Publications by authors named "Tiexiang Li"
Article Synopsis
- The research introduces a novel method that uses optimal mass transportation (OMT) to convert irregular 3D brain images into a cube format suited for U-net algorithms in medical imaging.
- A cubic volume-measure-preserving OMT (V-OMT) model is developed alongside a two-phase residual U-net algorithm to accurately predict and refine the tumor regions in the brain images.
- The method was validated using a dataset from the Brain Tumor Segmentation (BraTS) 2021, showing notable improvements in the accuracy of brain tumor detection and segmentation, with high Dice scores reported for different tumor regions.
Optimal mass transport (OMT) theory, the goal of which is to move any irregular 3D object (i.e., the brain) without causing significant distortion, is used to preprocess brain tumor datasets for the first time in this paper.
View Article and Find Full Text PDF