gOLIVES/OLIVES_Dataset
收藏资源简介:
OLIVES数据集是一个眼科医学领域的数据集,旨在解决现有数据集在疾病预测和生物标志物评估方面的不足。该数据集包含多种数据模态,包括临床标签、生物标志物、眼底图像和光学相干断层扫描(OCT)图像,以及时间序列的患者治疗信息。具体来说,数据集包含1268张眼底图像,每张图像对应49个OCT扫描和16个生物标志物,以及3个临床标签和DR或DME的疾病诊断。数据集还提供了96只眼睛的数据,这些数据平均覆盖了至少两年的治疗期,每只眼睛平均接受了66周的治疗和7次注射。OLIVES数据集在机器学习研究领域具有优势,特别是在自监督学习方面,因为它提供了基于医学的增强方案。
The OLIVES dataset is a medical dataset in the field of ophthalmology, designed to address the limitations of existing datasets in disease prediction and biomarker assessment. The dataset includes multiple data modalities such as clinical labels, biomarkers, fundus images, and Optical Coherence Tomography (OCT) scans, along with time-series patient treatment information. Specifically, the dataset contains 1268 fundus images, each associated with 49 OCT scans and 16 biomarkers, as well as 3 clinical labels and a diagnosis of DR or DME. The dataset also provides data for 96 eyes, averaging at least two years of treatment, with each eye receiving an average of 66 weeks of treatment and 7 injections. The OLIVES dataset has advantages in the field of machine learning research, particularly in self-supervised learning, as it provides medically grounded augmentation schemes.
OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
概述
- 名称: OLIVES Dataset
- 领域: 医学
- 标签: 眼科
- 规模: 10K<n<100K
数据集配置
- 默认配置:
- 数据文件:
- 分割: biomarkers
- 路径:
- "biomarkers/*.png"
- "biomarkers/*.tif"
- "biomarkers/metadata.csv"
- 数据文件:
数据集内容
- 图像: 1268张眼底图像,每张图像包含49张OCT扫描图像。
- 生物标志物: 16种生物标志物。
- 临床标签: 3种临床标签。
- 疾病诊断: 糖尿病视网膜病变(DR)或糖尿病黄斑水肿(DME)。
- 时间序列信息: 96只眼睛的数据,平均治疗时间为66周,平均注射次数为7次。
标签分类
- 完整标签: 包含所有用于相关研究的临床信息。
- 机器学习中心标签:
- Biomarker_Clinical_Data_Images.csv: 包含9408张图像的完整生物标志物和临床标签。
- Clinical_Data_Images.xlsx: 包含78000+张图像的BCVA、CST、Eye ID和Patient ID。
数据下载示例
python from datasets import load_dataset from torch.utils.data import DataLoader
olives = load_dataset(gOLIVES/OLIVES_dataset,split=train) olives = olives.with_format("torch") dataloader = DataLoader(olives, batch_size=4) for batch in dataloader: print(batch)
print(olives[0][VMT])
引用
plaintext @inproceedings{prabhushankarolives2022, title={OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics}, author={Prabhushankar, Mohit and Kokilepersaud, Kiran and Logan, Yash-yee and Trejo Corona, Stephanie and AlRegib, Ghassan and Wykoff, Charles}, booktitle={Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 2 (NeurIPS Datasets and Benchmarks 2022) }, year={2022} }




