DRIVE Digital Retinal Images for Vessel Extraction DRIVE数字视网膜图像进行血管提取

DRIVE Digital Retinal Images for Vessel Extraction

40 high res images for retinal vessel segmentation

DRIVE数字视网膜图像进行血管提取

40张视网膜血管分割的高分辨率图像

建立DRIVE数据库，对视网膜图像血管分割进行比较研究。视网膜血管分割和描绘视网膜血管的形态属性，如长度、宽度、弯曲度、分支模式和角度，可以用于诊断、筛选、治疗和评价各种心血管和眼科疾病。

1. Overview

The DRIVE: Digital Retinal Images for Vessel Extraction dataset was made public here.

No license was specified, yet all credits are due to the original authors.

The DRIVE database has been established to enable comparative studies on segmentation of blood vessels in retinal images. Retinal vessel segmentation and delineation of morphological attributes of retinal blood vessels, such as length, width, tortuosity, branching patterns and angles are utilized for the diagnosis, screening, treatment, and evaluation of various cardiovascular and ophthalmologic diseases such as diabetes, hypertension, arteriosclerosis and chorodial neovascularization. Automatic detection and analysis of the vasculature can assist in the implementation of screening programs for diabetic retinopathy, can aid research on the relationship between vessel tortuosity and hypertensive retinopathy, vessel diameter measurement in relation with diagnosis of hypertension, and computer-assisted laser surgery. Automatic generation of retinal maps and extraction of branch points have been used for temporal or multimodal image registration and retinal image mosaic synthesis. Moreover, the retinal vascular tree is found to be unique for each individual and can be used for biometric identification.

2. Data

The photographs for the DRIVE database were obtained from a diabetic retinopathy screening program in The Netherlands. The screening population consisted of 400 diabetic subjects between 25-90 years of age. Forty photographs have been randomly selected, 33 do not show any sign of diabetic retinopathy and 7 show signs of mild early diabetic retinopathy. Here is a brief description of the abnormalities in these 7 cases:

25_training: pigment epithelium changes, probably butterfly maculopathy with pigmented scar in fovea, or choroidiopathy, no diabetic retinopathy or other vascular abnormalities.

26_training: background diabetic retinopathy, pigmentary epithelial atrophy, atrophy around optic disk

32_training: background diabetic retinopathy

03_test: background diabetic retinopathy

08_test: pigment epithelium changes, pigmented scar in fovea, or choroidiopathy, no diabetic retinopathy or other vascular abnormalities

14_test: background diabetic retinopathy

17_test: background diabetic retinopathy

Each image has been JPEG compressed.

The images were acquired using a Canon CR5 non-mydriatic 3CCD camera with a 45 degree field of view (FOV). Each image was captured using 8 bits per color plane at 768 by 584 pixels. The FOV of each image is circular with a diameter of approximately 540 pixels. For this database, the images have been cropped around the FOV. For each image, a mask image is provided that delineates the FOV.

The set of 40 images has been divided into a training and a test set, both containing 20 images. For the training images, a single manual segmentation of the vasculature is available. For the test cases, two manual segmentations are available; one is used as gold standard, the other one can be used to compare computer generated segmentations with those of an independent human observer. Furthermore, a mask image is available for every retinal image, indicating the region of interest. All human observers that manually segmented the vasculature were instructed and trained by an experienced ophthalmologist. They were asked to mark all pixels for which they were for at least 70% certain that they were vessel.

1. 简介

建立DRIVE数据库，对视网膜图像血管分割进行比较研究。视网膜血管分割和描绘视网膜血管的形态属性，如长度、宽度、弯曲度、分支模式和角度，用于诊断、筛选、治疗和评价各种心血管和眼科疾病，如糖尿病、高血压、动脉硬化和脉络膜新生血管。血管系统的自动检测和分析有助于糖尿病视网膜病变筛查方案的实施，有助于研究血管弯曲与高血压视网膜病变的关系，有助于测量血管直径与高血压诊断的关系，有助于计算机辅助激光手术。视网膜地图的自动生成和分支点的提取被用于时间或多模态图像配准和视网膜图像拼接合成。此外，视网膜血管树对每个个体都是独一无二的，可以用于生物特征识别。

2. 数据

DRIVE数据库的照片来自荷兰的糖尿病性视网膜病变筛查计划。筛查人群由年龄在25-90岁之间的400位糖尿病患者组成。随机选择了40张照片，其中33张未显示任何糖尿病性视网膜病变的征兆，而7张显示了轻度早期糖尿病性视网膜病变的征兆。这是这7种情况下的异常的简要说明：

25_training：色素上皮改变，可能是蝶形黄斑病，中央凹有色素疤痕，或脉络膜病变，无糖尿病性视网膜病或其他血管异常。

26_training：糖尿病性视网膜病变，色素上皮萎缩，视盘周围萎缩

32_training：背景性糖尿病视网膜病变

03_test：背景性糖尿病视网膜病变

08_test：色素上皮改变，中央凹色素疤痕或脉络膜病变，无糖尿病性视网膜病变或其他血管异常

14_test：背景性糖尿病视网膜病变

17_test：背景性糖尿病视网膜病变

每个图像均已进行JPEG压缩。

使用具有45度视场（FOV）的佳能CR5非散光3CCD相机获取图像。使用每个色彩平面的8位以768 x 584像素捕获每个图像。每个图像的FOV是圆形的，直径约为540像素。对于此数据库，图像已在FOV周围裁剪。对于每个图像，提供了一个遮罩图像，用于描绘FOV。

这组40张图像已分为训练和测试集，均包含20张图像。对于训练图像，可以对脉管系统进行单个手动分割。对于测试用例，可以使用两种手动分段：一种用作黄金标准，另一种可以用于将计算机生成的细分与独立的人类观察者进行比较。此外，对于每个视网膜图像都可使用遮罩图像，指示感兴趣的区域。经验丰富的眼科医生对所有手动分割脉管系统的观察者进行了指导和培训。要求他们标记至少70％可以确定是容器的所有像素。