This collection contains FDG-PET/CT and radiotherapy planning CT imaging data of 300 patients from four different institutions in Québec with histologically proven head-and-neck cancer (H&N) All patients had pre-treatment FDG-PET/CT scans between April 2006 and November 2014, and within a median of 18 days (range: 6-66) before treatment (Note: date in the TCIA images have been changed in the interest of deidentification; the same change was applied across all images, preserving the time intervals between serial scans).
For 93 of the 300 patients (31 %), the radiotherapy contours were directly drawn on the CT of the FDG-PET/CT scan by expert radiation oncologists and thereafter used for treatment planning. For 207 of the 300 patients (69 %), the radiotherapy contours were drawn on a different CT scan dedicated to treatment planning and were propagated/resampled to the FDG-PET/CT scan reference frame using intensity-based free-form deformable registration with the software MIM® (MIM software Inc., Cleveland, OH).
Patients with recurrent H&N cancer or with metastases at presentation, and patients receiving palliative treatment were excluded from the study. From the 300 patients, 48 received radiation alone (16 %) and 252 received chemo-radiation (84 %) with curative intent as part of treatment management. The median follow-up period of all patients was 43 months (range: 6-112). Patients that did not develop a locoregional recurrence or distant metastases during the follow-up period and that had a follow-up time smaller than 24 months were also excluded from the study. During the follow-up period, 45 patients developed a locoregional recurrence (15 %), 40 patients developed distant metastases (13 %) and 56 patients died (19 %). Further information specific to each patient cohort (e.g. treatment details, image scanning protocols, etc.) is available in the following study:
In our study, we analyzed the FDG-PET and CT images of the 300 patients from four different cohorts for the risk assessment of locoregional recurrences (LR) and distant metastases in H&N cancer. Prediction models combining radiomic and clinical variables were constructed via random forests and imbalance-adjustment strategies using two of the four cohorts. Independent validation of the prediction and prognostic performance of the models was carried out on the other two cohorts (LR: AUC = 0.69 and CI = 0.67; DM: AUC = 0.86 and CI = 0.88). Furthermore, the results obtained via Kaplan-Meier analysis demonstrated the potential of radiomics for assessing the risk of specific tumour outcomes using multiple stratification groups.
See the DOI below for more details and links to access the whole dataset. Please contact Martin Vallières (firstname.lastname@example.org) of the Medical Physics Unit of McGill University for any scientific inquiries about this dataset. UPDATE: Errors were found in the initial data curation for the HN-HGJ-068 and HN-CHUS-079 patients. These patients were thus removed from this collection, which now contains a total of 298 patients.
We would like to acknowledge the individuals and institutions that have provided data for this collection:
- McGill University, Montreal, Canada - Special thanks to Martin Vallières of the Medical Physics Unit
Choosing the Download option will provide you with a file to launch the TCIA Download Manager to download the entire collection. If you want to browse or filter the data to select only specific scans/studies please use the Search By Collection option.
|Data Type||Download all or Query/Filter|
|Images (DICOM, 58.1 GB)|
|Clinical Data (XLS)|
|Names of GTV contours (XLS)|
|Source Code (web)|
Click the Versions tab for more info about data releases.
Number of Patients
Number of Studies
Number of Series
Number of Images
|Images Size (GB)||58.1|
We hope the available data and source code will facilitate the standardization and reproducibility of methods in the radiomics community.
- Clinical Data – This spreadsheet includes patient information, histopathological type, tumour grade, outcome follow-up information (metastases, survival), etc.
- Names of GTV contours -- This spreadsheet contains all the names of the "GTV primary" and "GTV lymph nodes" structures (as found in the associated RTstruct files) used in the publication of (Vallières et al., Sci Rep 7, 2017). Names of different structures are separated by commas in a given entry of the spreadsheet.
- Source Code – All software code implemented in this work is freely shared under the GNU General Public License at:https://github.com/mvallieres/radiomics.
Note: the images contain no private-vendor DICOM tags.
Citations & Data Usage Policy
This collection is freely available to browse, download, and use for commercial, scientific and educational purposes as outlined in the Creative Commons Attribution 3.0 Unported License. See TCIA's Data Usage Policies and Restrictions for additional details. Questions may be directed to email@example.com.
Please be sure to include the following citations in your work if you use this data set:
Martin Vallières, Emily Kay-Rivest, Léo Jean Perrin, Xavier Liem, Christophe Furstoss, Nader Khaouam, Phuc Félix Nguyen-Tan, Chang-Shu Wang, Khalil Sultanem. (2017). Data from Head-Neck-PET-CT. The Cancer Imaging Archive. doi: 10.7937/K9/TCIA.2017.8oje5q00
Vallières, M. et al. Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep 7, 10117 (2017). doi:10.1038/s41598-017-10371-5
Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. (paper)
Other Publications Using This Data
TCIA maintains a list of publications which leverage our data. At this time we are not aware of other publications based on this data. If you have a publication you'd like to add please contact the TCIA Helpdesk.
- No labels