A method for determining the size of an intravascular virtual stent

By using deep learning models and complete subnetworks to enhance, repair, and reconstruct the EEL, and combining the comprehensive loss function to optimize the virtual stent size, the problem of difficult EEL boundary identification is solved, enabling more accurate stent planning and FFR prediction, and improving clinical guidance value.

CN122176033APending Publication Date: 2026-06-09SECOND AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SECOND AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE
Filing Date
2026-01-27
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies have difficulty or incomplete identification of EEL boundaries when determining the size of intravascular virtual stents, leading to measurement errors in the reference frame and making it difficult to accurately define the lesion initiation and termination boundaries, thus weakening the guiding value of postoperative FFR prediction values.

Method used

By acquiring OCT images of the target vascular segment, a deep learning model is used to enhance and repair the EEL. When the EEL boundary is unclear, reconstruction is performed based on the completion subnetwork. The virtual stent size is determined by combining the comprehensive loss function. The stent planning is optimized by considering factors such as IPA, plaque burden, and EEL confidence.

Benefits of technology

It improves the accuracy of virtual stent size, avoids operator subjectivity differences, ensures that the stent placement point is not at vulnerable plaques, and enhances the clinical consistency and guiding value of FFR prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122176033A_ABST
    Figure CN122176033A_ABST
Patent Text Reader

Abstract

The application discloses a kind of intravascular virtual stent size determination method, it is related to medical image processing technical field.The method comprises the following steps: obtaining the OCT image group in the polar coordinate of target blood vessel section;Determine the IPA value of each OCT image in the OCT image group;Determine the preset value, based on the IPA value and the preset value, the EEL recognition state in the OCT image is configured as the first state and the second state;In the case where EEL is in the first state, EEL is enhanced and repaired based on the deep learning model;In the case where EEL is in the second state, EEL is completed and reconstructed based on the completion subnetwork, and the confidence is obtained;According to the comprehensive loss function, the size of the virtual stent is determined.The application improves the clinical consistency of FFR prediction: since the planning of virtual stent considers vulnerable plaque distribution, the predicted stent position is closer to the safe position that the doctor will actually choose during surgery.Therefore, the calculated virtual FFR value has higher consistency with the actual measured FFR value after surgery, and the clinical guidance value of the system is improved.
Need to check novelty before this filing date? Find Prior Art