基于蚁群优化支持向量机的颅内动脉瘤破裂风险预测模型

陈广新; 国威; 才莹; 郭金兴

doi:10.12263/newIT.2024.06.001

您当前的位置：

首页 >

文章列表页 >

基于蚁群优化支持向量机的颅内动脉瘤破裂风险预测模型

研究论文 | 更新时间：2025-07-04

- 基于蚁群优化支持向量机的颅内动脉瘤破裂风险预测模型
- Model for Predicting Intracranial Aneurysm Rupture Risk Based on Ant Colony Optimization and Support Vector Machine
- 新一代信息技术 2025年8卷第1期页码：1-5
- 作者机构：
  
  1.牡丹江医科大学，黑龙江牡丹江 157011
  2.牡丹江医科大学附属红旗医院，黑龙江牡丹江 157011
- 作者简介：
  
  陈广新（1978—），男，讲师，硕士，研究方向：医学人工智能。
  国威（2001—），男，硕士研究生，研究方向：医学人工智能。
  才莹（1996—），女，主治医师，硕士，研究方向：医学人工智能。
  郭金兴（1984—），女，主管护师，研究方向：医学人工智能。
- 基金信息：
  
  黑龙江省卫生健康委员会科技（资助）项目(20220909040626)
- DOI：10.12263/newIT.2024.06.001
  中图分类号： TP181
- 纸质出版日期：2025-01-15
- 稿件说明：
移动端阅览
陈广新, 国威, 才莹, 等. 基于蚁群优化支持向量机的颅内动脉瘤破裂风险预测模型[J]. 新一代信息技术, 2025, 8(1): 01-05

CHEN Guang-xin, GUO Wei, CAI Ying, et al. Model for Predicting Intracranial Aneurysm Rupture Risk Based on Ant Colony Optimization and Support Vector Machine[J]. New Generation of Information Technology, 2025, 8(1): 01-05
陈广新, 国威, 才莹, 等. 基于蚁群优化支持向量机的颅内动脉瘤破裂风险预测模型[J]. 新一代信息技术, 2025, 8(1): 01-05 DOI： 10.12263/newIT.2024.06.001.

CHEN Guang-xin, GUO Wei, CAI Ying, et al. Model for Predicting Intracranial Aneurysm Rupture Risk Based on Ant Colony Optimization and Support Vector Machine[J]. New Generation of Information Technology, 2025, 8(1): 01-05 DOI： 10.12263/newIT.2024.06.001.

摘要

本文提出了一种结合蚁群优化算法（Ant Colony Optimization，ACO）与支持向量机（Support Vector Machine，SVM）的分类模型，用于颅内动脉瘤破裂风险的预测。数据集的构建充分考虑了动脉瘤的形态学和血流动力学特征，通过CT图像的处理和计算，构建了一个全面的数据集。ACO算法用于优化SVM的参数选择，提高了模型的预测性能。支持向量机中选择了四种不同的核函数，通过混淆矩阵和ROC曲线评估了不同核函数模型的性能。结果表明，Sigmoid核函数模型的性能最佳，为颅内动脉瘤的诊断和风险评估提供了重要的参考依据。

Abstract

This paper proposes a classification model that combines the ant colony optimization (ACO) algorithm with the support vector machine (SVM) for the prediction of intracranial aneurysm rupture risk. The dataset construction takes into full account the morphological and hemodynamic characteristics of aneurysms. Through the processing and calculation of CT images

a comprehensive dataset has been constructed. The ACO algorithm is used to optimize the parameter selection of SVM

which improves the predictive performance of the model. Four different kernel functions are selected in the SVM

and the performance of the models with different kernel functions is evaluated using confusion matrices and ROC curves. The results indicate that the Sigmoid kernel function model performs the best

providing an important reference for the diagnosis and risk assessment of intracranial aneurysms.

关键词

Keywords

references

牛伟伟 , 买买提力·艾沙 , 王增亮 . 颅内镜像动脉瘤形态学及血流动力学特点预测破裂风险的研究进展 [J ] . 中国临床神经外科杂志 , 2023 , 28 ( 12 ): 724 - 727 .

王阔 , 李曼曼 , 李彦良 , 等 . 颅内动脉瘤影像学检查与破裂风险的研究现状 [J ] . 中国中西医结合影像学杂志 , 2023 , 21 ( 2 ): 206 - 210 .

范然 , 李一鸣 . 高分辨血管壁成像评估颅内动脉瘤破裂风险的研究进展 [J ] . 国际医学放射学杂志 , 2023 , 46 ( 2 ): 177 - 180 .

何佳倩 , 安兴伟 , 任贺成 , 等 . 计算机辅助诊断检测颅内动脉瘤进展 [J ] . 中国医学影像技术 , 2023 , 39 ( 2 ): 291 - 294 .

LECLER A , RAYMOND J , RODRIGUEZ-RÉGENT C , et al . Intracranial aneurysms: Recurrences more than 10 years after endovascular treatment: A prospective cohort study, systematic review, and meta-analysis [J ] . Radiology , 2015 , 277 ( 1 ): 173 - 180 .

CHUNG B J , MUT F , PUTMAN C M , et al . Identification of hostile hemodynamics and geometries of cerebral aneurysms: A case-control study [J ] . AJNR. American Journal of Neuroradiology , 2018 , 39 ( 10 ): 1860 - 1866 .

LEE K S , ZHANG J J Y , NGUYEN V , et al . The evolution of intracranial aneurysm treatment techniques and future directions [J ] . Neurosurgical Review , 2022 , 45 ( 1 ): 1 - 25 .

TAWK R G , HASAN T F , D'SOUZA C E , et al . Diagnosis and treatment of unruptured intracranial aneurysms and aneurysmal subarachnoid hemorrhage [J ] . Mayo Clinic Proceedings , 2021 , 96 ( 7 ): 1970 - 2000 .

GUÉDON A , THÉPENIER C , SHOTAR E , et al . Predictive score for complete occlusion of intracranial aneurysms treated by flow-diverter stents using machine learning [J ] . Journal of Neurointerventional Surgery , 2021 , 13 ( 4 ): 341 - 346 .

HAMMOUD B , EL ZINI J , AWAD M , et al . Predicting incomplete occlusion of intracranial aneurysms treated with flow diverters using machine learning models [J ] . Journal of Neurosurgery , 2023 , 140 ( 6 ): 1716 - 1725 .

TIAN Z B , LI W Q , FENG X , et al . Prediction and analysis of periprocedural complications associated with endovascular treatment for unruptured intracranial aneurysms using machine learning [J ] . Frontiers in Neurology , 2022 , 13 : 1027557 .

ISHIHARA M , SHIIBA M , MARUNO H , et al . Detection of intracranial aneurysms using deep learning-based CAD system: Usefulness of the scores of CNN's final layer for distinguishing between aneurysm and infundibular dilatation [J ] . Japanese Journal of Radiology , 2023 , 41 ( 2 ): 131 - 141 .

JOO B , AHN S S , YOON P H , et al . A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance [J ] . European Radiology , 2020 , 30 ( 11 ): 5785 - 5793 .

MUSTAFA ABDULLAH D , MOHSIN ABDULAZEEZ A . Machine learning applications based on SVM classification: A review [J ] . Qubahan Academic Journal , 2021 , 1 ( 2 ): 81 - 90 .

LIU C , WU L , XIAO W S , et al . An improved heuristic mechanism ant colony optimization algorithm for solving path planning [J ] . Knowledge-Based Systems , 2023 , 271 : 110540 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于Outlier-SMOTE和果蝇优化支持向量机的颅内动脉瘤破裂风险预测模型