Blood vessel segmentation method and device, electronic device and storage medium
A blood vessel and segmentation technology, which is applied in the field of medical image processing, can solve the problems of limited blood vessel segmentation accuracy, few blood vessel branches, and blocky segmentation, and achieve the effect of improving the accuracy of blood vessel segmentation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0025] Example one
[0026] The blood vessel segmentation method provided in this embodiment is applicable to the blood vessel segmentation of medical images, and is particularly suitable for the blood vessel segmentation in complex organs, such as liver blood vessel segmentation. The method can be executed by a blood vessel segmentation device, which can be implemented by software and / or hardware, and the device can be integrated in an electronic device with image processing functions, such as a desktop computer or a server. See figure 1 , The method of this embodiment specifically includes the following steps:
[0027] S110: Input the image to be segmented into at least two pre-trained set neural network models respectively, and generate initial segmentation results corresponding to each set neural network model.
[0028] Among them, the image to be segmented refers to a medical image containing a blood vessel that needs to be segmented, and it can be a two-dimensional medical ima...
Example Embodiment
[0044] Example two
[0045] This embodiment is based on the above-mentioned embodiment and illustrates the training method of the blood vessel segmentation model. The explanation of the terms that are the same as or corresponding to the above-mentioned embodiments will not be repeated here. See image 3 The model training method for blood vessel segmentation provided in this embodiment includes:
[0046] S310: Generate a first training sample set of the first set neural network model according to the sample image, and use the first training sample set to train the convolutional neural network model to obtain the first set neural network model.
[0047] Among them, the sample image refers to the medical image containing blood vessels used for the training of the blood vessel segmentation model. In order to improve the applicability of the blood vessel segmentation model, medical images of various organs can be selected, such as brain medical images, liver medical images, and limbs. ...
Example Embodiment
[0070] Example three
[0071] This embodiment provides a blood vessel segmentation device, see Figure 4 , The device specifically includes:
[0072] The initial segmentation result generation module 410 is configured to input the image to be segmented into at least two pre-trained set neural network models to generate at least two initial segmentation results;
[0073] The weighted segmentation result generation module 420 is used to use the target model weight value corresponding to each set neural network model to perform weighting processing on each initial segmentation result to generate a weighted segmentation result, wherein the target model weight value is used for training the set neural network Determine when model;
[0074] The segmented blood vessel image generation module 430 is configured to perform image post-processing on the weighted segmentation result to generate a segmented blood vessel image.
[0075] Optionally, the initial segmentation result generating module 41...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap