Detection, segmentation and classification of nuclei are fundamental analysis operations in digital pathology. Existing state-of-the-art approaches demand extensive amounts of supervised training data from pathologists and may still perform poorly in images from unseen tissue types. We propose an unsupervised approach for histopathology image segmentation that synthesizes heterogeneous sets of training image patches, of every tissue type. Although our synthetic patches are not always of high quality, we harness the motley crew of generated samples through a generally applicable importance sampling method.
This proposed approach, for the first time, re-weighs the training loss over synthetic data so that the ideal (unbiased) generalization loss over the true data distribution is minimized. This enables us to use a random polygon generator to synthesize approximate cellular structures (i.e., nuclear masks) for which no real examples are given in many tissue types, and hence, GAN-based methods are not suited. In addition, we propose a hybrid synthesis pipeline that utilizes textures in real histopathology patches and GAN models, to tackle heterogeneity in tissue textures. Compared with existing state-of-the-art supervised models, our approach generalizes significantly better on cancer types without training data. Even in cancer types with training data, our approach achieves the same performance without supervision cost.
In this dataset we release code and nucleus segmentations in whole slide tissue images with quality control results for over 5000 Whole Slide Images (WSI) in The Cancer Genome Atlas (TCGA) repository. There are two subsets of data: (1) automatic nucleus segmentation data of 5,060 whole slide tissue images of 10 cancer types, with quality control results, and (2) manual nucleus segmentation data of 1,356 image patches from the same 10 cancer types plus additional 4 cancer types.
These 5,060 Whole Slide Images (WSIs) are from the following 10 cancer types:
BLCA Bladder urothelial carcinoma
BRCA Breast invasive carcinoma
CESC Cervical squamous cell carcinoma and endocervical adenocarcinoma
GBM Glioblastoma Multiforme
LUAD Lung adenocarcinoma
LUSC Lung squamous cell carcinoma
PAAD Pancreatic adenocarcinoma
PRAD Prostate adenocarcinoma
SKCM Skin Cutaneous Melanom a
UCEC Uterine Corpus Endometrial Carcinom a
Note that you can also download segmentation data of following 4 cancer types, although they are not officially verified or released.
COAD Colon adenocarcinoma
READ Rectal adenocarcinoma
STAD Stomach adenocarcinoma
UVM Uveal Melanoma
Click the Download button to be redirected to Box for downloads. Note that Box has a 15GB at one time max download restriction.
|Data Type||Download all or Query/Filter|
|Tissue Slide Segmentation Results (1,200 GB)|
|List of histopathology slides (TXT, )|
|Whole slide image-level quality control results (TXT, 151.4 KB)|
|Segmentation region checking results (TXT, 169.4 KB)|
Click the Versions tab for more info about data releases.
Note: Please contact email@example.com with any questions regarding usage.
Collections Used in this Third Party Analysis
Below is a list of the Collections used in these analyses:
Additional visual segmentation data can be found on PathDB
Manual nucleus segmentation data of 1,356 patches
These 1,356 patches are randomly extracted from all 14 cancer types mentioned above. This data contains original H&E stained histopathology image patches, and instance-level segmentation masks. Additional information is in the readme.txt file of this data. Download here
Citations & Data Usage Policy
Users of this data must abide by the TCIA Data Usage Policy and the Creative Commons Attribution 3.0 Unported License under which it has been published. Attribution should include references to the following citations:
Hou, L., Gupta, R., Van Arnam, J. S., Zhang, Y., Sivalenka, K., Samaras, D., Kurc, T., & Saltz, J. H. (2019). Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images of 10 Cancer Types [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/TCIA.2019.4A4DKP9U
Hou, L., Agarwal, A., Samaras, D., Kurc, T. M., Gupta, R. R., & Saltz, J. H. (2019, June). Robust Histopathology Image Analysis: To Label or to Synthesize? 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pp. 8533-8542. https://doi.org/10.1109/cvpr.2019.00873 Open Access Here
Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of Digital Imaging, 26(6), 1045–1057. https://doi.org/10.1007/s10278-013-9622-7