Search

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 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]

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]

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]

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]