Summary
Acknowledgements
We would like to acknowledge these individuals and institutions:
- Canadian Cancer Society, grant #705772
- National Cancer institute of the National Institutes of Health under #U24CA199374
- Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada
Data Access
Data Type | Download all or Query/Filter | License |
---|---|---|
Slide Images (SVS, 43.2 GB) | ||
Annotations (XLSX, 26 kB) |
Detailed Description
Image Statistics | |
---|---|
Modalities | Pathology |
Number of Participants | 54 |
Number of Images | 96 |
Images Size (GB) | 43.2 |
Content
The Post-NAT-BRCA dataset is composed of:
- 96 whole slide images stored in an uncompressed .svs file format, standard for pathology slides. Slides were scanned at 20x objective on an Aperio slide scanner at Sunnybrook Health Sciences Centre.
- An Excel (.xlsx) file containing clinical features for each patient including age, treatment, ER/PR/HER2 status etc. A key and detailed description of each column is provided in a separate tab titled "Definitions". Each row in the spreadsheet corresponds to a single (.svs) slide and anonymised patient ID's are provided in a separate column.
- Manual annotations of tumor cellularity and cell labels, provided as Sedeen annotation files (.xml). Annotations are given in two directories, where the "WSI_train" folder contains WSIs annotated by a single rater and "WSI_test" was annotated by two raters.
Recommended Software
To browse whole slide images and annotations, we highly recommend you use Pathcore's Sedeen Viewer which is available for free: https://pathcore.com/sedeen/
Please ensure that the "sedeen" folder is unzipped and placed into the same folder containing the .svs files. Sedeen Viewer loads annotations from this folder automatically when images are opened.
Upon opening WSIs in Sedeen, you will notice that annotations have been color-coded according to the following key:
- Pink: Healthy (0% tumor cellularity)
- Blue: Low tumor cellularity (0 - 30%)
- Yellow: Medium tumor cellularity (31 - 70%)
- Green: High tumor cellularity (70 - 100%)
- White: Contains annotations at the cell level and labeled as:
- Lymphocyte: TIL-E, TIL-S
- Normal Epithelial: normal, UDH, ADH,
- Malignant Epithelial: IDC, ILC, Muc C, DCIS 1, DCIS 2, DCIS 3, MC- E, MC - C, MC - M
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
Martel, A. L., Nofech-Mozes, S., Salama, S., Akbar, S., & Peikari, M. (2019). Assessment of Residual Breast Cancer Cellularity after Neoadjuvant Chemotherapy using Digital Pathology [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/TCIA.2019.4YIBTJNO
Publication Citation
Peikari, M., Salama, S., Nofech‐Mozes, S., & Martel, A. L. (2017). Automatic cellularity assessment from post‐treated breast surgical specimens. In Cytometry Part A (Vol. 91, Issue 11, pp. 1078–1087). Wiley. https://doi.org/10.1002/cyto.a.23244
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
Additional Publication Resources
The Collection authors suggest the below will give context to this dataset:
- Akbar, S., Peikari, M., Salama, S., Panah, A. Y., Nofech-Mozes, S., Martel, A. L. (2019) Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment. Sci Rep, 9, 14099. https://doi.org/10.1038/s41598-019-50568-4
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 TCIA's Helpdesk.
- Zhang, X., Zhu, X., Tang, K., Zhao, Y., Lu, Z., & Feng, Q. (2022). DDTNet: A dense dual-task network for tumor-infiltrating lymphocyte detection and segmentation in histopathological images of breast cancer. In Medical Image Analysis (Vol. 78, p. 102415). Elsevier BV. https://doi.org/10.1016/j.media.2022.102415
- Diao, J. A., Wang, J. K., Chui, W. F., Mountain, V., Gullapally, S. C., Srinivasan, R., Mitchell, R. N., Glass, B., Hoffman, S., Rao, S. K., Maheshwari, C., Lahiri, A., Prakash, A., McLoughlin, R., Kerner, J. K., Resnick, M. B., Montalto, M. C., Khosla, A., Wapinski, I. N., … Taylor-Weiner, A. (2021). Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes. In Nature Communications (Vol. 12, Issue 1). Springer Science and Business Media LLC. https://doi.org/10.1038/s41467-021-21896-9
- Ciga, O., Xu, T., & Martel, A. L. (2022). Self supervised contrastive learning for digital histopathology. In Machine Learning with Applications (Vol. 7, p. 100198). Elsevier BV. https://doi.org/10.1016/j.mlwa.2021.100198
Version 1 (Current): Updated 2019/10/01
Data Type | Download all or Query/Filter |
---|---|
Images (SVS, 43.2 GB) | (Download and apply the IBM-Aspera-Connect plugin to your browser to retrieve this faspex package) |
Annotations (XLSX ) |