All Articles from Feng Li -Optical Coherence Tomography News

Articles from Feng Li

1-6 of 6
1. Automatic segmentation of multitype retinal fluid from optical coherence tomography images using semisupervised deep learning network
  
  Explore BJO Online Jun 14 2022 Ophthalmology
  
  Background/aims: To develop and validate a deep learning model for automated segmentation of multitype retinal fluid using optical coherence tomography (OCT) images. Methods: We retrospectively collected a total of 2814 completely anonymised OCT images with subretinal fluid (SRF) and intraretinal fluid (IRF) from 141 patients between July 2018 and June 2020, constituting our in-house retinal OCT dataset. On this dataset, we developed a novel semisupervised retinal fluid segmentation deep network (Ref-Net) to automatically identify SRF and IRF in a coarse-to-refine fashion. We performed quantitative and qualitative analyses on the model's performance while verifying its generalisation ability by using ...
  Read Full Article
  
  Comment
2. Fourier Domain Mode Locked Laser and Its Applications
  
  Explore MDPI Open Access Journals Platform May 28 2022 Tunable Sources
  
  The sweep rate of conventional short-cavity lasers with an intracavity-swept filter is limited by the buildup time of laser signals from spontaneous emissions. The Fourier domain mode-locked (FDML) laser was proposed to overcome the limitations of buildup time by inserting a long fiber delay in the cavity to store the whole swept signal and has attracted much interest in both theoretical and experimental studies. In this review, the theoretical models to understand the dynamics of the FDML laser and the experimental techniques to realize high speed, wide sweep range, long coherence length, high output power and highly stable swept signals ...
  Read Full Article
  
  Comment
  
  Mentions: Hong Kong Polytechnic University
3. 114 nm broadband all-fiber nonlinear polarization rotation mode locked-laser and time-stretch optical coherence tomography
  
  Explore OSA | OSA Publishing Oct 3 2021
  
  We propose and demonstrate an all-fiber Er-doped mode-locked laser with a 3-dB spectrum of 114 nm by using nonlinear polarization rotation (NPR), which to the best of our knowledge is the first realization to date of such a broad spectrum without any spatial optical devices. The repetition rate and pulse width of the laser are 183.6 MHz and 3.7 ps, respectively. Such an all-fiber NPR mode-locked laser is then applied in time-stretch optical coherence tomography. The axial resolution is 12.1 µm. The all-fiber high speed broadband swept laser based on the time stretching technique has compact structure ...
  Read Full Article
  
  Comment
4. 400 MHz ultrafast optical coherence tomography
  
  Explore OSA | OSA Publishing Dec 8 2020
  
  An ultrafast time-stretched swept source with a sweep rate of 400 MHz is demonstrated based on the buffering of a 100 MHz femtosecond laser pulse train. To the best of our knowledge, this is the highest sweep rate of swept sources for optical coherence tomography (OCT) that has been reported. With a 10 dB sweep range of ∼ 100 nm ∼100nm , an axial resolution of 19 µm is obtained in the OCT. OCT imaging of high-speed rotating disks is demonstrated. A composite complex apodization method is proposed and demonstrated to enhance the signal to noise ratio in the OCT imaging.
  Read Full Article
  
  Comment
5. Deep learning-based automated detection of retinal diseases using optical coherence tomography images
  
  Explore OSA | OSA Publishing Nov 18 2019 Ophthalmology
  
  Retinal disease classification is a significant problem in computer-aided diagnosis (CAD) for medical applications. This paper is focused on a 4-class classification problem to automatically detect choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL in optical coherence tomography (OCT) images. The proposed classification algorithm adopted an ensemble of four classification model instances to identify retinal OCT images, each of which was based on an improved residual neural network (ResNet50). The experiment followed a patient-level 10-fold cross-validation process, on development retinal OCT image dataset. The proposed approach achieved 0.973 (95% confidence interval [CI], 0.971–0.975) classification ...
  Read Full Article
  
  Comment
  
  Mentions: Florida International University
6. Eckhaus Instability in the Fourier-Domain Mode Locked Fiber Laser Cavity
  
  Explore arxiv.org Aug 17 2017 Tunable Sources
  
  High frequency fluctuation in the optical signal generated in Fourier-Domain Mode Locked fiber laser (FDML-FL), which is the major problem and degrades the laser performance, is not yet fully analyzed or studied. The basic theory which is causing this high frequency fluctuation is required to clearly understand its dynamics and to control it for various applications. In this letter, by analyzing the signal and system dynamics of FDML-FL, we theoretically demonstrate that the high frequency fluctuation is induced by the intrinsic instability of frequency offset of the signal in cavity with nonlinear gain and spectral filter. Unlike the instabilities observed ...
  Read Full Article
  
  Comment
  
  Mentions: University of Washington University of Aberdeen Hong Kong Polytechnic University
1-6 of 6