OCT 图像的分割(AMD）数据集，光学相干断层扫描（OCT）和老年性黄斑变性（AMD）

Images for segmentation of optical coherence tomography images with age-related macular degeneration. Individual SDOCT images and marking: 38400 BScans from 269 AMD patients and 115 normal subjects, their ages, and their corresponding segmentation boundaries on a 5mm diameter centered at the fovea. Individual SDOCT images and marking: 38400 BScans from 269 AMD patients and 115 normal subjects, their ages, and their corresponding segmentation boundaries on a 5mm diameter centered at the fovea. NOTE: These results are based on measurements on Bioptigen system. Our preliminary results indicate differences in measured thickness between and even within manufacturers (e.g., a correction factor of 1.16 would be used to convert our reported thicknesses at central fovea to those from Spectralis [Heidelberg Inc, Heidelberg, Germany]). For this study, we used the dataset from the A2A SD-OCT Study, which was registered at ClinicalTrials.gov (Identifier: NCT00734487) and approved by the institutional review boards of the 4 A2A SD-OCT clinics (Devers Eye Institute, Duke Eye Center, Emory Eye Center, and National Eye Institute). With adherence to the tenets of the Declaration of Helsinki, informed consent was obtained from all subjects. The AREDS2 and A2A SD-OCT Study design and protocol for grading fundus photographs (AREDS2) and SD-OCT images (A2A SD-OCT) have been described.20,21 In brief, subjects who met the following inclusion criteria were enrolled: between 50 and 85 years of age, exhibiting intermediate AMD with large drusen (>125 mm) in both eyes or large drusen in 1 eligible eye and advanced AMD in the fellow eye, with no history of vitreoretinal surgery or ophthalmologic disease that might affect acuity in either eye. Age-appropriate control subjects were enrolled with the same inclusion criteria as for AREDS2 except that they must have had no evidence of macular drusen or AMD in either eye at the baseline visit or in the follow-up years. Stereoscopic color fundus photograph pairs were taken at the baseline visit as part of the AREDS2 protocol20 and then graded by certified readers at the Wisconsin Fundus Photography Reading Center (University of Wisconsin, Madison, WI). For our study, eyes assigned a Wisconsin drusen area score of “cannot grade” (drusen area was only partially visible for the field under consideration, such as when an obscuring lesion or poor photographic quality did not permit a reasonably confident assessment of drusen) at the Wisconsin Center were excluded. The SD-OCT imaging systems from Bioptigen, Inc (Research Triangle Park, NC), located at the 4 clinic sites, were used to acquire volumetric rectangular (w6.7
w6.7 mm) scans as previously published.21 To summarize, for all subjects, 0 and 90 rectangular volumes centered at the fovea (defined as volumes acquired with the fast scan direction oriented horizontally and vertically, respectively) with 1000 A-scans per B-scan and 100 B-scans per volume were captured for both eyes. In the A2A SD-OCT Study, of the 345 participants with AMD, 314 had at least 1 eye with intermediate AMD, and of the 122 control subjects without AMD, 119 had no eye disease at baseline.21 From these, 1 eligible eye of each subject had been randomly selected as the study eye as detailed by Leuschen et al.21 Eye length was not measured. Certified SD-OCT readers assessed the scan quality for each volume.21 For this study, we selected the 0 volumes by default, and any poor-quality (as assessed by graders) 0 volumes were replaced by a 90 volume from the same visit; if both scan volumes were poor, then the eye was excluded altogether. The excluded eyes were mainly those that contained blank or extremely low-quality images due to blinks or imaging errors or those volumes that exhibited significant eye motion or loss of fixation during image acquisition. Thus, in this study, we analyzed 269 of the 314 eyes with intermediate AMD and 115 of the 119 control (normal) eyes. http://people.duke.edu/~sf59/Farsiu_Ophthalmology_2013.pdf http://people.duke.edu/~sf59/RPEDC_Ophth_2013_dataset.htm S. Farsiu, SJ. Chiu, R.V. O’Connell, F.A. Folgar, E. Yuan, J.A. Izatt, and C.A. Toth "Quantitative Classification of Eyes with and without Intermediate Age-related Macular Degeneration Using Optical Coherence Tomography", Ophthalmology, 121(1), 162-172 Jan. (2014). Please reference the paper if you would like to use any part of this method or datasets. Please contact Prof. Sina Farsiu, PhD or Prof. Cynthia A. Toth, MD if you have questions about this dataset. Banner Image by Harry Quan on Unsplash

用于年龄相关性黄斑变性（AMD, Age-related Macular Degeneration）光学相干断层扫描图像分割的图像数据集。个体光谱域光学相干断层扫描（SDOCT, Spectral Domain Optical Coherence Tomography）图像及标注：来自269名AMD患者与115名正常受试者的38400幅B扫描（BScans）图像，包含受试者年龄信息，以及以黄斑中心凹为中心、直径5mm区域内的对应分割边界。个体光谱域光学相干断层扫描图像及标注：来自269名AMD患者与115名正常受试者的38400幅B扫描图像，包含受试者年龄信息，以及以黄斑中心凹为中心、直径5mm区域内的对应分割边界。

注：本研究结果基于Bioptigen系统的测量数据。我们的初步研究结果显示，不同厂商（甚至同一厂商不同设备）间的测量厚度存在差异——例如，若要将本研究报告的黄斑中心凹厚度转换为Spectralis（德国海德堡公司，Heidelberg Inc, Heidelberg, Germany）设备的测量结果，需使用1.16的校正系数。

本研究使用的数据来自A2A光谱域光学相干断层扫描研究（A2A SD-OCT Study），该研究已在ClinicalTrials.gov注册（注册号：NCT00734487），并获得了4家A2A SD-OCT诊所（Devers眼科研究所、杜克眼科中心、埃默里眼科中心、美国国家眼科研究所）的伦理审查委员会批准。所有受试者均签署了知情同意书，研究严格遵循《赫尔辛基宣言》的伦理原则。

AREDS2与A2A SD-OCT研究的设计、眼底照片（AREDS2）及SD-OCT图像（A2A SD-OCT）的阅片方案已在既往文献中报道20,21。简言之，符合以下纳入标准的受试者被纳入研究：年龄介于50至85岁之间，双眼均患有伴巨大玻璃膜疣（>125 mm）的中期AMD，或单眼存在巨大玻璃膜疣、对侧眼为晚期AMD，且无可能影响双眼视力的玻璃体视网膜手术史或其他眼科疾病史。年龄匹配的正常对照受试者纳入标准与AREDS2研究一致，但需在基线访视及随访年内均未发现双眼存在黄斑玻璃膜疣或AMD证据。

作为AREDS2研究方案的一部分20，基线访视时采集了立体彩色眼底照片对，并由威斯康星州眼底照片阅片中心（威斯康星大学麦迪逊分校，威斯康星州麦迪逊）的认证阅片者进行分级。本研究排除了威斯康星中心评级为"无法分级"的患眼（即目标视野内玻璃膜疣区域仅部分可见，例如存在遮挡性病变或照片质量不佳，无法对玻璃膜疣进行可靠评估）。

本研究使用4家诊所所在地的Bioptigen, Inc（北卡罗来纳州研究三角园）生产的SD-OCT系统，采集容积式矩形扫描（尺寸为6.7mm×6.7mm），具体采集方法已在既往文献中发表21。简言之，所有受试者的双眼均采集了以黄斑中心凹为中心的0°和90°容积扫描（分别定义为快速扫描方向为水平和垂直方向的扫描），每幅B扫描包含1000条A扫描，每个容积包含100幅B扫描。

在A2A SD-OCT研究中，345名AMD参与者中，314名至少有一只眼患有中期AMD；122名无AMD的对照受试者中，119名在基线时无眼部疾病21。本研究按照Leuschen等人21的方法，为每位受试者随机选取一只符合条件的患眼作为研究眼。本研究未测量眼轴长度。认证的SD-OCT阅片者对每个容积的扫描质量进行评估21。本研究默认选择0°容积扫描，若某一患眼的0°容积扫描质量不佳，则使用同一次访视的90°容积扫描替代；若两次扫描质量均不佳，则直接排除该患眼。被排除的患眼主要包括因眨眼或成像错误导致图像空白或质量极差的患眼，以及在图像采集过程中出现明显眼球运动或注视丢失的扫描容积。因此，本研究最终分析了314只中期AMD患眼中的269只，以及119只正常对照患眼中的115只。

相关资源链接：
http://people.duke.edu/~sf59/Farsiu_Ophthalmology_2013.pdf
http://people.duke.edu/~sf59/RPEDC_Ophth_2013_dataset.htm

引用文献：S. Farsiu, SJ. Chiu, R.V. O’Connell, F.A. Folgar, E. Yuan, J.A. Izatt, 及C.A. Toth，“利用光学相干断层扫描对伴或不伴中期年龄相关性黄斑变性的患眼进行定量分类”，《眼科学》（Ophthalmology），121(1)，162-172，2014年1月。若需使用本研究方法或数据集的任何部分，请引用该文献。若对本数据集有任何疑问，请联系Sina Farsiu博士或Cynthia A. Toth医学博士。封面图片由Harry Quan在Unsplash平台发布。

搜集汇总

背景与挑战

背景概述

该数据集包含38400张光学相干断层扫描（OCT）图像，来自269名AMD患者和115名正常受试者，用于老年性黄斑变性的研究和分割。数据集还包括年龄信息和分割边界，支持AMD的定量分类研究。