Karadeniz Technical University, Department of Statistics and Computer Science, Faculty of Science, Trabzon 61080, Turkey.
Karadeniz Technical University, Department of Computer Engineering, Faculty of Engineering, Trabzon 61080, Turkey.
J Biomed Opt. 2014 Apr;19(4):046006. doi: 10.1117/1.JBO.19.4.046006.
Retinal image quality assessment (IQA) is a crucial process for automated retinal image analysis systems to obtain an accurate and successful diagnosis of retinal diseases. Consequently, the first step in a good retinal image analysis system is measuring the quality of the input image. We present an approach for finding medically suitable retinal images for retinal diagnosis. We used a three-class grading system that consists of good, bad, and outlier classes. We created a retinal image quality dataset with a total of 216 consecutive images called the Diabetic Retinopathy Image Database. We identified the suitable images within the good images for automatic retinal image analysis systems using a novel method. Subsequently, we evaluated our retinal image suitability approach using the Digital Retinal Images for Vessel Extraction and Standard Diabetic Retinopathy Database Calibration level 1 public datasets. The results were measured through the F1 metric, which is a harmonic mean of precision and recall metrics. The highest F1 scores of the IQA tests were 99.60%, 96.50%, and 85.00% for good, bad, and outlier classes, respectively. Additionally, the accuracy of our suitable image detection approach was 98.08%. Our approach can be integrated into any automatic retinal analysis system with sufficient performance scores.
视网膜图像质量评估 (IQA) 是自动视网膜图像分析系统获得准确和成功的视网膜疾病诊断的关键过程。因此，良好的视网膜图像分析系统的第一步是测量输入图像的质量。我们提出了一种用于寻找适合用于视网膜诊断的医学视网膜图像的方法。我们使用了一个由良好、不良和异常类组成的三级分级系统。我们创建了一个名为“糖尿病视网膜病变图像数据库”的总共 216 张连续图像的视网膜图像质量数据集。我们使用一种新方法在良好图像中识别适合自动视网膜图像分析系统的图像。随后，我们使用 Digital Retinal Images for Vessel Extraction 和 Standard Diabetic Retinopathy Database Calibration level 1 公共数据集评估了我们的视网膜图像适用性方法。结果通过 F1 度量进行衡量，F1 度量是精度和召回率度量的调和平均值。IQA 测试的最高 F1 分数分别为 99.60%、96.50%和 85.00%，适用于良好、不良和异常类。此外，我们的适用图像检测方法的准确率为 98.08%。我们的方法可以与具有足够性能分数的任何自动视网膜分析系统集成。
