Friedrich-Alexander-University Erlangen-Nuremberg, Germany.
Int J Comput Assist Radiol Surg. 2010 Nov;5(6):557-64. doi: 10.1007/s11548-010-0479-7. Epub 2010 May 19.
Automated, objective and fast measurement of the image quality of single retinal fundus photos to allow a stable and reliable medical evaluation.
The proposed technique maps diagnosis-relevant criteria inspired by diagnosis procedures based on the advise of an eye expert to quantitative and objective features related to image quality. Independent from segmentation methods it combines global clustering with local sharpness and texture features for classification.
On a test dataset of 301 retinal fundus images we evaluated our method on a given gold standard by human observers and compared it to a state of the art approach. An area under the ROC curve of 95.3% compared to 87.2% outperformed the state of the art approach. A significant p-value of 0.019 emphasizes the statistical difference of both approaches.
The combination of local and global image statistics models the defined quality criteria and automatically produces reliable and objective results in determining the image quality of retinal fundus photos.
自动、客观、快速地测量单张眼底照片的图像质量，以便进行稳定、可靠的医学评估。
所提出的技术基于眼科专家的建议，将诊断相关标准映射到与图像质量相关的定量和客观特征上。它与分割方法无关，将全局聚类与局部锐度和纹理特征相结合进行分类。
在一个包含 301 张眼底图像的测试数据集上，我们根据人类观察者的金标准评估了我们的方法，并将其与最先进的方法进行了比较。ROC 曲线下的面积为 95.3%，优于最先进的方法的 87.2%。p 值显著为 0.019，强调了两种方法的统计学差异。
局部和全局图像统计的组合模拟了定义的质量标准，并自动生成可靠和客观的结果，用于确定眼底照片的图像质量。
