PyTomography: A python library for medical image reconstruction
Lucas A. Polson,
Roberto Fedrigo,
Chenguang Li,
Maziar Sabouri,
Obed Dzikunu,
Shadab Ahamed,
Nicolas Karakatsanis,
Sara Kurkowska,
Peyman Sheikhzadeh,
Pedro Esquinas,
Arman Rahmim,
Carlos Uribe
Affiliations
Lucas A. Polson
Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada; Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada; Corresponding author at: Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada.
Roberto Fedrigo
Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada; Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada
Chenguang Li
Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada; Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada
Maziar Sabouri
Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada; Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada
Obed Dzikunu
Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada; School of Biomedical Engineering, University of British Columbia, Vancouver, Canada
Shadab Ahamed
Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada; Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada
Nicolas Karakatsanis
Department of Radiology, Weill Cornell Medical College, NY, USA
Sara Kurkowska
Molecular Imaging and Therapy Department, BC Cancer, Vancouver, Canada; Department of Nuclear Medicine, Pomeranian Medical University, Szczecin, Poland
Peyman Sheikhzadeh
Nuclear Medicine Department, IKHC, Faculty of Medicine, Tehran University of Medical Science, Tehran, Iran
Pedro Esquinas
Molecular Imaging and Therapy Department, BC Cancer, Vancouver, Canada
Arman Rahmim
Department of Physics & Astronomy, University of British Columbia, Vancouver, Canada; Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada; School of Biomedical Engineering, University of British Columbia, Vancouver, Canada; Department of Radiology, University of British Columbia, Vancouver, Canada
Carlos Uribe
Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada; Department of Radiology, University of British Columbia, Vancouver, Canada; Molecular Imaging and Therapy Department, BC Cancer, Vancouver, Canada
There is a need for open-source libraries in emission tomography that (i) use modern and popular backend code to encourage community contributions and (ii) offer support for the multitude of reconstruction techniques available in recent literature, such as those that employ artificial intelligence. The purpose of this research was to create and evaluate a GPU-accelerated, open-source, and user-friendly image reconstruction library, designed to serve as a central platform for the development, validation, and deployment of various tomographic reconstruction algorithms. PyTomography was developed using Python and inherits the GPU-accelerated functionality of PyTorch and parallelproj for fast computations. Its flexible and modular design decouples system matrices, likelihoods, and reconstruction algorithms, simplifying the process of integrating new imaging modalities using various python tools. Example use cases demonstrate the software capabilities in parallel hole SPECT and listmode PET imaging. Overall, we have developed and publicly share PyTomography, a highly optimized and user-friendly software for medical image reconstruction, with a class hierarchy that fosters the development of novel imaging applications.
