Artificial Intelligence Segmentation Algorithm-Based Optical Coherence Tomography Image in Evaluation of Binocular Retinopathy

Abstract

On account of optical coherence tomography (OCT) images with intelligent segmentation algorithm, this article investigated the clinical efficacy and safety of docetaxel combined with fluorouracil. In this study, 60 patients with retinopathy treated in hospital were selected as the research objects. There were 30 cases in each group, the control group was treated with conventional images, and the observation group was treated with algorithm-based OCT images. Intelligent segmentation boundary detection algorithm, boundary tracking, and contour localization were proposed and applied to the OCT images of patients to analyze features and measure corneal thickness in OCT images with high signal-to-noise ratio and noise and artifacts. Objects in the control group were treated with semiconductor laser, and those in the observation group were treated with OCT images with algorithm in addition to the treatment of the control group. The results showed that the number of images with relative error of 2 was more, and the number of images with relative error of -2 was the least. The average thickness of high-quality images was 562.7 μm, and the average thickness of images with noise and artifacts was 573.8 μm. The total effective rate of the observation group was 96.67%, which was significantly higher than that of the control group (80%), and the curative effect and physical improvement rate of the observation group were significantly better than that of the control group ( $P<0.05$ ). All in all, the feature extraction of OCT images and corneal measurement proposed in this study had a good measurement effect, and the method had the advantages of strong anti-interference ability and high measurement accuracy.