The Cancer Imaging Archive (TCIA) Public Access

Space shortcuts

Child pages
  • Breast Cancer Screening - Digital Breast Tomosynthesis (Breast-Cancer-Screening-DBT)

Versions Compared

Old Version 53

changes.mady.by.user Geri Blake

Saved on

compared with

New Version 54

changes.mady.by.user Geri Blake

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Breast cancer is among the most common cancers and a common cause of death among women. Over 39 million breast cancer screening exams are performed every year and are among the most common radiological tests. This creates a high need for accurate image interpretation. Machine learning has shown promise in interpretation of medical images. However, limited data for training and validation remains an issue.

Here, we share a curated dataset of digital breast tomosynthesis images that includes normal, actionable, biopsy-proven benign, and biopsy-proven cancer cases.  The dataset contains four components: (1) DICOM images, (2) a spreadsheet indicating which group each case belongs to (3) annotation boxes, and (4) Image paths for patients/studies/views.  A detailed description of this dataset can be found in the following paper:

Please reference this paper if you use this dataset. Version 1 of the dataset contains only a subset of all data described in the paper above. More data will be share in subsequent versions.

Acknowledgements

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

  • Duke University Hospital/Duke University, Durham, NC, USA

  • We would like to acknowledge all those who contributed to the curation of this dataset

  • This work was supported by a grant from the NIH: 1 R01 EB021360 (PI: Mazurowski).


Localtab Group


Localtab
activetrue
titleData Access

Data Access

Click the  Download button to save a ".tcia" manifest file to your computer, which you must open with the NBIA Data Retriever . Click the Search button to open our Data Portal, where you can browse the data collection and/or download a subset of its contents.

Data TypeDownload all or Query/Filter
Test set - Images (DICOM, 47 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT-Challenge-Test.TCIA?api=v2

Tcia button generator
labelSearch
url

 DBT-P00036, DBT-P00087, DBT-P00092, DBT-P00095, DBT-P00118, DBT-P00221, DBT-P00223, DBT-P00276, DBT-P00277, DBT-P00281, DBT-P00311, DBT-P00312, DBT-P00317, DBT-P00318, DBT-P00332, DBT-P00339, DBT-P00387, DBT-P00455, DBT-P00472, DBT-P00493, DBT-P00556, DBT-P00561, DBT-P00619, DBT-P00629, DBT-P00659, DBT-P00675, DBT-P00715, DBT-P00724, DBT-P00770, DBT-P00794, DBT-P00798, DBT-P00801, DBT-P00817, DBT-P00838, DBT-P00882, DBT-P00935, DBT-P00977, DBT-P00984, DBT-P00989, DBT-P01010, DBT-P01023, DBT-P01059, DBT-P01068, DBT-P01158, DBT-P01183, DBT-P01184, DBT-P01210, DBT-P01247, DBT-P01256, DBT-P01263, DBT-P01280, DBT-P01292, DBT-P01367, DBT-P01371, DBT-P01373, DBT-P01443, DBT-P01497, DBT-P01552, DBT-P01563, DBT-P01670, DBT-P01702, DBT-P01719, DBT-P01725, DBT-P01782, DBT-P01803, DBT-P01837, DBT-P01880, DBT-P01898, DBT-P01919, DBT-P01934, DBT-P01958, DBT-P01991, DBT-P02009, DBT-P02112, DBT-P02139, DBT-P02152, DBT-P02155, DBT-P02164, DBT-P02172, DBT-P02187, DBT-P02281, DBT-P02293, DBT-P02308, DBT-P02347, DBT-P02420, DBT-P02511, DBT-P02542, DBT-P02559, DBT-P02572, DBT-P02609, DBT-P02651, DBT-P02665, DBT-P02685, DBT-P02714, DBT-P02725, DBT-P02748, DBT-P02774, DBT-P02794, DBT-P02825, DBT-P02826, DBT-P02834, DBT-P02875, DBT-P02901, DBT-P02906, DBT-P02910, DBT-P02941, DBT-P02954, DBT-P03010, DBT-P03016, DBT-P03035, DBT-P03054, DBT-P03064, DBT-P03075, DBT-P03122, DBT-P03220, DBT-P03273, DBT-P03332, DBT-P03372, DBT-P03376, DBT-P03398, DBT-P03430, DBT-P03519, DBT-P03536, DBT-P03571, DBT-P03636, DBT-P03679, DBT-P03695, DBT-P03732, DBT-P03749, DBT-P03774, DBT-P03812, DBT-P03842, DBT-P03844, DBT-P03845, DBT-P03864, DBT-P03918, DBT-P03952, DBT-P03964, DBT-P03971, DBT-P04046, DBT-P04085, DBT-P04115, DBT-P04126, DBT-P04209, DBT-P04255, DBT-P04286, DBT-P04287, DBT-P04350, DBT-P04378, DBT-P04391, DBT-P04411, DBT-P04413, DBT-P04439, DBT-P04451, DBT-P04457, DBT-P04479, DBT-P04499, DBT-P04501, DBT-P04571, DBT-P04588, DBT-P04619, DBT-P04674, DBT-P04774, DBT-P04788, DBT-P04802, DBT-P04828, DBT-P04844, DBT-P04859, DBT-P04910, DBT-P04935, DBT-P04956, DBT-P04975, DBT-P04982, DBT-P05036, DBT-P05049

https://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-78441610719428450

Test set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-test.csv?api=v2

Validation set - Images (DICOM, 28 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT-Challenge%20Validation.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?MinNumberOfStudiesCriteria=1&PatientCriteria=DBT-P00002,DBT-P00114,DBT-P00160,DBT-P00176,DBT-P00213,DBT-P00238,DBT-P00351,DBT-P00385,DBT-P00431,DBT-P00450,DBT-P00547,DBT-P00549,DBT-P00577,DBT-P00651,DBT-P00655,DBT-P00697,DBT-P00714,DBT-P00718,DBT-P00843,DBT-P00844,DBT-P00864,DBT-P00866,DBT-P01150,DBT-P01152,DBT-P01153,DBT-P01173,DBT-P01207,DBT-P01226,DBT-P01249,DBT-P01293,DBT-P01296,DBT-P01305,DBT-P01334,DBT-P01356,DBT-P01490,DBT-P01496,DBT-P01536,DBT-P01538,DBT-P01700,DBT-P01746,DBT-P01772,DBT-P01778,DBT-P01849,DBT-P01851,DBT-P01941,DBT-P01957,DBT-P01967,DBT-P02072,DBT-P02111,DBT-P02117,DBT-P02160,DBT-P02170,DBT-P02214,DBT-P02226,DBT-P02314,DBT-P02381,DBT-P02394,DBT-P02498,DBT-P02558,DBT-P02560,DBT-P02598,DBT-P02648,DBT-P02686,DBT-P02766,DBT-P02776,DBT-P02816,DBT-P02864,DBT-P02898,DBT-P02959,DBT-P02989,DBT-P03027,DBT-P03092,DBT-P03110,DBT-P03113,DBT-P03129,DBT-P03215,DBT-P03263,DBT-P03343,DBT-P03360,DBT-P03390,DBT-P03403,DBT-P03448,DBT-P03501,DBT-P03574,DBT-P03598,DBT-P03605,DBT-P03621,DBT-P03628,DBT-P03651,DBT-P03689,DBT-P03694,DBT-P03728,DBT-P03831,DBT-P03901,DBT-P04008,DBT-P04045,DBT-P04087,DBT-P04097,DBT-P04105,DBT-P04106,DBT-P04208,DBT-P04257,DBT-P04295,DBT-P04344,DBT-P04346,DBT-P04380,DBT-P04396,DBT-P04577,DBT-P04596,DBT-P04622,DBT-P04695,DBT-P04803,DBT-P04808,DBT-P04837,DBT-P04884,DBT-P05018,DBT-P05060&CollectionCriteria=Breast-Cancer-Screening-DBT

Validation set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-validation.csv?api=v2

Training set - Images (DICOM, 186 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/DBT-Challenge-Train.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-3321609785776535

Training set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-train.csv?api=v2

Training set - Boxes indicating lesion locations (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive

Test set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20fileDBT%20boxes-pathstrain-testv2.csv?api=v2

Validation Training set - Images (DICOM, 28 GBSpreadsheet indicating which group each cases belongs to (see the paper for details on the groups) (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBTDBT%20labels-Challenge%20Validationtrain.TCIAcsv?api=v2
Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?MinNumberOfStudiesCriteria=1&PatientCriteria=DBT-P00002,DBT-P00114,DBT-P00160,DBT-P00176,DBT-P00213,DBT-P00238,DBT-P00351,DBT-P00385,DBT-P00431,DBT-P00450,DBT-P00547,DBT-P00549,DBT-P00577,DBT-P00651,DBT-P00655,DBT-P00697,DBT-P00714,DBT-P00718,DBT-P00843,DBT-P00844,DBT-P00864,DBT-P00866,DBT-P01150,DBT-P01152,DBT-P01153,DBT-P01173,DBT-P01207,DBT-P01226,DBT-P01249,DBT-P01293,DBT-P01296,DBT-P01305,DBT-P01334,DBT-P01356,DBT-P01490,DBT-P01496,DBT-P01536,DBT-P01538,DBT-P01700,DBT-P01746,DBT-P01772,DBT-P01778,DBT-P01849,DBT-P01851,DBT-P01941,DBT-P01957,DBT-P01967,DBT-P02072,DBT-P02111,DBT-P02117,DBT-P02160,DBT-P02170,DBT-P02214,DBT-P02226,DBT-P02314,DBT-P02381,DBT-P02394,DBT-P02498,DBT-P02558,DBT-P02560,DBT-P02598,DBT-P02648,DBT-P02686,DBT-P02766,DBT-P02776,DBT-P02816,DBT-P02864,DBT-P02898,DBT-P02959,DBT-P02989,DBT-P03027,DBT-P03092,DBT-P03110,DBT-P03113,DBT-P03129,DBT-P03215,DBT-P03263,DBT-P03343,DBT-P03360,DBT-P03390,DBT-P03403,DBT-P03448,DBT-P03501,DBT-P03574,DBT-P03598,DBT-P03605,DBT-P03621,DBT-P03628,DBT-P03651,DBT-P03689,DBT-P03694,DBT-P03728,DBT-P03831,DBT-P03901,DBT-P04008,DBT-P04045,DBT-P04087,DBT-P04097,DBT-P04105,DBT-P04106,DBT-P04208,DBT-P04257,DBT-P04295,DBT-P04344,DBT-P04346,DBT-P04380,DBT-P04396,DBT-P04577,DBT-P04596,DBT-P04622,DBT-P04695,DBT-P04803,DBT-P04808,DBT-P04837,DBT-P04884,DBT-P05018,DBT-P05060&CollectionCriteria=Breast-Cancer-Screening-DBT

Validation set - Image paths for patients/studies/views (csv)
Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-validation.csv?api=v2

Training set - Images (DICOM, 186 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/DBT-Challenge-Train.TCIA?api=v2
Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-3321609785776535
Training set - Image paths for patients/studies/views (csv)
Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-train.csv?api=v2
Training set - Boxes indicating lesion locations (csv)
Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20boxes-train-v2.csv?api=v2
Training set - Spreadsheet indicating which group each cases belongs to (see the paper for details on the groups) (csv)
Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20labels-train.csv?api=v2

Click the Versions tab for more info about data releases.

Click the Versions tab for more info about data releases.


Localtab
titleDetailed Description

Detailed Description

Image Statistics


Modalities

DBT

Number of Participants

985

Number of Studies

1000

Number of Series

3592

Number of Images

3592

Images Size (GB, compressed)260

Important considerations when using this dataset

Some scans contain skin markers. These markers can indicate moles, scars, other skin issues, palpable masses, or other areas of concern. The presence of these markers is reflective of clinical practice and a marker does not necessarily indicate a breast lesion. 

Each DBT exam typically consists of 4 views (2 per breast, craniocaudal and mediolateral oblique) but for some exams less than 4 views may be available for analysis. 

Images are stored in compressed DICOM format, with an entire 3D volume (view) per DICOM file. The images can be read with Radiant, MicroDICOM, ImageJ (with the Bio-Formats plug-in), Matlab, and all the main DICOM toolkits: GDCM, dcmtk, dicom3tools.  If using ImageJ, image files might first need to be uncompressed using one of the toolkits (e.g., with GDCM — `gdcmconv -w compressed.dcm uncompressed.dcm`).

Required preprocessing of DBT images: For some of the images, the laterality stored in the DICOM header and/or image orientation are incorrect. The reference standard "truth" boxes are defined with respect to the corrected image orientation in these instances. Therefore, it is crucial to provide your results for images in the correct image orientation. Python functions for loading image data from a DICOM file into 3D array of pixel values in the correct orientation and for displaying "truth" boxes (if any) are on GitHub. Please see the readme file there for instructions.

DBTex Challenge

Part of this dataset is used for the DBTex challenge (http://spie-aapm-nci-dair.westus2.cloudapp.azure.com/competitions/4), which contains a total of 1000 breast tomosynthesis scans from 985 patients from this collection.  The challenge dataset is broken down into the following cohorts:

  1. Total: 1000 scans
  2. Training: 700 scans
  3. Validation: 120 scans
  4. Test: 180 scans

Release of training set (with truth): December 14, 2020

The training set will consist of 700 cases. This dataset will be representative of the technical properties (equipment, acquisition parameters, file format) and the nature of lesions in the validation and test sets. An associated Excel file in CSV format will include DBT scan identifier and the definition of the bounding box of all lesions. 

Release of validation set (without truth): January 4, 2021

The validation set will consist of 120 cases. The locations of lesions will not be provided. The validation set needs to be processed, manipulated, and analyzed without human intervention. Validation set output submitted through the online challenge interface will contribute to the challenge leader board.

Release of test set (without truth): January 15, 2021

The test set will consist of 180 cases. The locations of lesions will not be provided. The test set needs to be processed, manipulated, and analyzed without human intervention. 




Localtab
titleCitations & Data Usage Policy

Citations & Data Usage Policy

Tcia license 4 noncommercial

Info
titleData Citation

Buda, M., Saha, A., Walsh, R., Ghate, S., Li, N., Święcicki, A., Lo, J.Y., Yang, J., & Mazurowski, M.A. (2020). Data from the Breast Cancer Screening – Digital Breast Tomosynthesis (BCS-DBT). Data from The Cancer Imaging Archive. (2020). DOI: https://doi.org/10.7937/e4wt-cd02.


Info
titlePublication Citation

M. Buda, A. Saha, R. Walsh, S. Ghate, N. Li, A. Święcicki, J. Y. Lo, M. A. Mazurowski, Detection of masses and architectural distortions in digital breast tomosynthesis: a publicly available dataset of 5,060 patients and a deep learning model. arXiv preprint https://arxiv.org/abs/2011.07995.


Info
titleTCIA 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.


Detailed Description

Important considerations when using this dataset

Some scans contain skin markers. These markers can indicate moles, scars, other skin issues, palpable masses, or other areas of concern. The presence of these markers is reflective of clinical practice and a marker does not necessarily indicate a breast lesion. 

Each DBT exam typically consists of 4 views (2 per breast, craniocaudal and mediolateral oblique) but for some exams less than 4 views may be available for analysis. 

Images are stored in compressed DICOM format, with an entire 3D volume (view) per DICOM file. The images can be read with Radiant, MicroDICOM, ImageJ (with the Bio-Formats plug-in), Matlab, and all the main DICOM toolkits: GDCM, dcmtk, dicom3tools.  If using ImageJ, image files might first need to be uncompressed using one of the toolkits (e.g., with GDCM — `gdcmconv -w compressed.dcm uncompressed.dcm`).

Required preprocessing of DBT images: For some of the images, the laterality stored in the DICOM header and/or image orientation are incorrect. The reference standard "truth" boxes are defined with respect to the corrected image orientation in these instances. Therefore, it is crucial to provide your results for images in the correct image orientation. Python functions for loading image data from a DICOM file into 3D array of pixel values in the correct orientation and for displaying "truth" boxes (if any) are on GitHub. Please see the readme file there for instructions.

DBTex Challenge

Part of this dataset is used for the DBTex challenge (http://spie-aapm-nci-dair.westus2.cloudapp.azure.com/competitions/4), which contains a total of 1000 breast tomosynthesis scans from 985 patients from this collection.  The challenge dataset is broken down into the following cohorts:

  1. Total: 1000 scans
  2. Training: 700 scans
  3. Validation: 120 scans
  4. Test: 180 scans

Release of training set (with truth): December 14, 2020

The training set will consist of 700 cases. This dataset will be representative of the technical properties (equipment, acquisition parameters, file format) and the nature of lesions in the validation and test sets. An associated Excel file in CSV format will include DBT scan identifier and the definition of the bounding box of all lesions. 

Release of validation set (without truth): January 4, 2021

The validation set will consist of 120 cases. The locations of lesions will not be provided. The validation set needs to be processed, manipulated, and analyzed without human intervention. Validation set output submitted through the online challenge interface will contribute to the challenge leader board.

Release of test set (without truth): January 15, 2021

The test set will consist of 180 cases. The locations of lesions will not be provided. The test set needs to be processed, manipulated, and analyzed without human intervention. 

Citations & Data Usage Policy

Localtab
titleVersions

Version 3 (Current): Updated 2021/01/15

Data TypeDownload all or Query/Filter
Test set - Images (DICOM, 47 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT-Challenge-Test.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-78441610719428450

Localtab
titleDetailed Description

Image Statistics

Modalities

DBT

Number of Participants

985

Number of Studies

1000

Number of Series

3592

Number of Images

3592

Images Size (GB, compressed)260
Localtab
titleCitations & Data Usage Policy
Tcia license 4 noncommercial

Info
titleData Citation

Buda, M., Saha, A., Walsh, R., Ghate, S., Li, N., Święcicki, A., Lo, J.Y., Yang, J., & Mazurowski, M.A. (2020). Data from the Breast Cancer Screening – Digital Breast Tomosynthesis (BCS-DBT). Data from The Cancer Imaging Archive. (2020). DOI: https://doi.org/10.7937/e4wt-cd02.

Info
titlePublication Citation

M. Buda, A. Saha, R. Walsh, S. Ghate, N. Li, A. Święcicki, J. Y. Lo, M. A. Mazurowski, Detection of masses and architectural distortions in digital breast tomosynthesis: a publicly available dataset of 5,060 patients and a deep learning model. arXiv preprint https://arxiv.org/abs/2011.07995.

Info
titleTCIA 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.

Localtab
titleVersions

Version 3 (Current): Updated 2021/01/15

Data TypeDownload all or Query/Filter
Test set - Images (DICOM, 47 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT-Challenge-Test.TCIA?api=v2
Tcia button generator
labelSearch
url DBT-P00036, DBT-P00087, DBT-P00092, DBT-P00095, DBT-P00118, DBT-P00221, DBT-P00223, DBT-P00276, DBT-P00277, DBT-P00281, DBT-P00311, DBT-P00312, DBT-P00317, DBT-P00318, DBT-P00332, DBT-P00339, DBT-P00387, DBT-P00455, DBT-P00472, DBT-P00493, DBT-P00556, DBT-P00561, DBT-P00619, DBT-P00629, DBT-P00659, DBT-P00675, DBT-P00715, DBT-P00724, DBT-P00770, DBT-P00794, DBT-P00798, DBT-P00801, DBT-P00817, DBT-P00838, DBT-P00882, DBT-P00935, DBT-P00977, DBT-P00984, DBT-P00989, DBT-P01010, DBT-P01023, DBT-P01059, DBT-P01068, DBT-P01158, DBT-P01183, DBT-P01184, DBT-P01210, DBT-P01247, DBT-P01256, DBT-P01263, DBT-P01280, DBT-P01292, DBT-P01367, DBT-P01371, DBT-P01373, DBT-P01443, DBT-P01497, DBT-P01552, DBT-P01563, DBT-P01670, DBT-P01702, DBT-P01719, DBT-P01725, DBT-P01782, DBT-P01803, DBT-P01837, DBT-P01880, DBT-P01898, DBT-P01919, DBT-P01934, DBT-P01958, DBT-P01991, DBT-P02009, DBT-P02112, DBT-P02139, DBT-P02152, DBT-P02155, DBT-P02164, DBT-P02172, DBT-P02187, DBT-P02281, DBT-P02293, DBT-P02308, DBT-P02347, DBT-P02420, DBT-P02511, DBT-P02542, DBT-P02559, DBT-P02572, DBT-P02609, DBT-P02651, DBT-P02665, DBT-P02685, DBT-P02714, DBT-P02725, DBT-P02748, DBT-P02774, DBT-P02794, DBT-P02825, DBT-P02826, DBT-P02834, DBT-P02875, DBT-P02901, DBT-P02906, DBT-P02910, DBT-P02941, DBT-P02954, DBT-P03010, DBT-P03016, DBT-P03035, DBT-P03054, DBT-P03064, DBT-P03075, DBT-P03122, DBT-P03220, DBT-P03273, DBT-P03332, DBT-P03372, DBT-P03376, DBT-P03398, DBT-P03430, DBT-P03519, DBT-P03536, DBT-P03571, DBT-P03636, DBT-P03679, DBT-P03695, DBT-P03732, DBT-P03749, DBT-P03774, DBT-P03812, DBT-P03842, DBT-P03844, DBT-P03845, DBT-P03864, DBT-P03918, DBT-P03952, DBT-P03964, DBT-P03971, DBT-P04046, DBT-P04085, DBT-P04115, DBT-P04126, DBT-P04209, DBT-P04255, DBT-P04286, DBT-P04287, DBT-P04350, DBT-P04378, DBT-P04391, DBT-P04411, DBT-P04413, DBT-P04439, DBT-P04451, DBT-P04457, DBT-P04479, DBT-P04499, DBT-P04501, DBT-P04571, DBT-P04588, DBT-P04619, DBT-P04674, DBT-P04774, DBT-P04788, DBT-P04802, DBT-P04828, DBT-P04844, DBT-P04859, DBT-P04910, DBT-P04935, DBT-P04956, DBT-P04975, DBT-P04982, DBT-P05036, DBT-P05049

Test set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-test.csv?api=v2

Validation set - Images (DICOM, 28 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT-Challenge%20Validation.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?MinNumberOfStudiesCriteria=1&PatientCriteria=DBT-P00002,DBT-P00114,DBT-P00160,DBT-P00176,DBT-P00213,DBT-P00238,DBT-P00351,DBT-P00385,DBT-P00431,DBT-P00450,DBT-P00547,DBT-P00549,DBT-P00577,DBT-P00651,DBT-P00655,DBT-P00697,DBT-P00714,DBT-P00718,DBT-P00843,DBT-P00844,DBT-P00864,DBT-P00866,DBT-P01150,DBT-P01152,DBT-P01153,DBT-P01173,DBT-P01207,DBT-P01226,DBT-P01249,DBT-P01293,DBT-P01296,DBT-P01305,DBT-P01334,DBT-P01356,DBT-P01490,DBT-P01496,DBT-P01536,DBT-P01538,DBT-P01700,DBT-P01746,DBT-P01772,DBT-P01778,DBT-P01849,DBT-P01851,DBT-P01941,DBT-P01957,DBT-P01967,DBT-P02072,DBT-P02111,DBT-P02117,DBT-P02160,DBT-P02170,DBT-P02214,DBT-P02226,DBT-P02314,DBT-P02381,DBT-P02394,DBT-P02498,DBT-P02558,DBT-P02560,DBT-P02598,DBT-P02648,DBT-P02686,DBT-P02766,DBT-P02776,DBT-P02816,DBT-P02864,DBT-P02898,DBT-P02959,DBT-P02989,DBT-P03027,DBT-P03092,DBT-P03110,DBT-P03113,DBT-P03129,DBT-P03215,DBT-P03263,DBT-P03343,DBT-P03360,DBT-P03390,DBT-P03403,DBT-P03448,DBT-P03501,DBT-P03574,DBT-P03598,DBT-P03605,DBT-P03621,DBT-P03628,DBT-P03651,DBT-P03689,DBT-P03694,DBT-P03728,DBT-P03831,DBT-P03901,DBT-P04008,DBT-P04045,DBT-P04087,DBT-P04097,DBT-P04105,DBT-P04106,DBT-P04208,DBT-P04257,DBT-P04295,DBT-P04344,DBT-P04346,DBT-P04380,DBT-P04396,DBT-P04577,DBT-P04596,DBT-P04622,DBT-P04695,DBT-P04803,DBT-P04808,DBT-P04837,DBT-P04884,DBT-P05018,DBT-P05060&CollectionCriteria=Breast-Cancer-Screening-DBT

Validation set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-validation.csv?api=v2

Training set - Images (DICOM, 186 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/DBT-Challenge-Train.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-3321609785776535

Training set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-train.csv?api=v2

Training set - Boxes indicating lesion locations (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20boxes-train-v2.csv?api=v2

Training set - Spreadsheet indicating which group each cases belongs to (see the paper for details on the groups) (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20labels-train.csv?api=v2

Test set - Images added.

Test set - Image paths for patients/studies/views spreadsheet added.

Version 2: Updated 2021/01/04

Data TypeDownload all or Query/Filter
Validation set - Images (DICOM, 28 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT-Challenge%20Validation.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?MinNumberOfStudiesCriteria=1&PatientCriteria=DBT-P00002,DBT-P00114,DBT-P00160,DBT-P00176,DBT-P00213,DBT-P00238,DBT-P00351,DBT-P00385,DBT-P00431,DBT-P00450,DBT-P00547,DBT-P00549,DBT-P00577,DBT-P00651,DBT-P00655,DBT-P00697,DBT-P00714,DBT-P00718,DBT-P00843,DBT-P00844,DBT-P00864,DBT-P00866,DBT-P01150,DBT-P01152,DBT-P01153,DBT-P01173,DBT-P01207,DBT-P01226,DBT-P01249,DBT-P01293,DBT-P01296,DBT-P01305,DBT-P01334,DBT-P01356,DBT-P01490,DBT-P01496,DBT-P01536,DBT-P01538,DBT-P01700,DBT-P01746,DBT-P01772,DBT-P01778,DBT-P01849,DBT-P01851,DBT-P01941,DBT-P01957,DBT-P01967,DBT-P02072,DBT-P02111,DBT-P02117,DBT-P02160,DBT-P02170,DBT-P02214,DBT-P02226,DBT-P02314,DBT-P02381,DBT-P02394,DBT-P02498,DBT-P02558,DBT-P02560,DBT-P02598,DBT-P02648,DBT-P02686,DBT-P02766,DBT-P02776,DBT-P02816,DBT-P02864,DBT-P02898,DBT-P02959,DBT-P02989,DBT-P03027,DBT-P03092,DBT-P03110,DBT-P03113,DBT-P03129,DBT-P03215,DBT-P03263,DBT-P03343,DBT-P03360,DBT-P03390,DBT-P03403,DBT-P03448,DBT-P03501,DBT-P03574,DBT-P03598,DBT-P03605,DBT-P03621,DBT-P03628,DBT-P03651,DBT-P03689,DBT-P03694,DBT-P03728,DBT-P03831,DBT-P03901,DBT-P04008,DBT-P04045,DBT-P04087,DBT-P04097,DBT-P04105,DBT-P04106,DBT-P04208,DBT-P04257,DBT-P04295,DBT-P04344,DBT-P04346,DBT-P04380,DBT-P04396,DBT-P04577,DBT-P04596,DBT-P04622,DBT-P04695,DBT-P04803,DBT-P04808,DBT-P04837,DBT-P04884,DBT-P05018,DBT-P05060&CollectionCriteria=Breast-Cancer-Screening-DBT

Validation set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-validation.csv?api=v2

Training set - Images (DICOM, 186 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/DBT-Challenge-Train.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-3321609785776535

Training set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-train.csv?api=v2

Training set - Boxes indicating lesion locations (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20boxes-train-v2.csv?api=v2

Training set - Spreadsheet indicating which group each cases belongs to (see the paper for details on the groups) (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20labels-train.csv?api=v2

Validation set - Images added.

Validation set - Image paths for patients/studies/views spreadsheet added.

Volume Slices column added to the Training set - Boxes indicating lesion locations spreadsheet.

Version 1: Updated 2020/12/14

Data TypeDownload all or Query/Filter

Training set - Images (DICOM, 186 GB)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/DBT-Challenge-Train.TCIA?api=v2

Tcia button generator
labelSearch
urlhttps://nbia.cancerimagingarchive.net/nbia-search/?saved-cart=nbia-3321609785776535

Training set - Image paths for patients/studies/views (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20file-paths-train.csv?api=v2

Training set - Boxes indicating lesion locations (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20boxes-train.csv?api=v2

Training set - Spreadsheet indicating which group each cases belongs to (see the paper for details on the groups) (csv)

Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/64685580/BCS-DBT%20labels-train.csv?api=v2