Instrument detection system and method applied to digestive endoscopic surgery video analysis

Abstract

According to the technical scheme, the instrument detection system applied to digestive endoscopic surgery video analysis is characterized by comprising an endoscopic video collection module, a video analysis module and a video analysis module, an instrument detection module; an instrument state discrimination module; a surgical procedure analysis module; and an analysis result display module. Another technical scheme of the invention is to provide an instrument detection method applied to video analysis of the digestive endoscopic surgery based on the instrument detection system. According to the invention, deep learning and computer vision technologies are utilized to dynamically identify the type and the opening and closing state of the endoscopic instrument. The system and the method not only can be used for detecting and identifying instruments in real time in the endoscopic surgery process so as to mark the surgery process in real time, but also can be used for retrospectively analyzing historical videos, and a viewer can position the operation processes of different instruments through the system.

Description

technical field

[0001] The invention relates to a device detection system applied to video analysis of digestive endoscope surgery and a device detection method realized by the system. Background technique

[0002] In the process of endoscopic surgery, there are nearly ten kinds of commonly used endoscopic instruments, including: biopsy forceps, hook knife, dual knife, IT knife, snare, metal clip, nylon rope, Haibo knife, APC, injection needle, etc. . And these devices often have a variety of different states, including closed, open and released. In order to complete the analysis of digestive endoscopic surgery videos, it is necessary to identify and discriminate different endoscopic instruments.

[0003] The existing intraoperative identification methods of digestive endoscopy instruments are mainly manual identification, in which the operator manually identifies the type of the instrument and judges the status of the instrument, and completely relies on the operator's ph...

Examples

Embodiment Construction

[0040] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these examples are only used to illustrate the present invention and not to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of the present application.

[0041] like figure 1 As shown, a device detection system for video analysis of digestive endoscopic surgery disclosed in the present invention includes the following modules:

[0042] Endoscope video acquisition module: It adopts an image acquisition card to obtain real-time video streams from the HDMI interface of the intraoperative endoscope host, or reads historically stored surgical video files from the HDMI interface of th...

technical field

[0001] The invention relates to a device detection system applied to video analysis of digestive endoscope surgery and a device detection method realized by the system. Background technique

[0002] In the process of endoscopic surgery, there are nearly ten kinds of commonly used endoscopic instruments, including: biopsy forceps, hook knife, dual knife, IT knife, snare, metal clip, nylon rope, Haibo knife, APC, injection needle, etc. . And these devices often have a variety of different states, including closed, open and released. In order to complete the analysis of digestive endoscopic surgery videos, it is necessary to identify and discriminate different endoscopic instruments.

[0003] The existing intraoperative identification methods of digestive endoscopy instruments are mainly manual identification, in which the operator manually identifies the type of the instrument and judges the status of the instrument, and completely relies on the operator's ph...

Examples

Embodiment Construction

[0040] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these examples are only used to illustrate the present invention and not to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of the present application.

[0041] like figure 1 As shown, a device detection system for video analysis of digestive endoscopic surgery disclosed in the present invention includes the following modules:

[0042] Endoscope video acquisition module: It adopts an image acquisition card to obtain real-time video streams from the HDMI interface of the intraoperative endoscope host, or reads historically stored surgical video files from the HDMI interface of th...

Images