Search

This paper provides a comprehensive analysis of the current state of intelligent ophthalmology in China, including technological advancements, academic exchange platforms, policy support, future challenges, and potential solutions. Technologically, remarkable progress have been made in various areas of intelligent ophthalmology in China, including diabetic retinopathy, fundus image analysis, and crucial aspects such as quality assessment of medical artificial intelligence products, clinical research methods, technological evaluation, and industrial standards. Researchers are constantly improving the safety and standardization of intelligent ophthalmology technology by formulating clinical application guidelines and standards. Academic exchange platforms have been established to provide extensive collaboration opportunities for professionals across diverse fields, and various academic journals serve as publication platforms for intelligent ophthalmology research. Regarding public policy, the Chinese government has not only established a supportive policy environment for the advancement of intelligent ophthalmology through various documents and regulations, but provided a legal basis and management framework. However, there are still challenges to overcome, such as technological innovation, data privacy and security, outdated regulations, and talent shortages. To tackle these issues, there is a requirement for increased technological research and development, the establishment of regulatory frameworks, talent cultivation, and greater awareness and acceptance of new technologies among patients. By comprehensively addressing these challenges, intelligent ophthalmology in China is expected to continue leading the industry's global development, bringing more innovation and convenience to the field of ophthalmic healthcare.

Pathologic myopia (PM) is a common blinding retinal degeneration suffered by highly myopic population. Early screening of this condition can reduce the damage caused by the associated fundus lesions and therefore prevent vision loss. Automated diagnostic tools based on artificial intelligence methods can benefit this process by aiding clinicians to identify disease signs or to screen mass populations using color fundus photographs as inputs. This paper provides insights about PALM, our open fundus imaging dataset for pathological myopia recognition and anatomical structure annotation. Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment. In addition, this paper elaborates on other details such as the labeling process used to construct the database, the quality and characteristics of the samples and provides other relevant usage notes. [ABSTRACT FROM AUTHOR]

The doubly salient electromagnetic generator (DSEG) has the advantages of flexible control, high robustness, and low cost. Since multiple stator poles share a common set of field windings, the magnetic circuit of each phase is asymmetrical, which limits the output performance of the DSEG. The three-phase current balance control for the DSEG system was proposed. By investigating the current waveform under the angular position control (APC), a three-phase current prediction method was proposed. The conduction angle of the power switches in the active rectifier was predicted to make the three-phase current balanced. Based on the analysis and experiment, the current waveform was further analyzed, and the effectiveness of the three-phase current balance control was verified. Compared with the APC method, the output power capacity was improved using the three-phase current balance control under a limited winding current density. The maximum potential of the DSEG was explored, and the electromagnetic load capacity of the DSEG was fully released. [ABSTRACT FROM AUTHOR]

Secoeudesma sesquiterpenes lactone A (SESLA) is a sesquiterpene derived from Inula japonica Thunb. and is known to possess many pharmacological properties, e.g. anti-tumor and anti-inflammatory activities. However, the immunomodulatory role of SESLA in gram-positive (G+) bacterial infection is not clear. To set up a G+ bacterial infection model in vitro, we carried out a bacterial mimic (PGN or Pam3CSK4) or Methicillin-resistant Staphylococcus aureus (MRSA) stimulated experiment using macrophages or dendritic cells (DCs). ELISA and qPCR were performed to measure the expression of inflammatory cytokines. Flow cytometry was used to detect the expression of MHC II and co-stimulatory molecules on the surface of DCs. The network pharmacology was used to identify the molecular mechanism and potential targets of SESLA that are predicted to be involved in the MRSA-elicited inflammation. Western blot and dual luciferase reporter assay were adopted to certify possible molecular mechanism of SESLA. This study demonstrated that SESLA treatment significantly reduced the levels of inflammatory cytokines stimulated by PGN, Pam3CSK4 or even MRSA in vitro, and it also reduced PGN-induced expression of MHC II and co-stimulatory molecules on the surface of DCs. Mechanistically, the inhibition of IκBα phosphorylation and the suppression of T cells activation could account for its anti-inflammatory activity. The present study validated the notable anti-inflammatory activity of SESLA and discovered its previously uncharacterized immunoregulatory role and the underlying mechanism in G+ bacterial infections. Overall, SESLA has a potential to be an antibiotic adjuvant for the treatment of G+ bacterial infections. [ABSTRACT FROM AUTHOR]

The vehicle longitudinal control algorithm is the core function of the adaptive cruise control system, whose main task is to convert vehicle acceleration and deceleration requirements into vehicle driving and braking commands so that the vehicle can quickly and accurately track the desired acceleration. Traditional longitudinal control algorithms rely on accurate vehicle dynamic modeling or complex controller parameter calibrations. To overcome those difficulties, a longitudinal control algorithm based on RBF-PID is proposed in this paper. The algorithm uses the RBFNN (radial basis function neural network), which can simply and quickly approximate any complex nonlinear system, to identify the Jacobian information of the vehicle and perform parameter tuning for PID control and achieve vehicle longitudinal control with self-tuning capability. Finally, the algorithm of this paper is verified by the joint simulation of Matlab/Simulink and Carsim. The results show that this algorithm has a better response rate and anti-jamming capability than the traditional PID control and can achieve accurate and rapid tracking of the desired acceleration. [ABSTRACT FROM AUTHOR]

Cardiac ischemia, hypoxia, arrhythmias, and heart failure share the common electrophysiological changes featured by the elevation of intracellular Ca2+ (Ca2+ overload) and inhibition of the inward rectifier potassium (IK1) channel. IK1 channel agonists have been considered a new type of anti‐arrhythmia and cardioprotective agents. We predicted using a drug repurposing strategy that tetramisole (Tet), a known anthelminthic agent, was a new IK1 channel agonist. The present study aimed to experimentally identify the above prediction and further demonstrate that Tet has cardioprotective effects. Results of the whole‐cell patch clamp technique showed that Tet at 1–100 μmol/L enhanced IK1 current, hyperpolarized resting potential (RP), and shortened action potential duration (APD) in isolated rat cardiomyocytes, while without effects on other ion channels or transporters. In adult Sprague–Dawley (SD) rats in vivo, Tet showed anti‐arrhythmia and anticardiac remodeling effects, respectively, in the coronary ligation‐induced myocardial infarction model and isoproterenol (Iso, i.p., 3 mg/kg/day, 10 days) infusion‐induced cardiac remodeling model. Tet also showed anticardiomyocyte remodeling effect in Iso (1 μmol/L) infused adult rat ventricular myocytes or cultured H9c2 (2‐1) cardiomyocytes. Tet at 0.54 mg/kg in vivo or 30 μmol/L in vitro showed promising protections on acute ischemic arrhythmias, myocardial hypertrophy, and fibrosis. Molecular docking was performed and identified the selective binding of Tet with Kir2.1. The cardioprotection of Tet was associated with the facilitation of IK1 channel forward trafficking, deactivation of PKA signaling, and inhibition of intracellular calcium overload. Enhancing IK1 may play dual roles in anti‐arrhythmia and antiventricular remodeling mediated by restoration of Ca2+ homeostasis. [ABSTRACT FROM AUTHOR]

Automatic angle-closure assessment in Anterior Segment OCT (AS-OCT) images is an important task for the screening and diagnosis of glaucoma, and the most recent computer-aided models focus on a binary classification of anterior chamber angles (ACA) in AS-OCT, i.e., open-angle and angle-closure. In order to assist clinicians who seek better to understand the development of the spectrum of glaucoma types, a more discriminating three-class classification scheme was suggested, i.e., the classification of ACA was expended to include open-, appositional- and synechial angles. However, appositional and synechial angles display similar appearances in an AS-OCT image, which makes classification models struggle to differentiate angle-closure subtypes based on static AS-OCT images. In order to tackle this issue, we propose a 2D-3D Hybrid Variation-aware Network (HV-Net) for open-appositional-synechial ACA classification from AS-OCT imagery. Specifically, taking into account clinical priors, we first reconstruct the 3D iris surface from an AS-OCT sequence, and obtain the geometrical characteristics necessary to provide global shape information. 2D AS-OCT slices and 3D iris representations are then fed into our HV-Net to extract cross-sectional appearance features and iris morphological features, respectively. To achieve similar results to those of dynamic gonioscopy examination, which is the current gold standard for diagnostic angle assessment, the paired AS-OCT images acquired in dark and light illumination conditions are used to obtain an accurate characterization of configurational changes in ACAs and iris shapes, using a Variation-aware Block. In addition, an annealing loss function was introduced to optimize our model, so as to encourage the sub-networks to map the inputs into the more conducive spaces to extract dark-to-light variation representations, while retaining the discriminative power of the learned features. The proposed model is evaluated across 1584 paired AS-OCT samples, and it has demonstrated its superiority in classifying open-, appositional- and synechial angles. [ABSTRACT FROM AUTHOR]

In recent years, an increasing number of people have myopia in China, especially the younger generation. Common myopia may develop into high myopia. High myopia causes visual impairment and blindness. Parapapillary atrophy (PPA) is a typical retinal pathology related to high myopia, which is also a basic clue for diagnosing high myopia. Therefore, accurate segmentation of the PPA is essential for high myopia diagnosis and treatment. In this study, we propose an optimized Unet (OT-Unet) to solve this important task. OT-Unet uses one of the pre-trained models: Visual Geometry Group (VGG), ResNet, and Res2Net, as a backbone and is combined with edge attention, parallel partial decoder, and reverse attention modules to improve the segmentation accuracy. In general, using the pre-trained models can improve the accuracy with fewer samples. The edge attention module extracts contour information, the parallel partial decoder module combines the multi-scale features, and the reverse attention module integrates high- and low-level features. We also propose an augmented loss function to increase the weight of complex pixels to enable the network to segment more complex lesion areas. Based on a dataset containing 360 images (Including 26 pictures provided by PALM), the proposed OT-Unet achieves a high AUC (Area Under Curve) of 0.9235, indicating a significant improvement over the original Unet (0.7917). [ABSTRACT FROM AUTHOR]

In this article, the advanced angle control (AAC) for the active rectifier (AR) is proposed to improve the output power of doubly salient electromagnetic generator systems. The AAC AR is an optimization by turning on the switches in advance with an angle based on the angular position control (APC) and pulsewidth modulation (PWM) ARs. The operation principle of the AAC in ARs is different from that in the inverters. The phase inductance variation is analyzed. The inductance flat top at load condition is utilized to accelerate the commutation process and enlarge the phase current. The unified analysis is proposed by summarizing the four states of the conduction modes in the AR. The analysis of the proposed AAC strategies, the conventional APC, and PWM strategies are unified. The output power of AAC APC ARs is significantly improved compared with that of the conventional AR. The copper loss, iron loss, and torque ripple are reduced. The AAC strategies are compared with conventional strategies. The optimized performances of AAC strategies are verified by finite-element analysis and experimental results. [ABSTRACT FROM AUTHOR]

A doubly salient electromagnetic starter/ generator (DSESG) system based on the bidirectional converter (BDC) is proposed, in this article. The BDC is operated as an inverter in starting mode and as an active rectifier (AR) in generation mode. Compared to the conventional DSESG system, which is based on an inverter and a diode rectifier or a discrete inverter/rectifier unit (IRU), the configuration is simplified and the weight is reduced. Since the output voltage is improved by the angular position control (APC), field and phase currents are redistributed. The copper loss optimization control (CLOC) for the AR is proposed. The copper loss is analyzed based on the extreme learning machine (ELM) and the turn-off angles are selected. The copper loss is minimized and the heat is reduced. The copper loss and heat generation are also balanced in the field and phase windings to decrease the temperature of the field windings at low speed. Experimental verifications are conducted on a 9 kW DSESG prototype. The effectiveness of the proposed ELM-based CLOC is verified by simulation and experiments. A lighter and simpler DSESG system with reduced loss is presented. [ABSTRACT FROM AUTHOR]

A DC-link voltage regulation method is proposed based on capacitor energy control (CEC) for the doubly salient electro-magnetic generator (DSEG) system. Instead of tracking the DC-link voltage, the stored energy in the DC-link capacitor is set as the control target in the outer loop. A proportional component that converts the command output current into the command field current is developed between the capacitor energy loop and field current loop. The coefficient in the proportional component is investigated based on the mathematical model of the 12–8 pole DSEG, considering the load and speed variation. The dynamic response of the DSEG system is accelerated and the DC-link voltage variation is reduced with the proposed method. Furthermore, the adaptability to speed variation of the controlled is optimized. Since the DC-link capacitance is an additional parameter, the influences of capacitor degradation are investigated. The conventional voltage control and the CEC are implemented and compared on a DSEG platform. The optimized performance of the proposed method is verified by both finite element analysis (FEA) and experiments. The proposed method provides optimized dynamic performance over the entire speed range, enabling the DSEG system as a competitive option in the aircraft application. [ABSTRACT FROM AUTHOR]

Due to its high power density, the fractional slot concentrated winding permanent magnet synchronous machine (PMSM) is a competitive candidate for the aircraft starter generator (SG) system. However, the short circuit (SC) fault, especially the turn-to-turn SC fault, is the obstruct crux in aviation applications. The turn-to-turn SC current can be restricted to a permissible level with higher reactance and the current injection mitigation method. However, higher self-inductance always leads to lower power density. So far, there have been no numerical criteria for the tradeoff between the two characteristics in machine design. In this article, an analytical model based on flux distribution is used to estimate the SC current. The effectiveness of the d-axis current injection mitigation method is numerically analyzed in the series and parallel connected windings individually. The requirement for PMSMs to survive the turn-to-turn SC fault is derived. The mathematical analysis is verified by finite-element analysis and experiments on a 12-slot, 10-pole PMSM. This article provides theoretical support for designing high-performance permanent magnet starter generator (PMSG) with SC current mitigation ability for the aviation power system. [ABSTRACT FROM AUTHOR]

The doubly salient electromagnetic generator (DSEG) is gaining increasing attention in aircraft high voltage dc generator application due to its simplicity and de-excitation ability. However, the field winding inductance and the dc-link capacitor result in a larger electrical time constant. The dynamic response is decelerated, leading to difficulties in meeting aircraft electrical power standards. Minimum transient point tracking (MTPT) strategy based on the trajectory with minimum field current variation is proposed for the DSEG system with an angular position control (APC) controlled rectifier. Since the dc load current depends on both field current and the turn-off angle, the change in the field current is minimized and the dc load current is varied by controlling the turn-off angle. The trajectory of the optimized turn-off angle is studied to partly or fully fill the gap between the field currents at different loads. By tracking the MTPT trajectory, the change of the field current is decreased during the sudden load changes. The transient process is accelerated and the voltage variation is suppressed. In most operations, the voltage variation can be even neglected under both loaded and unloaded conditions. A 9-kW DSEG system based on controlled rectifier is implemented. The MTPT strategy is verified by experiments. The performances of the diode rectifier, controlled rectifier with fixed turn-off angle, and controlled rectifier with MTPT are compared. The dynamic performance is improved by the proposed method, making the DSEG more competitive in aircraft applications. [ABSTRACT FROM AUTHOR]

Numerous studies have shown that exosomes play important roles in tumor biology development. However, the function of exosomal protein in cancer progression under different oxygen condition after irradiation is poorly understood. In this study, non-small cell lung cancer (NSCLC) A549 cells were γ-ray irradiated under normoxic or hypoxic conditions, then the exosomes released from the irradiated cells were collected and co-cultured with nonirradiated A549 cells or human umbilical vein endothelial cells (HUVECs). It was found that the exosomes significantly promoted the proliferation, migration and invasion of A549 cells as well as the proliferation and angiogenesis of HUVECs. Moreover, the exosomes released from hypoxic cells and/or irradiated cells had more powerful driving force in tumor progression compared to that generated from normoxia cells. Meanwhile, the proteins contained in the exosomes derived from A549 cells under different conditions were detected using tandem mass tag (TMT), and their expression profiles were analyzed. It was found that the exosome-derived protein of angiopoietin-like 4 (ANGPTL4) contributed to the migration of A549 cells as well as the angiogenesis of HUVECs, suggesting its potential as an effective diagnostic biomarker of metastasis and even a therapeutic target of lung cancer. [ABSTRACT FROM AUTHOR]

Irreversible visual impairment is often caused by primary angle-closure glaucoma, which could be detected via anterior segment optical coherence tomography (AS-OCT). In this paper, an automated system based on deep learning is presented for angle-closure detection in AS-OCT images. Our system learns a discriminative representation from training data that captures subtle visual cues not modeled by handcrafted features. A multilevel deep network is proposed to formulate this learning, which utilizes three particular AS-OCT regions based on clinical priors: 1) the global anterior segment structure; 2) local iris region; and 3) anterior chamber angle (ACA) patch. In our method, a sliding window-based detector is designed to localize the ACA region, which addresses ACA detection as a regression task. Then, three parallel subnetworks are applied to extract AS-OCT representations for the global image and at clinically relevant local regions. Finally, the extracted deep features of these subnetworks are concatenated into one fully connected layer to predict the angle-closure detection result. In the experiments, our system is shown to surpass previous detection methods and other deep learning systems on two clinical AS-OCT datasets. [ABSTRACT FROM AUTHOR]

Accurate segmentation is an essential task when working with medical images. Recently, deep convolutional neural networks achieved a state-of-the-art performance for many segmentation benchmarks. Regardless of the network architecture, the deep learning-based segmentation methods view the segmentation problem as a supervised task that requires a relatively large number of annotated images. Acquiring a large number of annotated medical images is time consuming, and high-quality segmented images (i.e., strong labels) crafted by human experts are expensive. In this paper, we have proposed a method that achieves competitive accuracy from a "weakly annotated" image where the weak annotation is obtained via a 3D bounding box denoting an object of interest. Our method, called "3D-BoxSup," employs a positive-unlabeled learning framework to learn segmentation masks from 3D bounding boxes. Specially, we consider the pixels outside of the bounding box as positively labeled data and the pixels inside the bounding box as unlabeled data. Our method can suppress the negative effects of pixels residing between the true segmentation mask and the 3D bounding box and produce accurate segmentation masks. We applied our method to segment a brain tumor. The experimental results on the BraTS 2017 dataset (Menze et al., 2015; Bakas et al., 2017a,b,c) have demonstrated the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Recent works show that generative adversarial networks (GANs) can be successfully applied to image synthesis and semi-supervised learning, where, given a small labeled database and a large unlabeled database, the goal is to train a powerful classifier. In this paper, we trained a retinal image synthesizer and a semi-supervised learning method for automatic glaucoma assessment using an adversarial model on a small glaucoma-labeled database and a large unlabeled database. Various studies have shown that glaucoma can be monitored by analyzing the optic disc and its surroundings, and for that reason, the images used in this paper were automatically cropped around the optic disc. The novelty of this paper is to propose a new retinal image synthesizer and a semi-supervised learning method for glaucoma assessment based on the deep convolutional GANs. In addition, and to the best of our knowledge, this system is trained on an unprecedented number of publicly available images (86926 images). This system, hence, is not only able to generate images synthetically but to provide labels automatically. Synthetic images were qualitatively evaluated using t-SNE plots of features associated with the images and their anatomical consistency was estimated by measuring the proportion of pixels corresponding to the anatomical structures around the optic disc. The resulting image synthesizer is able to generate realistic (cropped) retinal images, and subsequently, the glaucoma classifier is able to classify them into glaucomatous and normal with high accuracy (AUC = 0.9017). The obtained retinal image synthesizer and the glaucoma classifier could then be used to generate an unlimited number of cropped retinal images with glaucoma labels. [ABSTRACT FROM AUTHOR]

Glaucoma is a chronic eye disease that leads to irreversible vision loss. Most of the existing automatic screening methods first segment the main structure and subsequently calculate the clinical measurement for the detection and screening of glaucoma. However, these measurement-based methods rely heavily on the segmentation accuracy and ignore various visual features. In this paper, we introduce a deep learning technique to gain additional image-relevant information and screen glaucoma from the fundus image directly. Specifically, a novel disc-aware ensemble network for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region. Four deep streams on different levels and modules are, respectively, considered as global image stream, segmentation-guided network, local disc region stream, and disc polar transformation stream. Finally, the output probabilities of different streams are fused as the final screening result. The experiments on two glaucoma data sets (SCES and new SINDI data sets) show that our method outperforms other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup to disc ratio (CDR) plays an important role in the screening and diagnosis of glaucoma. Thus, the accurate and automatic segmentation of optic disc (OD) and optic cup (OC) from fundus images is a fundamental task. Most existing methods segment them separately, and rely on hand-crafted visual feature from fundus images. In this paper, we propose a deep learning architecture, named M-Net, which solves the OD and OC segmentation jointly in a one-stage multi-label system. The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function. The multi-scale input layer constructs an image pyramid to achieve multiple level receptive field sizes. The U-shape convolutional network is employed as the main body network structure to learn the rich hierarchical representation, while the side-output layer acts as an early classifier that produces a companion local prediction map for different scale layers. Finally, a multi-label loss function is proposed to generate the final segmentation map. For improving the segmentation performance further, we also introduce the polar transformation, which provides the representation of the original image in the polar coordinate system. The experiments show that our M-Net system achieves state-of-the-art OD and OC segmentation result on ORIGA data set. Simultaneously, the proposed method also obtains the satisfactory glaucoma screening performances with calculated CDR value on both ORIGA and SCES datasets. [ABSTRACT FROM AUTHOR]

Doubly salient electromagnetic machines (DSEMs), which are characterised with fault tolerance, low cost, high reliability, and de‐excitation ability, are gaining more and more attention in safety‐critical and hash environment applications, such as the aircraft generation systems. Nevertheless, the non‐linear and strong coupled characteristics of the flux linkage is the obstruct crux in DSEM modelling. The DSEM model is the critical part of the system model, which is the foundation of theoretical analysis, control strategy developing, and stability analysis. This study is aimed to demonstrate the feasibility of indirect flux linkage measurement method, as well as the effectiveness of the extreme learning machine (ELM)‐based flux linkage modelling method. The basic principles of the indirect measurement are analysed and the measurement processes excluding rotor‐clamping devices are proposed. The ELM is employed to high‐precision flux linkage modelling with high efficiency. A three‐phase 12/8‐pole DSEM is tested to confirm the validity of the proposed modelling method. Both finite element analysis and experimental results are presented, verifying the effectiveness of the indirect flux linkage measurement and the ELM‐based modelling method. [ABSTRACT FROM AUTHOR]

Most electric vehicles adopt cooperative braking systems that can blend friction braking torque with regenerative braking torque to achieve higher energy efficiency while maintaining a certain braking performance and driving safety. This paper presented a new cooperative regenerative braking system that contained a fully-decoupled hydraulic braking mechanism based on a modified electric stability control system. The pressure control algorithm and brake force distribution strategy were also discussed. Dynamic models of a front wheel drive electric car equipped with this system and a simulation platform with a driver model and driving cycles were established. Tests to evaluate the braking performance and energy regeneration were simulated and analyzed on this platform and the simulation results showed the feasibility and effectiveness of this system. [ABSTRACT FROM AUTHOR]

Angle-closure glaucoma is a major cause of irreversible visual impairment and can be identified by measuring the anterior chamber angle (ACA) of the eye. The ACA can be viewed clearly through anterior segment optical coherence tomography (AS-OCT), but the imaging characteristics and the shapes and locations of major ocular structures can vary significantly among different AS-OCT modalities, thus complicating image analysis. To address this problem, we propose a data-driven approach for automatic AS-OCT structure segmentation, measurement, and screening. Our technique first estimates initial markers in the eye through label transfer from a hand-labeled exemplar data set, whose images are collected over different patients and AS-OCT modalities. These initial markers are then refined by using a graph-based smoothing method that is guided by AS-OCT structural information. These markers facilitate segmentation of major clinical structures, which are used to recover standard clinical parameters. These parameters can be used not only to support clinicians in making anatomical assessments, but also to serve as features for detecting anterior angle closure in automatic glaucoma screening algorithms. Experiments on Visante AS-OCT and Cirrus high-definition-OCT data sets demonstrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]