Skip to content Skip to search Skip to footer
Washington University in St. Louis

Computational Medical Imaging and Therapy (CMIT) Lab

Menu
  • Research
    • Ultra-low-count imaging for treatment of cancers
    • Task-specific design of imaging algorithms
    • Using deep learning to advance quantitative PET
    • Physics and deep-learning-based CT-less SPECT
    • Deep-learning-based methods for brain SPECT
    • No-gold-standard evaluation (NGSE)
    • List-mode SPECT systems
    • Other projects
      • Detectors for nuclear-medicine imaging
      • Diffusion MRI
        • PI Biography
      • Computational methods for optical tomography
  • People
  • Open positions
  • Publications
  • News and Fun!
  • Software
    • A Bayesian approach to tissue-fraction estimation for oncological PET segmentation
    • A fully automated modular framework for PET segmentation
    • Simulating SiPM response
    • Image reconstruction in FMT
    • Computational methods for diffuse optical imaging
    • Segmentation and quantification in diffusion MR images
  • Press/media
  • Journal Club
  • Teaching
  • Contact Us

Software

Our lab develops multiple computational medical imaging solutions and we strongly support dissemination of the resultant software and data. For commercial applications however, we ask that you contact the lab PI.  The following software are available:

  1. A Bayesian approach to tissue-fraction estimation for oncological PET segmentation
  2. A fully automated modular framework for PET segmentation
  3. Simulating response of Silicon photomultipliers for SPECT and PET systems
  4. Image reconstruction in fluorescence molecular tomography
  5. Computational methods for diffuse optical imaging
  6. Segmentation and apparent diffusion coefficient quantification from diffusion MR images

 

  • Software
    • A Bayesian approach to tissue-fraction estimation for oncological PET segmentation
    • A fully automated modular framework for PET segmentation
    • Simulating SiPM response
    • Image reconstruction in FMT
    • Computational methods for diffuse optical imaging
    • Segmentation and quantification in diffusion MR images

©2023 Washington University in St. Louis