LivermorE AI Projector for Computed Tomography

LEAP is a C++/CUDA library (Linux, Windows, and Mac) of 3D tomographic algorithms (pre-processing algorithms, projectors, and analytic (FBP) and iterative reconstruction algorithms) with a Python interface. The projectors (forward and back projection) are implemented for both multi-GPU and multi-core CPU and we provide bindings to PyTorch to achieve differentiable forward and backward projectors for AI/ML-driven Computed Tomography (CT) applications.

Contents:

• Installation and Tutorial
• Technical Manual
• Python API (leapctype)
  • High-Level Functions
  • CT Geometries
  • CT Volume
  • Forward and Back Projection
  • Analytic Reconstruction (FBP)
  • Iterative Reconstruction
  • Filter Sequence
  • Projection Filters and Transforms
  • Volume Filters and Transforms
  • Filters Applied to Arbitrary 3D Arrays
  • File I/O
  • CT Simulation Functions
• Preprocessing Algorithms
  • makeAttenuationRadiographs()
  • outlierCorrection()
  • outlierCorrection_highEnergy()
  • detectorDeblur_FourierDeconv()
  • detectorDeblur_RichardsonLucy()
  • ringRemoval_fast()
  • ringRemoval()
• Physics-Based Preprocessing Algorithms
• PyTorch Neural Network Interface (leaptorch)
  • BackProjectorFunctionCPU
  • BackProjectorFunctionGPU
  • Projector
  • ProjectorFunctionCPU
  • ProjectorFunctionGPU

Indices and tables

• Index

• Module Index

• Search Page