A newer version of this dataset is available. View the latest version.
Data for the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics
Cite this dataset:
Gotsis, Dimitrios; Kelkar, Varun; Deshpande, Rucha; Brooks, Frank; KC, Prabhat; Myers, Kyle; Zeng, Rongping; Anastasio, Mark (2023): Data for the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics. University of Illinois at Urbana-Champaign. https://doi.org/10.13012/B2IDB-2773204_V1
Use this persistent URL to link to this dataset:
Dataset Description

This repository contains the training dataset associated with the 2023 Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics (DGM-Image Challenge), hosted by the American Association of Physicists in Medicine. This dataset contains more than 100,000 8-bit images of size 512x512. These images emulate coronal slices from anthropomorphic breast phantoms adapted from the VICTRE toolchain [1], with assigned X-ray attenuation coefficients relevant for breast computed tomography. Please follow the instructions given on the following page in order to register for the challenge: https://www.aapm.org/GrandChallenge/DGM-Image/.

[1] Badano, Aldo, et al. "Evaluation of digital breast tomosynthesis as replacement of full-field digital mammography using an in-silico imaging trial." JAMA network open 1.7 (2018): e185474-e185474

Subject Technology and Engineering
Keywords Deep generative models; breast computed tomography
License CC BY
Funder U.S. National Institutes of Health (NIH)-Grant:R01 EB031585
Funder American Association of Physicists in Medicine
Corresponding Creator Mark Anastasio
Downloaded 44 times
Version DOI Comment Publication Date
3 10.13012/B2IDB-2773204_V3 Added add a file containing image labels (breast_types.csv), and 4 example images (PNG) from each breast type. 2023-11-14
1 10.13012/B2IDB-2773204_V1 2023-07-17
Open in Globus File Manager what's this?
2.23 KB File
7.67 GB File

Contact the Research Data Service for help interpreting this log.

update: {"nested_updated_at"=>[Thu, 25 Apr 2024 14:48:46.345509000 UTC +00:00, Fri, 26 Apr 2024 16:58:22.411415000 UTC +00:00]} 2024-04-26T16:58:22Z
update: {"nested_updated_at"=>[Thu, 18 Apr 2024 18:23:38.805479000 UTC +00:00, Thu, 25 Apr 2024 14:48:46.345509000 UTC +00:00]} 2024-04-25T14:48:46Z
update: {"nested_updated_at"=>[Wed, 13 Dec 2023 22:21:19.945304000 UTC +00:00, Thu, 18 Apr 2024 18:23:38.805479000 UTC +00:00]} 2024-04-18T18:23:38Z
update: {"nested_updated_at"=>[nil, Wed, 13 Dec 2023 22:21:19.945304000 UTC +00:00]} 2024-01-03T18:24:13Z
update: {"publication_state"=>["file embargo", "released"]} 2023-07-17T08:00:08Z
update: {"publication_state"=>["released", "file embargo"]} 2023-01-23T17:27:40Z
update: {"publication_state"=>["file embargo", "released"]} 2023-01-23T17:27:40Z
update: {"subject"=>["", "Technology and Engineering"]} 2023-01-23T17:27:39Z
update: {"publication_state"=>["released", "file embargo"]} 2023-01-17T21:39:12Z
update: {"publication_state"=>["file embargo", "released"]} 2023-01-17T21:39:11Z