Abstract: Deep convolutional neural network (DCNN) models have been widely explored for skin disease diagnosis and some of them have achieved the diagnostic outcomes comparable or even superior to those of dermatologists. However, broad implementation of DCNN in skin disease detection is hindered by small size and data imbalance of the publically accessible skin lesion datasets. This paper proposes a novel single-model based strategy for classification of skin lesions on small and imbalanced datasets. First, various DCNNs are trained on different small and imbalanced datasets to verify that the models with moderate complexity outperform the larger models. Second, regularization DropOut and DropBlock are added to reduce overfitting and a Modified RandAugment augmentation strategy is propose

Abstract: BACKGROUND: Lack of intuitiveness and poor hand-eye coordination present a major technical challenge in neurosurgical navigation. METHODS: We developed an integrated dexterous stereotactic co-axial projection imaging (sCPI) system featuring orthotopic image projection for augmented reality (AR) neurosurgical navigation. The performance characteristics of the sCPI system, including projection resolution and navigation accuracy, were quantitatively verified. The resolution of the sCPI was tested with a USAF1951 resolution test chart. The stereotactic navigation accuracy of the sCPI was measured using a calibration panel with a 7x7 circle array pattern. In benchtop validation, the navigation accuracy of the sCPI and the BrainLab Kick Navigation Station was compared using a skull pha

Abstract: Objective and Impact Statement. There is a need to develop high-performance and low-cost data augmentation strategies for intelligent skin cancer screening devices that can be deployed in rural or underdeveloped communities. The proposed strategy can not only improve the classification performance of skin lesions but also highlight the potential regions of interest for clinicians' attention. This strategy can also be implemented in a broad range of clinical disciplines for early screening and automatic diagnosis of many other diseases in low resource settings. Methods. We propose a high-performance data augmentation strategy of search space 10(1), which can be combined with any model through a plug-and-play mode and search for the best argumentation method for a medical database

Abstract: PURPOSE: The purpose of this study is to investigate the retinal vascular morphological characteristics in high myopia patients of different severity. METHODS: 317 eyes of high myopia patients and 104 eyes of healthy control subjects were included in this study. The severity of high myopia patients is classified into C0-C4 according to the Meta Analysis of the Pathologic Myopia (META-PM) classification and their vascular morphological characteristics in ultra-wide field imaging were analyzed using transfer learning methods and RU-net. Correlation with axial length (AL), best corrected visual acuity (BCVA) and age was analyzed. In addition, the vascular morphological characteristics of myopic choroidal neovascularization (mCNV) patients and their matched high myopia patients were

Abstract: Traditional line-scan Raman imaging features a rapid imaging speed while preserving complete spectral information, yet has diffraction-limited resolution. Sinusoidally structured line excitation can yield an improvement in the lateral resolution of the Raman image along the line's direction. However, given the need for the line and spectrometer slit to be aligned, the resolution in the perpendicular direction remains diffraction limited. To overcome this, we present here a galvo-modulated structured line imaging system, where a system of three galvos can arbitrarily orient the structured line on the sample plane, while keeping the beam aligned to the spectrometer slit in the detection plane. Thus, a two-fold isotropic improvement in the lateral resolution fold is possible. We dem

Abstract: In quest of an efficient delivery system and for accurate delivery of drug to the ailment site, various researchers focused on development of a versatile delivery system. In progression, investigations on novel materials gained spotlight to add new dimension in the delivery devices to provide a more compatible and innovative platform for drug delivery. For innovative delivery systems, biomaterials like nanocelluloses were exploited for designing various scaffolds and delivery devices like microneedles. Microneedle devices are current trends of drug delivery where nanocellulose has evolved as protagonist for delivery aspects andstrengthen the structural integrity of device. Nanocelluloses provided a wide choice for polymers to design biodegradable microneedle device. Nanocellulose

Abstract: BACKGROUND: Near-infrared (NIR) autofluorescence detection is an effective method for identifying parathyroid glands (PGs) in thyroidectomy or parathyroidectomy. Fiber optical probes provide quantitative autofluorescence measurements for PG detection owing to its high sensitivity and high excitation light cut-off efficiency at a fixed detection distance. However, an optical fiber probe lacks the imaging capability and cannot map the autofluorescence distribution on top of normal tissue background. Therefore, there is a need for intraoperative mapping of PGs with high sensitivity and imaging resolution. METHODS: We have developed a fluorescence scanning and projection (FSP) system that combines a scanning probe and a co-axial projector for intraoperative localization and in situ d

Abstract: Electrospun nanofibrous mats (ENM) have been extensively used for removal of suspended particles, cells and bacteria in membrane filtration because of its high porosity and permeability. However, microfiltration process is driven by a certain transmembrane pressure, and the filtration performance of traditional ENM are thereby hindered by its limited mechanical property. In this study, we propose a new strategy that sandwich the ENM between two layers of electrospray-deposited microparticles to enhance the mechanical properties of ENM membrane. Through a suitable thermal treatment, the microparticles stick with each other forming firm networks, while the ENM is rarely influenced. The mechanical tests show that the tensile strength and elastic modulus of the sandwich-structure com

Abstract: Collecting water from fog by microscale fibrous materials is a promising solution to the global water scarcity crisis. However, the previously designed fog harvesting microfibers solely imitate the characteristic structure of the wetted spider silk and have a limited water collection ability. To improve the water collection efficiency, we introduce a dynamic interfacial spinning (DIS) process to fabricate a novel type of fog harvesting microfibers that combine multiple biomimetic structures. Specifically, the DIS process utilizes a tunable vibration of the spinning nozzle at the air–liquid interface to facilitate the facile and controllable generation of the spider-silk-like microfibers consisting of periodic spindle knots and slender joints. Attributed to their distinct surface

Abstract: In gas-driven flow focusing, mechanical disturbance is applied to modulate formation of droplets under the condition that the jet breaks at a high speed. By changing the conditions of jet generation, a systematic experimental study of the relevant parameters is carried out. In the axisymmetric mode, the diameter and velocity of the jet are affected by changing the flow rate and pressure drop condition. The results show that the jet can be regulated in a very large range, and the size of the generated droplets can also be accurately predicted. For viscous liquids, mechanical disturbances can also be used to make them break uniformly within a certain range. Due to the high frequency and precise controllability of droplet preparation in the experiment, these findings can be extended

Abstract: Engineering high-performance cathodes for high energy-density lithium-sulfur (Li-S) batteries is quite significant to achieve commercialization. Here, we develop a graphene oxide scaffold/sulfur composite-encapsulated microcapsule (GSM) for high-performance Li-S batteries, which is prepared through the co-flow focusing (CFF) approach. The GSM-based cathode displays a high capacity of 1004 mA h g(-1) at 0.2C after cycling 200 times, a long-term cycling stability after 1000 cycles at 2C, and a good rate-performance. At temperatures of -5 degrees C and 45 degrees C, the electrochemical performance is also excellent. The computational calculations based on density functional theory (DFT) verify the high adsorption energies of the microcapsules towards polysulfides, suppressing the sh

Abstract: Though widely used, most deep convolutional neural networks fail to capture prediction uncertainty, which can be crucial in scenarios such as automotive applications and disease diagnosis. Aleatoric and epistemic uncertainties have been proposed in the Bayesian deep learning framework for regression and classification, which require training images with unambiguous labels for success. Some situations do not have precise labels by nature, such as age estimation or lesion contour annotation by different physicians in the real world. Label distribution learning (LDL) has been proposed to account for the label ambiguity. However, uncertainty estimation has not been studied for LDL. This study presents a Bayesian deep label distribution learning (BLDL) to obtain the uncertainties of L