Comput Methods Programs Biomed. 2021 Apr;202:105969. doi: 10.1016/j.cmpb.2021.105969. Epub 2021 Feb 5.
This paper reports a quantitative analysis of the effects of joint photographic experts group (JPEG) image compression of retinal fundus camera images on automatic vessel segmentation and on morphometric vascular measurements derived from it, including vessel width, tortuosity and fractal dimension.
Measurements are computed with vascular assessment and measurement platform for images of the retina (VAMPIRE), a specialized software application adopted in many international studies on retinal biomarkers. For reproducibility, we use three public archives of fundus images (digital retinal images for vessel extraction (DRIVE), automated retinal image analyzer (ARIA), high-resolution fundus (HRF)). We generate compressed versions of original images in a range of representative levels.
We compare the resulting vessel segmentations with ground truth maps and morphological measurements of the vascular network with those obtained from the original (uncompressed) images. We assess the segmentation quality with sensitivity, specificity, accuracy, area under the curve and Dice coefficient. We assess the agreement between VAMPIRE measurements from compressed and uncompressed images with correlation, intra-class correlation and Bland-Altman analysis.
Results suggest that VAMPIRE width-related measurements (central retinal artery equivalent (CRAE), central retinal vein equivalent (CRVE), arteriolar-venular width ratio (AVR)), the fractal dimension (FD) and arteriolar tortuosity have excellent agreement with those from the original images, remaining substantially stable even for strong loss of quality (20% of the original), suggesting the suitability of VAMPIRE in association studies with compressed images.
本文报告了对视网膜眼底相机图像的联合图像专家组(JPEG)图像压缩对自动血管分割以及由此得出的形态学血管测量结果(包括血管宽度、迂曲度和分形维数)影响的定量分析。
使用视网膜图像血管评估与测量平台(VAMPIRE)进行测量,VAMPIRE是一款在许多关于视网膜生物标志物的国际研究中采用的专业软件应用程序。为确保可重复性,我们使用了三个眼底图像公共档案库(用于血管提取的数字视网膜图像(DRIVE)、自动视网膜图像分析仪(ARIA)、高分辨率眼底(HRF))。我们在一系列具有代表性的水平上生成原始图像的压缩版本。
我们将所得的血管分割结果与真实地图进行比较,并将血管网络的形态学测量结果与从原始(未压缩)图像中获得的结果进行比较。我们使用灵敏度、特异性、准确性、曲线下面积和骰子系数来评估分割质量。我们使用相关性、组内相关性和布兰德 - 奥特曼分析来评估压缩图像和未压缩图像的VAMPIRE测量结果之间的一致性。
结果表明,VAMPIRE与宽度相关的测量结果(视网膜中央动脉等效直径(CRAE)、视网膜中央静脉等效直径(CRVE)、动静脉宽度比(AVR))、分形维数(FD)和小动脉迂曲度与原始图像的测量结果具有极好的一致性,即使在质量严重损失(原始质量的20%)的情况下仍基本保持稳定,这表明VAMPIRE适用于与压缩图像相关的研究。