Child pages
  • Osteosarcoma data from UT Southwestern/UT Dallas for Viable and Necrotic Tumor Assessment (Osteosarcoma Tumor Assessment)

Summary


Osteosarcoma is the most common type of bone cancer that occurs in adolescents in the age of 10 to 14 years. The dataset is composed of Hematoxylin and eosin (H&E) stained osteosarcoma histology images. The data was collected by a team of clinical scientists at University of Texas Southwestern Medical Center, Dallas. Archival samples for 50 patients treated at Children’ s Medical Center, Dallas, between 1995 and 2015, were used to create this dataset. Four patients (out of 50) were selected by pathologists based on diversity of tumor specimens after surgical resection. The images are labelled as Non-Tumor, Viable Tumor and Necrosis according to the predominant cancer type in each image. The annotation was performed by two medical experts. All images were divided between two pathologists for the annotation activity. Each image had a single annotation as any given image was annotated by only one pathologist. The dataset consists of 1144 images of size 1024 X 1024 at 10X resolution with the following distribution: 536 (47%) non-tumor images, 263 (23%) necrotic tumor images and 345 (30%) viable tumor tiles.



Data Access

Data TypeDownload all or Query/FilterLicense
Slide Images (JPG, 196MB)

   

(Download and apply the IBM-Aspera-Connect plugin to your browser to retrieve this faspex package) 

Features (CSV, 860 kB)


Detailed Description

Image Statistics


Modalities

Pathology

Number of Participants

4

Number of Images

1144

Images Size (MB)196

Folder_Structure

  • Data_Osteo_Files
    • ML_Features_1144.csv - Contains 1144 rows for all the image tiles and 69 columns for filename, classification, and 65 machine learning features.
      • Training_Set_1 - 11 folders with 547 images. Each folder contains 48~50 image tiles and 1 csv for annotation.
        • set 1- 49 Image Tiles
        • set 2- 50 Image Tiles
        • set 3- 50 Image Tiles
        • set 4- 50 Image Tiles
        • set 5- 50 Image Tiles
        • set 6- 50 Image Tiles
        • set 7- 50 Image Tiles
        • set 8- 50 Image Tiles
        • set 9- 50 Image Tiles
        • set 10- 50 Image Tiles
        • set 11- 48 Image Tiles
      • Training_Set_2 - 12 folders with 597 images. Each folder contains 48~50 image tiles and 1 csv for annotation.
        • set 1- 49 Image Tiles
        • set 2- 50 Image Tiles
        • set 3- 50 Image Tiles
        • set 4- 50 Image Tiles
        • set 5- 50 Image Tiles
        • set 6- 50 Image Tiles
        • set 7- 50 Image Tiles
        • set 8- 50 Image Tiles
        • set 9- 50 Image Tiles
        • set 10- 50 Image Tiles
        • set 11- 50 Image Tiles
        • set 12- 48 Image Tiles

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

Leavey, P., Sengupta, A., Rakheja, D., Daescu, O., Arunachalam, H. B., & Mishra, R. (2019). Osteosarcoma data from UT Southwestern/UT Dallas for Viable and Necrotic Tumor Assessment [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/tcia.2019.bvhjhdas

Publication Citation

Mishra, R., Daescu, O., Leavey, P., Rakheja, D., & Sengupta, A. (2017). Histopathological Diagnosis for Viable and Non-viable Tumor Prediction for Osteosarcoma Using Convolutional Neural Network. In Bioinformatics Research and Applications (pp. 12–23). Springer International Publishing. https://doi.org/10.1007/978-3-319-59575-7_2

Publication Citation

Arunachalam, H. B., Mishra, R., Armaselu, B., Daescu, O., Martinez, M., Leavey, P., Rakheja, D., Cederberg, K., Sengupta, A., & Ni’suilleabhain, M. (2016). COMPUTER AIDED IMAGE SEGMENTATION AND CLASSIFICATION FOR VIABLE AND NON-VIABLE TUMOR IDENTIFICATION IN OSTEOSARCOMA. In Biocomputing 2017. Proceedings of the Pacific Symposium. WORLD SCIENTIFIC. https://doi.org/10.1142/9789813207813_0020

Publication Citation

Mishra, R., Daescu, O., Leavey, P., Rakheja, D., & Sengupta, A. (2018). Convolutional Neural Network for Histopathological Analysis of Osteosarcoma. In Journal of Computational Biology (Vol. 25, Issue 3, pp. 313–325). Mary Ann Liebert Inc. https://doi.org/10.1089/cmb.2017.0153

Publication Citation

Leavey, P., Arunachalam, H.B., Armaselu, B., Sengupta, A., Rakheja, D., Skapek, S., Cederberg, K., Bach, J.P., Glick, S., Ni'Suilleabhain, M. and Mishra, R., "Implementation of Computer-Based Image Pattern Recognition Algorithms to Interpret Tumor Necrosis; a First Step in Development of a Novel Biomarker in Osteosarcoma." PEDIATRIC BLOOD & CANCER. Vol. 64. 111 RIVER ST, HOBOKEN 07030-5774, NJ USA: WILEY, 2017.

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. (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

Other Publications Using This Data

TCIA maintains a list of publications which leverage our data. If you have a manuscript you'd like to add please contact TCIA's Helpdesk.

Version 1 (Current): Updated 2019/03/22

Data TypeDownload all or Query/Filter
Images (JPG, 196MB)

   

(Download and apply the IBM-Aspera-Connect plugin to your browser to retrieve this faspex package) 

Features (CSV)






  • No labels