基于显著性分析的脑血管分割基础方法研究

脑血管组织错综复杂，形态细小、分支众多以及位置特殊和形态复杂等特性，精确地提取及重建脑血管成为一项国际性难题。由于缺乏有效、精准的血管分割方法，目前基于影像引导的方案存在着脑血管细节信息提取不全、血管连通性差、拓扑结构缺失等问题，这将直接导致了客观量化的监测手段的缺乏，常规影像引导的手术治疗手段风险极高。本项目针对脑血管高精度手术的迫切需求，开展脑血管精准分割的基础方法研究。拟研究内容具体包括基于Retinex的血管图像增强技术；基于紧凑性为特征的显著性分析方法，对核磁共振图像中的血管区域进行定位；基于无限边缘活动轮廓模型结合图像的显著性特征，实现在三维空间内对脑血管结构提取与精确分割；基于多分支预测并结合机器学习实现脑血管拓扑结构的建立。通过本项目研究所提出的理论方法来解决目前已有方法存在的问题，提高脑血管分割的准确性和有效性，本项工作在脑血管精准手术及疾病的临床预防诊断具有深远意义。

The automated detection of blood vessels is a prerequisite in the development of automated system for the analysis of vessels. Cerebrovascular diseases are often life-critical for individuals, and present a challenging public health problem for society, since the brain structure contains vascular bifurcations, small shapes, and complicated patterns. As thus, the detection and analysis of the cerebrovascular is a fundamental task in many clinical applications to support early detection, diagnosis and optimal treatment. In line with the proliferation of imaging modalities, there is an ever-increasing demand for automated vessel analysis systems for which where blood vessel segmentation is the first and most important step. The proposed framework consists of three technical components: Retinex-based image enhancement is employed to enhance vessels for its superiority in preserving the vessel edges, and also correct the image inhomogeneity; then, intensity and compactness enabled saliency detection is proposed to locate the vascular regions; finally, based on the detected saliency region, a saliency driven infinite perimeter active contour segmentation is proposed. This framework will become a powerful tool for management of a wide spectrum of vascular-related diseases.