Development of a New Image Reconstruction Method Using Bayesian Estimation with Limited View-Angle Projection Data for BNCT-SPECT

Abstract

Boron Neutron Capture Therapy (BNCT) is an emerging radiation treatment for cancer, and its challenges are being explored. Systems capable of capturing real-time observations of this treatment’s effectiveness, particularly BNCT-SPECT methods that measure gamma rays emitted instantaneously from outside the body during nuclear reactions and that reconstruct images using Single Photon Emission Computed Tomography (SPECT) techniques, remain unavailable. BNCT-SPECT development is hindered by two main factors, the first being the projection angle. Unlike conventional SPECT, the projection angle range which is achievable by rotating a detector array cannot exceed approximately 90 degrees. Consequently, Fourier-based image reconstruction methods, requiring projections from at least 180 degrees, do not apply to BNCT-SPECT. The second limitation is the measurement time. Given these challenges, we developed a new sequential approximation image reconstruction method using Bayesian estimation, which is effective under the stringent BNCT-SPECT conditions. We also compared the proposed method with the existing Maximum Likelihood-Expectation Maximization (ML-EM) image reconstruction method. Numerical experiments were conducted by obtaining BNCT-SPECT projection data from true images and reconstructing images using both the proposed and ML-EM methods from the resulting sinograms. Performance comparisons were conducted using a dedicated program applying Bayesian estimation and this showed promise as a new image reconstruction method useful under BNCT-SPECT conditions.

Keywords

• BNCT-SPECT
• image reconstruction
• limited view-angle projection
• Bayesian estimation