System and device for improving segmentation accuracy of left ventricles of multiple heart views
A high-precision, left-ventricular technology, applied in the field of medical testing, can solve problems such as inaccurate segmentation of the left ventricle, and achieve the effects of improving segmentation accuracy, reducing workflow, and improving training accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0025] In order to solve the above problems, as attached Figure 1-3 As shown, the present invention proposes a left ventricular myocardium segmentation system and device based on a deep learning segmentation method, and the system can automatically segment the left ventricular myocardium under different views.
[0026] A deep learning-based system to improve the accuracy of left ventricle segmentation in multiple cardiac views, including:
[0027] The data collection module is configured to: collect image data of several echocardiograms with different views to form an original image data set; collect the echocardiograms to be processed as data to be segmented;
[0028] The preprocessing module is configured to: perform preprocessing on the original image data set to form an experimental data set;
[0029] The training module is configured to: build a deep neural network training model, input the experimental data set into the training model for training, and when the loss fu...
Embodiment 2
[0044] A heart multi-view left ventricular myocardium segmentation system based on deep learning, including:
[0045] Acquisition module: Take the patient as the unit, collect medical images of the apical second chamber and apical fourth chamber of the echocardiogram, mark the outline of the left ventricular myocardium in different views, and make it into an original image data set;
[0046] Preprocessing module: preprocess the data set to obtain the experimental data set;
[0047] Training module: input the experimental data set into the deep learning RetinaNet network to obtain the heart view recognition result and left ventricle detection result, and input the detection result to the segmentation network to obtain the segmentation result.
[0048] Further, the method for making the original image data set is specifically:
[0049] Taking the patient as the unit, first derive the images of the apical second chamber, apical third chamber, and apical fourth chamber from the e...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com