Recently, diabetic retinopathy (DR) screening utilizing ultra-wide optical coherence tomography angiography (UW-OCTA) has been used in clinical practices to detect signs of early DR. However, developing a deep learning-based DR analysis system using UW-OCTA images is not trivial due to the difficulty of data collection and the absence of public datasets. By realistic constraints, a model trained on small datasets may obtain sub-par performance. Therefore, to help ophthalmologists be less confused about models' incorrect decisions, the models should be robust even in data scarcity settings. To address the above practical challenging, we present a comprehensive empirical study for DR analysis tasks, including lesion segmentation, image quality assessment, and DR grading. For each task, we introduce a robust training scheme by leveraging ensemble learning, data augmentation, and semi-supervised learning. Furthermore, we propose reliable pseudo labeling that excludes uncertain pseudo-labels based on the model's confidence scores to reduce the negative effect of noisy pseudo-labels. By exploiting the proposed approaches, we achieved 1st place in the Diabetic Retinopathy Analysis Challenge.
翻译:最近,利用超广光学一致性的摄影成像学成像学(UW-OCTA)进行糖尿病视网膜病(DR)筛查,在临床实践中用于检测早期DR的迹象。然而,利用UW-OCTA图像开发基于深学习的DR分析系统并非微不足道,因为数据收集困难和缺乏公共数据集。由于现实的限制因素,一个小数据集培训的模型可能会取得分级性能。因此,为了帮助眼科医生减少对模型不正确的决定的混淆,即使在数据稀缺的情况下,模型也应该是稳健的。为了解决上述实际挑战性的问题,我们为DR分析任务提供了全面的实证研究,包括损害分解、图像质量评估和DR分级。对于每一项任务,我们通过利用共性学习、数据增强和半超强的学习手段,引入一个强有力的培训计划。此外,我们提出了可靠的假标签,排除基于模型信心评分的不确定的假标签,以减少噪音假标签的负面效果。我们通过利用拟议的方法,在“挑战”分析中实现了“挑战分析”的位置。