You are viewing an old version of this page. View the current version.
Microscopic images were captured from bone marrow aspirate slides of patients diagnosed with B-lineage Acute Lymphoid Leukemia (B-ALL) and Multiple Myeloma (MM) as per the standard guidelines. Slides were stained using Jenner-Giemsa and H&E stains. Images were captured at 1000x magnification using Nikon Eclipse-200 microscope equipped with a digital camera. Images were captured in raw BMP format with a size of 2560x1920 pixels. In all, this dataset consists of 90 images of B-ALL, 100 images of MM, and 116 images of H&E. Both MM and B-ALL images have sufficient variability from one image to another image to rigorously test any stain normalization methodology developed. More information about each subset are provided on the Detailed Description tab below.
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 Type||Download all or Query/Filter|
|Images (BMP, TIFF, 2.9 GB)|
Please note that Box has a 15GB download limit, so you will need to download images in batches.
Click the Versions tab for more info about data releases.
Number of Patients
Number of Studies
Number of Images
|Images Size (GB)||2.9|
Data Subset-1: H&E stained images
The first data subset contains publicly available Hematoxylin-Eosin (H&E) stained microscopic images of breast cancer collected from online site “http://bioimage.ucsb.edu/research/bio-segmentation”. This dataset consists of 58 images, wherein one image has been used as the reference image and the proposed stain normalization method has been tested on 57 images. The mapping of image numbers to the actual file names provided by the authors at “http://bioimage.ucsb.edu/research/bio-segmentation” is provided here. Further, for each of these 58 images, we have also provided one additional image that contains the nucleus mask for that particular image. For example, if the original file is saved with the name “H&E_1.tif”, the corresponding image with mask on the nuclei is saved as “H&E_1_nucleus_mask.tif.” Thus, in all, we have 116 images for this dataset.
Data subset-2: ALL images
Microscopic images were captured from bone marrow aspirate slides of patients diagnosed with B-lineage Acute Lymphoblastic Leukemia (B-ALL). Slides were stained using Jenner-Giemsa stain and lymphoblasts, that are cells of interest, have been evaluated. Images were captured in raw BMP format with a size of 2560x1920 pixels using Nikon Eclipse-200 microscope equipped with a digital camera at 1000x magnification. In all, this dataset consists of 30 images, wherein one image has been used as the reference image and the proposed stain normalization method has been tested on 29 images. For each of these 30 images, we have also provided two additional images that contain the nucleus mask and the background mask, respectively, for that particular image. For example, if the original file is saved with the name “ALL_1.bmp”, the corresponding image with mask on the nuclei is saved as “ALL_1_nucleus_mask.bmp”, and the corresponding image with mask on the background is saved as “ALL_1_background_mask.bmp Thus, in all, we have 90 images for this dataset.
Data subset-3: MM images
The third data subset contains microscopic images captured from slides prepared from bone marrow aspirate collected from patients with Multiple Myeloma (MM). Slides are stained using Jenner-Giemsa stain and plasma cells, that are cells of interest, have been evaluated. A total of 30 images have been considered, wherein one image has been used as the reference image to which 29 images have been stain normalized. For each of these 30 images, we have also provided two additional images that contain the nucleus mask and the background mask, respectively, for that particular image. For example, if the original file is saved with the name “MM_1.bmp”, the corresponding image with mask on the nuclei is saved as “MM_1_nucleus_mask.bmp”, and the corresponding image with mask on the background is saved as “MM_1_background_mask.bmp. In addition, for 17 images, the mask images are also provided for the cytoplasm of the plasma cells, namely, “MM_1_cyto_mask.bmp. Thus, in all, we have 100 images for this dataset.
Citations & Data Usage Policy
Add any special restrictions in here.
These collections are freely available to browse, download, and use for commercial, scientific and educational purposes as outlined in the Creative Commons Attribution 3.0 Unported License. Questions may be directed to firstname.lastname@example.org. Please be sure to acknowledge both this data set and TCIA in publications by including the following citations in your work:
"Gupta, A., & Gupta, R. (2019). SN-CanData: White Blood Cancer Dataset of B-ALL and MM for Stain Normalization [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/tcia.2019.of2w8lxr"
- Anubha Gupta, Rahul Duggal, Ritu Gupta, Lalit Kumar, Nisarg Thakkar, and Devprakash Satpathy, “GCTI-SN: Geometry-Inspired Chemical and Tissue Invariant Stain Normalization of Microscopic Medical Images”, under review.
- Ritu Gupta, Pramit Mallick, Rahul Duggal, Anubha Gupta, and Ojaswa Sharma, "Stain Color Normalization and Segmentation of Plasma Cells in Microscopic Images as a Prelude to Development of Computer Assisted Automated Disease Diagnostic Tool in Multiple Myeloma," 16th International Myeloma Workshop (IMW), India, March 2017.
- Rahul Duggal, Anubha Gupta, Ritu Gupta, and Pramit Mallick, "SD-Layer: Stain Deconvolutional Layer for CNNs in Medical Microscopic Imaging," In: Descoteaux M., Maier- Hein L., Franz A., Jannin P., Collins D., Duchesne S. (eds) Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017, MICCAI 2017. Lecture Notes in Computer Science, Part III, LNCS 10435, pp. 435–443. Springer, Cham. DOI: https://doi.org/10.1007/978- 3-319-66179-7_50.
- Rahul Duggal, Anubha Gupta, Ritu Gupta, Manya Wadhwa, and Chirag Ahuja, “Overlapping Cell Nuclei Segmentation in Microscopic Images UsingDeep Belief Networks,” Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), India, December 2016.
Rahul Duggal, Anubha Gupta, and Ritu Gupta, “Segmentation of overlapping/touching white blood cell nuclei using artificial neural networks,” CME Series on Hemato-Oncopathology, All India Institute of Medical Sciences (AIIMS), New Delhi, India, July 2016.
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
- No labels