Fully Automatic Segmentation of Fluorescein Leakage in Subjects With Diabetic Macular Edema
Fully Automatic Segmentation of Fluorescein Leakage in Subjects With Diabetic Macular Edema
复制标题
DOI：
10.1167/iovs.14-15457
复制
发表时间：
2015-03-01
影响因子：
4.4
通讯作者：
Farsiu, Sina
中科院分区：
文献类型：
--
作者：
Rabbani, Hossein;Allingham, Michael J.;Farsiu, Sina
目的.目的：建立和验证一种能够自动分割糖尿病性黄斑水肿（DME）患者临床荧光素血管造影（FA）图像中渗漏区域的软件。回顾性分析24例（24只眼）DME患者的血管造影图像。使用Heidelberg Spectralis 6模式HRA/OCT装置获得视频和静止帧图像。我们对齐早期和晚期FA帧的视频中的两步非刚性注册方法。为了去除背景伪影，我们减去了早期和晚期FA帧。最后，经过后处理步骤，包括检测和修复的血管，一个强大的主动轮廓方法被用来获得泄漏面积在一个1500 μ m半径的圆形区域为中心的中央凹。图像是在不同的视场（FOV）下捕获的，并且经常被离群值污染，就像现实世界的临床成像一样。我们的算法应用于这些图像，没有手动输入。另外，所有图像都由两名视网膜专家手动分割。计算人工观察者间、人工观察者内和自动方法的敏感性、特异性和准确性。自动与手动分割方法的平均准确度为0.86 ± 0.08，手动观察者间分割方法为0.83 ± 0.16，手动观察者内分割方法为0.90 ± 0.08。我们的全自动算法可以重复和准确地量化临床级FA视频的泄漏面积，并与专家手动分割一致。对于不同的DME亚型，性能是可靠的。这种方法有可能减少时间和劳动力成本，并可能产生客观和可重复的定量测量DME成像生物标志物。
PURPOSE. To create and validate software to automatically segment leakage area in real-world clinical fluorescein angiography (FA) images of subjects with diabetic macular edema (DME).METHODS. Fluorescein angiography images obtained from 24 eyes of 24 subjects with DME were retrospectively analyzed. Both video and still-frame images were obtained using a Heidelberg Spectralis 6-mode HRA/OCT unit. We aligned early and late FA frames in the video by a two-step nonrigid registration method. To remove background artifacts, we subtracted early and late FA frames. Finally, after postprocessing steps, including detection and inpainting of the vessels, a robust active contour method was utilized to obtain leakage area in a 1500-mu m-radius circular region centered at the fovea. Images were captured at different fields of view (FOVs) and were often contaminated with outliers, as is the case in real-world clinical imaging. Our algorithm was applied to these images with no manual input. Separately, all images were manually segmented by two retina specialists. The sensitivity, specificity, and accuracy of manual interobserver, manual intraobserver, and automatic methods were calculated.RESULTS. The mean accuracy was 0.86 +/- 0.08 for automatic versus manual, 0.83 +/- 0.16 for manual interobserver, and 0.90 +/- 0.08 for manual intraobserver segmentation methods.CONCLUSIONS. Our fully automated algorithm can reproducibly and accurately quantify the area of leakage of clinical-grade FA video and is congruent with expert manual segmentation. The performance was reliable for different DME subtypes. This approach has the potential to reduce time and labor costs and may yield objective and reproducible quantitative measurements of DME imaging biomarkers.