Image AddedThis dataset contains image annotations derived from the NCI Clinical Trial "Chemotherapy and Radiation Therapy in Treating Young Patients With Newly Diagnosed, Previously Untreated, High-Risk Medulloblastoma/PNET (ACNS0332)".  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. It is primed for both human and AI software analysis. 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 clinically relevant time points and sequences. In a typical patient the following time points were annotated:

1. Pre-surgical study
2. Post-surgical study [if applicable]
3. Follow-up study at the completion of radiotherapy.
4. Follow-up study at the end of chemotherapy.
5. Follow-up study relapse [if applicable]

At each time point, the following items were annotated:

1. Enhancing tumor on an axial 3D T1 post contrast sequence
   1. If not available, a 3D post contrast sequence in another plane was used.
   2. If no 3D post contrast sequence was available, the tumor was annotated in all 3 planes utilizing 2D post contrast sequences.
   3. On post-contrast sequences, the entire tumor, including the cystic and non enhancing components was annotated.
   4. Any resection cavity or post-op changes/products was excluded.
2. Edema on an axial T2 FLAIR sequence
   1. If not available, an axial T2 or other T2 weighted sequence was used.
   2. The segmentation mask contains both the edematous tissue and the tumor.
3. The portion of the tumor demonstrating restricted diffusion on an ADC sequence
4. Up to 5 metastatic lesions within the brain and and up to 5 metastatic lesions in the spine as demonstrated on whatever T1 post contrast sequence they are visualized on
   1. When present, the 5 largest lesions were annotated.
5. A manually placed seed point (kernel) were created for each segmented structure
   1. The seed points for each segmentation are provided in a separate DICOM RTSS file.
   2. Spinal metastases, which are too small to apply a volumetric mask to, only have a seed point annotation.

Important information added to DICOM headers:

1. Anatomic Region Sequence (0x0008, 0x2218) was inserted containing CNS Segmentation Types as defined in: https://dicom.nema.org/medical/dicom/current/output/chtml/part16/sect_CID_7153.html. In cases where tumor spans multiple regions, multiple location codes were inserted. For example, if the tumor is centered in the parietal lobe, but also involves the frontal and temporal lobes, anatomical codes for all three locations were attached to the structure.
2. Segmented Property Category Code Sequence (0x0062,0x0003) was inserted into DICOM SEG objects containing one of the following codes:
   • (NCIt, C113842, "Enhancing Lesion")
   • (NCIt, C81175, "Non-Enhancing Lesion")
   • (SNOMED-CT, 14799000, "Neoplasm, Secondary")
   • (SNOMED-CT, 79654002, "Edema")
3. Tracking ID (0x0062,0x0020) and Tracking UID (0x0062,0x0021) tags were inserted for each segmented structure to enable longitudinal lesion tracking.
4. A study time point description was inserted into the Clinical Trial Time Point ID (0x0012,0x0050) attribute to help identify each annotation in the context of the clinical trial assessment protocol. The time point description contains one of the following strings: pre-operative, post-operative, post-radiation, post-chemotherapy, or recurrence. Additionally, a Concept Name Code Sequence (0x0040, 0xA043) and Concept Code Sequence (0x0040,0xA168) were added to Acquisition Context Sequence (0x0040, 0x0555).The former defines a Time Point Type concept and latter is populated with one of the following concepts:
   • (SNOMED-CT, 262068006, "Pre-operative")
   • (SNOMED-CT, 262061000, "Post-operative")
   • (SNOMED-CT, 264908009, "Post-radiation")
   • (SNOMED-CT, 262502001, "Post-chemotherapy")
   • (SNOMED-CT, 25173007, "Recurrent tumor (finding)")
5. For reviewed studies with no radiologic findings, a "negative" DICOM SEG and/or RTSS file are provided. These files contain no segmentation or contour data, but still contain pertinent metadata in Clinical Trial Time Point ID, Acquisition Context Sequence, Anatomic Region Sequence, and Segmented Property Category Code Sequence. The primary motivation for providing these annotations is to capture the information that no radiologic findings (e.g. progression or new metastatic disease) were found during review.