Deep learning-enabled high-speed, multi-parameter diffuse optical tomography.

Journal: Journal of biomedical optics
PMID: 39035576

Abstract

SIGNIFICANCE: Frequency-domain diffuse optical tomography (FD-DOT) could enhance clinical breast tumor characterization. However, conventional diffuse optical tomography (DOT) image reconstruction algorithms require case-by-case expert tuning and are too computationally intensive to provide feedback during a scan. Deep learning (DL) algorithms front-load computational and tuning costs, enabling high-speed, high-fidelity FD-DOT.

Authors

  • Robin Dale
    University of Birmingham, School of Computer Science, Medical Imaging Lab, Birmingham, United Kingdom.
  • Biao Zheng
    Department of Orthopaedics, Yuhang Bang Er Hospital, Hangzhou, China. Electronic address: jmrsyl@126.com.
  • Felipe Orihuela-Espina
    Department of Surgery and Cancer, Imperial College London, London, United Kingdom.
  • Nicholas Ross
    University of Notre Dame, Department of Electrical Engineering, Notre Dame, Indiana, United States.
  • Thomas D O'Sullivan
    University of Notre Dame, Department of Electrical Engineering, Notre Dame, Indiana, United States.
  • Scott Howard
    University of Notre Dame, Department of Electrical Engineering, Notre Dame, Indiana, United States.
  • Hamid Dehghani
    School of Computer Science, College of Engineering and Physical Sciences, University of Birmingham, Birmingham, United Kingdom.

Keywords

External Resources

Popular Topics
Recent Journals