer filtration of liposomes, enabling membrane structure to be related with function and performance. Two polyethersulfone membranes with nominal retention ratings of 650 nm and 200 nm were used to filter liposomes of an average diameter of 143 nm and a polydispersity index of 0.1. Operating conditions including differential pressure were evaluated. X-ray computed tomography at a pixel size of 63 nm was capable of resolving the internal geometry of each membrane. The respective asymmetry and symmetry of the upstream and downstream membranes could be measured, with pore network modeling used to identify pore sizes as a function of distance through the imaged volume. Reconstructed 3D digital datasets were the basis of tortuous flow simulation through each porous structure. Confocal microscopy visualized liposome retention within each membrane using fluorescent dyes, with bacterial challenges also performed. It was found that increasing pressure drop from 0.07 MPa to 0.21 MPa resulted in differing fluorescent retention profiles in the upstream membrane. These results highlighted the capability for complementary imaging approaches to deepen understanding of liposome sterilizing grade filtration.


Sign in / Sign up

Export Citation Format

Share Document