Labeled Optical Coherence Tomography (OCT)

Dataset of validated OCT images described and analyzed in "Deep learning-based classification and referral of treatable human diseases". The OCT Images are split into a training set and a testing set of independent patients. OCT Images are labeled as (disease)-(randomized patient ID)-(image number by this patient) and split into 4 directories: CNV, DME, DRUSEN, and NORMAL. 250 files in directory ./test/CNV 250 files in directory ./test/DME 250 files in directory ./test/DRUSEN 250 files in directory ./test/NORMAL 37205 files in directory ./train/CNV 11348 files in directory ./train/DME 8616 files in directory ./train/DRUSEN 26315 files in directory ./train/NORMAL ## Acknowledgements Data: License: CC BY 4.0 ## Citation: Kermany D, Goldbaum M, Cai W et al. Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell. 2018; 172(5):1122-1131. doi:10.1016/j.cell.2018.

本数据集为经验证的OCT图像集，详细描述与分析见于《基于深度学习的可治疗人类疾病的分类与推荐》一文。OCT图像被划分为独立患者的训练集和测试集。图像标签形式为（疾病）-（随机患者ID）-（患者所拍摄图像编号），并分别存入四个目录：CNV、DME、DRUSEN和NORMAL。测试集目录./test/CNV、./test/DME、./test/DRUSEN及./test/NORMAL中各包含250个文件，而训练集目录./train/CNV、./train/DME、./train/DRUSEN及./train/NORMAL中分别含有37205、11348、8616及26315个文件。