Liver and tumor segmentation method and system based on multitask deep convolution network
A deep convolution, liver tumor technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve the problems of difficult tumor segmentation, lack of liver tumor segmentation methods, under-segmentation, etc., to achieve a wide range of applications, The effect of shortening the completion time
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0050] The present invention will be further described below in conjunction with illustrations and specific embodiments. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.
[0051] In this embodiment, the task goal is to train the segmenter so that it can effectively perform liver and liver tumor segmentation on CT scan (computerized tomography) image data. The embodiment uses a V-Net-based multi-task convolutional network as a specific segmentation network, and uses training data for 21237 slices in the vertical direction of CT scans of liver parts with labels. Lesions vary in size.
[0052] see figure 1 As shown, the concrete steps of the present embodiment method are as follows:
[0053] Step 1, data collection and preprocessing
[0054] Step 1.1, Data Collection
[0055] Through various approaches, a total of 151 CT scan images with liv...
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