CN113706536B

CN113706536B - Sliding mirror risk early warning method and device and computer readable storage medium

Info

Publication number: CN113706536B
Application number: CN202111263641.2A
Authority: CN
Inventors: 于红刚; 姚理文; 李迅; 张丽辉
Original assignee: Wuhan University WHU
Current assignee: Wuhan Endoangel Medical Technology Co Ltd
Priority date: 2021-10-28
Filing date: 2021-10-28
Publication date: 2022-01-18
Anticipated expiration: 2041-10-28
Also published as: CN113706536A

Abstract

The application provides a slippery mirror risk early warning method, a device and a computer readable storage medium, wherein the method comprises the steps of obtaining a plurality of pieces of first image information of a target bowel section of enteroscopy in a preset time period; determining a category attribute of the target intestine section based on a plurality of first image information of the target intestine section and pre-acquired part activation logic information; acquiring a slippery mirror risk parameter corresponding to a target intestinal segment; and performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameters and the category attribute of the target intestinal segment. The embodiment of the application sets corresponding slide mirror risk parameters aiming at the category attributes of different intestine sections in enteroscopy, carries out real-time slide mirror risk early warning on the current enteroscopy based on the slide mirror risk parameters and the category attributes of target intestine sections, improves the slide mirror risk early warning accuracy rate, and effectively reduces slide mirror risks because the doctor can adjust the speed of withdrawing the endoscope according to the slide mirror risk early warning.

Description

Sliding mirror risk early warning method and device and computer readable storage medium

Technical Field

The application relates to the technical field of medical assistance, in particular to a sliding mirror risk early warning method and device and a computer readable storage medium.

Background

Colonoscopy is the gold standard for examining the lower digestive tract, plays an important role in the diagnosis and treatment of patients with lower digestive tract diseases and colorectal cancer screening of asymptomatic individuals, and high-quality colonoscopy is crucial to reducing colorectal cancer mortality. High-quality colonoscopy needs to include a complete examination process and comprehensive intestinal tract internal observation, and needs a stable and smooth endoscope withdrawing process, which is an operation element for improving the comfort of patients and avoiding medical accidents.

However, in the real clinical enteroscopy operation process, due to the long operation time and the influence of different factors such as the ductility of intestinal tracts of different individuals and the length of intestinal tracts, the difficulty in operation and identification of doctors is high, and the adverse conditions such as the identification error of the intestinal tracts or the omission of observation are easily caused. The slipping of the endoscope is easy to occur at the turning position and the intestinal canal with high freeness. The generation of the slippery mirror not only can reduce the quality of enteroscopy and increase the examination time, but also can unnecessarily increase pain to patients and even cause serious injury.

Therefore, how to effectively reduce the risk of sliding the endoscope is a technical problem which needs to be solved urgently in the technical field of medical assistance at present.

Disclosure of Invention

The application provides a sliding mirror risk early warning method and device and a computer readable storage medium, aiming at solving the problem of how to effectively reduce sliding mirror risk.

In one aspect, the application provides a sliding mirror risk early warning method, which includes:

acquiring a plurality of pieces of first image information of a target intestinal segment of enteroscopy in a preset time period;

determining a category attribute of the target intestine section based on a plurality of first image information of the target intestine section and pre-acquired part activation logic information;

acquiring a slippery mirror risk parameter corresponding to the target intestinal segment;

and performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameter and the category attribute of the target intestinal segment.

In a possible implementation manner of the present application, the performing, based on the paradoxical telescope risk parameter and the category attribute of the target bowel segment, paradoxical telescope risk early warning on the current enteroscope includes:

determining a synoptoscope risk parameter threshold corresponding to the target intestine section based on the category attribute of the target intestine section;

comparing the sliding mirror risk parameter to the sliding mirror risk parameter threshold;

and if the sliding mirror risk parameter is greater than or equal to the sliding mirror risk parameter threshold value, performing sliding mirror risk early warning on the current enteroscope.

In one possible implementation manner of the present application, the determining the category attribute of the target intestine section based on the plurality of first image information of the target intestine section and the pre-acquired region activation logic information includes:

identifying at least one anatomical landmark corresponding to the target intestinal segment from a plurality of first image information of the target intestinal segment;

reading the part activation logic information corresponding to the target intestine section from a preset part activation system to obtain the pre-acquired part activation logic information;

determining a category attribute of the target bowel segment based on the at least one anatomical landmark and the pre-acquired site activation logic information.

In one possible implementation manner of the present application, the identifying, from the plurality of first image information of the target intestine section, at least one anatomical landmark corresponding to the target intestine section includes:

and identifying the plurality of first image information of the target intestine section by adopting a preset anatomical landmark identification model to obtain at least one anatomical landmark corresponding to the target intestine section.

In a possible implementation manner of the present application, the acquiring a slippery mirror risk parameter corresponding to the target bowel segment includes:

acquiring the corresponding endoscope withdrawal time of the target intestinal segment;

acquiring a corresponding endoscope withdrawal speed of the target intestinal segment;

and calculating a slippery mirror risk parameter corresponding to the target intestinal segment based on the endoscope withdrawing time and the endoscope withdrawing speed.

In one possible implementation manner of the present application, the acquiring a withdrawal speed corresponding to the target intestine section includes:

preprocessing each image information in the first image information to obtain a plurality of preprocessed second image information;

acquiring a hash fingerprint corresponding to each piece of image information in the plurality of pieces of second image information;

calculating Hamming distances between different image information in the plurality of second image information;

and determining the corresponding speed of the endoscope withdrawing in the target intestinal section based on the Hash fingerprint corresponding to each image information in the second image information and the Hamming distance between different image information in the second image information.

In one possible implementation manner of the present application, the determining, based on the hash fingerprint corresponding to each of the plurality of second image information and the hamming distance between different image information in the plurality of second image information, a speed of endoscope withdrawal corresponding to the target intestine section includes:

comparing the hash fingerprints of the target image information of the current enteroscopy in the plurality of second image information with the hash fingerprints of the target image information of n frames of enteroscopy before the image information of the current enteroscopy, and respectively obtaining the overlapping rate of the target image information and any image information in the target image information of the n frames of enteroscopy before the image information of the current enteroscopy;

calculating a weighted overlapping rate corresponding to the target image information based on the overlapping rate of the target image information and any image information in the target image information of the previous n frames of enteroscopy;

converting the weighted overlap ratio into a stability factor;

and determining a corresponding speed of endoscope withdrawal at the target intestinal segment based on the stability coefficient.

On the other hand, this application provides a sliding mirror risk early warning device, the device includes:

a first acquisition unit configured to acquire a plurality of pieces of first image information of a target bowel segment for enteroscopy within a preset time period;

a first determination unit configured to determine a category attribute of the target intestine section based on a plurality of first image information of the target intestine section and previously acquired site activation logic information;

the second acquisition unit is used for acquiring a slippery mirror risk parameter corresponding to the target intestinal segment;

and the first early warning unit is used for carrying out slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameter and the category attribute of the target intestinal segment.

In a possible implementation manner of the present application, the first warning unit is specifically configured to:

In a possible implementation manner of the present application, the first determining unit specifically includes:

the first identification unit is used for identifying at least one anatomical mark corresponding to the target intestinal segment from a plurality of pieces of first image information of the target intestinal segment;

the first reading unit is used for reading the part activation logic information corresponding to the target intestinal segment from a preset part activation system so as to obtain the pre-acquired part activation logic information;

a second determination unit for determining a category attribute of the target bowel segment based on the at least one anatomical landmark and the pre-acquired site activation logic information.

In a possible implementation manner of the present application, the first identification unit is specifically configured to:

In a possible implementation manner of the present application, the second obtaining unit specifically includes:

the third acquisition unit is used for acquiring the endoscope withdrawal time corresponding to the target intestinal segment;

the fourth acquisition unit is used for acquiring the corresponding endoscope withdrawing speed of the target intestinal section;

and the first calculating unit is used for calculating a slippery mirror risk parameter corresponding to the target intestinal segment based on the endoscope withdrawing time and the endoscope withdrawing speed.

In a possible implementation manner of the present application, the fourth obtaining unit specifically includes:

the first preprocessing unit is used for preprocessing each image information in the plurality of first image information to obtain a plurality of preprocessed second image information;

a fifth acquiring unit, configured to acquire a hash fingerprint corresponding to each of the plurality of pieces of second image information;

a second calculation unit configured to calculate hamming distances between different image information of the plurality of second image information;

a third determining unit, configured to determine a withdrawal speed corresponding to the target intestinal segment based on the hash fingerprint corresponding to each of the plurality of second image information and a hamming distance between different image information of the plurality of second image information.

In a possible implementation manner of the present application, the third determining unit is specifically configured to:

converting the weighted overlap ratio into a stability factor;

In another aspect, the present application further provides a computer device, including:

one or more processors;

a memory; and

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the sliding mirror risk pre-warning method.

In another aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is loaded by a processor to execute the steps in the sliding mirror risk early warning method.

The method for pre-warning the risk of the paraglider comprises the steps of obtaining a plurality of pieces of first image information of a target intestinal section of enteroscopy in a preset time period; then, based on a plurality of first image information of the target intestinal segment and the pre-acquired part activation logic information, determining the category attribute of the target intestinal segment; acquiring a slippery mirror risk parameter corresponding to the target intestinal segment; and finally, performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameters and the category attribute of the target intestinal segment. Compared with the prior art, the method and the device have the advantages that the corresponding slippery mirror risk parameters are set according to the category attributes of different intestinal sections in the enteroscopy, real-time slippery mirror risk early warning is conducted on the current enteroscopy based on the slippery mirror risk parameters and the category attributes of the target intestinal sections, the slippery mirror risk early warning accuracy is improved, and due to the real-time slippery mirror risk early warning, doctors can adjust the withdrawal rhythm according to the slippery mirror risk early warning, and the slippery mirror risk is effectively reduced.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a scene schematic diagram of a sliding mirror risk early warning system provided in an embodiment of the present application;

fig. 2 is a schematic flowchart of an embodiment of a sliding mirror risk early warning method provided in an embodiment of the present application;

FIG. 3 is a flowchart illustrating an embodiment of step 202 in the present application;

FIG. 4 is a schematic flow chart diagram illustrating an embodiment of step 203 in the present application;

FIG. 5 is a flowchart of an embodiment of step 402 in the present application;

FIG. 6 is a flowchart illustrating an embodiment of step 504 in an embodiment of the present application;

FIG. 7 is a flowchart illustrating an embodiment of step 204 in the present application;

fig. 8 is a schematic structural diagram of an embodiment of a sliding mirror risk early warning device provided in an embodiment of the present application;

FIG. 9 is a schematic structural diagram of an embodiment of a computer device provided in the embodiments of the present application;

fig. 10 is a schematic view of a site activation process provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In the description of the present application, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed in a particular orientation, and be operated, and thus should not be considered as limiting the present application. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes are not set forth in detail in order to avoid obscuring the description of the present application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

The embodiment of the application provides a sliding mirror risk early warning method, a sliding mirror risk early warning device and a computer readable storage medium, which are respectively described in detail below.

As shown in fig. 1, fig. 1 is a scene schematic diagram of a sliding mirror risk early warning system provided in an embodiment of the present application, where the sliding mirror risk early warning system may include a plurality of terminals 100 and a server 200, the terminals 100 and the server 200 are connected through a network, and a sliding mirror risk early warning device is integrated in the server 200, such as the server in fig. 1, and the terminals 100 may access the server 200.

In the embodiment of the present application, the server 200 is mainly configured to obtain a plurality of pieces of first image information of a target bowel segment for enteroscopy in a preset time period; determining a category attribute of the target intestine section based on a plurality of first image information of the target intestine section and pre-acquired part activation logic information; acquiring a slippery mirror risk parameter corresponding to a target intestinal segment; and performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameters and the category attribute of the target intestinal segment.

In this embodiment, the server 200 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server 200 described in this embodiment includes, but is not limited to, a computer, a network terminal, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). In the embodiment of the present application, the server and the terminal may implement communication through any communication manner, including but not limited to mobile communication based on the third Generation Partnership Project (3 GPP), Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP/IP Protocol Suite (TCP/IP), User Datagram Protocol (UDP), and the like.

It is to be understood that the terminal 100 used in the embodiments of the present application may be a device that includes both receiving and transmitting hardware, as well as a device that has both receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a terminal may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The terminal 100 may specifically be a desktop terminal or a mobile terminal, and the terminal 100 may also specifically be one of a mobile phone, a tablet computer, a notebook computer, and the like.

Those skilled in the art will understand that the application environment shown in fig. 1 is only one application scenario of the present application, and does not constitute a limitation to the application scenario of the present application, and other application environments may also include more or fewer terminals than those shown in fig. 1, or a server network connection relationship, for example, only 1 server and 2 terminals are shown in fig. 1. It is understood that the sliding mirror risk early warning system may further include one or more other servers, or/and one or more terminals connected to the server network, and is not limited herein.

In addition, as shown in fig. 1, the sliding scope risk early warning system may further include a memory 300 for storing data, such as image data of enteroscopy and sliding scope risk early warning data, for example, sliding scope risk early warning data during operation of the sliding scope risk early warning system.

It should be noted that the scene schematic diagram of the sliding mirror risk early warning system shown in fig. 1 is only an example, and the sliding mirror risk early warning system and the scene described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not form a limitation on the technical solution provided in the embodiment of the present application.

Next, a sliding mirror risk early warning method provided by the embodiment of the present application is introduced.

In the embodiment of the sliding mirror risk early warning method in the embodiment, a sliding mirror risk early warning device is used as an execution main body, and in order to simplify and facilitate description, the execution main body is omitted in subsequent method embodiments, and the sliding mirror risk early warning device is applied to a computer device, and the method includes: acquiring a plurality of pieces of first image information of a target intestinal segment of enteroscopy in a preset time period; determining a category attribute of the target intestine section based on a plurality of first image information of the target intestine section and pre-acquired part activation logic information; acquiring a slippery mirror risk parameter corresponding to a target intestinal segment; and performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameters and the category attribute of the target intestinal segment.

Referring to fig. 2 to 10, fig. 2 is a schematic flowchart illustrating an embodiment of a sliding mirror risk early warning method provided in an embodiment of the present application, where the sliding mirror risk early warning method includes steps 201 to 204:

201. a plurality of first image information of a target bowel segment for enteroscopy within a preset time period is acquired.

The enteroscopy is a method of inserting the enteroscopy circulation cavity into the ileocecal part through the anus and observing the colon lesion from the side of the mucous membrane. Enteroscopy can meet the needs of examination of all colon areas. In the observation of enteroscopy, the colon sequentially passes through the cecum, ascending colon, transverse colon, descending colon, sigmoid colon and rectum, wherein the lengths of the different intestinal sections and the corresponding anatomical marks of the different intestinal sections have certain differences. Thus, when the enteroscope is at a different bowel segment, a plurality of first image information of the respective target bowel segment will be acquired, wherein the plurality of first image information may be consecutive frame images. It is understood that an anatomical landmark is an anatomical structure or field of view.

In this embodiment, a real-time enteroscopy video can be acquired through an enteroscopy device, and the video is decoded into image information (preset frames per second) to acquire a plurality of first image information of a target enteroscopy segment within a preset time period.

202. Based on the plurality of first image information of the target bowel segment and the pre-acquired site activation logic information, a category attribute of the target bowel segment is determined.

The site activation logic information refers to information that a sequence of anatomical landmarks has been identified by the current enteroscope. Wherein the site activation logic information includes an activation condition. It should be noted that, because a plurality of segments of the intestine are included in the colon, and the same or similar anatomical landmarks exist in the plurality of segments of the intestine, the present application introduces the position activation logic information in order to determine the target segment of the intestine where the current enteroscope is located in real time.

The class attribute of the target segment refers to which segment of the colon the target segment belongs, such as one of the classes cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum.

Specifically, how to determine the category attribute of the target intestine section based on the plurality of first image information of the target intestine section and the pre-acquired region activation logic information is described in detail in the following embodiments, which is not repeated herein, and please refer to the following embodiments.

203. And acquiring a slippery mirror risk parameter corresponding to the target intestinal segment.

In the real clinical enteroscope operation process, because the operation time is long and is influenced by different factors such as the ductility of intestinal tracts of different individuals and the length of intestinal sections, the operation and identification difficulty of doctors is high, and adverse conditions such as intestinal section identification errors or observation omission are easily caused. The slipping of the endoscope is easy to occur at the turning position and the intestinal canal with high freeness. The generation of the slippery mirror can not only reduce the quality of enteroscopy and increase the examination time, but also can unnecessarily increase pain for patients and even cause serious injury, and meanwhile, the probability and risk of the occurrence of the slippery mirror are different due to certain difference of physical structures of different intestinal sections.

The slippery mirror risk parameter corresponding to the target intestinal segment refers to a risk parameter of the enteroscope in which a slippery mirror phenomenon occurs in the target intestinal segment.

Specifically, how to obtain the glide mirror risk parameter corresponding to the target intestine section is described in detail in the following embodiments, which are not repeated herein, please refer to the following embodiments.

204. And performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameters and the category attribute of the target intestinal segment.

And performing sliding mirror risk early warning on the current enteroscopy, namely performing sliding mirror risk early warning in real time.

Specifically, how to perform a slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameter and the category attribute of the target intestinal segment is described in detail in the following embodiments, which are not described herein again, and please refer to the following embodiments.

In the embodiment of the present application, as shown in fig. 3, the step 202 of determining the category attribute of the target intestine section based on the plurality of first image information of the target intestine section and the pre-acquired region activation logic information includes steps 301 to 303:

301. at least one anatomical landmark corresponding to the target intestine segment is identified from the plurality of first image information of the target intestine segment.

Since each target intestine segment may correspond to one or more anatomical landmarks, for example, the cecum corresponds to two anatomical landmarks, i.e., ileocecal valve and appendiceal orifice, in the plurality of first image information of the target intestine segment, at least one anatomical landmark corresponding to the target intestine segment may be identified.

In a specific embodiment, identifying at least one anatomical landmark corresponding to the target intestine segment from the plurality of first image information of the target intestine segment includes: and recognizing the first image information of the target intestine section by adopting a preset anatomical landmark recognition model to obtain at least one anatomical landmark corresponding to the target intestine section.

In the embodiment of the application, before the preset anatomical landmark recognition model is used for recognizing the first image information of the target intestinal segment and obtaining the at least one anatomical landmark corresponding to the target intestinal segment, the preset anatomical landmark recognition model can be trained, and the specific training process is as follows:

firstly, performing target recognition on an anatomical landmark (anatomical structure or visual field) image in colonoscopy by adopting a deep learning convolutional neural network technology, and classifying the anatomical landmark (anatomical structure or visual field) image into n classes of targets for recognition according to the characteristics of color, shape and the like of each anatomical structure or visual field, for example, classifying the targets into 5 classes, wherein the specific classes are shown in the following table 1:

table 1: recognition target class of anatomical landmarks

Secondly, classifying the examination image of the colonoscopy (without distinguishing the intestinal sections) into 5 classes according to the table for labeling, and then training an image recognition model.

302. And reading the part activation logic information corresponding to the target intestinal segment from a preset part activation system to obtain the part activation logic information acquired in advance.

The part activation logic information corresponding to the target intestinal segment refers to the information that the current enteroscope corresponding to the current intestinal segment has recognized a certain sequence of anatomical landmarks. As shown in table 2 below, assuming that the target intestine segment is a colon ascending segment and a colon transverse segment, the corresponding site activation logic information is activation conditions after identifying the cecum and after identifying the colon ascending segment.

Table 2: site activation logic

In the embodiment of the present application, as shown in fig. 10, the procedure determination process is introduced in conjunction with table 1 and table 2:

starting enteroscopy operation, and starting a program; when the ileocecal valve and the appendiceal orifice structure of classification 1 are activated, the ileocecal segment is considered to be located; after cecal structure identification, when the normal colon image of the classification 2 is activated, the colon is considered to be in an ascending colon segment; after the ascending colon segment is identified, when the classified 3 hepatic curve image is activated, the ascending colon segment is considered to be ended; after hepatic flexure identification, when the classification 2 normal colon image is activated, the colon is considered to be a transverse colon segment; after the transverse colon segment is identified, when the classification 3 splenic flexure image is activated, the transverse colon segment is considered to be ended; after splenic flexure identification, when the classification 2 normal colon image is activated, the descending colon segment is considered; after the identification of the descending colon segment, when the special folds of the sigmoid colon of the classification 4 are activated, the descending colon segment is considered to be ended and is located in the sigmoid colon segment; after the sigmoid colon segment is identified, when the special mucous membrane expression of the rectum is activated in the classification 5, the sigmoid colon segment is considered to be finished and is positioned in the rectal segment; the enteroscope exits the body and the procedure ends.

In the embodiment of the application, before the part activation logic information corresponding to the target intestine section is read from the preset part activation system to obtain the pre-acquired part activation logic information, the part activation system can be established. Wherein a random forest algorithm may be used for the part activation logic decision.

It should be noted that the part activation system needs to recognize according to a preset endoscope reversing sequence, specifically, after the recognition of the previous intestine section is finished, the recognition of the next intestine section is started, so that the jumping recognition can be avoided, and the recognition error can be prevented.

In this embodiment, the site activation system may update the site activation logic information in real time and store the updated site activation logic information, and specifically, may store the updated site activation logic information in a preset storage device, so that the preset storage device may be directly accessed from the preset site activation system to read the site activation logic information corresponding to the target intestine section, so as to obtain the previously acquired site activation logic information.

303. Based on the at least one anatomical landmark and the pre-acquired site activation logic information, a category attribute of the target bowel segment is determined.

In this embodiment, the category attribute of the target bowel segment may be determined based on a correspondence between the at least one anatomical landmark and the pre-acquired region activation logic information.

For example, as can be seen from the region activation logic corresponding to table 2, when the region activation logic information is that the activation condition is after identifying the cecum and after identifying the ascending colon, and the identified at least one anatomical landmark is the hepatic flexure, the target intestine segment is identified as the ascending colon and the transverse colon boundary intestine segment. I.e. the type attribute of the target segment is the ascending colon, the transverse colon boundary segment.

In the embodiment of the application, based on the activation logic of the intestinal tract anatomical marker part, the risk assessment restart logic of each intestinal segment can be set, namely, when the activation of each part is started, the gliding endoscope risk early warning unit corresponding to the corresponding intestinal segment is started. Specifically, the restart logic of the risk assessment of each intestinal segment may be that when the anatomical landmark is identified as ileocecal valve and appendiceal orifice, the program is determined to reach the cecum, and the program logic is to start the sliding scope risk assessment system and start the sliding scope risk assessment of the ascending colon segment; when the anatomical landmark is identified as the hepatic flexure, the program recognizes that the boundary between the ascending colon and the transverse colon is reached, and the program logic is to start the risk evaluation of the sliding mirror of the transverse colon section; when the anatomical landmark is identified as splenic flexure, the program recognizes as reaching the junction of the descending colon and the descending colon, and the program logic initiates the glide slope risk assessment of the sections of the descending colon and the sigmoid colon.

Specifically, based on the anatomical landmark identification procedure, a restart logic of the synoptoscope risk of each intestinal segment is established, which specifically comprises the following steps: when the ileocecal valve and the appendiceal junction structure in the classification 1 are activated, the endoscope is considered to be withdrawn, a risk evaluation system is started, and meanwhile, the sliding lens risk evaluation of the ascending colon section is started; after the ascending colon segment is identified, when the classified 3 hepatic curve image is activated, the ascending colon segment is considered to be finished, the transverse colon segment is considered to be started, and the slide endoscope risk assessment of the transverse colon segment is started; after the transverse colon segment is identified, when the classified 3 splenic flexure image is activated, the transverse colon segment is considered to be finished, the descending colon segment is considered to be started, and the colonoscopy risk assessment of the descending colon and sigmoid colon segments is started; after sigmoid segment identification, the sigmoid segment is considered to be over when class 5 rectal-specific mucosal manifestations are activated. And the risk assessment routine ends.

In the embodiment of the present application, as shown in fig. 4, the step 203 of obtaining the glide mirror risk parameter corresponding to the target intestine section includes steps 401 to 403:

401. and acquiring the corresponding endoscope withdrawal time of the target intestinal segment.

The endoscope withdrawing time corresponding to the target intestine section refers to the effective endoscope withdrawing time from the current intestine section starting time to the current time, wherein the current intestine section starting time can be determined as the current intestine section starting time by combining the part activation logic in the step 302.

In some embodiments, a preset withdrawal time monitoring model may be used to obtain a corresponding withdrawal time at the target bowel segment. The preset endoscope withdrawing time monitoring model is a timer based on an image classification model, and the image classification model divides an enteroscope image into a clear normal endoscope withdrawing image and an unqualified image (including images such as blurred images, flushing images, water absorption images, biopsy images and polyp excision images). After the anatomical marker of a certain intestinal segment is activated, if the image is a clear normal endoscope withdrawal image, the endoscope withdrawal time monitoring model starts to calculate the endoscope withdrawal time, and when an unqualified image is detected, the timing is paused.

It should be noted that after the anatomical marker is identified at the beginning of each intestine section, the risk assessment is performed again, that is, timing is performed again, so that the endoscope withdrawal time given by the endoscope withdrawal time monitoring model is the effective endoscope withdrawal time from the beginning of the currently located intestine section to the current time.

402. And acquiring the corresponding speed of endoscope withdrawal of the target intestinal segment.

The endoscope withdrawing speed corresponding to the target intestinal segment refers to the endoscope withdrawing speed of the current enteroscope detection equipment at the target intestinal segment.

Specifically, how to obtain the speed of the endoscope withdrawal corresponding to the target intestine section is described in detail in the following embodiments, which are not described herein again, please refer to the following embodiments.

403. And calculating a slippery mirror risk parameter corresponding to the target intestinal segment based on the endoscope withdrawal time and the endoscope withdrawal speed.

Specifically, the endoscope withdrawing time and the endoscope withdrawing speed can be input into a preset slippery mirror risk parameter model to calculate a slippery mirror risk parameter corresponding to the target intestine section. If the preset sliding mirror risk parameter model is as follows:

(formula 1);

wherein t = the mirror-down time; v = speed of mirror backing.

In the embodiment of the present application, as shown in fig. 5, the step 402 of obtaining the withdrawal speed corresponding to the target intestine section includes steps 501 to 504:

501. and preprocessing each image information in the plurality of first image information to obtain a plurality of preprocessed second image information.

Preprocessing each image information in the plurality of first image information, specifically, reducing the picture to 9 x 8 by adopting a bicubic (cubic convolution) interpolation method, and only keeping the structural information of the picture; the reduced size picture is then converted into a grey scale map.

Wherein, the picture is converted into a gray scale map; in general, the contrast image similarity and the color relation are not very large, so the contrast image is processed into a gray scale image, and the complexity of post-calculation is reduced. A weighted average method is used: for each pixel point of the picture, different weights are given to human eyes due to different sensitivity degrees of the human eyes to red light, green light and blue light, so that the gray value of the point is obtained, and the formula is as follows:

gray =0.30 × R +0.59 × G +0.11 × B (formula 2);

502. and acquiring the hash fingerprint corresponding to each piece of image information in the plurality of pieces of second image information.

Commonly used perceptual hash algorithms include aHash, pHash and dHash, wherein the aHash (average hash) speed is high but is often not very accurate; the accuracy of pHash (perceptual hashing) is higher, but the speed is poorer; dHash (difference value hash) has high accuracy and high speed. Therefore, in the embodiment of the application, the difference value hash algorithm is selected to obtain the hash fingerprint of the picture.

Specifically, a hash fingerprint of the picture may be obtained by using a difference value hash algorithm, so as to generate a 64-bit hash fingerprint.

503. A Hamming distance between different ones of the plurality of second image information is calculated.

Calculating Hamming distances among different image information; in the information theory, Hamming Distance represents the number of different characters at corresponding positions of two character strings with equal length, and the Hamming Distance between the character strings x and y can be represented by d (x, y).

d(x，y)=∑x⊕y；

In another aspect, the hamming distance measures the minimum number of times of replacement required to change the character string x into y by replacing characters. The hamming distance indicates how many steps are required to modify a to B. Such as the strings "abc" and "ab 3", the hamming distance is l, since "c" only needs to be modified to "3".

The hamming distance in dHash is the number of modified bits by which the disparity value is calculated. Specifically, the difference value can be represented by 0 and 1, and can be regarded as a binary value. The Hamming distance for binary 0110 and 1111 is 2. And converting the dHash values of the two pieces of image information into binary difference, and performing exclusive OR. The number of bits of "1" of the xor result is calculated, i.e., the number of bits that are not the same, which is the hamming distance.

504. And determining the corresponding endoscope withdrawal speed of the target intestinal segment based on the Hash fingerprint corresponding to each image information in the second image information and the Hamming distance between different image information in the second image information.

In this embodiment of the application, as shown in fig. 6, step 504, determining a withdrawal speed corresponding to the target bowel segment based on the hash fingerprint corresponding to each of the plurality of pieces of second image information and the hamming distance between different pieces of second image information, includes steps 601 to 604:

601. and comparing the hash fingerprints of the target image information of the current enteroscopy in the second image information with the hash fingerprints of the target pre-image information of n frames before the image information of the current enteroscopy to respectively obtain the overlapping rate of the target image information and any image information in the target pre-image information of n frames before the enteroscopy.

602. Based on the overlapping rate of the target image information and any image information in the target image information of the previous n frames of enteroscopy, the weighted overlapping rate corresponding to the target image information is calculated.

In this embodiment, based on the overlapping ratio of the target image information and any one of the image information before the target of the n previous frames of enteroscopy, the similarity between the target image information and any one of the image information before the target of the n previous frames of enteroscopy is calculated: sim =100 x (64-of (x, y))/64;

and then according to the similarity between the target image information and any image information in the target previous image information of the previous n frames of enteroscopy: sim =100 — (x, y) of 64 °/64, calculating a weighted overlap ratio corresponding to the target image information: sim = ∑ 9i =1i45 × Simt, where Simt refers to a similarity between a current picture (i.e., target image information) corresponding to the t time point and an nth frame (whose value range is 1-9) preceding picture.

603. The weighted overlap ratio is converted into a stability factor.

I.e. the down-weighted overlap ratio Sim is converted into a stability factor ESim =1n Σ ESim.

604. And determining the corresponding speed of the endoscope withdrawing in the target intestinal section based on the stability coefficient.

That is, the average stability factor of the target intestinal segment in the time period from 0 to t is ESim =1n Σ ESim, and the application defines the average stability factor as the average withdrawal speed, that is, the average withdrawal speed is the withdrawal speed corresponding to the target intestinal segment.

In the embodiment of the present application, as shown in fig. 7, step 204, performing a slippery mirror risk early warning on the current enteroscope based on the slippery mirror risk parameter and the category attribute of the target intestinal segment, includes steps 701 to 703:

701. and determining a threshold value of a synoptoscope risk parameter corresponding to the target intestine section based on the category attribute of the target intestine section.

In this embodiment, before determining the slippery mirror risk parameter threshold corresponding to the target bowel segment, the slippery mirror risk parameter threshold corresponding to each bowel segment may be set first.

Specifically, 60 cases of sliding mirror and non-sliding mirror videos can be selected, and statistics of sliding mirror occurrence of each intestinal segment can be carried out

Value, calculating the sliding mirror risk, and the available risk threshold is:

ascending colon segment 1500, transverse colon segment 4700, descending colon, and sigmoid colon segment 4000.

The starting conditions of the risk early warning program of each intestinal segment are as follows:

ascending a colon section:

when in use

When the number is larger than or equal to 1500, prompting that the sliding mirror is in a high-risk time period;

a transverse colon section:

when in use

When not less than 4700, prompting that the sliding mirror is in a high-risk time period;

descending the colon section:

when in use

When the number is larger than or equal to 4000, prompting that the sliding mirror is in a high-risk time period;

wherein t = the mirror-down time; v = speed of mirror backing.

Namely, based on the category attribute of the target bowel segment, the synoptoscope risk parameter threshold corresponding to the target bowel segment is matched from the above-mentioned synoptoscope risk parameter threshold corresponding to each bowel segment.

702. And comparing the sliding mirror risk parameter with a sliding mirror risk parameter threshold value.

703. And if the sliding mirror risk parameter is greater than or equal to the sliding mirror risk parameter threshold value, performing sliding mirror risk early warning on the current enteroscope.

Specifically, assuming that the target bowel segment is a transverse colon segment, the threshold of the glide-scope risk parameter is 4700, and when the current glide-scope risk parameter obtained by calculation in the above embodiment is 4900, it can be known that the glide-scope risk parameter is greater than or equal to the threshold of the glide-scope risk parameter, and then the glide-scope risk early warning is performed on the current enteroscope.

And if the current sliding mirror risk parameter is smaller than the sliding mirror risk parameter threshold value, no sliding mirror risk early warning is carried out on the current enteroscope.

In order to better implement the sliding mirror risk early warning method in the embodiment of the present application, on the basis of the sliding mirror risk early warning method, an embodiment of the present application further provides a sliding mirror risk early warning device, as shown in fig. 8, the sliding mirror risk early warning device 800 includes a first obtaining unit 801, a first determining unit 802, a second obtaining unit 803, and a first early warning unit 804:

a first acquisition unit 801 for acquiring a plurality of first image information of a target bowel segment for enteroscopy within a preset time period.

A first determining unit 802, configured to determine a category attribute of the target intestine segment based on a plurality of first image information of the target intestine segment and the pre-acquired region activation logic information.

The second obtaining unit 803 is configured to obtain a slippery mirror risk parameter corresponding to the target bowel segment.

The first early warning unit 804 is configured to perform a slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameter and the category attribute of the target intestinal segment.

In this embodiment of the application, the first warning unit 804 is specifically configured to:

and determining a threshold value of a synoptoscope risk parameter corresponding to the target intestine section based on the category attribute of the target intestine section.

And comparing the sliding mirror risk parameter with a sliding mirror risk parameter threshold value.

In this embodiment of the application, the first determining unit 802 specifically includes:

the first identification unit is used for identifying at least one anatomical mark corresponding to the target intestinal segment from a plurality of pieces of first image information of the target intestinal segment.

The first reading unit is used for reading the part activation logic information corresponding to the target intestine section from a preset part activation system so as to obtain the part activation logic information acquired in advance.

In an embodiment of the present application, the first identification unit is specifically configured to:

and recognizing the first image information of the target intestine section by adopting a preset anatomical landmark recognition model to obtain at least one anatomical landmark corresponding to the target intestine section.

In this embodiment of the application, the second obtaining unit 803 specifically includes:

and the third acquisition unit is used for acquiring the corresponding endoscope withdrawal time of the target intestinal segment.

And the fourth acquisition unit is used for acquiring the corresponding endoscope withdrawal speed of the target intestinal section.

And the first calculating unit is used for calculating the slippery mirror risk parameter corresponding to the target intestinal segment based on the mirror withdrawal time and the mirror withdrawal speed.

In an embodiment of the present application, the fourth obtaining unit specifically includes:

the first preprocessing unit is used for preprocessing each image information in the plurality of first image information to obtain a plurality of preprocessed second image information.

And the fifth acquisition unit is used for acquiring the hash fingerprint corresponding to each piece of image information in the second image information.

And the second calculating unit is used for calculating the Hamming distance between different image information in the second image information.

And the third determining unit is used for determining the corresponding endoscope withdrawing speed of the target intestinal section based on the Hash fingerprint corresponding to each image information in the second image information and the Hamming distance between different image information in the second image information.

In an embodiment of the present application, the third determining unit is specifically configured to:

and comparing the hash fingerprints of the target image information of the current enteroscopy in the second image information with the hash fingerprints of the target pre-image information of n frames before the image information of the current enteroscopy to respectively obtain the overlapping rate of the target image information and any image information in the target pre-image information of n frames before the enteroscopy.

Based on the overlapping rate of the target image information and any image information in the target image information of the previous n frames of enteroscopy, the weighted overlapping rate corresponding to the target image information is calculated.

The weighted overlap ratio is converted into a stability factor.

And determining the corresponding speed of the endoscope withdrawing in the target intestinal section based on the stability coefficient.

In addition to the above-mentioned method and apparatus for slide mirror risk early warning, an embodiment of the present application further provides a computer device, which integrates any one of the slide mirror risk early warning apparatuses provided in the embodiment of the present application, where the computer device includes:

one or more processors;

a memory; and

one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to perform the operations of any of the methods in any of the foregoing embodiments of the sliding mirror risk pre-warning method.

The embodiment of the application also provides computer equipment, which integrates any sliding mirror risk early warning device provided by the embodiment of the application. Referring to fig. 9, fig. 9 is a schematic structural diagram of an embodiment of a computer device according to an embodiment of the present application.

As shown in fig. 9, it shows a schematic structural diagram of a sliding mirror risk early warning device designed in the embodiment of the present application, specifically:

the sliding mirror risk early warning device may include one or more processors 901 of a processing core, one or more storage units 902 of a computer-readable storage medium, a power supply 903, an input unit 904, and the like. Those skilled in the art will appreciate that the configuration of the sliding mirror risk early warning apparatus shown in fig. 9 does not constitute a limitation of the sliding mirror risk early warning apparatus, and may include more or less components than those shown, or combine some components, or arrange different components. Wherein:

the processor 901 is a control center of the sliding mirror risk early warning device, connects each part of the whole sliding mirror risk early warning device by using various interfaces and lines, and executes various functions and processing data of the sliding mirror risk early warning device by running or executing software programs and/or modules stored in the storage unit 902 and calling data stored in the storage unit 902, thereby performing overall monitoring on the sliding mirror risk early warning device. Optionally, processor 901 may include one or more processing cores; preferably, the processor 901 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 901.

The storage unit 902 may be used to store software programs and modules, and the processor 901 executes various functional applications and data processing by operating the software programs and modules stored in the storage unit 902. The storage unit 902 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required by at least one function, and the like; the storage data area may store data created from use of the sliding mirror risk early warning device, and the like. Further, the storage unit 902 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the storage unit 902 may further include a memory controller to provide the processor 901 with access to the storage unit 902.

The sliding mirror risk early warning device further comprises a power supply 903 for supplying power to each component, preferably, the power supply 903 can be logically connected with the processor 901 through a power management system, and therefore functions of charging, discharging, power consumption management and the like can be managed through the power management system. The power supply 903 may also include any component including one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

The sliding mirror risk warning apparatus may further include an input unit 904, and the input unit 904 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the sliding mirror risk early warning device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment of the present application, the processor 901 in the sliding mirror risk early warning apparatus loads an executable file corresponding to a process of one or more application programs into the storage unit 902 according to the following instructions, and the processor 901 runs the application programs stored in the storage unit 902, so as to implement various functions as follows:

acquiring a plurality of pieces of first image information of a target intestinal segment of enteroscopy in a preset time period; determining a category attribute of the target intestine section based on a plurality of first image information of the target intestine section and pre-acquired part activation logic information; acquiring a slippery mirror risk parameter corresponding to a target intestinal segment; and performing slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameters and the category attribute of the target intestinal segment.

To this end, an embodiment of the present application provides a computer-readable storage medium, which may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like. The computer readable storage medium stores a plurality of instructions, and the instructions can be loaded by a processor to perform the steps of any one of the sliding mirror risk early warning methods provided by the embodiments of the present application. For example, the instructions may perform the steps of:

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The method, the device and the computer-readable storage medium for early warning of the risk of the sliding mirror provided by the embodiment of the application are introduced in detail, a specific example is applied in the description to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A sliding mirror risk early warning method is characterized by comprising the following steps:

performing a slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameter and the category attribute of the target intestinal segment;

wherein the region activation logic information refers to information that a sequence of anatomical landmarks has been identified by a current enteroscope;

the determining a category attribute of the target intestine section based on the plurality of first image information of the target intestine section and the pre-acquired part activation logic information comprises:

determining a category attribute of the target bowel segment based on the at least one anatomical landmark and the pre-acquired site activation logic information;

the acquiring of the slippery mirror risk parameter corresponding to the target intestine section comprises:

2. The slippery mirror risk early warning method according to claim 1, wherein the performing slippery mirror risk early warning on the current enteroscope based on the slippery mirror risk parameter and the class attribute of the target intestinal segment comprises:

3. The slippery mirror risk pre-warning method according to claim 1, wherein the identifying at least one anatomical landmark corresponding to the target bowel segment from the plurality of first image information of the target bowel segment comprises:

4. The slippery mirror risk early warning method according to claim 1, wherein the acquiring of the withdrawal speed corresponding to the target bowel segment comprises:

5. The slippery mirror risk early warning method according to claim 4, wherein the determining a speed of endoscope withdrawal corresponding to the target bowel segment based on the corresponding hashed fingerprint of each of the plurality of second image information and the hamming distance between different ones of the plurality of second image information comprises:

converting the weighted overlap ratio into a stability factor;

6. A sliding mirror risk early warning device, characterized in that the device comprises:

the first early warning unit is used for carrying out slippery mirror risk early warning on the current enteroscopy based on the slippery mirror risk parameter and the category attribute of the target intestinal segment;

the first determining unit specifically includes:

the first reading unit is used for reading the part activation logic information corresponding to the target intestine section from a preset part activation system so as to obtain the part activation logic information acquired in advance;

a second determination unit, configured to determine a category attribute of the target bowel segment based on the at least one anatomical landmark and the pre-acquired region activation logic information;

the second obtaining unit specifically includes:

the third acquisition unit is used for acquiring the corresponding endoscope withdrawal time of the target intestinal segment;

the fourth acquisition unit is used for acquiring the corresponding endoscope withdrawal speed of the target intestinal section;

7. A computer device, characterized in that the computer device comprises:

one or more processors;

a memory; and

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the sliding mirror risk pre-warning method of any of claims 1 to 5.

8. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps of the sliding mirror risk pre-warning method according to any one of claims 1 to 5.