arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.00515eess.IVcs.CV
收藏

Deep-OCTA:用于糖尿病视网膜病变OCTA图像分析的嵌入式深度学习方法

Deep-OCTA: Ensemble Deep Learning Approaches for Diabetic Retinopathy Analysis on OCTA Images

Fudan University(复旦大学);Shanghai General Hospital, School of Medicine, Shanghai Jiao Tong University(上海交通大学医学院附属上海市第一人民医院)

Junlin Hou, Fan Xiao, Jilan Xu, Yuejie Zhang, Haidong Zou, Rui Feng

摘要:

超广角光学相干断层扫描血管造影(OCTA)已成为糖尿病视网膜病变(DR)诊断的重要影像学手段。然而,很少有研究集中在自动DR分析使用超宽OCTA。在本文中,我们提出了基于超宽OCTA的新颖实用的深度学习解决方案,用于糖尿病视网膜病变分析挑战赛(Diabetic Retinopathy Analysis Challenge,简称OCTA)。在DR病变的分割任务中,我们利用UNet和UNet++分割三个病变,具有强大的数据增强和模型集成。在图像质量评估任务中,我们创建了InceptionV 3、SE-ResNeXt和Vision Transformer模型的集合。在大数据集上进行预训练,并采用混合MixUp和CutMix策略来提高模型的泛化能力。在DR分级任务中,我们构建了一个Vision Transformer(ViT),并发现在彩色眼底图像上预训练的ViT模型可以作为OCTA图像的有用基底。我们提出的方法分别在三个排行榜上排名第4、第3和第5。源代码将在https://github.com/FDU-VTS/DRAC上提供。

英文摘要:

The ultra-wide optical coherence tomography angiography (OCTA) has become an important imaging modality in diabetic retinopathy (DR) diagnosis. However, there are few researches focusing on automatic DR analysis using ultra-wide OCTA. In this paper, we present novel and practical deep-learning solutions based on ultra-wide OCTA for the Diabetic Retinopathy Analysis Challenge (DRAC). In the segmentation of DR lesions task, we utilize UNet and UNet++ to segment three lesions with strong data augmentation and model ensemble. In the image quality assessment task, we create an ensemble of InceptionV3, SE-ResNeXt, and Vision Transformer models. Pre-training on the large dataset as well as the hybrid MixUp and CutMix strategy are both adopted to boost the generalization ability of our model. In the DR grading task, we build a Vision Transformer (ViT) and fnd that the ViT model pre-trained on color fundus images serves as a useful substrate for OCTA images. Our proposed methods ranked 4th, 3rd, and 5th on the three leaderboards of DRAC, respectively. The source code will be made available at https://github.com/FDU-VTS/DRAC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑