{"collection_id":"ct4harmonization_multicentric","collection_name":"CT4Harmonization-Multicentric","cancer_types":"Hemangioma, Pathologically Benign, Metastatic disease","tumor_locations":"Liver Phantom","species":"Phantom","subjects":1,"supporting_data":"Software/Source Code","description":"This collection introduces an open-source, anthropomorphic phantom-based dataset of CT scans for\ndeveloping harmonization methods for deep learning based models. The phantom mimics human anatomy,\nallowing repeated scans without radiation delivery to real patients and isolating scanner effects by\nremoving inter- and intra-patient variations. The dataset includes 268 image series from 13\nscanners, 4 manufacturers, and 8 institutions, repeated 18-30 times at a 10 mGy dose using a\nharmonized protocol. An additional 1,378 image series were acquired with the same 13 scanners and\nharmonized protocol but including additional acquisition doses. The presented phantom scans consist\nof three compartments from thorax, liver and test patterns. The 3D-printed liver includes three\ntypes of abnormal regions of interest, including two cysts, a metastasis, and a hemangioma, with\nground truth segmentation masks that could be used for classification and segmentation.\nPlease see the CT4Harmonization-Multicentric (https://doi.org/10.7937/M0PB-BH69) landing page to\nlearn more\nabout the images and to obtain any supporting metadata for this collection.","patients":1,"studies":1378,"series":2756,"instances":467224,"size_TB":0.252,"modalities":["CT","SEG"],"licenses":[{"license_short_name":"CC BY 4.0","series":2756,"size_TB":0.252}]}