Coronavirus disease 2019 (COVID-19) has infected more than 1.3 million individuals all over the world and caused more than 106,000 deaths. One major hurdle in controlling the spreading of this disease is the inefficiency and shortage of medical tests. There have been increasing efforts on developing deep learning methods to diagnose COVID-19 based on CT scans. However, these works are difficult to reproduce and adopt since the CT data used in their studies are not publicly available. Besides, these works require a large number of CTs to train accurate diagnosis models, which are difficult to obtain. In this paper, we aim to address these two problems. We build a publicly-available dataset containing hundreds of CT scans positive for COVID-19 and develop sample-efficient deep learning methods that can achieve high diagnosis accuracy of COVID-19 from CT scans even when the number of training CT images are limited. Specifically, we propose an Self-Trans approach, which synergistically integrates contrastive self-supervised learning with transfer learning to learn powerful and unbiased feature representations for reducing the risk of overfitting. Extensive experiments demonstrate the superior performance of our proposed Self-Trans approach compared with several state-of-the-art baselines. Our approach achieves an F1 of 0.85 and an AUC of 0.94 in diagnosing COVID-19 from CT scans, even though the number of training CTs is just a few hundred.
Eye-tracking can help decode the intricate control mechanism in human performance. In healthcare, physicians-in-training requires extensive practice to improve their healthcare skills. When a trainee encounters any difficulty in the practice, they will need feedback from experts to improve their performance. The personal feedback is time-consuming and subjected to bias. In this study, we tracked the eye movements of trainees during their colonoscopic performance in simulation. We applied deep learning algorithms to detect the eye-tracking metrics on the moments of navigation lost (MNL), a signature sign for performance difficulty during colonoscopy. Basic human eye gaze and pupil characteristics were learned and verified by the deep convolutional generative adversarial networks (DCGANs); the generated data were fed to the Long Short-Term Memory (LSTM) networks with three different data feeding strategies to classify MNLs from the entire colonoscopic procedure. Outputs from deep learning were compared to the expert’s judgment on the MNLs based on colonoscopic videos. The best classification outcome was achieved when we fed human eye data with 1000 synthesized eye data, where accuracy (90%), sensitivity (90%), and specificity (88%) were optimized. This study built an important foundation for our work of developing a self-adaptive education system for training healthcare skills using simulation.
After reviewing the spectrum-dividing principle of the Savart polariscope (SP) in the polarization interference imaging spectrometer (PIIS) that we developed, we analyze the influences of the thickness, misalignment, and dispersion of the SP on the optical path difference (OPD). The theoretical expression of the OPD for the misalignment of the SP optical axis is deduced, and the OPD is analyzed when the incident plane is parallel, at 45°, or orthogonal to the principal section of the left plate of the SP. The selective thickness of the single Savart plate is analyzed when it is placed at the ideal and misalignment positions. The influence of dispersion of the SP on the OPD is analyzed when the misalignment error is ±1'. The relationships between the OPD and wavelength are simulated and validated with experiments. This work can provide theoretical and practical guidance for the design, calibration, modulation, innovation, experiment, and engineering of the PIIS.
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.