You can now access digital, whole-slide, hematoxylin and eosin (H&E) stained Rhabdomyosarcoma (RMS) images in DICOM format¹ via NCI’s Imaging Data Commons (IDC)².

The images are from diagnostic specimens of 403 RMS patients who participated in Children’s Oncology Group trials between 1998 and 2017³. You have access to metadata added by researchers and the benefit of DICOM whole-slide microscopy representation^4,5 using custom, open-source scripts and tools⁶.

In addition, you can get:

• accompanying clinical data via the SQL interface in IDC BigQuery tables⁷.
• gene panel sequencing data through the database of Genotypes and Phenotypes phs000720.v4.p1.
• an inventory of these data in the Childhood Cancer Data Initiative’s Childhood Cancer Data Catalog.

Researchers used these diagnostic H&E images to train deep learning models for identifying tumor features, predicting the presence of high-risk mutations, assessing relative risk, and predicting molecular subtypes and survival in RMS⁸. This methodology extends to other pediatric and adult malignancies, with the potential to integrate deep learning algorithms into clinical decision-making and precision medicine. Such advancements hold promise for the future of cancer care.

References

¹ DICOM Converted Whole Slide Hematoxylin and Eosin Images of Rhabdomyosarcoma from Children's Oncology Group Trials. Zenodo, 2023.

² NCI Imaging Data Commons. Cancer Research, 2021.

³ Genomic Classification and Clinical Outcome in Rhabdomyosarcoma: A Report from an International Consortium. Journal of Clinical Oncology, 2021.

⁴ National Electrical Manufacturers Association (NEMA). DICOM PS3.3 - Information Object Definitions: A.32.8 VL Whole Slide Microscopy Image IOD. Accessed September 5, 2023.

⁵ Implementing the DICOM Standard for Digital Pathology. Journal of Pathology Informatics, 2018.

⁶ IDC-WSI-Conversion: RMS. Accessed September 5, 2023.

⁷ IDC-Tutorials: IDC Clinical Data Exploration. Accessed September 5, 2023.

⁸ Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children’s Oncology Group. Clinical Cancer Research, 2023.