Welcome to cuCIM’s documentation!#

cuCIM (Compute Unified Device Architecture Clara IMage) is an open-source, accelerated computer vision and image processing software library for multidimensional images used in biomedical, geospatial, material and life science, and remote sensing use cases.

cuCIM provides GPU-accelearted I/O, computer vision and image processing primitives for N-Dimensional images including:

  • color conversion

  • exposure

  • feature extraction

  • filters

  • measure

  • metrics

  • morphology

  • registration

  • restoration

  • segmentation

  • transforms

cuCIM supports the following formats:

  • Aperio ScanScope Virtual Slide (SVS)

  • Philips TIFF

  • Generic Tiled, Multi-resolution RGB TIFF files with the following compression schemes:

    • No Compression

    • JPEG

    • JPEG2000

    • Lempel-Ziv-Welch (LZW)

    • Deflate

Our API mirrors scikit-image for image manipulation and OpenSlide for image loading.

cuCIM is interoperable with the following workflows:

  • Albumentations

  • cuPY

  • Data Loading Library (DALI)

  • JFX


  • Numba

  • NumPy

  • PyTorch

  • Tensorflow

  • Triton

cuCIM is fully open sourced under the Apache-2.0 license, and the Clara and RAPIDS teams welcomes new and seasoned contributors, users and hobbyists! You may download cuCIM via Anaconda Conda or PyPI Thank you for your wonderful support! Below, we provide some resources to help get you started.




Indices and tables#