Deep vessel segmentation based on a new combination of vesselness filters

arXiv:2402.14509v1 Announce Type: cross
Abstract: Vascular segmentation represents a crucial clinical task, yet its automation remains challenging. Because of the recent strides in deep learning, vesselness filters, which can significantly aid the learning process, have been overlooked. This study introduces an innovative filter fusion method crafted to amplify the effectiveness of vessel segmentation models. Our investigation seeks to establish the merits of a filter-based learning approach through a comparative analysis. Specifically, we contrast the performance of a U-Net model trained …

abstract amplify arxiv automation clinical combination cs.cv deep learning eess.iv filter filters fusion process segmentation study type