Chest X-Ray Image Dataset

Estimated reading: 3 minutes 2072 views

Visualization of the Chest X-ray Image Dataset in the Deep Lake UI

Chest X-Ray Image Dataset

What is Chest X-Ray Image Dataset?

The Chest X-Ray Image dataset consists of a total of approximately 5856 images. All chest X-ray imaging was chosen from retrospective cohorts of children aged one to five years and was done as part of the patients’ usual clinical treatment. Before being approved to train the AI system, all chest x – rays were first examined for quality control, and diagnoses for the radiographs were assessed by two expert physicians.

Download Chest X-Ray Image Dataset in Python

Instead of downloading the Chest X-Ray Image dataset in Python, you can effortlessly load it in Python via our Deep Lake open-source with just one line of code.

Load Chest X-Ray Image Dataset Training Subset in Python

				
					import deeplake
ds = deeplake.load('hub://activeloop/chest-xray-train')

Load Chest X-Ray Image Dataset Testing Subset in Python

				
					import deeplake
ds = deeplake.load('hub://activeloop/chest-xray-test')

Load Chest X-Ray Image Dataset Validation Subset in Python

				
					import deeplake
ds = deeplake.load('hub://activeloop/chest-xray-val')

Chest X-Ray Image Dataset Structure

Chest X-Ray Image Data Fields

images: tensor containing images of the dataset

labels: tensor containing labels that represent the 3 categories, normal, bacterial, and viral.

person_num: tensor containing the patient number. Note that this data field is available only for images belonging to bacterial and viral categories and is not available for normal categories.

Chest X-Ray Image Data Splits

The Chest X-Ray Image training set is composed of 5216 images.

The Chest X-Ray Image testing set is composed of 624 images.

The Chest X-Ray Image validation set is composed of 16 images.

How to use Chest X-Ray Image Dataset with PyTorch and TensorFlow in Python

Train a model on the Chest X-Ray Image dataset with PyTorch in Python

Let’s use Deep Lake built-in PyTorch one-line dataloader to connect the data to the compute:

				
					dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)

Train a model on Chest X-Ray Image dataset with TensorFlow in Python

				
					dataloader = ds.tensorflow()

Additional Information about Chest X-Ray Image Dataset

Chest X-Ray Image Dataset Description

Homepage: https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

Chest X-Ray Image Dataset Curators

Daniel S. Kermany, Michael Goldbaum, Wenjia Cai, Carolina C.S. Valentim, Huiying Liang, Sally L. Baxter, Alex McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, Justin Dong, Made K. Prasadha, Jacqueline Pei, Magdalene Y.L. Ting, Jie Zhu, Christina Li, Sierra Hewett, Jason Dong, Ian Ziyar, Alexander Shi, Runze Zhang, Lianghong Zheng, Rui Hou, William Shi, Xin Fu Yaou Duan, Viet A.N. Huu, Cindy Wen, Edward D. Zhang, Charlotte L. Zhang, Oulan Li, Xiaobo Wang, Michael A. Singer, Xiaodong Sun, Jie Xu, Ali Tafreshi, M. Anthony Lewis, Huimin Xia Kang Zhang

Chest X-Ray Image Dataset Licensing Information

CC BY 4.0

Chest X-Ray Image Dataset Citation Information

				
					@article{kermany2018identifying,
title={Identifying medical diagnoses and treatable diseases by image-based deep learning},
author={Kermany, Daniel S and Goldbaum, Michael and Cai, Wenjia and Valentim, Carolina CS and Liang, Huiying and Baxter, Sally L and McKeown, Alex and Yang, Ge and Wu, Xiaokang and Yan, Fangbing and others},
journal={Cell},
volume={172},
number={5},
pages={1122--1131},
year={2018},
publisher={Elsevier}
}