Salvato in:
Dettagli Bibliografici
Autori principali: Shang, Fangxin, Fu, Jie, Yang, Yehui, Huang, Haifeng, Liu, Junwei, Ma, Lei
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2312.00377
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929275614003200
author Shang, Fangxin
Fu, Jie
Yang, Yehui
Huang, Haifeng
Liu, Junwei
Ma, Lei
author_facet Shang, Fangxin
Fu, Jie
Yang, Yehui
Huang, Haifeng
Liu, Junwei
Ma, Lei
contents Large-scale public datasets with high-quality annotations are rarely available for intelligent medical imaging research, due to data privacy concerns and the cost of annotations. In this paper, we release SynFundus-1M, a high-quality synthetic dataset containing over one million fundus images in terms of \textbf{eleven disease types}. Furthermore, we deliberately assign four readability labels to the key regions of the fundus images. To the best of our knowledge, SynFundus-1M is currently the largest fundus dataset with the most sophisticated annotations. Leveraging over 1.3 million private authentic fundus images from various scenarios, we trained a powerful Denoising Diffusion Probabilistic Model, named SynFundus-Generator. The released SynFundus-1M are generated by SynFundus-Generator under predefined conditions. To demonstrate the value of SynFundus-1M, extensive experiments are designed in terms of the following aspect: 1) Authenticity of the images: we randomly blend the synthetic images with authentic fundus images, and find that experienced annotators can hardly distinguish the synthetic images from authentic ones. Moreover, we show that the disease-related vision features (e.g. lesions) are well simulated in the synthetic images. 2) Effectiveness for down-stream fine-tuning and pretraining: we demonstrate that retinal disease diagnosis models of either convolutional neural networks (CNN) or Vision Transformer (ViT) architectures can benefit from SynFundus-1M, and compared to the datasets commonly used for pretraining, models trained on SynFundus-1M not only achieve superior performance but also demonstrate faster convergence on various downstream tasks. SynFundus-1M is already public available for the open-source community.
format Preprint
id arxiv_https___arxiv_org_abs_2312_00377
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of Annotation
Shang, Fangxin
Fu, Jie
Yang, Yehui
Huang, Haifeng
Liu, Junwei
Ma, Lei
Computer Vision and Pattern Recognition
Artificial Intelligence
Large-scale public datasets with high-quality annotations are rarely available for intelligent medical imaging research, due to data privacy concerns and the cost of annotations. In this paper, we release SynFundus-1M, a high-quality synthetic dataset containing over one million fundus images in terms of \textbf{eleven disease types}. Furthermore, we deliberately assign four readability labels to the key regions of the fundus images. To the best of our knowledge, SynFundus-1M is currently the largest fundus dataset with the most sophisticated annotations. Leveraging over 1.3 million private authentic fundus images from various scenarios, we trained a powerful Denoising Diffusion Probabilistic Model, named SynFundus-Generator. The released SynFundus-1M are generated by SynFundus-Generator under predefined conditions. To demonstrate the value of SynFundus-1M, extensive experiments are designed in terms of the following aspect: 1) Authenticity of the images: we randomly blend the synthetic images with authentic fundus images, and find that experienced annotators can hardly distinguish the synthetic images from authentic ones. Moreover, we show that the disease-related vision features (e.g. lesions) are well simulated in the synthetic images. 2) Effectiveness for down-stream fine-tuning and pretraining: we demonstrate that retinal disease diagnosis models of either convolutional neural networks (CNN) or Vision Transformer (ViT) architectures can benefit from SynFundus-1M, and compared to the datasets commonly used for pretraining, models trained on SynFundus-1M not only achieve superior performance but also demonstrate faster convergence on various downstream tasks. SynFundus-1M is already public available for the open-source community.
title SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of Annotation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2312.00377