This collection comprises 25 patients with Manufacturer CT at Veteran's Hospital before treatment and 2 follow up T1-weighted and FLAIR MRI along with accompanying digitized histopathology (H&E stained) images of corresponding biopsy specimens. Each slide was digitized at 10x magnification using an Aperio slide scanner resulting in a set of .svs images. Annotations of cancer presence on the pseudo-whole mount sections were made by an expert pathologist. Segmentation was performed with by Software (github, below) and compared to expert radiologist segmentation. co-registered the corresponding radiologic and histopathologic tissue sections to map disease extent onto the corresponding MRI scans. Co-clinical data that led to this therapy in humans is available within TCIA (here) as ThisOther Collection. For more information about the original aims of this trial please see: http://meeting.conference.org/abstract/35849. |
DICOM Data was provided by Principal Investigator, PhD, University of City and Co-Investigator, MD, City Veteran's Hospital. This work was supported by NIH Grant (link). Pathology segmentations were performed by Helpful Expert, MD.
Prior F, Clark K, Commean P, Freymann J, Jaffe C, Kirby J, et al. TCIA: an information resource to enable open science. Engineering in Medicine and Biology Society (EMBC), 35th Int’l Conf of the IEEE, Osaka: IEEE; 2013:1282-5. PMCID: PMC4257783 DOI: 10.1109/EMBC.2013.6609742
Moore S, Maffitt D, Smith K, Kirby J, Clark K, Freymann J, et al. De-identification of Medical Images with Retention of Scientific Research Value. RadioGraphics. 2015;35:3:727-35. DOI: 10.1148/rg.2015140244
For scientific inquiries about this dataset, please contact Junior Investigator through the TCIA Helpdesk: help@cancerimagingarchive.net
|