CNN-KCL: Automatic myocarditis diagnosis using convolutional neural network combined with k-means clustering

<abstract> <p>Myocarditis is the form of an inflammation of the middle layer of the heart wall which is caused by a viral infection and can affect the heart muscle and its electrical system. It has remained one of the most challenging diagnoses in cardiology. Myocardial is the prime cause of unexpected death in approximately 20% of adults less than 40 years of age. Cardiac MRI (CMR) has been considered a noninvasive and golden standard diagnostic tool for suspected myocarditis and plays an indispensable role in diagnosing various cardiac diseases. However, the performance of CMR depends heavily on the clinical presentation and features such as chest pain, arrhythmia, and heart failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, and more importantly qualitatively visual interpretation can affect the result of the diagnosis. This paper introduces a new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose Myocarditis. In this study, we used 47 subjects with a total number of 98,898 images to diagnose myocarditis disease. Our results demonstrate that the proposed method achieves an accuracy of 97.41% based on 10 fold-cross validation technique with 4 clusters for diagnosis of Myocarditis. To the best of our knowledge, this research is the first to use deep learning algorithms for the diagnosis of myocarditis.</p> </abstract>

Increasing of the Accuracy of Signalsʼ Time Parameters Measuring Using Double Pulse Trains

In modern diagnostics, much attention is paid to measuring of time parameters, as well as their change over time. The purpose of this work is to develop a method for measuring of time intervals which made it possible to increase the measurement accuracy by reducing errors associated with the instability of main parameters of the pulse signal.In the most of approaches used, the error associated with the instability of main parameters of signals under study is not enough taken into account. As an alternative, a spectral method is proposed in which the measurement of time intervals, as well as their changes, is performed based on the analysis of pulse sequences formed on the basis of characteristic points of the measured signal. For this a double pulse sequence was considered, an equation for the amplitudes of its spectral components was obtained, and in accordance with this it was determined that the delay time between double pulses is the most informative parameter.Using the Mathcad software, an analysis of the sensitivity regions was carried out for the change in the main parameters of the pulse sequence, namely the repetition rate, as the main destabilizing factor.As a result of the implementation of the developed technique, a structural diagram of the measuring system is proposed and an analysis of the measurement error associated with the instability of the main parameters of the pulse sequence is carried out. This error is estimated to be less than 0.01 %.The considered method makes it possible to increase the accuracy of measuring time intervals due to the almost complete elimination of the influence of the instability of the reference frequency and the amplitude of the generated pulses which is unattainable with modern hardware, including digital signal processing.

Slice-direction geometric distortion evaluation and correction with reversed slice-select gradient acquisitions

Accurate spatial alignment of MRI data acquired across multiple contrasts in the same subject is often crucial for data analysis and interpretation, but can be challenging in the presence of geometric distortions that differ between acquisitions. It is well known that single-shot echo-planar imaging (EPI) acquisitions suffer from distortion in the phase-encoding direction due to B0 field inhomogeneities arising from tissue magnetic susceptibility differences and other sources, however there can be distortion in other encoding directions as well in the presence of strong field homogeneities. High-resolution ultrahigh-field MRI typically uses low bandwidth in the slice-encoding direction to acquire thin slices and, when combined with the pronounced B0 inhomogeneities, is prone to an additional geometric distortion in the slice direction as well. Here we demonstrate a presence of this slice distortion in high-resolution 7T EPI acquired with a novel pulse sequence allowing for the reversal of the slice-encoding gradient polarity that enables the acquisition of pairs of images with equal magnitudes of distortion in the slice direction but with opposing polarities. We also show that the slice-direction distortion can be corrected using gradient reversal-based method applying the same software used for conventional corrections of phase-encoding direction distortion.

Mo:BiVO4 Nanoparticles-Based Optical Modulator and Its Application in a 2-μm Pulsed Laser

Mo:BiVO4 nanoparticles were employed as an optical modulator in a Q-switched all-solid-state Tm:YAP laser for the first time. The nonlinear optical parameters of Mo:BiVO4 nanoparticles in the 2-μm region were characterized by measuring nonlinear transmission. Saturation intensity was 718 MW/cm2, and the modulation depth was 12.3%. A stable pulse sequence was acquired with a 70.08 kHz maximum repetition rate and an 821 ns pulse width. The maximum output average power was 153 mW, corresponding to 2.18 μJ single pulse energy and 2.67 W peak power. Although the response wavelength of Mo:BiVO4 is in visible light region, our experimental results demonstrates that a saturable absorption effect for wavelengths much longer than visible light (2 μm wavelength) is still possible due to sub-bandgap absorption. Therefore, we experimentally proved that Mo:BiVO4 nanoparticles are a great candidate for use as an optical modulator of a 2-μm pulsed laser.

Signal-to-noise ratio uniformity and stability of agar gel phantom with iron (III) oxide as relaxation modifier

Background Agar has been commonly used as one of the materials to fabricate magnetic resonance imaging phantoms in the past few decades. In this study, eleven agar gel phantoms with different iron (III) oxide (Fe2O3) masses were prepared. This study was aimed to evaluate the signal-to-noise ratio (SNR) uniformity and stability of agar gel phantoms with and without the addition of Fe2O3 at two different time points (TPs). Fe2O3 powder was used as a relaxation modifier to manipulate and produce various SNR, T1 and T2 values. These phantoms were scanned using turbo spin echo pulse sequence to produce T1- and T2-measurement images. The SNR was then computed by plotting 1, 3 and 25 regions of interest on the images using ImageJ software. The T1 and T2 relaxation equations were then fitted to the experimental results of SNR versus TR and SNR versus TE curves for the determination of saturation (SNRo), T1 and T2 values. Results The results demonstrated that the agar gel phantoms were able to maintain SNR uniformity but not SNR stability after 4 weeks of phantom preparation. The change in the water content and microstructure of the phantoms have no significant effect on T2 relaxation but on T1 relaxation. The T1 and T2 of the agar gel phantoms were minimally affected although there was a systemic increase in the content of the Fe2O3 powder. Conclusions It can be concluded that the agar gel phantoms exhibited the characteristics of SNR uniformity, but they showed instability of SNR at TP2. The Fe2O3 in powder form is not an effective relaxation modifier to reduce the T1 and T2 when it is introduced into the agar gel phantoms. Dissolved nanosized particles should be the focus of future studies.

Micromotion minimization using Ramsey interferometry

We minimize the stray electric field in a linear Paul trap quickly and accurately, by applying interferometry pulse sequences to a trapped ion optical qubit. The interferometry sequences are sensitive to the change of ion equilibrium position when the trap stiffness is changed, and we use this to determine the stray electric field. The simplest pulse sequence is a two-pulse Ramsey sequence, and longer sequences with multiple pulses offer a higher precision. The methods allow the stray field strength to be minimized beyond state-of-the-art levels. Using a sequence of nine pulses we reduce the 2D stray field strength to (10.5±0.8)mVm-1 in 11s measurement time. The pulse sequences are easy to implement and automate, and they are robust against laser detuning and pulse area errors. We use interferometry sequences with different lengths and precisions to measure the stray field with an uncertainty below the standard quantum limit. This marks a real-world case in which quantum metrology offers a significant enhancement. Also, we minimize micromotion in 2D using a single probe laser, by using an interferometry method together with the resolved sideband method; this is useful for experiments with restricted optical access. Furthermore, a technique presented in this work is related to quantum protocols for synchronizing clocks; we demonstrate these protocols here.

Construction of 3D model of knee joint motion based on MRI image registration

There is a growing demand for information and computational technology for surgeons help with surgical planning as well as prosthetics design. The two-dimensional images are registered to the three-dimensional (3D) model for high efficiency. To reconstruct the 3D model of knee joint including bone structure and main soft tissue structure, the evaluation and analysis of sports injury and rehabilitation treatment are detailed in this study. Mimics 10.0 was used to reconstruct the bone structure, ligament, and meniscus according to the pulse diffusion-weighted imaging sequence (PDWI) and stir sequences of magnetic resonance imaging (MRI). Excluding congenital malformations and diseases of the skeletal muscle system, MRI scanning was performed on bilateral knee joints. Proton weighted sequence (PDWI sequence) and stir pulse sequence were selected for MRI. The models were imported into Geomagic Studio 11 software for refinement and modification, and 3D registration of bone structure and main soft tissue structure was performed to construct a digital model of knee joint bone structure and accessory cartilage and ligament structure. The 3D knee joint model including bone, meniscus, and collateral ligament was established. Reconstruction and image registration based on mimics and Geomagic Studio can build a 3D model of knee joint with satisfactory morphology, which can meet the requirements of teaching, motion simulation, and biomechanical analysis.

A New Approach to the Development of Additive Fibonacci Generators Based on Prime Numbers

Pseudorandom number and bit sequence generators are widely used in cybersecurity, measurement, and other technology fields. A special place among such generators is occupied by additive Fibonacci generators (AFG). By itself, such a generator is not cryptographically strong. Nevertheless, when used as a primary it can be quite resistant to cryptanalysis generators. This paper proposes a modification to AGF, the essence of which is to use prime numbers as modules of recurrent equations describing the operation of generators. This modification made it possible to ensure the constancy of the repetition period of the output pseudorandom pulse sequence in the entire range of possible values of the initial settings–keys (seed) at specific values of the module. In addition, it has proposed a new generator scheme, which consists of two generators: the first of which is based on a modified AFG and the second is based on a linear feedback shift register (LFSR). The output pulses of both generators are combined through a logic element XOR. The results of the experiment show that the specific values of modules provide a constant repetition period of the output pseudorandom pulse sequence in a whole range of possible values of the initial settings–keys (seed) and provide all the requirements of the NIST test to statistical characteristics of the sequence. Modified AFGs are designed primarily for hardware implementation, which allows them to provide high performance.