This diagnostic study develops and prospectively validates a deep learning algorithm that uses ocular fundus images to recognize numerous retinal diseases in a clinical setting at 65 screening centers in 19 Chinese provinces.
BackgroundThyroid-associated ophthalmopathy (TAO) is one of the most common orbital diseases that seriously threatens visual function and significantly affects patients’ appearances, rendering them unable to work. This study established an intelligent diagnostic system for TAO based on facial images.MethodsPatient images and data were obtained from medical records of patients with TAO who visited Shanghai Changzheng Hospital from 2013 to 2018. Eyelid retraction, ocular dyskinesia, conjunctival congestion, and other signs were noted on the images. Patients were classified according to the types, stages, and grades of TAO based on the diagnostic criteria. The diagnostic system consisted of multiple task-specific models.ResultsThe intelligent diagnostic system accurately diagnosed TAO in three stages. The built-in models pre-processed the facial images and diagnosed multiple TAO signs, with average areas under the receiver operating characteristic curves exceeding 0.85 (F1 score >0.80).ConclusionThe intelligent diagnostic system introduced in this study accurately identified several common signs of TAO.
Active magnetic bearing (AMB) is competent in rotor trajectory control for potential applications such as mechanical processing and spindle attitude control, while the highly nonlinear and coupled dynamic characteristics especially in the condition of rotor large motion are obstacles in controller design. In this paper, a controller of AMB is proposed to achieve rotor 3D trajectory control. First, the dynamic model of the AMB-rotor system containing a nonlinear electromagnetic force model is introduced. Then the DCNN-SMC (deep convolutional neural network - sliding mode control) controller is proposed. Sliding mode control is used to achieve the tracking control with high robustness and responsiveness, and a deep convolutional neural network based on deep learning method is designed to compensate the uncertainties of the system. Finally, simulation of a 5-degree of freedom (DOF) system on various trajectories demonstrates evident control effect of the proposed controller in precision and significant effect of DCNN based on deep learning method in compensation control.
Rotor tracking control, which can be implemented by active magnetic bearing (AMB) system with high precision, can realize many functions, such as attitude control and special surface processing. However, large-motion rotor tracking control is difficult to implemented, due to AMB's highly nonlinear characteristics. In this paper, a dual-loop neural network sliding mode control (DL-NNSMC) system of AMB is proposed for rotor radial tracking control. The complete model of the AMB system is established and the dual-loop control system is designed. A circuit model that considers the rotor motion is established and the model-based inner loop of current control is established, conjointly for dealing with the influence of rotor motion on the current response and the unknown characteristics of the power amplifier. In the outer loop, a nonlinear electromagnetic force model is applied and a wavelet neural network sliding mode control algorithm is designed for accurate position control. Two cases of rotor trajectory tracking are simulated, and the simulation results demonstrate the validity of the proposed control system for large-motion rotor tracking control and its far superior control performance in terms of precision compared with common approaches based on sliding mode control (SMC). INDEX TERMS Active magnetic bearing, rotor tracking control, control system design, AMB system modeling, sliding mode control.
In medical image segmentation, it is difficult to mark ambiguous areas accurately with binary masks, especially when dealing with small lesions. Therefore, it is a challenge for radiologists to reach a consensus by using binary masks under the condition of multiple annotations. However, these areas may contain anatomical structures that are conducive to diagnosis. Uncertainty is introduced to study these situations. Nevertheless, the uncertainty is usually measured by the variances between predictions in a multiple trial way. It is not intuitive, and there is no exact correspondence in the image. Inspired by image matting, we introduce matting as a soft segmentation method and a new perspective to deal with and represent uncertain regions into medical scenes, namely medical matting. More specifically, because there is no available medical matting dataset, we first labeled two medical datasets with alpha matte. Secondly, the matting method applied to the natural image is not suitable for the medical scene, so we propose a new architecture to generate binary masks and alpha matte in a row. Thirdly, the uncertainty map is introduced to highlight the ambiguous regions from the binary results and improve the matting performance. Evaluated on these datasets, the proposed model outperformed state-of-the-art matting algorithms by a large margin, and alpha matte is proved to be a more efficient labeling form than a binary mask.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.