Training Data Attribution

Building on publicly available medical imaging research

All training cases in Absolutely Rad are derived from publicly available medical imaging datasets. We are deeply grateful to the researchers, institutions, and patients who contributed to these collections through The Cancer Imaging Archive (TCIA).

Dataset Citations

Kurdziel, Karen A, Apolo, Andrea B., Lindenberg, Liza, Mena, Esther, McKinney, Yolanda Y., Adler, Stephen S., ... Choyke, Peter L. (2015). Data From NaF PROSTATE [Dataset]. The Cancer Imaging Archive.

https://doi.org/10.7937/K9/TCIA.2015.ISOQTHKO

Wee, L., Aerts, H., Kalendralis, P., & Dekker, A. (2020). RIDER Lung CT Segmentation Labels from: Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [Data set]. The Cancer Imaging Archive.

https://doi.org/10.7937/tcia.2020.jit9grk8

Software & Libraries

Open Source Dependencies

Absolutely Rad is built using the following open-source libraries and tools. We are grateful to their maintainers and contributors.

NumPy — Fundamental package for numerical computing in Python. Used for DRR calculations and image processing operations.

License: BSD-3-Clause

https://github.com/numpy/numpy

SimpleITK — Simplified interface to the Insight Toolkit (ITK) for medical image I/O, processing, and DRR generation from DICOM volumes.

License: Apache 2.0

https://github.com/SimpleITK/SimpleITK

About TCIA

The Cancer Imaging Archive

The Cancer Imaging Archive (TCIA) is a service which de-identifies and hosts a large archive of medical images of cancer accessible for public download. The data are organized as "collections," typically defined by a common disease, research focus, or type of imaging modality.

Learn more at www.cancerimagingarchive.net

Feedback