A Novel 3D Joint MGRF Framework for Precise Lung Segmentation

Abstract

A new framework implemented on NVIDIA Graphics Processing Units (GPU) using CUDA for the precise segmentation of lung tissues from Computed Tomography (CT) is proposed. The CT images, Gaussian Scale Space (GSS) data generation using Gaussian Kernels (GKs), and desired maps of regions (lung and the other chest tissues) are described by a joint Markov-Gibbs Random Field (MGRF) model of independent image signals and interdependent region labels implemented on GPU. The initial segmentation from the original and the generated GSS CT images is based on the Linear Combination of Discrete Gaussian (LCDG) models; The initial segmentation is obtained from the original and the generated GSS CT images; then they are iteratively refined using a parallel MGRF model implemented on GPU with analytically estimated potentials. Finally, these initial segmentations are fused together using a Bayesian fusion approach to get the final segmentation of the lung region. Experiments on eleven real data sets based on Dice Similarity Coefficient (DSC) metric confirms the high accuracy of the proposed approach. The execution time results show that our algorithm takes about three seconds which is about 10³ times faster when compared to a naive single threaded implementation on CPU.