Visual Computing for Industry, Biomedicine, and Art最新文献

Although the education sector is improving more quickly than ever with the help of advancing technologies, there are still many areas yet to be discovered, and there will always be room for further enhancements. Two of the most disruptive technologies, machine learning (ML) and blockchain, have helped replace conventional approaches used in the education sector with highly technical and effective methods. In this study, a system is proposed that combines these two radiant technologies and helps resolve problems such as forgeries of educational records and fake degrees. The idea here is that if these technologies can be merged and a system can be developed that uses blockchain to store student data and ML to accurately predict the future job roles for students after graduation, the problems of further counterfeiting and insecurity in the student achievements can be avoided. Further, ML models will be used to train and predict valid data. This system will provide the university with an official decentralized database of student records who have graduated from there. In addition, this system provides employers with a platform where the educational records of the employees can be verified. Students can share their educational information in their e-portfolios on platforms such as LinkedIn, which is a platform for managing professional profiles. This allows students, companies, and other industries to find approval for student data more easily.

When the object contains metals, its x-ray computed tomography (CT) images are normally affected by streaking artifacts. These artifacts are mainly caused by the x-ray beam hardening effects, which deviate the measurements from their true values. One interesting observation of the metal artifacts is that certain regions of the metal artifacts often appear as negative pixel values. Our novel idea in this paper is to set up an objective function that restricts the negative pixel values in the image. We must point out that the naïve idea of setting the negative pixel values in the reconstructed image to zero does not give the same result. This paper proposes an iterative algorithm to optimize this objective function, and the unknowns are the metal affected projections. Once the metal affected projections are estimated, the filtered backprojection algorithm is used to reconstruct the final image. This paper applies the proposed algorithm to some airport bag CT scans. The bags all contain unknown metallic objects. The metal artifacts are effectively reduced by the proposed algorithm.

Photoacoustic (PA) microscopy is being increasingly used to visualize the microcirculation of the brain cortex at the micron level in living rodents. By combining it with long-term cranial window techniques, vasculature can be monitored over a period of days extending to months through a field of view. To fulfill the requirements of long-term in vivo PA imaging, the cranial window must involve a simple and rapid surgical procedure, biological compatibility, and sufficient optical-acoustic transparency, which are major challenges. Recently, several cranial window techniques have been reported for longitudinal PA imaging. Here, the development of chronic cranial windows for PA imaging is reviewed and its technical details are discussed, including window installation, imaging quality, and longitudinal stability.

A numerical simulation of a patient's nasal airflow was developed via computational fluid dynamics. Accordingly, computerized tomography scans of a patient with septal deviation and allergic rhinitis were obtained. The three-dimensional (3D) nasal model was designed using InVesalius 3.0, which was then imported to (computer aided 3D interactive application) CATIA V5 for modification, and finally to analysis system (ANSYS) flow oriented logistics upgrade for enterprise networks (FLUENT) to obtain the numerical solution. The velocity contours of the cross-sectional area were analyzed on four main surfaces: the vestibule, nasal valve, middle turbinate, and nasopharynx. The pressure and velocity characteristics were assessed at both laminar and turbulent mass flow rates for both the standardized and the patient's model nasal cavity. The developed model of the patient is approximately half the size of the standardized model; hence, its velocity was approximately two times more than that of the standardized model.

A neural network is one of the current trends in deep learning, which is increasingly gaining attention owing to its contribution in transforming the different facets of human life. It also paves a way to approach the current crisis caused by the coronavirus disease (COVID-19) from all scientific directions. Convolutional neural network (CNN), a type of neural network, is extensively applied in the medical field, and is particularly useful in the current COVID-19 pandemic. In this article, we present the application of CNNs for the diagnosis and prognosis of COVID-19 using X-ray and computed tomography (CT) images of COVID-19 patients. The CNN models discussed in this review were mainly developed for the detection, classification, and segmentation of COVID-19 images. The base models used for detection and classification were AlexNet, Visual Geometry Group Network with 16 layers, residual network, DensNet, GoogLeNet, MobileNet, Inception, and extreme Inception. U-Net and voxel-based broad learning network were used for segmentation. Even with limited datasets, these methods proved to be beneficial for efficiently identifying the occurrence of COVID-19. To further validate these observations, we conducted an experimental study using a simple CNN framework for the binary classification of COVID-19 CT images. We achieved an accuracy of 93% with an F1-score of 0.93. Thus, with the availability of improved medical image datasets, it is evident that CNNs are very useful for the efficient diagnosis and prognosis of COVID-19.

Fiber laser technology has experienced a rapid growth over the past decade owing to increased applications in precision measurement and optical testing, medical care, and industrial applications, including laser welding, cleaning, and manufacturing. A fiber laser can output laser pulses with high energy, a high repetition rate, a controllable wavelength, low noise, and good beam quality, making it applicable in photoacoustic imaging. Herein, recent developments in fiber-laser-based photoacoustic microscopy (PAM) are reviewed. Multispectral PAM can be used to image oxygen saturation or lipid-rich biological tissues by applying a Q-switched fiber laser, a stimulated Raman scattering-based laser source, or a fiber-based supercontinuum source for photoacoustic excitation. PAM can also incorporate a single-mode fiber laser cavity as a high-sensitivity ultrasound sensor by measuring the acoustically induced lasing-frequency shift. Because of their small size and high flexibility, compact head-mounted, wearable, or hand-held imaging modalities and better photoacoustic endoscopes can be enabled using fiber-laser-based PAM.

A crime is a deliberate act that can cause physical or psychological harm, as well as property damage or loss, and can lead to punishment by a state or other authority according to the severity of the crime. The number and forms of criminal activities are increasing at an alarming rate, forcing agencies to develop efficient methods to take preventive measures. In the current scenario of rapidly increasing crime, traditional crime-solving techniques are unable to deliver results, being slow paced and less efficient. Thus, if we can come up with ways to predict crime, in detail, before it occurs, or come up with a "machine" that can assist police officers, it would lift the burden of police and help in preventing crimes. To achieve this, we suggest including machine learning (ML) and computer vision algorithms and techniques. In this paper, we describe the results of certain cases where such approaches were used, and which motivated us to pursue further research in this field. The main reason for the change in crime detection and prevention lies in the before and after statistical observations of the authorities using such techniques. The sole purpose of this study is to determine how a combination of ML and computer vision can be used by law agencies or authorities to detect, prevent, and solve crimes at a much more accurate and faster rate. In summary, ML and computer vision techniques can bring about an evolution in law agencies.