Summary
The goal of the CT segmentation challenge was to compare the bias (where possible) and repeatability of automatic, semi-automatic and manual segmentations for lung CT studies. Investigators from Columbia, MGH, Moffitt and Stanford identified 50 lung CT nodules and made available the data in DICOM format. Algorithm developers and users were requested to submit at least 4 repetitions of their algorithm for each nodule. A variety of image formats for the segmentation volumes were utilized including NIFTI, NRRD, JPG, PNG, DICOM-SEG, DICOM-RT, AIM, and LIDC-XML. The results were ultimately converted into DICOM-SEG format and uploaded back to TCIA.
Citation
TBD
Data Description
Images from multiple TCIA collections were utilized in the challenge and general information about nodule locations were provided as follows:
Image Collection | Nodule Locations |
---|---|
Lung Phantom (CUMC) | Lung Phantom Nodule Locations |
QIN Lung and QIN Lung LSC (Moffitt - restricted access) | QIN Lung Nodule Locations |
RIDER Lung CT (MSKCC) | RIDER Lung CT Nodule Locations |
NSCLC Radiogenomics (Stanford) | NSCLC Radiogenomics Nodule Locations |
LIDC-IDRI (multi-site) | LIDC-IDRI Nodule Locations |
Data Downloads
Content Type | File Format | Notes |
---|---|---|
Images + Segmentations | DICOM (CT, SEG) | Use this link to download all of images and segmentations associated with the challenge |
Segmentations | NIFTI | Use this link to download only the segmentation files in NIFTI format |
The subset of image data from each collection that was used in this challenge can be downloaded using the following Shared Lists:
- QIN Lung CT Challenge
- QIN Lung CT Challenge (public data only)
Note: To obtain access for QIN Lung and QIN Lung LSC collections please contact the helpdesk and request permission.