Child pages
  • A whole-body FDG-PET/CT dataset with manually annotated tumor lesions (FDG-PET-CT-Lesions)

Summary

Purpose: To provide an annotated data set of oncologic PET/CT studies for the development and training of machine learning methods and to help address the limited availability of publicly available high-quality training data for PET/CT image analysis projects.  This data can also be used for machine learning challenges, which is exemplified in the autoPET MICCAI 2022 competition: https://autopet.grand-challenge.org/.  

Data: The anonymized publication of data was approved by the local ethics committee and data protection officer. 501 consecutive whole body FDG-PET/CT data sets of patients with malignant lymphoma, melanoma and non small cell lung cancer (NSCLC) as well as 513 data sets without PET-positive malignant lesions (negative controls) examined between 2014 and 2018 at the University Hospital Tübingen were included. All examinations were acquired on a single, state-of-the-art PET/CT scanner (Siemens Biograph mCT). The imaging protocol consists of a diagnostic CT scan (mainly from skull base to mid-thigh level) with intravenous contrast enhancement in most cases, except for patients with contraindications. The following CT parameters were used: reference dose of 200 mAs, tube voltage of 120 kV, iterative reconstruction with a slice thickness of 2 - 3 mm. In addition, a whole-body FDG-PET scan was acquired 60 minutes after I.V. injection of 300-350 MBq 18F-FDG. PET data were reconstructed using an ordered-subset expectation maximization (OSEM) algorithm with 21 subsets and 2 iterations and a gaussian kernel of 2 mm and a matrix size of 400 x 400.

All data sets were analyzed in a clinical setting by a radiologist and nuclear medicine physician in consensus identifying primary tumors and metastases in each data set. All FDG-avid lesions identified as malignant based on patient history and prior examinations were manually segmented on PET images in a slice-per-slice manner by a single reader using dedicated software (NORA imaging platform, University of Freiburg, Germany).

We provide the anonymized original DICOM files of all studies as well as the DICOM segmentation masks. Primary diagnosis, age and sex are provided as non-imaging information (csv). In addition, we provide links to code for you to make a preprocessed version of the data with resampled and aligned PET, CT, and masks as a NIfTI file and in the hdf5 format ready to use in machine learning projects. 

Acknowledgements

We would like to acknowledge the individuals and institutions that have provided data for this collection:

  • University Hospital Tübingen, Tübingen, Germany - Special thanks
    • Christian La Fougère, MD from the Department of Nuclear Medicine 
    • Tobias Hepp, MD from the Department of Radiology
    • Konstantin Nikolaou, MD from the Department of Radiology
    • Christina Pfannenberg, MD from the Department of Radiology 
  • University Hospital of the LMU (Munich), Germany – Special thanks
    • Clemens Cyran, MD from the Department of Radiology
    • Michael Ingrisch from the Department of Radiology


Data Access

Some data in this collection contains images that could potentially be used to reconstruct a human face. To safeguard the privacy of participants, users must sign and submit a TCIA Restricted License Agreement to help@cancerimagingarchive.net before accessing the data.

Data TypeDownload all or Query/FilterLicense
Images (DICOM, 418.9 GB)

TCIA Restricted

Clinical data (CSV)

CC BY 4.0

Click the Versions tab for more info about data releases.

Additional Resources for this Dataset



Detailed Description

Image Statistics

Radiology Image Statistics

Modalities

PT, CT, SEG

Number of Patients

900

Number of Studies

1014

Number of Series

3088

Number of Images

916,957

Images Size (GB)418.9

Notes: 

Here are conversion scripts for these data https://github.com/lab-midas/TCIA_processing

  • Converts DICOM to NIfTI , and also create resampled/resliced CT and an SUV file using tcia_dicom_to_nifti.py (requires install of dicom2nifti and matplotlib)
  • It is straight forward to generate HDF5 files from the NIfTI files using tcia_nifti_to_hdf5.py.
  • Organizes NIfTI into HDF5 structure; note this output is a single large package.

SEG are most easily reviewed as overlay using MITK viewer or 3D Slicer.


Citations & Data Usage Policy

Users must abide by the TCIA Data Usage Policy and Restrictions. Attribution should include references to the following citations:

Data Citation

Gatidis S, Kuestner T. A whole-body FDG-PET/CT dataset with manually annotated tumor lesions (FDG-PET-CT-Lesions) [Dataset]. The Cancer Imaging Archive, 2022. DOI: 10.7937/gkr0-xv29 

TCIA Citation

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. DOI: 10.1007/s10278-013-9622-7

Other Publications Using This Data

TCIA maintains a list of publications which leverage TCIA data. If you have a manuscript you'd like to add please contact the TCIA Helpdesk.

Version 1 (Current): Updated 2022/06/02

Data TypeDownload all or Query/FilterLicense
Images (DICOM, 418.9 GB)

TCIA Restricted

Clinical data (CSV)

CC BY 4.0

  • No labels