A Real-Time Optimization Method for Multimodal Photoacoustic Tomography Based on Ultrasonic Image Features and Deep Learning

By combining ultrasound image features with a multimodal photoacoustic tomography method based on deep learning, the problems of artifacts and noise interference in photoacoustic tomography have been solved, achieving enhanced contrast and real-time imaging optimization of deep blood vessels, providing efficient imaging quality improvement and clinical diagnostic support.

CN120689454BActive Publication Date: 2026-05-26RES INST OF ZHEJIANG UNIV TAIZHOU
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
RES INST OF ZHEJIANG UNIV TAIZHOU
Filing Date
2025-06-26
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing photoacoustic tomography systems cannot accurately calculate light flux during real-time scanning, resulting in inaccurate reconstruction of image signal intensity, limited resolution, artifacts and noise interference, and the inability to achieve real-time optimization.

Method used

A multimodal photoacoustic tomography method based on ultrasound image features and deep learning is adopted. The ResUNet and U-net networks are trained to acquire real-time photoacoustic images and perform light intensity correction and noise processing. Monte Carlo optical simulation and acoustic simulation are combined to improve the imaging quality.

Benefits of technology

It significantly improves imaging quality, eliminates artifacts and noise interference, enhances the contrast of deep blood vessels, realizes the restoration of the true size of blood vessels and real-time imaging optimization, and provides an efficient and reliable auxiliary tool for clinical diagnosis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120689454B_ABST
    Figure CN120689454B_ABST
Patent Text Reader

Abstract

This invention discloses a real-time optimization method for multimodal photoacoustic tomography based on ultrasound image features and deep learning, comprising: acquiring ultrasound image data; inputting the ultrasound image data into a ResUNet network for training to obtain a pre-trained residual model, wherein the pre-trained residual model is used to output a real-time photoacoustic image after light intensity correction; acquiring raw sine wave data; inputting the raw sine wave data into a U-net network for training to obtain a pre-trained attention model; and inputting the real-time photoacoustic image into the pre-trained attention model to obtain optimized photoacoustic image data. This invention solves the problems of artifacts and noise interference, insufficient contrast of deep blood vessels, inability to restore the true size of blood vessels, and inability to provide real-time imaging optimization in existing linear photoacoustic tomography.
Need to check novelty before this filing date? Find Prior Art