Clinical Impact of Using Real-Time Image-Processing Algorithms (Comb Removal and Image Sharpening) in Dacryoendoscopic Surgery

实时图像处理算法(梳状伪影去除和图像锐化)在泪道内镜手术中的临床应用

阅读:1

Abstract

Background/Objectives: Lacrimal passage intubation is commonly used to treat lacrimal duct obstruction. However, conventional dacryoendoscopes, which are limited by their low resolution and comb-structure artifacts, pose challenges for visualization. Two novel image processing algorithms-comb removal and image sharpening-have been developed to enhance visibility, and this study aimed to evaluate the clinical effects of these algorithms on the outcomes of dacryoendoscopic surgery. Methods: A retrospective study was conducted on 121 sides of 84 patients (mean age, 72.3 ± 10.5 years) who had undergone lacrimal passage intubation. The patients were categorized into comb-removal and image-sharpening groups according to the algorithm used during the procedure. The clinical parameters of pain score, endoscopy duration, irrigation fluid volume, and irrigation fluid flow rate were compared between the groups using the linear mixed-effects model, and recurrence rates were evaluated using Kaplan-Meier analysis. Results: The image-sharpening algorithm was associated with a significant reduction in irrigation fluid usage (β = -1.34 mL, SE = 0.52, p = 0.012), with the pain score (β = -1.71, SE = 0.93, p = 0.069) and endoscopy duration (β = -0.50 min, SE = 0.39, p = 0.199) also showing reduction trends, but these did not reach statistical significance. The comb-removal algorithm showed no significant associations with any evaluated outcome. Recurrence rates were similar between the groups. Conclusions: Real-time image sharpening was associated with improved procedural efficiency during dacryoendoscopic surgery, while clinical outcomes showed favorable trends that did not reach statistical significance. These findings suggest a potential supportive role of these algorithms in intraoperative handling; however, whether this translates into clinically meaningful benefits requires further investigation.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。