Hybrid segmentation of ventilation defect regions in low signal-to-noise ratio hyperpolarized 129Xe MRI

Ventilation defect percentage (VDP) generated from hyperpolarized gas (3He or 129Xe) MRI is a sensitive indicator of lung disease. However, the commonly used K-means method for the calculation of VDP is not suitable for low signal-to-noise ratio (SNR) images. In this work, we proposed a hybrid segmentation method to segment the ventilation defect regions and calculate VDP values under low SNR conditions. The results show that the proposed method has improved both the accuracy of segmenting VDP map and calculating VDP value.