Quantum-classical hybrid distance-based and q-means optimization-based lung tumor sub-region automatic delineation method, system and program product
By employing a quantum-classical hybrid distance metric and the Q-means clustering algorithm, the shortcomings of traditional methods in lung cancer FDG PET image data processing are addressed, enabling efficient and accurate delineation of tumor subregions and enhancing the application effect of quantum computing in medical image processing.
CN122416077APending Publication Date: 2026-07-17TONGJI UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202610502423.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-16
- Publication Date
- 2026-07-17
Smart Images
Figure CN122416077A_ABST
Abstract
本发明公开了基于量子‑经典混合距离与Q‑means优化的肺部肿瘤亚区域自动勾画方法、系统及程序产品。所述勾画方法包括数据采集与预处理、量子空间距离计算、经典特征距离计算、混合距离度量构建、Q‑means++初始化、Q‑means迭代聚类、Z轴切片轮廓提取与可视化、模型性能评估等步骤：首先对患者的肺部三维PET影像数据进行预处理，提取体素的三维空间坐标和功能特征并完成归一化；其次分别通过量子电路计算空间坐标的量子距离、加权欧氏距离计算功能特征的经典距离，融合两者构建混合距离度量；最后采用Q‑means++初始化策略和Q‑means迭代聚类实现肿瘤亚区域自动勾画，通过轮廓提取可视化验证并采用轮廓系数和CH指数评估模型性能。本发明能提高亚区域勾画的准确性和临床适用性。
Need to check novelty before this filing date? Find Prior Art