{"collection_id":"pseudo_phi_dicom_data","collection_name":"Pseudo-PHI-DICOM-Data","cancer_types":"Various","tumor_locations":"Various","species":"Human","subjects":42,"supporting_data":null,"description":"The process of image de-identification is time consuming, requires significant human resources, and\nis prone to human error. Automated image de-identification algorithms have been developed but the\nresearch community requires some method of evaluation before such tools can be widely accepted.\nThis evaluation requires a robust dataset that can be used as part of an evaluation process for\nde-identification algorithms. We developed a DICOM dataset that can be used to evaluate the\nperformance of de-identification algorithms.\nPlease see the\nMedical Imaging De-Identification Initiative (MIDI) (https://doi.org/10.7937/s17z-r072) wiki page\nto learn more about the images and to obtain\nany\nsupporting metadata for this collection.","patients":42,"studies":44,"series":52,"instances":3386,"size_TB":0.001,"modalities":["CR","CT","DX","MG","MR","PT"],"licenses":[{"license_short_name":"CC BY 4.0","series":52,"size_TB":0.001}]}