[data request] A Large-Scale CT and PET/CT Dataset for Lung Cancer Diagnosis (Lung-PET-CT-Dx)

• Name of dataset: A Large-Scale CT and PET/CT Dataset for Lung Cancer Diagnosis (Lung-PET-CT-Dx)
• URL of dataset: https://wiki.cancerimagingarchive.net/download/attachments/70224216/Lung-PET-CT-Dx-NBIA-manifest-07242020.tcia?api=v2, https://wiki.cancerimagingarchive.net/download/attachments/70224216/Lung-PET-CT-Dx-Annotations-XML-Files-rev07142020.zip?version=1&modificationDate=1594757790879&api=v2
• License of dataset: Creative Commons Attribution 3.0 Unported License
• Short description of dataset and use case(s): This data set consists of CT and PET-CT DICOM images of lung cancer subjects alongside XML Annotation files which highlight tumor location using boundary boxes. Images were retrospectively obtained from patients who received standard-of-care lung biopsy and PET/CT with suspicion of lung cancer. Patient DICOMS are categorized into Adenocarcinoma, Small Cell Carcinoma, Large Cell Carcinoma, and Squamous Cell Carcinoma. The locations of tumors in each DICOM have been annotated by 5 academic thoracic radiologists to make this dataset useful towards developing algorithms for medical diagnosis.

Folks who would also like to see this dataset in tensorflow/datasets, please thumbs-up so the developers can know which requests to prioritize.

And if you'd like to contribute the dataset (thank you!), see our guide to adding a dataset.

Start with docs/add_dataset.md and review the linked Lung-PET-CT-Dx manifest and annotation files to understand the requested dataset. Follow the contribution guide and verify that the resulting dataset definition represents the provided CT, PET/CT, DICOM, and XML annotation data as described.