Laparoscopic surgery stage automatic recognition method and device based on double-flow network

An automatic identification and laparoscopy technology, applied in the field of medical image processing, can solve problems such as loss of motion information, meet the needs of identification tasks, reduce the number of parameters, and improve the accuracy of identification

Pending Publication Date: 2020-10-16
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, some motion information has been lost during the process of extracting high-level visual information with advanced residual networks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Laparoscopic surgery stage automatic recognition method and device based on double-flow network
  • Laparoscopic surgery stage automatic recognition method and device based on double-flow network
  • Laparoscopic surgery stage automatic recognition method and device based on double-flow network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Previous neural network-based methods usually adopt a 'sequential structure', which first extracts deep visual information and then models temporal dependencies. This method combines the two into a 'parallel structure', which can reduce the information loss when performing time-dependent modeling while obtaining deep-level visual information.

[0024] Such as Figure 4 As shown, this double-flow network-based automatic identification method for laparoscopic surgery stage includes the following steps:

[0025] (1) Obtain the laparoscopic cholecystectomy video, and obtain the video key frame sequence;

[0026] (2) Use the shared convolutional layer Shared CNN to initially extract the visual features of N images at the same time, and the obtained feature maps are used as the input of the subsequent dual-stream network structure;

[0027] (3) Using the dual-stream network structure to extract time-related information and deep visual semantic information of the video seque...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

According to the automatic recognition method and device for the laparoscopic surgery stage based on the double-flow network, the requirement of an recognition task can be met, end-to-end training optimization of the network is achieved, and the recognition accuracy of the laparoscopic surgery stage is greatly improved. The method comprises the following steps: acquiring a laparoscopic cholecystectomy video to obtain a video key frame sequence; preliminarily extracting visual features of the N images at the same time by utilizing a shared convolutional CNN (Convolutional Neural Network), and taking an obtained feature map as input of a subsequent double-flow network structure; respectively extracting time correlation information and deep visual semantic information of the video sequence byusing a double-flow network structure, further extracting the deep visual semantic information by using a visual branch undertaking a Shared CNN, and fully capturing the time correlation informationof adjacent N images by using three-dimensional convolution and non-local convolution by using a time sequence branch; wherein the deep visual semantic information extracted by the double-flow networkstructure and the time associated information supplement each other, and obtaining an operation stage recognition result by using the fused features.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a double-stream network-based laparoscopic operation stage automatic identification method and a double-stream network-based laparoscopic operation stage automatic identification device. Background technique [0002] Surgical workflow identification is an important topic in the field of computer-assisted surgery as it offers solutions to numerous needs of the modern operating room. Specifically, automated surgical workflow recognition can explain the specific activities currently underway and facilitate the standardization of surgical procedures. The workflow identification performed online during the operation can help improve the efficiency of the operation and assist doctors to make correct decisions, especially for less experienced surgeons. Additionally, automatic workflow recognition of surgical videos is useful for surgeon skill assessment and ind...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/46G06V2201/03G06N3/045G06F18/253G06F18/214
Inventor 丛伟建范敬凡丁媛
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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