NiftyPET

by Open Sourcegithub.com
VISIT OFFICIAL WEBSITE →
Disclaimer: This page is an independent third-party listing and is not affiliated with, sponsored by, or endorsed by NiftyPET or Open Source. All product names, logos, and brands are property of their respective owners.

OVERVIEW

High-throughput, GPU-accelerated, open-source Python platform for quantitative PET image reconstruction and analysis, especially for hybrid PET/MR data.

NiftyPET is an open-source Python package for high-throughput Positron Emission Tomography (PET) image reconstruction, manipulation, processing, and quantitative analysis, primarily developed at University College London (UCL).

The platform is specifically engineered for high quantitative accuracy and precision, with a strong emphasis on data acquired using hybrid and simultaneous PET/MR scanners. Its core routines are written in CUDA C and embedded in Python C extensions, enabling efficient, high-throughput execution on NVIDIA Graphics Processing Units (GPUs).

NiftyPET covers the entire processing pipeline, from raw list-mode (LM) PET data through to the final image statistic of interest (e.g., regional SUV). Key capabilities include:

  • High-Fidelity Correction Models: Accurate attenuation coefficient map generation, fully 3D scatter modelling, and estimation of reduced-variance random events.
  • Image Processing: Voxel-based Partial Volume Correction (PVC), image manipulation, processing, and registration (via the nimpa sub-package).
  • Uncertainty Estimation: Facilitates voxel-wise estimation of uncertainties of image statistics by enabling LM bootstrapping and multiple independent reconstructions.

While a key application is brain imaging in neurodegeneration (e.g., with amyloid tracers), the software is equally capable for whole-body imaging. It is a powerful tool for scientific research, allowing for the development and validation of new reconstruction and analysis algorithms within a high-performance, open-source framework.

RATING & STATS

Customers
100+
Founded
2016

SCREENSHOTS

NiftyPET screenshot 1

KEY FEATURES

  • GPU-Accelerated Processing (CUDA C)
  • Quantitative PET Image Reconstruction
  • Full List-Mode (LM) Data Processing Pipeline
  • Voxel-based Partial Volume Correction (PVC)
  • Uncertainty Estimation via LM Bootstrapping
  • Accurate Attenuation Correction
  • Fully 3D Scatter Modelling
  • Image Manipulation and Registration

PRICING

Model: free
Open-source, free Python package for scientific research and high-throughput image processing.
FREE TIER

TECHNICAL DETAILS

Deployment: on_premise
Platforms: linux, windows, mac
🔌 API Available⚡ Open Source

USE CASES

Brain Imaging in Neurodegeneration (Amyloid PET)Quantitative Whole-Body PET ImagingProcessing Hybrid PET/MR Scanner DataDevelopment of New Reconstruction Algorithms

INTEGRATIONS

dcm2niixNiftyReg

COMPLIANCE & SECURITY

Security Features:
  • 🔒DICOM anonymisation

SUPPORT & IMPLEMENTATION

Support: community_forum, github_issues
Implementation Time: < 1 week
Target Company Size: enterprise
TRAINING AVAILABLE

PROS & CONS

✓ Pros:
  • +Open-source and free for all users
  • +High-throughput performance via GPU acceleration (CUDA)
  • +High quantitative accuracy and precision (peer-reviewed)
  • +Covers full PET processing pipeline from raw list-mode data
  • +Includes uncertainty estimation (LM bootstrapping)
✗ Cons:
  • -Requires NVIDIA GPU and CUDA environment
  • -Steep learning curve (Python/command-line interface)
  • -Community-based support only
  • -No formal clinical/regulatory certifications (e.g., FDA, CE)

TRY IT OUT

ABOUT OPEN SOURCE

Other software by Open Source:
3D Slicer (3D Imaging & Reconstruction3D medical visualization)
3D Slicer Volume Rendering (3D Imaging & ReconstructionVolume rendering platforms)
3DimViewer (3D Imaging & ReconstructionVolume rendering platforms)
APPIAN (Nuclear Medicine & Molecular ImagingMolecular imaging quantification)
Arriba (Cancer Genomics & Precision Oncology PlatformsFusion detection and analysis)