Summary:

This dataset contains image annotations derived from the NCI Clinical Trial "Combination Chemotherapy With or Without Radiation Therapy in Treating Young Patients With Newly Diagnosed Stage III or Stage IV Wilms Tumor (AREN0533)”.  This curated dataset provides a comprehensive picture of imaging in pediatric patients with newly diagnosed primitive neuroectodermal tumors throughout their treatment and until any potential relapse. This is the largest known dataset of patients with supratentorial primitive neuroectodermal tumors and pineoblastomas. The key objective of this project was to generate a large and highly curated imaging dataset of pediatric medulloblastoma patients with annotations suitable for cancer researchers and AI developers. 

Annotation Protocol:

For each patient, every DICOM Study and DICOM Series was reviewed to identify and annotate the clinically relevant time points and sequences. In a typical patient the following time points will be annotated:

1. Pre-treatment CT chest and abdomen
2. CT chest and/or CT abdomen at 6 weeks
3. Possible CT abdomen at 12 weeks. 

At each timepoint, volumetric segmentations, (DICOM RTSTRUCT), seed points (DICOM RTSTRUCT) and negative finding assessments (DICOM RTSTRUCT) were created:

1. SNOMED-CT “Anatomic Region Sequence” and “Segmented Property Category Code Sequence” and codes will be inserted for all segmented structures.
2. Imaging time point codes will be inserted to help identify each annotation in the context of the clinical trial assessment protocol. 

1. “Clinical Trial Time Point ID” will be used to encode time point type using one of the following strings as applicable: “pre-dose” or “post-chemotherapy”
2. Content Item in “Acquisition Context Sequence” will be added containing "Time Point Type" using Concept Code Sequence (0040,A168) selected from:

1. (255235001, SCT, “Pre-dose”)
2. (262502001, SCT, "Post-chemotherapy")
3. (262502001, SCT, "Post-chemotherapy")

Important supplementary information and sample code

1. A spreadsheet containing a variety of useful metadata about the annotations, including calculated tumor volumes, is available in the Data Access section below.
2. Important information about how to interpret the DICOM annotation data can be found on the Detailed Description section below.  It includes information about specific tags which document where the tumor was found, whether it was enhancing/non-enhancing, which study time point the annotation relates to, details for lesion tracking across time points, etc.
3. A Jupyter notebook demonstrating how to use the NBIA Data Retriever Command-Line Interface application and our REST API (with authentication) to access these data can be found in the Additional Resources section below.

Put Collection Abstract here.  If it's really long ask them to help you break it up such that the most important summary stuff is here and the rest goes in the Detailed Description tab.