A Novel Aβ Segmentation Algorithm Based on 3D Lattice Boltzmann Method

Pittsburgh compound B Positron Emission Tomography (PiB-PET) imaging is a new technology for detecting amyloid-beta peptide (A beta). A beta l is a pathological bio-data that distinctly appears in most neuro-degeneration diseases, such as Alzheimer's disease (AD). The 3D segmentation of A beta in PiB-PET images aids radiologists in diagnosing AD. However, the existing 3D segmentation algorithms (e.g., thresholding based algorithms, Level Set Method (LSM) based algorithms, etc.) are limited by their accuracy or computing time and thus cannot meet clinical requirements. This paper proposes a novel A beta segmentation algorithm based on the 3D Lattice Boltzmann Method (LBM). The experimental results demonstrate that the novel algorithm achieves effective and efficient segmentation results in PiB-PET images.