Fundus Quality Score (FQS)
收藏资源简介:
Fundus Quality Score (FQS) 数据集由清华大学深圳国际研究生院和深圳眼科医院联合创建,包含2246张眼底图像,每张图像有两个标签:一个连续的平均意见分数(MOS)和一个三级质量标签。该数据集旨在评估眼底图像质量,涵盖了临床诊断中常见的降质类型。数据集的创建过程经过严格的标注流程,由经验丰富的眼科医生进行标注,确保了数据集的专业性和可用性。FQS数据集主要应用于眼底图像质量评估,旨在提高临床诊断的准确性和效率。
The Fundus Quality Score (FQS) dataset was co-developed by Tsinghua University Shenzhen International Graduate School and Shenzhen Eye Hospital. It consists of 2246 fundus images, each annotated with two labels: a continuous Mean Opinion Score (MOS) and a three-level quality label. This dataset is designed for fundus image quality assessment and covers common degradation types frequently encountered in clinical practice. The dataset was built following a strict annotation workflow, with all annotations conducted by experienced ophthalmologists, ensuring its professionalism and usability. The FQS dataset is primarily applied to fundus image quality assessment, aiming to improve the accuracy and efficiency of clinical diagnosis.




