Dynamic lung cancer curative effect prediction method and system based on CT image change

The dynamic feature matrix of CT images was processed through the Transformer attention network, combined with the time-sharing training strategy, and the problem of integrating follow-up data in patients with advanced NSCLC was solved, dynamic prediction of lung cancer efficacy and real-time adjustment of treatment strategies, and improved the patient's survival prognosis.

CN120376155AActive Publication Date: 2025-07-25ZHEJIANG CANCER HOSPITAL
7 Cites 2 Cited by

Patent Information

Application Number
CN202510886779.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-30
Publication Date
2025-07-25
Estimated Expiration
2045-06-30

AI Technical Summary

Technical Problem

The prior art is difficult to effectively integrate the follow-up CT image data of patients with advanced non-small cell lung cancer (NSCLC), and the efficacy prediction results cannot be dynamically updated during the follow-up process, resulting in delays in treatment.

Method used

Transformer attention network is used to identify the relationship between the dynamic feature matrix of CT images, and combined with the time-sharing training strategy, a dynamic prediction system for lung cancer efficacy based on CT image changes is constructed. The baseline and follow-up features are processed through the self-attention and cross-attention modules, and the efficacy prediction results at different time points are output.

Benefits of technology

It realizes dynamic update of the efficacy prediction model without changing the data dimension, and can adjust the treatment strategy in real time during the follow-up process, improving the prognostic effect of patients with advanced NSCLC.

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

Abstract

The invention discloses a CT image change-based lung cancer curative effect dynamic prediction method and system, and relates to the technical field of medical imaging. Clinical information, a baseline CT image and a follow-up CT image of a patient are acquired; performing feature extraction on the baseline CT image and the follow-up CT image to obtain baseline features and follow-up features; obtaining an enhanced CT dynamic feature matrix and a flat-scanning CT dynamic feature matrix based on the baseline features and the follow-up visit features; inputting the enhanced CT dynamic feature matrix, the plain-scan CT dynamic feature matrix and clinical information into a curative effect prediction model, outputting logic risk scores at different time points, and obtaining progress or death risk probabilities of the patient at different time points; according to the method, image feature changes in a baseline and follow-up visit are effectively represented through a dynamic feature matrix, correlation between the interior of the dynamic feature matrix and between different matrixes is identified through a Transform attention network to predict the curative effect, and the relationship between accumulated data at each follow-up visit time point and the curative effect is learned through a time-sharing training strategy.
Need to check novelty before this filing date? Find Prior Art