Core utilities for volumetric medical image analysis, written in pytorch. Voxel provides methods for working with 3D image grid data and triangular meshes with consideration of their representation in a world (or scanner) coordinate system. The toolbox is fully GPU compatible and developed with particular emphasis on its use for deep-learning applications. More documentation to come soon!
If you find this package useful in your work, please cite the following publication (for which this package was originally developed).
VoxelPrompt: A Vision-Language Agent for Grounded Medical Image Analysis
Andrew Hoopes, Victor Ion Butoi, John V. Guttag, Adrian V. Dalca