一种用于血管形态分类的混合框架：基于离散几何的曲折度特征测量、基于信息增益的特征选择和随机森林分类
A Hybrid Framework for Blood Vessel Morphology Classification: Discrete Geometry-based Tortuosity Feature Measurement, Information Gain-based Feature Selection, and Random Forest Classification
浏览论文内容
中文总结 AI 辅助
针对血管曲折度量化难题，提出融合离散几何特征测量、信息增益特征选择和随机森林分类的框架，用于颈内动脉形态分类。提取并筛选特征，经实验取得良好分类结果，还定义形态风险指数，为临床评估提供参考。
中文摘要 AI 辅助
血管曲折度的主观视觉分级严重依赖临床经验，传统基于距离的指标常无法充分表征三维空间变形。由于颈内动脉形态异常与脑血管评估及中风风险评估相关，客观且可重复的血管曲折度量化很重要。为此提出颈内动脉（ICA - C1）段形态分类的数学框架，集成离散几何特征测量等。从379条临床血管中心线提取13个曲折度特征，经信息增益特征选择后缩减为6个特征子集。在两个分类任务中评估该框架，二分类Macro - F1分数为0.9206，三分类为0.8626。结果表明伸长和曲率相关特征用于初步筛查，扭转相关特征辅助更详细分类。基于随机森林特征重要性值定义形态风险指数（MRI），为血管形态提供直接数值参考，有助于更客观一致的临床评估。
英文摘要
Subjective visual grading of blood vessel tortuosity relies heavily on clinical experience, while traditional distance-based indices often fail to adequately characterize three-dimensional spatial deformation. Because abnormal internal carotid artery morphology may be clinically relevant to cerebrovascular assessment and stroke-risk evaluation, objective and reproducible quantification of vascular tortuosity is of considerable importance. To address this limitation, we propose a mathematical framework for the morphological classification of the internal carotid artery (ICA-C1) segment. The framework integrates discrete geometric feature measurement, Information Gain-based feature selection, and Random Forest classification. An initial set of 13 tortuosity features is extracted from the corresponding 379 clinical vascular centerlines using discrete geometric methods and subsequently reduced to a six-feature subset consisting of $\mathcal{TI}$, $\mathcal{AC}$, $\mathcal{TC}$, $\mathcal{AC}/\mathcal{AT}$, $\mathcal{AT}$, and $\mathcal{TT}$. The framework is evaluated in two classification tasks. For binary classification of non-severe and severe tortuosity, the RF model achieves a Macro-F1 score of 0.9206. For ternary morphological grading into straight, low-tortuosity, and high-tortuosity groups, it achieves a Macro-F1 score of 0.8626. The results indicate that elongation- and curvature-related features provide strong discriminatory information for basic screening, whereas torsion-related features contribute additional information for more detailed morphological classification. Based on the RF feature-importance values, we further define a Morphological Risk Index (MRI), which provides a direct numerical reference for vascular morphology and may facilitate more objective and consistent clinical assessment.
