Movatterモバイル変換


[0]ホーム

URL:


CN116269168B - Method, controller and system for detecting relative positions of capsule endoscope and pylorus - Google Patents

Method, controller and system for detecting relative positions of capsule endoscope and pylorus
Download PDF

Info

Publication number
CN116269168B
CN116269168BCN202310560313.1ACN202310560313ACN116269168BCN 116269168 BCN116269168 BCN 116269168BCN 202310560313 ACN202310560313 ACN 202310560313ACN 116269168 BCN116269168 BCN 116269168B
Authority
CN
China
Prior art keywords
pylorus
capsule endoscope
time
real
gastric cavity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310560313.1A
Other languages
Chinese (zh)
Other versions
CN116269168A (en
Inventor
吴婉雯
王羽嗣
刘绍毅
招展鹏
周可
刘思德
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Side Medical Technology Co ltd
Original Assignee
Guangzhou Side Medical Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Side Medical Technology Co ltdfiledCriticalGuangzhou Side Medical Technology Co ltd
Priority to CN202310560313.1ApriorityCriticalpatent/CN116269168B/en
Publication of CN116269168ApublicationCriticalpatent/CN116269168A/en
Application grantedgrantedCritical
Publication of CN116269168BpublicationCriticalpatent/CN116269168B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

The application relates to the technical field of computers, in particular to a method, a controller and a system for detecting the relative positions of a capsule endoscope and a pylorus, wherein the method for detecting the relative positions of the capsule endoscope and the pylorus comprises the following steps: the method comprises the steps of obtaining pylorus information, the real-time position of a capsule endoscope in a gastric cavity and obtaining a real-time pressure value detected by the capsule endoscope in the gastric cavity; determining a real-time relative relationship between the capsule endoscope and the pylorus based on pylorus information, a real-time position of the capsule endoscope in the gastric cavity, and a real-time pressure value detected by the capsule endoscope in the gastric cavity; the pylorus information includes the presence or absence of an image of the pylorus and the open or closed state of the pylorus. The accurate relative relation of the capsule endoscope at the position of the gastric cavity and the pylorus is determined, which is equivalent to the determination of the position of the capsule endoscope by taking the pylorus as a reference standard, so that the moving position of the capsule endoscope can be tracked and positioned in real time, and the pose of a subject or the travelling path of the capsule endoscope can be controlled according to the real-time relative relation between the capsule endoscope and the pylorus.

Description

Method, controller and system for detecting relative positions of capsule endoscope and pylorus
Technical Field
The application relates to the technical field of computers, in particular to a method, a controller, a system, electronic equipment and a non-transitory computer readable storage medium for detecting the relative position of a capsule endoscope and a pylorus.
Background
The related capsule endoscopes applied to stomach examination mainly comprise a magnetic control capsule endoscope and a body position transformation guide capsule endoscopy. During the examination, the capsule endoscope corresponds to food entering the gastric cavity, which enters the digestive phase, and gastric peristalsis occurs. Peristalsis of the stomach occurs 2/3 below the stomach and in the antrum, begins in the middle of the stomach, and advances in the direction of the pylorus. At the beginning, the peristaltic amplitude is weaker, and in the process of propagation, the peristaltic amplitude is gradually strengthened, and meanwhile, the frequency is obviously accelerated. The rate of increase in the amplitude and frequency of peristaltic waves is highest in a region of the antrum near the pylorus, increasing the pressure differential across the gastroduodenal, facilitating drainage of solids or semi-solids from the gastric cavity into the duodenum.
At present, the capsule endoscope enters the gastric cavity, and the peristaltic amplitude and frequency of the stomach are enhanced, especially in the gastric antrum region. In the inspection process, the capsule endoscope is easily affected by the peristalsis of the stomach and enters the duodenum, and the inspection of the capsule endoscope in the stomach is passively ended, so that the inspection completion degree is affected, and the medical expense is wasted.
Disclosure of Invention
The application provides a method, a controller, a system, electronic equipment and a non-transitory computer readable storage medium for detecting the relative position of a capsule endoscope and a pylorus, which are used for solving the defect that the real-time position of the capsule endoscope in a gastric cavity is uncontrollable in the prior art, realizing the effect of tracking and positioning the moving position of the capsule endoscope in real time and controlling the pose of a detected person or the travelling path of the capsule endoscope according to the relative position relation of the capsule endoscope and the pylorus.
The application provides a method for detecting the relative position of a capsule endoscope and a pylorus, which comprises the following steps:
the method comprises the steps of obtaining pylorus information, the real-time position of a capsule endoscope in a gastric cavity and obtaining a real-time pressure value detected by the capsule endoscope in the gastric cavity;
determining a real-time relative relationship between the capsule endoscope and the pylorus based on the pylorus information, a real-time position of the capsule endoscope in the gastric cavity, and a real-time pressure value detected by the capsule endoscope in the gastric cavity;
the pylorus information includes the presence or absence of an image of the pylorus and the open or closed state of the pylorus.
According to the method for detecting the relative position of the capsule endoscope and the pylorus, provided by the application, the real-time relative relation between the capsule endoscope and the pylorus comprises the following steps:
the actual time for the capsule endoscope to reach the pylorus;
and/or the number of the groups of groups,
the actual distance between the capsule endoscope and the pylorus.
According to the method for detecting the relative position of the capsule endoscope and the pylorus provided by the application, the real-time relative relation between the capsule endoscope and the pylorus is determined based on the pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, and the method comprises the following steps:
determining that an image of the pylorus is present and the pylorus is in an open-close rhythm;
based on the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, a first predicted time for the capsule endoscope to reach the pylorus is obtained.
According to the method for detecting the relative position of the capsule endoscope and the pylorus provided by the application, after the first prediction time for the capsule endoscope to reach the pylorus is obtained, the method comprises the following steps:
establishing a pylorus opening and closing rule model;
based on the pylorus opening and closing rule model, determining that the first predicted time of the capsule endoscope reaching the pylorus is close to the opening time of the pylorus, outputting an early warning signal, or determining that the first predicted time of the capsule endoscope reaching the pylorus is close to the closing time of the pylorus, and outputting a safety signal.
According to the method for detecting the relative position of the capsule endoscope and the pylorus provided by the application, the real-time relative relation between the capsule endoscope and the pylorus is determined based on the pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, and the method comprises the following steps:
determining that an image of the pylorus is absent;
and obtaining a second predicted time for the capsule endoscope to reach the pylorus based on the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity.
According to the method for detecting the relative position of the capsule endoscope and the pylorus provided by the application, after the second predicted time for the capsule endoscope to reach the pylorus is obtained, the method further comprises the following steps:
determining that the second predicted time for the capsule endoscope to reach the pylorus is greater than or equal to the preset time, and outputting a safety signal;
or determining that the second predicted time for the capsule endoscope to reach the pylorus is smaller than the preset time, and outputting an early warning signal.
According to the method for detecting the relative position of the capsule endoscope and the pylorus provided by the application, the real-time relative relation between the capsule endoscope and the pylorus is determined based on the pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, and the method comprises the following steps:
and determining that the image of the pylorus exists and the pylorus is in a normally open state, and outputting an early warning signal.
According to the method for detecting the relative position of the capsule endoscope and the pylorus, which is provided by the application, the method for acquiring pylorus information and the real-time position of the capsule endoscope in the gastric cavity comprises the following steps:
acquiring all images shot by the capsule endoscope in the gastric cavity within a set period of time;
and processing all images shot by the capsule endoscope in the gastric cavity within a set period of time based on a convolutional neural network model to obtain the pylorus information and the real-time position of the capsule endoscope in the gastric cavity.
The application also provides a controller for executing the method for detecting the relative positions of the capsule endoscope and the pylorus, which comprises the following steps:
the acquisition module is used for acquiring pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity;
the processing module is used for determining the real-time relative relation between the capsule endoscope and the pylorus based on the pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity;
the pylorus information includes the presence or absence of an image of the pylorus and the open or closed state of the pylorus.
The present application also provides a capsule endoscope system comprising:
a controller as described above;
the capsule endoscope comprises a capsule body, a pressure sensor and a shooting device, wherein the pressure sensor and the shooting device are arranged on the capsule body, and the pressure sensor and the shooting device are connected with the controller.
The application also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the method for detecting the relative position of the capsule endoscope and the pylorus when executing the computer program.
The present application also provides a non-transitory computer readable storage medium comprising a computer program which, when executed by a processor, implements the method for detecting the relative position of a capsule endoscope and a pylorus as described above.
According to the method for detecting the relative position of the capsule endoscope and the pylorus, provided by the application, after the capsule endoscope enters the gastric cavity, the real-time relative relation between the capsule endoscope and the pylorus is obtained based on the acquired pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, so that the accurate relative relation between the capsule endoscope and the position of the pylorus is determined, which is equivalent to that of determining the position of the capsule endoscope by taking the pylorus as a reference standard, the moving position of the capsule endoscope can be tracked and positioned in real time conveniently, and the pose of a detected person or the travelling path of the capsule endoscope can be controlled according to the real-time position of the capsule endoscope. The possibility that the capsule endoscope enters the duodenum at the current detection moment can be judged through the real-time relative relation between the capsule endoscope and the pylorus, so that corresponding measures can be timely taken, and the occurrence of the event that the capsule endoscope enters the duodenum is avoided.
In addition to the technical problems, features of the constituent technical solutions and advantages brought by the technical features of the technical solutions described above, other technical features of the present application and advantages brought by the technical features of the technical solutions will be further described with reference to the accompanying drawings or will be understood through practice of the present application.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for detecting the relative position of a capsule endoscope and a pylorus.
Detailed Description
Embodiments of the present application are described in further detail below with reference to the accompanying drawings and examples. The following examples are illustrative of the application but are not intended to limit the scope of the application.
In the description of the embodiments of the present application, it should be noted that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the embodiments of the present application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In describing embodiments of the present application, it should be noted that, unless explicitly stated and limited otherwise, the terms "coupled," "coupled," and "connected" should be construed broadly, and may be either a fixed connection, a removable connection, or an integral connection, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium. The specific meaning of the above terms in embodiments of the present application will be understood in detail by those of ordinary skill in the art.
In embodiments of the application, unless expressly specified and limited otherwise, a first feature "up" or "down" on a second feature may be that the first and second features are in direct contact, or that the first and second features are in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.
Furthermore, in the description of the embodiments of the present application, unless otherwise indicated, the meaning of "a plurality of", "a plurality of" means two or more, and the meaning of "a plurality of", "a plurality of" means one or more ".
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the embodiments of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
As shown in fig. 1, the method for detecting the relative position of the capsule endoscope and the pylorus provided by the embodiment of the application comprises the following steps:
the method comprises the steps of obtaining pylorus information, the real-time position of a capsule endoscope in a gastric cavity and obtaining a real-time pressure value detected by the capsule endoscope in the gastric cavity;
determining a real-time relative relationship between the capsule endoscope and the pylorus based on pylorus information, a real-time position of the capsule endoscope in the gastric cavity, and a real-time pressure value detected by the capsule endoscope in the gastric cavity;
the pylorus information includes the presence or absence of an image of the pylorus and the open or closed state of the pylorus.
According to the method for detecting the relative position of the capsule endoscope and the pylorus, after the capsule endoscope enters the gastric cavity, the real-time relative relation between the capsule endoscope and the pylorus is obtained based on the acquired pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, so that the accurate relative relation between the capsule endoscope and the position of the pylorus is determined, which is equivalent to the determination of the position of the capsule endoscope by taking the pylorus as a reference standard, the moving position of the capsule endoscope can be tracked and positioned in real time conveniently, and the pose of a subject or the travelling path of the capsule endoscope can be controlled according to the real-time position of the capsule endoscope. The possibility that the capsule endoscope enters the duodenum at the current detection moment can be judged through the real-time relative relation between the capsule endoscope and the pylorus, so that corresponding measures can be timely taken, and the occurrence of the event that the capsule endoscope enters the duodenum is avoided.
In this embodiment, the pylorus information mainly includes two aspects, namely, information that the image of the pylorus is not known yet, and information that the image of the pylorus is known at the same time.
According to one embodiment of the present application, the real-time relative relationship between the capsule endoscope and the pylorus includes the actual time the capsule endoscope reaches the pylorus; and/or the actual distance between the capsule endoscope and the pylorus. In this embodiment, the real-time relative relationship between the capsule endoscope and the pylorus is the actual time required for the capsule endoscope to move to the pylorus at the current moving state of the current moment, or the real-time position of the capsule endoscope to move to the expected time point of the pylorus at the current moment, and in other embodiments, the real-time relative relationship between the capsule endoscope and the pylorus may also be the actual distance between the real-time position of the capsule endoscope and the pylorus at the current moment, or may also be the actual distance between the real-time position of the capsule endoscope and the pylorus at the current moment, and the actual time or the expected time point required for reaching the pylorus.
It can be understood that the distance between the capsule endoscope and the pylorus and the time for reaching the pylorus can be used as relative relations, so that the position of the capsule endoscope can be judged, meanwhile, the two conditions can be mutually converted, namely, the distance can be calculated and obtained by knowing the time, and the time can be calculated and obtained by knowing the distance. In other embodiments, the relative actual relationship between the capsule endoscope and the pylorus can be in other relationship forms, and the relative actual relationship is selected according to actual requirements.
According to an embodiment of the present application, determining a real-time relative relationship between the capsule endoscope and the pylorus based on pylorus information, a real-time position of the capsule endoscope within the gastric cavity, and a real-time pressure value detected by the capsule endoscope within the gastric cavity, includes:
determining that an image of the pylorus exists and that the pylorus is in an open-close rhythm;
based on the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, a first predicted time for the capsule endoscope to reach the pylorus is obtained.
In this embodiment, after the pylorus information is obtained, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity are input, whether an image of the pylorus in the pylorus information exists or not is first determined, if yes, whether the pylorus is in an open-close rhythm is determined, and if yes, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity are calculated, so that a first prediction time for the capsule endoscope to reach the pylorus is obtained.
Normally, the pylorus is opened and closed regularly, and is in a periodic opening and closing state, which is called pylorus opening and closing rhythm. Typically, a normal person's pylorus will open for about 1-2 seconds and then close for several seconds, opening and closing regularly.
The actual position of the capsule endoscope in the gastric cavity can be known through the first prediction time of the capsule endoscope reaching the pylorus, and the possibility of entering the duodenum can be judged. When the pylorus is known to be in an open-close rhythm, namely the pylorus keeps normal retraction and expansion activities, the first prediction time for the capsule endoscope to reach the pylorus is a prediction time point, and the prediction time point can reflect the possibility that the capsule endoscope passes through the pylorus and falls into the duodenum under the normal pylorus state.
In one embodiment, the method for calculating the first prediction time may be to first substitute the real-time pressure value P into v=sqrt (2*P/ρ), where ρ is the density of the preset capsule endoscope, calculate the real-time velocity v of the capsule endoscope, and then substitute p=ma, where m is the mass of the preset capsule endoscope, calculate the real-time acceleration a of the capsule endoscope, and then measure the distance between the capsule endoscope and the pylorus at the current moment S according to all images captured by the capsule endoscope and the real-time images captured by the capsule endoscope. And finally substituting the obtained distance S, the obtained speed v and the obtained acceleration a into S=vt+1/2at≡2, and calculating the first predicted time for the capsule endoscope to reach the pylorus.
According to an embodiment of the present application, after obtaining a first predicted time for the capsule endoscope to reach the pylorus, the method includes:
establishing a pylorus opening and closing rule model;
based on the pylorus opening and closing rule model, determining the opening time of the first predicted time of the capsule endoscope reaching the pylorus to be close to the pylorus, outputting an early warning signal, or determining the closing time of the first predicted time of the capsule endoscope reaching the pylorus to be close to the pylorus, and outputting a safety signal.
In this embodiment, a pylorus opening and closing rule model is established, and based on the pylorus opening and closing rule model, that is, by acquiring an image with a pylorus captured by a capsule endoscope and combining the time of the image, the pylorus opening and closing model is established, that is, the opening and closing state of the pylorus in a period is deduced through the opening and closing states of the pylorus at each time point, so as to predict the opening period and the closing period of the pylorus. According to the real-time position of the capsule endoscope in the gastric cavity and the detected real-time pressure value, calculating the predicted time point of the capsule endoscope reaching the pylorus as first predicted time, comparing the first predicted time with the time period of the pylorus opening and closing model, judging the relation between the first predicted time and the pylorus opening and closing time point, if the first time point is close to the pylorus opening time point, proving that the possibility of the capsule endoscope entering the duodenum is high, and directly outputting an early warning signal; if the first time point is close to the closing time point of the pylorus, the probability that the capsule endoscope enters the duodenum is proved to be small, and a safety signal is directly output.
According to an embodiment of the present application, determining a real-time relative relationship between the capsule endoscope and the pylorus based on pylorus information, a real-time position of the capsule endoscope within the gastric cavity, and a real-time pressure value detected by the capsule endoscope within the gastric cavity, includes:
determining that an image of the pylorus is absent;
based on the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity, a second predicted time for the capsule endoscope to reach the pylorus is obtained.
In this embodiment, after the pylorus information is obtained, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity are input, whether the pylorus image exists in the pylorus information is firstly judged, if the pylorus image is not detected by the capsule endoscope before the pylorus image is proved to exist, so that the information of the pylorus image existence cannot be obtained, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity are directly calculated, and the second prediction time for the capsule endoscope to reach the pylorus is obtained. The second prediction time is the actual time required by the capsule endoscope to reach the pylorus, the actual position of the capsule endoscope in the gastric cavity can be known through the actual time required by the capsule endoscope to reach the pylorus, and the possibility of entering the duodenum can be judged.
In one embodiment, the second prediction time calculating method is to firstly substitute the real-time pressure value P into v=sqrt (2*P/ρ), wherein ρ is the density of the preset capsule endoscope, calculate the real-time speed v of the capsule endoscope, then substitute p=ma, wherein m is the mass of the preset capsule endoscope, calculate the real-time acceleration a of the capsule endoscope, and then measure the distance between the capsule endoscope and the pylorus at the current moment as S according to all images shot by the capsule endoscope and the real-time images shot by the capsule endoscope. And finally, substituting the obtained distance S, the obtained speed v and the obtained acceleration a into S=vt+1/2at≡2, and calculating the second predicted time for the capsule endoscope to reach the pylorus.
According to an embodiment of the present application, after obtaining the second predicted time for the capsule endoscope to reach the pylorus, the method further includes:
determining that the second predicted time for the capsule endoscope to reach the pylorus is greater than or equal to the preset time, and outputting a safety signal;
or determining that the second predicted time for the capsule endoscope to reach the pylorus is smaller than the preset time, and outputting an early warning signal.
In this embodiment, after determining that the pylorus information is the pylorus is absent, calculating to obtain the actual time required by the capsule endoscope to reach the pylorus, namely, the second prediction time, by the real-time position of the capsule endoscope in the gastric cavity and the detected real-time pressure value, judging the size relationship between the second prediction time and the preset time, if the second prediction time is greater than or equal to the preset time, proving that the distance between the capsule endoscope and the pylorus is larger, and the probability that the actual position of the capsule endoscope at the current moment and the pose of the capsule endoscope at the current moment are kept or moved is not fallen into the duodenum or fall into the duodenum is smaller, so that a safety signal is output; if the second prediction time is smaller than the preset time, the distance between the capsule endoscope and the pylorus is proved to be smaller, the actual position of the capsule endoscope at the current moment and the possibility that the capsule endoscope is kept or moved in the pose of the current moment can fall into the duodenum or fall into the duodenum are higher, and therefore an early warning signal is output.
It is understood that the preset time is a time period required for moving into the duodenum in the case of moving at a set speed, and the preset time can be adjusted according to an actual moving speed of the capsule endoscope. When the real-time relative relation between the capsule endoscope and the pylorus is the actual distance between the capsule endoscope and the pylorus, the preset time can be the preset distance, and a safety signal is output when the actual distance between the capsule endoscope and the pylorus is determined to be equal to or less than the preset distance; or determining that the actual distance between the capsule endoscope and the pylorus is smaller than the preset distance, and outputting an early warning signal.
According to an embodiment of the present application, determining a real-time relative relationship between the capsule endoscope and the pylorus based on pylorus information, a real-time position of the capsule endoscope within the gastric cavity, and a real-time pressure value detected by the capsule endoscope within the gastric cavity, includes:
and determining that the image of the pylorus exists and the pylorus is in a normally open state, and outputting an early warning signal.
In this embodiment, after the pylorus information is obtained, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity are input, whether an image of the pylorus in the pylorus information exists or not is first determined, if yes, the opening and closing state of the pylorus is determined, and if the pylorus is in a normally open state, an early warning signal is directly output.
After the pylorus is determined to be in a normally open state, the possibility of entering the duodenum is directly judged. When the pylorus is known to be in a normally open state, namely the pylorus cannot keep normal retraction and expansion activities, the pylorus is always kept under the condition of expansion, and the capsule endoscope can possibly fall into the duodenum at any time, so that the third actual time for the capsule endoscope to reach the pylorus is set time, the set time is a specific output parameter, and when the parameter is obtained and the condition that the capsule endoscope can pass through the pylorus and fall into the duodenum is proved, an early warning signal is directly output.
According to one embodiment of the present application, the method for acquiring pylorus information and real-time position of a capsule endoscope in a gastric cavity comprises:
acquiring all images shot by the capsule endoscope in the gastric cavity within a set period of time;
and processing all images shot by the capsule endoscope in the gastric cavity within a set period of time based on a convolutional neural network model to obtain the pylorus information and the real-time position of the capsule endoscope in the gastric cavity.
In this embodiment, firstly, image acquisition is performed through a capsule endoscope, images shot by the capsule endoscope in a gastric cavity are acquired, all the images in a set time period are input into a convolutional neural network model, and pylorus information and the real-time position of the capsule endoscope in the gastric cavity are acquired. After the convolutional neural network model is established, the method leads to the convolutional neural network model to input an image, and the information in the image is identified to finally obtain the needed pylorus information and the real-time position of the capsule endoscope in the gastric cavity, so that the method has convenience and rapidness.
It is understood that the set period of time is a period of time that continues for a certain length of time from the real-time instant to be confirmed.
In this embodiment, the method for building the convolutional neural network model includes:
and (3) performing image screening on images shot by the capsule endoscope in the gastric cavity, and eliminating images with poorly identified gastric anatomical positions.
And then, marking the images to obtain marked images, and marking the anatomical positions of the stomach in the images shot by the capsule endoscope according to the characteristics of the gastric mucosa, such as color, shape, texture and the like, wherein the anatomical positions comprise the cardia, the fundus, the upper part of the stomach body, the lower part of the stomach body, the lesser curvature of the stomach body, the greater curvature of the stomach body, the antrum, the pylorus opening and the pylorus closing.
And then preprocessing the images to obtain preprocessed images, cutting off black frames at the edges of the images shot by the original capsule endoscope in the gastric cavity, freely rotating the cut-out images between 0 and 359 degrees, randomly amplifying or shrinking the images by 0.9-1.5 times, and adjusting each image to be 243 multiplied by 243 pixels.
And then carrying out image enhancement on the preprocessed images to obtain enhanced images, and separating B channels, log transformation and Laplace sharpening enhancement preprocessing on each image so as to highlight color, shape and texture information of each preprocessed image, wherein three enhanced images with different effects are obtained after each preprocessed image is subjected to enhancement processing, namely all images shot by the capsule endoscope in the gastric cavity are generated into B channel groups, log transformation groups and Laplace sharpening groups.
Randomly dividing the labeling images into a training set and a testing set, inputting the labeling images of the training set after the enhancement processing into a convolutional neural network, comparing the obtained training result with the testing set, evaluating the processing accuracy of the convolutional neural network on the enhancement images, and training the convolutional neural network to obtain a convolutional neural network model.
The method comprises the steps of establishing a convolutional neural network model, namely randomly dividing an enhanced marked image into a training set and a testing set, respectively transmitting a B channel group, a Log transformation group and a Laplacian sharpening group of the testing set to three identical convolutional neural networks, respectively extracting features from each group of images by the three convolutional neural networks, and then carrying out feature fusion by adopting a fusion network to obtain a total convolutional neural network model. And (3) utilizing three groups of images of the test set to evaluate the accuracy of the total convolutional neural network in the identification of the preprocessing pictures respectively for the B channel, the Log transformation and the Laplace sharpening enhancement.
It can be understood that the judgment of whether the pylorus image exists in pylorus information is based on whether the pylorus exists in the image shot by the capsule endoscope in the gastric cavity, the judgment of the opening and closing state of the pylorus is based on the comprehensive judgment processing of the pylorus state of all the images shot by the capsule endoscope in the gastric cavity in a period of time from the current moment forward. If the pylorus is not present in the image shot by the capsule endoscope in the gastric cavity, the pylorus information is determined to be absent, if the pylorus is not open at different time points in the gastric cavity, the pylorus information is determined to be present and the pylorus is in a normally open state, and if the pylorus is determined to be present and the pylorus is in an open-close rhythm.
According to the application, the pylorus condition of a patient is analyzed through the convolutional neural network model image, the position of the capsule endoscope is identified in real time, the possibility that the capsule endoscope enters the duodenum is obtained by combining the pressure value detected by the capsule endoscope, and if the possibility that the capsule endoscope enters the duodenum is high, an early warning signal is output. Medical staff or a detected person can take corresponding measures in time according to the early warning signals, such as adjusting the body position, so as to avoid occurrence of an event that the capsule endoscope enters the duodenum to cause the forced ending of the detection.
The embodiment of the application also provides a controller for executing the method for detecting the relative position of the capsule endoscope and the pylorus, which comprises the following steps:
the acquisition module is used for acquiring pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity;
the processing module is used for determining the real-time relative relation between the capsule endoscope and the pylorus based on pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity;
the pylorus information includes the presence or absence of an image of the pylorus and the open or closed state of the pylorus.
According to the controller provided by the embodiment of the application, the pylorus information, the real-time position of the capsule endoscope in the gastric cavity and the real-time pressure value detected by the capsule endoscope in the gastric cavity are acquired through the acquisition module, and the processing module processes based on the content acquired by the acquisition module to determine the real-time relative relation between the capsule endoscope and the pylorus.
The capsule endoscope system comprises the controller and the capsule endoscope in the embodiment, wherein the capsule endoscope comprises a capsule body, and a pressure sensor and a shooting device which are arranged on the capsule body, and the pressure sensor and the shooting device are connected with the controller.
In the capsule endoscope system provided by the embodiment of the application, an annular pressure sensor is arranged on the shell of the capsule endoscope. When the capsule endoscope runs in the gastric cavity, the pressure sensor can sense the pressure sensed by the periphery of the capsule endoscope, detects a real-time pressure value, and transmits the real-time pressure value to the input end of the controller through a radio frequency signal to be acquired by the acquisition module. A camera is arranged in the shell of the capsule endoscope. When the capsule endoscope runs in the gastric cavity, the camera can shoot images of the capsule endoscope corresponding to a specific angle, and the camera shoots the images and transmits the images to the input end of the controller through radio frequency signals to be acquired by the acquisition module.
When the capsule endoscope passively enters the duodenum under the influence of the peristalsis of the stomach in the examination process, for the magnetic control capsule endoscope examination, on one hand, the controller can be used for controlling external magnetic control, the capsule endoscope is guided back to the gastric cavity through the magnetic field for continuous examination, and on the other hand, the controller can be used for enabling the magnetic control capsule endoscope to avoid entering the duodenum, and the capsule endoscope always works in the gastric cavity; for the capsule endoscopy guided by the body position change, the subject can guide the capsule endoscope to change the position in the gastric cavity by changing the posture under the gravity action of the capsule endoscope, so that the capsule endoscope is prevented from entering the duodenum and is always operated in the gastric cavity.
The embodiment of the application also provides electronic equipment, which comprises: a processor (processor), a communication interface (Communications Interface), a memory (memory) and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The processor may invoke logic instructions in the memory to perform the capsule endoscope and pylorus relative position detection method of the above-described embodiments.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In yet another aspect, embodiments of the present application further provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the above-provided method of detecting a relative position of a capsule endoscope and a pylorus.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (9)

CN202310560313.1A2023-05-182023-05-18Method, controller and system for detecting relative positions of capsule endoscope and pylorusActiveCN116269168B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202310560313.1ACN116269168B (en)2023-05-182023-05-18Method, controller and system for detecting relative positions of capsule endoscope and pylorus

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202310560313.1ACN116269168B (en)2023-05-182023-05-18Method, controller and system for detecting relative positions of capsule endoscope and pylorus

Publications (2)

Publication NumberPublication Date
CN116269168A CN116269168A (en)2023-06-23
CN116269168Btrue CN116269168B (en)2023-09-08

Family

ID=86796387

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202310560313.1AActiveCN116269168B (en)2023-05-182023-05-18Method, controller and system for detecting relative positions of capsule endoscope and pylorus

Country Status (1)

CountryLink
CN (1)CN116269168B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110367913A (en)*2019-07-292019-10-25杭州电子科技大学Wireless capsule endoscope image pylorus and ileocaecal sphineter localization method
CN110811497A (en)*2019-12-062020-02-21深圳市资福医疗技术有限公司Control method of capsule endoscope and capsule endoscope using control method
CN111986196A (en)*2020-09-082020-11-24贵州工程应用技术学院Automatic monitoring method and system for retention of gastrointestinal capsule endoscope
CN114637871A (en)*2022-03-232022-06-17安翰科技(武汉)股份有限公司Method and device for establishing digestive tract database and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110367913A (en)*2019-07-292019-10-25杭州电子科技大学Wireless capsule endoscope image pylorus and ileocaecal sphineter localization method
CN110811497A (en)*2019-12-062020-02-21深圳市资福医疗技术有限公司Control method of capsule endoscope and capsule endoscope using control method
CN111986196A (en)*2020-09-082020-11-24贵州工程应用技术学院Automatic monitoring method and system for retention of gastrointestinal capsule endoscope
CN114637871A (en)*2022-03-232022-06-17安翰科技(武汉)股份有限公司Method and device for establishing digestive tract database and storage medium

Also Published As

Publication numberPublication date
CN116269168A (en)2023-06-23

Similar Documents

PublicationPublication DateTitle
EP3762863B1 (en)Systems and methods for processing real-time video from a medical image device and detecting objects in the video
US10860930B2 (en)Learning method, image recognition device, and computer-readable storage medium
CN112543941B (en) Systems and methods for training a generative adversarial network and using a trained generative adversarial network
JP5191240B2 (en) Scene change detection apparatus and scene change detection program
KR100991915B1 (en) Recording media recording endoscopy diagnostic support method, endoscopy diagnostic support device and endoscopy diagnostic support program
KR102338018B1 (en)Ultrasound diagnosis apparatus for liver steatosis using the key points of ultrasound image and remote medical-diagnosis method using the same
EP4093025B1 (en)Medical image processing system
US20200090548A1 (en)Image processing apparatus, image processing method, and computer-readable recording medium
KR102505791B1 (en)Control method, apparatus, and program of lesion determination system acquired through real-time image
US20240016366A1 (en)Image diagnosis system for lesion
CN114259197B (en)Capsule endoscope quality control method and system
CN111986196A (en)Automatic monitoring method and system for retention of gastrointestinal capsule endoscope
US20190298159A1 (en)Image processing device, operation method, and computer readable recording medium
CN104918534A (en)Endoscope system and operation method of endoscope system
KR102372351B1 (en)Ultrasound diagnosis apparatus and ultrasound diagnosis method
CN116269168B (en)Method, controller and system for detecting relative positions of capsule endoscope and pylorus
US20230215022A1 (en)Image-based motion detection method
KR102191412B1 (en)Apparatus and method for diagnosing uterine lesion using deep leaking algorithm
JP4749732B2 (en) Medical image processing device
CN116596927B (en)Endoscope video processing method, system and device
CN116385977B (en) An Intraoperative Bleeding Point Detection System Based on Deep Learning
CN112907726B (en)Image processing method, device, equipment and computer readable storage medium
CN114451848A (en)Endoscope capsule track guiding method, device and system
CN113409312B (en)Image processing method and device for biomedical images
Hegenbart et al.On the implicit handling of varying distances and gastrointestinal regions in endoscopic video sequences with indication for celiac disease

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp