Laparoscopic surgery stage identification method and system based on dual-granularity time convolution
A recognition method and double-grained technology, applied in neural learning methods, character and pattern recognition, image data processing, etc., can solve problems such as difficult to accurately distinguish transition frames between stages, and achieve good recognition effect, improved recognition effect, and good generalization effect of ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0084] Example 1
[0085] as Figures 1 through 4 As shown, the present embodiment discloses a method based on two-particle size time convolution laparoscopic surgical stage identification method, the specifics of which are as follows:
[0086] 1) First, the laparoscopic minimally invasive surgical process is recorded through a miniature camera mounted at the tip of the surgical instrument, and each complete surgical process is stored as a video. Each video is then sliced using ffpmeg, saving a picture every 5 frames, in frame number order. Abnormal images, including those with full-scale blur, large-scale phantoms, extreme lighting, and incomplete shooting, were then eliminated and made into datasets for laparoscopic surgery and split into training, validation, and testing sets at a 40:8:32 ratio. Finally, OpenCV was used to perform image enhancement operations such as center flipping, random cropping, and scrambling order of laparoscopic surgery pictures.
[0087] 2) The processe...
Example Embodiment
[0118] Example 2
[0119] See Figure 5 As shown, the present embodiment discloses a laparoscopic surgical stage recognition system based on two-particle size time convolution, comprising the following functional modules:
[0120] Data acquisition module for collecting laparoscopic surgical videos, downsampling each video, retaining several images at each stage of each video, making a laparoscopic surgical dataset, and arranging them in the format of "address / video serial number / frame sequence number" to form a video sequence;
[0121] Data processing module, which is used to input the video sequence in the laparoscopic surgical dataset into the first part of the two-particle time convolutional network, that is, the double-particle time convolution module, model the long-distance time context information, generate the initial prediction result, and use the cross-entropy loss function to calculate the degree of difference between the initial prediction result and the actual data; th...
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