Silicodata: An Annotated Benchmark CXR Dataset for Silicosis Detection
This research attempts to provide the first of its type public dataset for silicosis detection. The dataset contains frontal chest X-rays collected over three years. The data was collected from stone workers in the primary health centers of Rajasthan, India. The dataset contains samples of silicosis, STB, TB and normal. The dataset is divided into two sets:
Set A: It contains images with only disease labels. The total count is 3044 samples.
Set B contains images with lung segmentation maps, annotations, radiology reports and disease labels. The total count is 445 samples.
- The database can be downloaded from the following link: SilicoData
- To obtain access to the dataset, please email the duly filled license agreement to databases@iab-rubric.org with the subject line "Licence agreement for Silicodata dataset".
- NOTE: The license agreement has to be signed by someone with legal authority to sign it on behalf of the institute, such as the head of the institution or registrar. If a license agreement is signed by someone else, it will not be processed further.
- If you use the database in any publications or reports, you must refer to the following paper:
- Akhter Y, Ranjan R, Vatsa M, Singh R, Chaudhury S, Agrawal A, Rao P, Aggarwal S, Kalyanpur A. Silicodata: An Annotated Benchmark CXR Dataset for Silicosis Detection, Nature Scientific Data.