Aortic dissection postoperative remodeling risk prediction method and system

By receiving CTA images from multiple time points, and utilizing deep learning segmentation models and vascular deformation mapping technology, multi-dimensional features are extracted to predict the risk of remodeling after aortic dissection. This solves the problems of assessment lag, singularity, and low efficiency in existing technologies, and achieves early warning and high-precision risk prediction.

CN122290997APending Publication Date: 2026-06-26ZHONGSHAN HOSPITAL FUDAN UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202610337819.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-19
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies for assessing the postoperative effects and long-term risks of aortic dissection suffer from problems such as lag, singularity, subjectivity, low efficiency, and lack of integrated models, and cannot fully reflect the three-dimensional morphological changes and local biomechanical state of the aorta.

Method used

By receiving CTA images from multiple time points, aortic segmentation and 3D modeling are performed using a deep learning segmentation model. Combined with vascular deformation mapping technology, multi-dimensional features are extracted and input into a risk prediction model to achieve automated risk prediction.

Benefits of technology

It achieves strong early warning capabilities, high prediction accuracy, and fully automated and efficient risk prediction, outputting objective parameters to support individualized management and clinical decision-making.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an aortic dissection postoperative remodeling risk prediction method and system, and the method comprises the following steps: receiving the CTA images of the chest and abdomen of a patient at a plurality of time points, such as a preoperative time point and a postoperative short-term time point or a postoperative middle-term time point, and obtaining an aortic segmentation result according to the CTA images; obtaining a displacement field of each voxel point between two time points according to the aorta segmentation result, and obtaining a blood vessel deformation mapping result according to the displacement field; extracting multi-dimensional features from the three-dimensional aorta segmentation model and the blood vessel deformation mapping result; predicting the risk of postoperative aortic malfunction remodeling of the patient according to the multi-dimensional features; the beneficial effects of the invention are that the method comprehensively utilizes the multi-dimensional, dynamic and static combined features, and the constructed prediction model theoretically has higher distinction degree and calibration degree than an existing single-index model, so that the method can detect early and local abnormal deformation which cannot be found by traditional diameter measurement. And the risk identification time point is greatly advanced.
Need to check novelty before this filing date? Find Prior Art