BND-VGG-19: A deep learning algorithm for COVID-19 identification utilizing X-ray images.

During the past two years, a highly infectious virus known as COVID-19 has been damaging and harming the health of people all over the world. Simultaneously, the number of patients is rising in various countries, with many new cases appearing daily, posing a significant challenge to hospital medical staff. It is necessary to improve the efficiency of virus detection. To this end, we combine modern technology and visual assistance to detect COVID-19. Based on the above facts, for accurate and rapid identification of infected persons, the BND-VGG-19 method was proposed. This method is based on VGG-19 and further incorporates batch normalization and dropout layers between the layers to improve network accuracy. Then, the COVID-19 dataset including viral pneumonia, COVID-19, and normal X-ray images, are used to diagnose lung abnormalities and test the performance of the proposed algorithm. The experimental results show the superiority of BND-VGG-19 with a 95.48% accuracy rate compared with existing COVID-19 diagnostic methods.

In vivo two-dimensional quantitative imaging of skin and cutaneous microcirculation with perturbative spatial frequency domain imaging (p-SFDI).

We introduce perturbative spatial frequency domain imaging (p-SFDI) for fast two-dimensional (2D) mapping of the optical properties and physiological characteristics of skin and cutaneous microcirculation using spatially modulated visible light. Compared to the traditional methods for recovering 2D maps through a pixel-by-pixel inversion, p-SFDI significantly shortens parameter retrieval time, largely avoids the random fitting errors caused by measurement noise, and enhances the image reconstruction quality. The efficacy of p-SFDI is demonstrated by in vivo imaging forearm of one healthy subject, recovering the 2D spatial distribution of cutaneous hemoglobin concentration, oxygen saturation, scattering properties, the melanin content, and the epidermal thickness over a large field of view. Furthermore, the temporal and spatial variations in physiological parameters under the forearm reactive hyperemia protocol are revealed, showing its applications in monitoring temporal and spatial dynamics.

Robust quantitative single-exposure laser speckle imaging with true flow speckle contrast in the temporal and spatial domains.

A systematic and robust laser speckle contrast imaging (LSCI) method and procedure is presented covering the LSCI system calibration, static scattering removal, and measurement noise estimation and correction to obtain a true flow speckle contrast K f 2 and the flow speed from single-exposure LSCI measurements. We advocate the use of K 2 as the speckle contrast instead of the conventional contrast K, as the former relates simply to the flow velocity and is with additive noise alone. We demonstrate the efficacy of the proposed true flow speckle contrast by imaging phantom flow at varying speeds, showing that (1) the proposed recipe greatly enhances the linear sensitivity of the flow index (inverse decorrelation time) and the linearity covers the full span of flow speeds from 0 to 40 mm/s; and (2) the true flow speed can be recovered regardless of the overlying static scattering layers and the type of speckle statistics (temporal or spatial). The fundamental difference between the apparent temporal and spatial speckle contrasts is further revealed. The flow index recovered in the spatial domain is much more susceptible to static scattering and exhibit a shorter linearity range than that obtained in the temporal domain. The proposed LSCI analysis framework paves the way to estimate the true flow speed in the wide array of laser speckle contrast imaging applications.

Transmission matrix-based Electric field Monte Carlo study and experimental validation of the propagation characteristics of Bessel beams in turbid media.

A novel Transmission matrix-based Electric field Monte Carlo (TEMC) method is introduced to study the propagation characteristics of Bessel beams with different orbital angular momentum (OAM) in turbid media. As an extension to the Electric field Monte Carlo (EMC) approach, electric field transmission modes were simulated to properly evaluate light interference. Beam transmission patterns, intensity attenuation, and the degree of polarization (DOP) through turbid media of varying thickness were analyzed. It was found that the OAM plays a subtle role in transmission through turbid media, showing only a weak correlation with total transmission, the preservation of DOP, and the penetration depth. The TEMC simulation results were in excellent agreement with experiments, validating the proposed method for the study of coherence phenomenon in turbid media.

Quantitative diagnosis of tissue microstructure with wide-field high spatial frequency domain imaging.

Non-contact and minimally invasive endoscopic optical imaging is an invaluable diagnostic tool for tissue examination and cancer screening. The point sampling techniques with high sensitivity to the tissue microenvironment are time consuming and often not affordable in clinics. There is a major clinical need for a large field-of-view (FOV) rapid screening method to highlight subtle tissue microstructural alterations. To address this unmet need, we have developed High Spatial Frequency Domain Imaging (HSFDI)-a non-contact imaging modality that spatially maps the tissue microscopic scattering structures over a large field of view (>1cm2). Based on an analytical reflectance model of sub-diffusive light from forward-peaked highly scattering media, HSFDI quantifies the spatially-resolved parameters of the light scattering phase function (i.e., the backscattering probability and the light spreading length) from the reflectance of structured light modulated at high spatial frequencies. Enhanced signal to noise ratio (SNR) is achieved at even ultra-high modulation frequencies with single snapshot multiple frequency demodulation (SSMD). The variations in tissue microstructures, including the strength of the background (pudding) refractive index fluctuation and the prominent scattering structure (plum) morphology, can then be inferred. After validation with optical phantoms, measurements of fresh ex vivo tissue samples revealed significant contrast and differentiation of the phase function parameters between different types and disease states (normal, inflammatory, and cancerous) of tissue whereas tissue absorption and reduced scattering coefficients only show modest changes. HSFDI may provide wide-field images of microscopic structural biomarkers unobtainable with either diffuse light imaging or point-based optical sampling. Potential clinical applications include the rapid screening of excised tissue and the noninvasive examination of suspicious lesions during operation.

Trapping two types of particles by modified circular Airy beams.

The radiation force of modified circular Airy beams (MCAB) exerted on both a high-refractive-index particle and a low-refractive-index particle are analyzed in this paper. Our results show that the two kinds of particles can be simultaneously stably trapped by MCAB at different positions. Compared with the common circular Airy beams (CAB) with the same parameters, trapping forces on the two kinds of particles are greatly increased because of the enhanced abruptly autofocusing property and the appearance of hollow region in MCAB. The trapping forces can be modulated by varying parameters of MCAB, and it is important to choose appropriate parameters to trap particles in practice.