基于深度学习的卒中术前多模态影像融合及评估系统

By using deep learning technology and combining feature analysis of DSA angiography and MRI images, the edge intensity map is dynamically adjusted, which solves the problem of missing pathological semantic association and spatiotemporal complementarity in cross-modal image fusion. This enables accurate fusion and assessment of preoperative stroke images, reduces anatomical topological distortion and microlesion edge dissolution, and improves the accuracy of risk assessment.

CN122265278BActive Publication Date: 2026-07-17THE FIRST AFFILIATED HOSPITAL OF TSINGHUA UNIV +2
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
THE FIRST AFFILIATED HOSPITAL OF TSINGHUA UNIV
Filing Date
2026-05-26
Publication Date
2026-07-17

Smart Images

  • Figure CN122265278B_ABST
    Figure CN122265278B_ABST
Patent Text Reader

Abstract

本发明涉及医疗图像处理技术领域，具体涉及一种基于深度学习的卒中术前多模态影像融合及评估系统，包括：获取多模态影像序列；根据DSA造影序列的边缘特征，确定每个血管中心点的血管崩溃指数；根据MRI影像确定每个局部区域的细胞水肿显著指数和血管崩溃指数均值，进而确定每个局部区域的细胞毒性水肿程度；将MRI影像的局部区域映射到CT影像中，根据CT影像序列中每个局部区域的边缘特征，结合细胞毒性水肿程度，确定每个局部区域的边缘溶解风险系数；将多模态影像序列作为输入，利用边缘溶解风险系数动态调整边缘强度图谱，得到多模态的术前病灶区域融合结果，以辅助医生进行评估，本发明有效确保了三维融合结果的真实性。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Multi-modality medical image identification method and device based on deep learning

    CN106909778A

  • Intelligent focus detection and diagnosis system based on multi-modal medical image fusion

    CN121482012A