A semi-automatic labeling method and system for ultrasound image videos
By performing semi-automatic annotation on ultrasound images and videos, and utilizing deep learning models and convolutional neural networks for feature extraction and arbitration, the problem of low annotation efficiency in ultrasound images and videos by existing tools is solved, and more efficient and accurate annotation results are achieved.
CN116704243BActive Publication Date: 2026-07-14SHANGHAI SOUNDWISE TECHNOLOGY CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI SOUNDWISE TECHNOLOGY CO LTD
- Filing Date
- 2023-05-23
- Publication Date
- 2026-07-14
AI Technical Summary
Technical Problem
Existing video annotation tools struggle to effectively annotate subtle changes in ultrasound images, resulting in low annotation efficiency and errors, especially when annotating complex structures.
Method used
A semi-automatic annotation method is adopted, which pre-labels the target frame images of ultrasound video data, extracts spatiotemporal features using a deep learning model, and combines convolutional neural networks for feature fusion and voting mechanism for arbitration, and automatically updates the labeling results.
Benefits of technology
It improves the accuracy and efficiency of ultrasound image video annotation, reduces annotation errors and redundancy, and achieves more accurate target identification and marking.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116704243B_ABST
Abstract
The application provides a kind of semi-automatic labeling method and system of ultrasonic video, comprising: step S1, target marking is carried out to target frame image in ultrasonic video data, and first marking information is obtained;Step S2, according to first marking information, target identification marking is carried out to front and rear frame image, and then second marking information corresponding to all frame images is obtained;Step S3, when the same target exists different marking, all markings corresponding to the repeatedly marked target are arbitrated;Step S4, according to the arbitration result, update second marking information.Have beneficial effect: the application carries out target tracking marking to front and rear frame image by the marking information of the target of target frame image, can mark target more accurately, and can automatically update the marking of front and rear frame;At the same time, arbitration and update are carried out to repeated marking, determine the final marking result, can avoid labeling error and reduce labeling redundancy, can further improve labeling accuracy.
Need to check novelty before this filing date? Find Prior Art