Choroidal neovascularization(CNV) refers to abnormal choroidal vessels that grow through the Bruch’s membrane to the bottom of retinal pigment epithelium (RPE) or retinal neurepithelium (RNE) layer, which is the pathological characterization of age-related macular degeneration (AMD) and pathological myopia (PM). Nowadays, optical coherence tomography (OCT) is an important imaging modality for observing CNV. This paper creatively proposes a convolutional neural network with differential amplification blocks (DACNN) to segment CNV in OCT images. There are two main contributions. (1) A differential amplification block (DAB) is proposed to extract the contrast information of foreground and background. (2) The DAB is integrated into the U-shaped convolutional neural network for CNV segmentation. The method proposed in this paper was verified on a dataset composed of 886 OCT B-scans. Compared with manual segmentation, the mean Dice similarity coefficient can reach 86.40%, outperforming some existing deep networks for segmentation.
In this paper, the method of Radial basis function(RBF) to Electronic Speckle Pattern Interferometry (ESPI)information extraction is studied, mainly including: the filtering method based on radial basis function for ESPI fringe patterns with wide density; introducing the radial basis function to interpolate the number of fringe in the fringe skeleton method. Thermal deformation phase measurement of Al2O3 ceramic substrate at the circumstance of thermal load was estimated based on the ESPI. In the experiment, four ESPI fringe patterns at different moment at the beginning of the experiment were captured. The RBF filtering method and the fringe skeleton method with RBF interpolating were used to estimating the thermal deformation phase measurement. The acquiring out-of-plane displacements by our method were in good agreement with the real deformation under the stepped-up thermal load gradually. This measurement can provide assistance for studying the performance of ceramic substrate in the process of laser processing.
Data imbalance is a classic problem in image classification, especially for medical images where normal data is much more than data with diseases. To make up for the absence of disease images, methods which can generate retinal OCT images with diseases from normal retinal images are investigated. Conditional GANs (cGAN) have shown significant success in natural images generation, but the applications for medical images are limited. In this work, we propose an end-to-end framework for OCT image generation based on cGAN. The new structural similarity index (SSIM) loss is introduced so that the model can take the structure-related details into consideration. In experiments, three kinds of retinal disease images are generated. The generated images assume the natural structure of the retina and thus are visually appealing. The method is further validated by testing the classification performance trained by the generated images.
Change of the thickness and volume of the choroid, which can be observed and quantified from optical coherence tomography (OCT) images, is a feature of many retinal diseases, such as aged-related macular degeneration and myopic maculopathy. In this paper, we make purposeful improvements on the U-net for segmenting the choroid of either normal or pathological myopia retina, obtaining the Bruch’s membrane (BM) and the choroidal-scleral interface (CSI). There are two main improvements to the U-net framework: (1) Adding a refinement residual block (RRB) to the back of each encoder. This strengthens the recognition ability of each stage; (2) The channel attention block (CAB) is integrated with the U-net. This enables high-level semantic information to guide the underlying details and handle the intra-class inconsistency problem. We validated our improved network on a dataset which consists of 952 OCT Bscans obtained from 95 eyes from both normal subjects and patients suffering from pathological myopia. Comparing with manual segmentation, the mean choroid thickness difference is 8μm, and the mean Dice similarity coefficient is 85.0%.