Cerebrovascular segmentation in phase-contrast magnetic resonance angiography by multi-feature fusion and vessel completion

Phase-Contrast Magnetic Resonance Angiography (PC-MRA) is a potential way of cerebrovascular imaging, which can suppress non-vascular tissue while presenting vessels. But PC-MRA will bring much noise and is easy to result in partially broken vessels. Usually, deep learning is an effective way to quantify vessels. However, how to choose an appropriate deep learning model is an important and difficult issue. In this work, we adopted the Dempster-Shafer (DS) evidence theory to fuse multi-feature from different models. Also, the vessel thinning and completion method were proposed to fill in information of broken cerebrovascular in PC-MRA images. For quantitative analysis, we chose Precision (PRE), Recall (REC), and Dice Similarity Coefficient (DSC) as assessment metrics, and established U-Net, V-Net, and Dense-Net. The 22 subjects tested this method. Comparison with different fusion strategies and common deep learning models have confirmed the effectiveness of the proposed method. In addition, we scanned Contrast-Enhanced MRA (CE-MRA) for 12 patients to verify reliability of vessel completion. Experiments show that the completion vessel can improve the matching ratio with CE-MRA, which has clinical potential.

Automated summary

Phase-Contrast Magnetic Resonance Angiography (PC-MRA) is a potential method for cerebrovascular imaging, but it often has noise and broken vessels. This study used the Dempster-Shafer evidence theory to fuse features from different models and proposed a vessel thinning and completion method. Experimental results show the effectiveness of this method and the completion vessels can improve the matching ratio with CE-MRA.