CN114419050B - Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium - Google Patents

Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium Download PDF

Info

Publication number
CN114419050B
CN114419050B CN202210328705.0A CN202210328705A CN114419050B CN 114419050 B CN114419050 B CN 114419050B CN 202210328705 A CN202210328705 A CN 202210328705A CN 114419050 B CN114419050 B CN 114419050B
Authority
CN
China
Prior art keywords
type
mucosa
preset
visualization
gastroscope image
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
CN202210328705.0A
Other languages
Chinese (zh)
Other versions
CN114419050A (en
Inventor
于红刚
董泽华
陶逍
朱益洁
吴练练
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.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
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 Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN202210328705.0A priority Critical patent/CN114419050B/en
Publication of CN114419050A publication Critical patent/CN114419050A/en
Application granted granted Critical
Publication of CN114419050B publication Critical patent/CN114419050B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10068—Endoscopic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30092—Stomach; Gastric

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Endoscopes (AREA)

Abstract

The application provides a method, a device, a terminal and a readable storage medium for quantifying the visualization degree of gastric mucosa, wherein the method comprises the following steps: acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts; classifying gastroscope image sets corresponding to a plurality of preset types of parts; determining a foreign matter shielding area proportion parameter set corresponding to the first type position set; determining a mucous membrane occlusion area proportion parameter set corresponding to a second type part set included in a gastroscope image set of a mucous membrane contracture type; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval. The embodiment of the application improves the comprehensiveness, the inspection quality and the inspection accuracy of the gastroscopy.

Description

Gastric mucosa visualization degree quantification method, device, terminal and readable storage medium
Technical Field
The application relates to the technical field of auxiliary medical treatment, in particular to a method, a device, a terminal and a readable storage medium for quantifying the visualization degree of a gastric mucosa.
Background
The upper gastrointestinal endoscope (hereinafter abbreviated as gastroscope) is one of the most intuitive methods for detecting the pathological changes of the gastric cavity. Sufficient preoperative preparation can fully expose gastric cavity mucosa, which is the premise of high-quality gastroscopy. The current routine gastroscopic preoperative preparations are: fasting and water deprivation, administration of antifoaming agent before operation, pepsin and the like.
However, even if the patient receives perfect preoperative preparation according to the requirements of guidelines due to abnormal conditions such as bile reflux, gastric motility reduction, bleeding in the gastric cavity and the like, the phenomena of bile covering, drug metabolite residue, food retention, blood stain covering, mucosal contracture and the like still exist, part of the gastric mucosa is shielded or concealed, and the visibility of the gastric mucosa is greatly reduced. The washing can partially clear away the stomach cavity foreign matter in the art, but can't improve above condition completely, and this will influence the comprehensiveness of inspection, weakens inspection quality, and like this, can't provide a reliable judgement for gastroscope preoperative preparation to reduce the accuracy of follow-up inspection.
Therefore, how to improve the accuracy of the follow-up examination is a technical problem which needs to be solved urgently in the technical field of the current auxiliary medical treatment.
Disclosure of Invention
The application provides a quantification method of gastric mucosa visualization degree, aiming at solving the technical problem of how to improve the accuracy of follow-up examination.
In one aspect, the present application provides a method for quantifying the degree of visualization of a gastric mucosa, the method comprising:
acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts;
classifying the gastroscope image sets corresponding to the preset types of parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type;
determining a foreign matter shielding area ratio parameter set corresponding to a first type part set included in the gastroscope image set of the foreign matter shielding type;
determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in the gastroscope image set of the mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to the preset type parts;
determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to the preset types of parts;
and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
In one possible implementation manner of the present application, the determining a foreign object occlusion area ratio parameter set corresponding to a first type site set included in the gastroscope image set of the type occluded by a foreign object includes:
acquiring a first mucosa total area parameter set corresponding to each type part in the first type part set based on the gastroscope image set of the type blocked by the foreign matter;
dividing the foreign matters of each type part in the first type part set to obtain a foreign matter ratio area parameter set;
and determining a foreign matter shielding area ratio parameter set corresponding to each type part in the first type part set based on the first mucosa total area parameter set and the foreign matter ratio area parameter set.
In one possible implementation manner of the present application, the determining a mucosal occlusion area ratio parameter set corresponding to a second type of part set included in the gastroscope image set of the mucosal contracture type includes:
acquiring a second set of mucosal total area parameters for each type of site in the second set of sites based on the set of gastroscopic images of the mucosal contracture type;
acquiring a hidden area parameter set of mucosa bulges corresponding to each type of part in the second type of part set based on a preset three-dimensional reconstruction model;
determining a mucosal occlusion area ratio parameter set corresponding to each type of site in the second type of site set based on the second mucosal total area parameter set and the hidden area parameter set of the mucosal prominence.
In one possible implementation manner of the present application, the acquiring a gastroscope image set including a plurality of preset type portions corresponding to a preset lens distance requirement includes:
acquiring a second gastroscope image set meeting the requirement of the preset lens distance from the first gastroscope image set on the basis of a preset lens distance identification model;
and acquiring a gastroscope image set comprising a plurality of parts of preset types corresponding to parts from the second gastroscope image set based on a gastroscope image part identification model.
In one possible implementation manner of the present application, before acquiring, based on a preset lens distance identification model, a second gastroscopic image set satisfying a preset lens distance requirement from the first gastroscopic image set, the method further includes:
decoding the gastroscope image video to obtain an initial gastroscope image set;
and carrying out size normalization processing on the images in the initial gastroscope image set to obtain a first gastroscope image set.
In one possible implementation manner of the present application, before obtaining a gastroscopic image set including a plurality of preset type parts from the first gastroscopic image set based on a gastroscopic image part identification model, the method further includes:
identifying an invalid image in the first gastroscope image set by adopting a preset invalid image identification model;
the invalid image is removed from the first set of gastroscopic images.
In one possible implementation manner of the present application, the quantifying the visualization degree of the whole gastric mucosa based on the average visualized mucosa proportion parameter and a preset visualized mucosa proportion threshold interval includes:
if the average visualized mucous membrane proportion parameter is between the preset visualized mucous membrane proportion threshold intervals, determining the visualization degree of the whole gastric mucous membrane;
if the average visualized mucous membrane proportion parameter is larger than a larger boundary value of the preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is good;
and if the average visualized mucous membrane proportion parameter is smaller than the smaller boundary value of the preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is poor.
In another aspect, the present application provides a device for quantifying the degree of visualization of a gastric mucosa, the device comprising:
the gastroscope image acquisition device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of preset type parts;
the first classification unit is used for classifying the gastroscope image sets corresponding to the preset types of parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type;
the first determining unit is used for determining a foreign matter shielding area proportion parameter set corresponding to a first type part set included in the gastroscope image set of the foreign matter shielding type;
a second determining unit, configured to determine a mucosa occlusion area ratio parameter set corresponding to a second type of region set included in the gastroscope image set of the mucosa contracture type, where a total number of regions corresponding to a third type of region set included in the gastroscope image set of the first type, the second type, and the normal type is the same as a total number of regions corresponding to the preset types of regions;
a third determining unit, configured to determine an average visualized mucosa proportion parameter of the entire gastric mucosa based on the foreign object occlusion area ratio parameter set, the mucosa occlusion area proportion parameter set, and the number of parts parameters corresponding to the plurality of preset types of parts;
and the first quantification unit is used for quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
In a possible implementation manner of the present application, the first determining unit is specifically configured to:
acquiring a first mucosa total area parameter set corresponding to each type part in the first type part set based on the gastroscope image set of the type blocked by the foreign matter;
dividing the foreign matters of each type part in the first type part set to obtain a foreign matter ratio area parameter set;
and determining a foreign matter shielding area ratio parameter set corresponding to each type part in the first type part set based on the first mucosa total area parameter set and the foreign matter ratio area parameter set.
In a possible implementation manner of the present application, the second determining unit is specifically configured to:
acquiring a second set of mucosal total area parameters for each type of site in the second set of sites based on the set of gastroscopic images of the mucosal contracture type;
acquiring a hidden area parameter set of mucosa bulges corresponding to each type of part in the second type of part set based on a preset three-dimensional reconstruction model;
determining a mucosal occlusion area ratio parameter set corresponding to each type of site in the second type of site set based on the second mucosal total area parameter set and the hidden area parameter set of the mucosal prominence.
In a possible implementation manner of the present application, the first obtaining unit specifically includes:
the second acquisition unit is used for acquiring a second gastroscope image set meeting the requirement of the preset lens distance from the first gastroscope image set on the basis of a preset lens distance identification model;
and the third acquisition unit is used for acquiring a gastroscope image set comprising a plurality of preset types of parts corresponding to the parts from the second gastroscope image set based on the gastroscope image part identification model.
In one possible implementation manner of the present application, before acquiring, based on a preset lens distance identification model, a second gastroscopic image set satisfying a preset lens distance requirement from the first gastroscopic image set, the apparatus is further configured to:
decoding the gastroscope image video to obtain an initial gastroscope image set;
and carrying out size normalization processing on the images in the initial gastroscope image set to obtain a first gastroscope image set.
In one possible implementation manner of the present application, before obtaining a gastroscopic image set including a plurality of preset type parts from the first gastroscopic image set based on a gastroscopic image part identification model, the apparatus is further configured to:
identifying an invalid image in the first gastroscope image set by adopting a preset invalid image identification model;
the invalid image is removed from the first set of gastroscopic images.
In a possible implementation manner of the present application, the first quantization unit is specifically configured to:
if the average visualized mucous membrane proportion parameter is between the preset visualized mucous membrane proportion threshold intervals, determining the visualization degree of the whole gastric mucous membrane;
if the average visualized mucous membrane proportion parameter is larger than a larger boundary value of the preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is good;
and if the average visualized mucous membrane proportion parameter is smaller than the smaller boundary value of the preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is poor.
On the other hand, the present application also provides a terminal, 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 gastric mucosa visualization degree quantifying method.
In another aspect, the present application further provides a computer readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to execute the steps of the quantification method for the visualization degree of gastric mucosa.
The method for quantifying the visualization degree of the gastric mucosa comprises the steps of obtaining a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts of the preset types; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter blocking area proportion parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter blocking type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval. Compare in traditional mode, when endoscopy, can only simply carry out the foreign matter to the stomach and clear away, can't carry out the background of quantization to the visual degree of gastric mucosa entirely, the visual degree of mucosa that this application creative proposition leads to owing to the foreign matter shelters from is poor through bringing into, with mucosa crimp, the visual degree of mucosa that the fold leads to is poor these two kinds of circumstances carry out integrated analysis and calculation, in order to quantify the visual degree of whole gastric mucosa, the emergence of the false retrieval condition that has reduced because the foreign matter shelters from, mucosa crimp, the fold leads to, improve the comprehensiveness of gastroscope inspection, inspection quality, and the accuracy of inspection.
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 gastric mucosa visualization degree quantifying system provided by an embodiment of the application;
fig. 2 is a flowchart illustrating an embodiment of a method for quantifying the degree of visualization of a gastric mucosa provided in an embodiment of the present application;
FIG. 3 is a schematic view of a mucosal occlusion area provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an embodiment of a device for quantifying the degree of visualization of a gastric mucosa provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of an embodiment of a terminal provided in the 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" and "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 method, a device, a terminal and a readable storage medium for quantifying the visualization degree of gastric mucosa, which are respectively described in detail below.
As shown in fig. 1, fig. 1 is a schematic view of a scene of a gastric mucosa visualization degree quantifying system provided in an embodiment of the present application, where the gastric mucosa visualization degree quantifying system may include a plurality of terminals 100 and a server 200, the terminals 100 and the server 200 are connected in a network, and a gastric mucosa visualization degree quantifying 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 application, the server 200 is mainly used for acquiring a gastroscope image set which meets the requirement of the preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter shielding area ratio parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter shielding type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
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 be a desktop terminal or a mobile terminal, and the terminal 100 may also be one of a mobile phone, a tablet computer, a notebook computer, a medical auxiliary apparatus, 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 to be understood that the system for quantifying the degree of gastric mucosa visualization may further include one or more other servers, or/and one or more terminals connected to a server network, and is not limited herein.
In addition, as shown in fig. 1, the system for quantifying the degree of visualization of the gastric mucosa may further include a memory 300 for storing data, such as a gastroscope image set and data for quantifying the degree of visualization of the gastric mucosa, for example, data for quantifying the degree of visualization of the gastric mucosa during operation of the system for quantifying the degree of visualization of the gastric mucosa.
It should be noted that the scene diagram of the gastric mucosa visualization degree quantifying system shown in fig. 1 is merely an example, and the gastric mucosa visualization degree quantifying 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, and it can be known by those skilled in the art that the technical solution provided in the embodiment of the present application is also applicable to similar technical problems along with the evolution of the gastric mucosa visualization degree quantifying system and the appearance of new business scenes.
Next, a method for quantifying the degree of visualization of the gastric mucosa provided in the embodiments of the present application will be described.
In the embodiment of the method for quantifying the degree of gastric mucosa visualization in the present application, a device for quantifying the degree of gastric mucosa visualization is used as an execution subject, and for simplicity and convenience of description, the execution subject is omitted in the following method embodiments, and the device for quantifying the degree of gastric mucosa visualization is applied to a terminal, and the method includes: acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter shielding area ratio parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter shielding type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
Referring to fig. 2 to 5, fig. 2 is a flowchart illustrating an embodiment of a method for quantifying a degree of gastric mucosa visualization provided in an embodiment of the present application, where the method for quantifying a degree of gastric mucosa visualization includes:
201. and acquiring a gastroscope image set which meets the requirement of the preset lens distance and comprises a plurality of preset type parts.
In this embodiment, the plurality of predetermined types of regions are a plurality of types of regions into which the physician divides the entire stomach lumen. Specifically, the following 22 types of sites may be included: big curvature of antrum, small curvature of antrum, anterior wall of antrum, posterior wall of antrum, big curvature of lower part of orthopscope stomach, small curvature of lower part of orthopscope stomach, anterior wall of lower part of orthopscope stomach, posterior wall of lower part of orthopscope stomach, big curvature of upper part in orthopscope stomach, small curvature of upper part in orthopscope stomach, anterior wall of upper part in orthopscope stomach, posterior wall of upper part in orthopscope stomach, small curvature of inverted scope stomach angle, anterior wall of inverted scope stomach angle, posterior wall of inverted scope stomach angle, small curvature of upper part in inverted scope stomach body, anterior wall of upper part in inverted scope stomach body, posterior wall of upper part in inverted scope stomach body, big curvature of inverted scope stomach fundus, small curvature of inverted scope stomach fundus, anterior wall of inverted scope stomach fundus, posterior wall of inverted scope stomach fundus.
The preset lens distance refers to the distance between a lens of an endoscope and a stomach entity, and because related area parameters of subsequent calculation all take shot images as main bodies, the applicant considers that the areas of the same object shot at different lens distances have differences, and sets a preset lens distance requirement in order to ensure the calculation accuracy, wherein the preset lens distance requirement comprises the same lens distance corresponding to a gastroscope image set corresponding to a plurality of preset type parts, and the lens distance type is moderate.
In some embodiments of the present application, acquiring a gastroscopic image set including a plurality of preset type sites corresponding to preset lens distance requirements comprises: acquiring a second gastroscope image set meeting the requirement of the preset lens distance from the first gastroscope image set on the basis of a preset lens distance identification model; and acquiring a gastroscope image set comprising a plurality of preset type parts corresponding to the parts from the second gastroscope image set based on the gastroscope image part identification model.
The preset lens distance recognition model can recognize three types of lens distance, namely far, medium and near lens distance types. The present application selects the lens distance type to be moderate.
202. Classifying the gastroscope image sets corresponding to the preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type.
The gastric mucosa visualization degree classification model can be obtained by training by adopting a VGG-16 model as a basic neural network structure.
203. And determining a foreign matter occlusion area ratio parameter set corresponding to the first type part set included in the gastroscope image set of the foreign matter occlusion type.
In the present embodiment, the first type site set refers to a set of type sites included in a gastroscopic image set of a type occluded by a foreign object. The foreign matter shielding area proportion parameter set refers to a set formed by a plurality of foreign matter shielding area proportion parameters corresponding to each part in the first type part set, for example, the first type part set comprises three types of parts, namely a middle and upper rear wall of a orthopscope stomach body, a small bend of an inverted scope stomach angle and an anterior wall of the inverted scope stomach angle, and the corresponding foreign matter shielding area proportion parameter set comprises three foreign matter shielding area proportion parameters, namely a foreign matter shielding area proportion parameter of the middle and upper rear wall of the orthopscope stomach body, a foreign matter shielding area proportion parameter of the small bend of the inverted scope stomach angle and a foreign matter shielding area proportion parameter of the anterior wall of the inverted scope stomach angle.
In some embodiments of the present application, determining a foreign object occlusion area fraction parameter set corresponding to a first type site set included in a gastroscopic image set of a foreign object occlusion type comprises: acquiring a first mucosa total area parameter set corresponding to each type part in a first type part set based on a gastroscope image set of a type blocked by foreign matters; the foreign matter of each type position in the first type position set is divided to obtain a foreign matter ratio area parameter set; and determining a foreign matter shielding area ratio parameter set corresponding to each type part in the first type part set based on the first mucosa total area parameter set and the foreign matter ratio area parameter set.
Specifically, the foreign object shielding area ratio parameter set includes { s }y1、sy2、sy3.。。。synThe foreign matter shielding area ratio parameter calculation formula corresponding to each type part is as follows:
Figure 598965DEST_PATH_IMAGE001
；
wherein s isynIs a type of site differentArea ratio of object to be shielded, sanA first mucosa total area parameter corresponding to a certain type of part, i.e. the image size area of the type of part, sbnThe area of the foreign matter image is a parameter of the specific area of the foreign matter of a certain type of part, namely the size area of the foreign matter image of the type of part.
204. And determining a mucous membrane occlusion area proportion parameter set corresponding to the second type part set included in the gastroscope image set of the mucous membrane contracture type.
And the total number of the parts corresponding to the third type part set in the first type part set, the second type part set and the normal type gastroscope image set is the same as the total number of the parts corresponding to the preset type parts. Specifically, the total number of sites is 22.
In some embodiments of the present application, determining a set of mucosal occlusion area ratio parameters corresponding to a set of second type sites included in a set of gastroscopic images of a mucosal contracture type comprises: acquiring a second mucosa total area parameter set of each type of part in a second type of part set based on the gastroscope image set of mucosa contracture type; acquiring a hidden area parameter set of mucosa bulges corresponding to each type part in the second type part set based on a preset three-dimensional reconstruction model; and determining a mucous membrane occlusion area proportion parameter set corresponding to each type part in the second type part set based on the second mucous membrane total area parameter set and the hidden area parameter set of the mucous membrane bulge.
Specifically, the mucosa shielding area ratio parameter set comprises { s }z1、sz2、sz3.。。。sznAnd calculating a mucous membrane shielding area ratio parameter corresponding to each type of part according to the following formula:
Figure 250526DEST_PATH_IMAGE002
；
wherein s isznIs a certain type of site mucous membrane shielding area proportion parameter, sanA second mucosa total area parameter corresponding to a certain type of part, i.e. the image size area of the type of part, sz1To sznHidden area parameter for each segment of mucosal ridge, i.e.The hidden area corresponding to each type of region is shown in fig. 3.
205. And determining the average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to the preset types of parts.
According to the above steps, in this embodiment, the number parameter of the parts corresponding to the plurality of preset types of parts is 22, and specifically, the calculation formula of the average visualized mucous membrane ratio parameter of the whole gastric mucosa is as follows:
Figure 827001DEST_PATH_IMAGE003
wherein s iswAverage visualized mucosal ratio parameter of the whole gastric mucosa.
206. And quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
In some embodiments of the present application, the visualization degree of the entire gastric mucosa is quantified based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval, including: if the average visualized mucous membrane proportion parameter is between preset visualized mucous membrane proportion threshold intervals, determining the visualized degree of the whole gastric mucous membrane; if the average visualized mucous membrane proportion parameter is larger than a larger boundary value of a preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is good; and if the average visualized mucous membrane proportion parameter is smaller than a smaller boundary value of a preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucosa is poor.
Specifically, according to the obtained average visualized mucous membrane proportion parameter swAnd judging the whole visual condition of the gastric cavity in the following ways:
the visualization degree is good: sw≧0.9；
In the degree of visualization: 0.8 ≦ sw<0.9；
Poor visualization degree: sw>0.8。
It should be noted that the visual mucosa proportion threshold interval preset in the application can be adjusted according to actual conditions.
The method for quantifying the visualization degree of the gastric mucosa comprises the steps of obtaining a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts of the preset types; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter shielding area ratio parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter shielding type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval. Compare in traditional mode, when endoscopy, can only simply carry out the foreign matter to the stomach and clear away, can't carry out the background of quantization to the visual degree of gastric mucosa entirely, the visual degree of mucosa that this application creative proposition leads to owing to the foreign matter shelters from is poor through bringing into, with mucosa crimp, the visual degree of mucosa that the fold leads to is poor these two kinds of circumstances carry out integrated analysis and calculation, in order to quantify the visual degree of whole gastric mucosa, the emergence of the false retrieval condition that has reduced because the foreign matter shelters from, mucosa crimp, the fold leads to, improve the comprehensiveness of gastroscope inspection, inspection quality, and the accuracy of inspection.
In some embodiments of the present application, prior to obtaining a second set of gastroscopic images from the first set of gastroscopic images that meet the preset lens distance requirements based on the preset lens distance identification model, the method further comprises: decoding the gastroscope image video to obtain an initial gastroscope image set; and carrying out size normalization processing on the images in the initial gastroscope image set to obtain a first gastroscope image set.
In some embodiments of the present application, before obtaining a gastroscopic image set including correspondence to a plurality of preset types of sites from the first gastroscopic image set based on the gastroscopic image site identification model, the method further includes: identifying an invalid image in the first gastroscope image set by adopting a preset invalid image identification model; invalid images are removed from the first set of gastroscopic images.
According to the embodiment of the application, the invalid image in the first gastroscope image set is identified by adopting a preset invalid image identification model; invalid images are removed from the first gastroscope image set, and the efficiency and accuracy of subsequent image identification can be effectively improved.
In order to better implement the quantification method of the visualization degree of the gastric mucosa in the embodiment of the present application, on the basis of the quantification method of the visualization degree of the gastric mucosa, a quantification apparatus of the visualization degree of the gastric mucosa is further provided in the embodiment of the present application, as shown in fig. 4, the quantification apparatus 400 of the visualization degree of the gastric mucosa includes:
a first obtaining unit 401, configured to obtain a gastroscope image set that meets a preset lens distance requirement and includes a plurality of preset type parts;
a first classification unit 402, configured to classify gastroscope image sets corresponding to multiple preset types of portions based on a preset classification model of gastric mucosa visualization degree, so as to obtain a gastroscope image set of a type blocked by foreign matter, a gastroscope image set of a normal type, and a gastroscope image set of a mucosa crimp type, respectively;
a first determining unit 403, configured to determine a foreign object occlusion area ratio parameter set corresponding to a first type location set included in a gastroscope image set of a foreign object occlusion type;
a second determining unit 404, configured to determine a mucosa occlusion area ratio parameter set corresponding to a second type of region set included in the gastroscope image set of mucosa contracture type, where a total number of regions corresponding to a third type of region set included in the gastroscope image set of first type, second type, and normal type is the same as a total number of regions corresponding to a plurality of preset types of regions;
a third determining unit 405, configured to determine an average visualized mucosa proportion parameter of the whole gastric mucosa based on the foreign object occlusion area ratio parameter set, the mucosa occlusion area proportion parameter set, and the number of parts parameters corresponding to the multiple preset types of parts;
the first quantifying unit 406 is configured to quantify the visualization degree of the entire gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
In some embodiments of the present application, the first determining unit 403 is specifically configured to:
acquiring a first mucosa total area parameter set corresponding to each type part in a first type part set based on a gastroscope image set of a type blocked by foreign matters;
the foreign matter of each type position in the first type position set is divided to obtain a foreign matter ratio area parameter set;
and determining a foreign matter shielding area ratio parameter set corresponding to each type part in the first type part set based on the first mucosa total area parameter set and the foreign matter ratio area parameter set.
In some embodiments of the present application, the second determining unit 404 is specifically configured to:
acquiring a second mucosa total area parameter set of each type of part in a second type of part set based on the gastroscope image set of mucosa contracture type;
acquiring a hidden area parameter set of mucosa bulges corresponding to each type part in the second type part set based on a preset three-dimensional reconstruction model;
and determining a mucous membrane occlusion area proportion parameter set corresponding to each type part in the second type part set based on the second mucous membrane total area parameter set and the hidden area parameter set of the mucous membrane bulge.
In some embodiments of the present application, the first obtaining unit 401 specifically includes:
the second acquisition unit is used for acquiring a second gastroscope image set meeting the requirement of the preset lens distance from the first gastroscope image set on the basis of a preset lens distance identification model;
and the third acquisition unit is used for acquiring a gastroscope image set comprising a plurality of preset type parts corresponding to the parts from the second gastroscope image set based on the gastroscope image part identification model.
In some embodiments of the present application, prior to obtaining a second set of gastroscopic images from the first set of gastroscopic images that meet the preset lens distance requirements based on the preset lens distance identification model, the apparatus is further configured to:
decoding the gastroscope image video to obtain an initial gastroscope image set;
and carrying out size normalization processing on the images in the initial gastroscope image set to obtain a first gastroscope image set.
In some embodiments of the present application, prior to obtaining a gastroscopic image set including correspondence to a plurality of preset type sites from the first gastroscopic image set based on the gastroscopic image site identification model, the apparatus is further configured to:
identifying an invalid image in the first gastroscope image set by adopting a preset invalid image identification model;
invalid images are removed from the first set of gastroscopic images.
In some embodiments of the present application, the first quantization unit 406 is specifically configured to:
if the average visualized mucous membrane proportion parameter is between preset visualized mucous membrane proportion threshold intervals, determining the visualized degree of the whole gastric mucous membrane;
if the average visualized mucous membrane proportion parameter is larger than a larger boundary value of a preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is good;
and if the average visualized mucous membrane proportion parameter is smaller than a smaller boundary value of a preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucosa is poor.
The gastric mucosa visualization degree quantifying device 400 comprises a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts corresponding to preset types; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter shielding area ratio parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter shielding type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval. Compare in traditional device, when the scope inspection, can only simply carry out the foreign matter to stomach and clear away, can't be whole carry out the background quantified to the visual degree of gastric mucosa, the visual degree of mucosa that this application creatively proposed through bringing in because the foreign matter shelters from the messenger is poor, curl with the mucosa, the visual degree of mucosa that the fold leads to carries out integrated analysis and calculation with this two kinds of circumstances, in order to quantify the visual degree of whole gastric mucosa, the emergence of the false retrieval condition that has reduced because the foreign matter shelters from, curl the mucosa, the fold leads to, improve the comprehensiveness of gastroscope inspection, the inspection quality, and the accuracy of inspection.
In addition to the above described method and apparatus for quantifying visualization degree of gastric mucosa, an embodiment of the present application further provides a terminal, which integrates any one of the apparatuses for quantifying visualization degree of gastric mucosa provided by the embodiments of the present application, and the terminal includes:
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 perform the operations of any of the methods in any of the above-described gastric mucosa visualization degree quantifying method embodiments.
The embodiment of the application also provides a terminal, which integrates any one of the gastric mucosa visualization degree quantification devices provided by the embodiment of the application. Referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of a terminal according to the present application.
As shown in fig. 5, it shows a schematic structural diagram of a device for quantifying the visualization degree of gastric mucosa designed by the embodiment of the present application, specifically:
the apparatus for quantifying the degree of visualization of the gastric mucosa may include one or more processors 501 of a processing core, one or more storage units 502 of a computer-readable storage medium, a power source 503, an input unit 504, and the like. Those skilled in the art will appreciate that the structure of the gastric mucosa visualization degree quantifying device illustrated in fig. 5 does not constitute a definition of a gastric mucosa visualization degree quantifying device, and may include more or fewer components than illustrated, or combine certain components, or a different arrangement of components. Wherein:
the processor 501 is a control center of the apparatus for quantifying the degree of gastric mucosa visualization, and is connected to each part of the apparatus for quantifying the degree of gastric mucosa visualization through various interfaces and lines, and executes various functions and processing data of the apparatus for quantifying the degree of gastric mucosa visualization by operating or executing software programs and/or modules stored in the storage unit 502 and calling data stored in the storage unit 502, thereby integrally monitoring the apparatus for quantifying the degree of gastric mucosa visualization. Optionally, processor 501 may include one or more processing cores; preferably, the processor 501 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 501.
The storage unit 502 may be used to store software programs and modules, and the processor 501 executes various functional applications and data processing by operating the software programs and modules stored in the storage unit 502. The storage unit 502 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 stored data area may store data created from use of the gastric mucosa visualization degree quantifying device, and the like. Further, the storage unit 502 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 memory unit 502 may also include a memory controller to provide the processor 501 access to the memory unit 502.
The gastric mucosa visualization degree quantifying device further comprises a power supply 503 for supplying power to each component, and preferably, the power supply 503 can be logically connected with the processor 501 through a power management system, so that functions of charging, discharging, power consumption management and the like can be managed through the power management system. The power supply 503 may also include any component of 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 apparatus for quantifying the degree of visualization of gastric mucosa may further comprise an input unit 504, and the input unit 504 may be configured 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 gastric mucosa visualization degree quantifying device may further include a display unit or the like, which is not described in detail herein. Specifically, in the embodiment of the present application, the processor 501 in the gastric mucosa visualization process measuring apparatus loads an executable file corresponding to a process of one or more application programs into the storage unit 502 according to the following instructions, and the processor 501 runs the application programs stored in the storage unit 502, so as to implement various functions as follows:
acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter blocking area proportion parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter blocking type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of mucosa crimp type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type is the same as the total number of parts corresponding to a plurality of preset types of parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
The method for quantifying the visualization degree of the gastric mucosa comprises the steps of obtaining a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts; classifying gastroscope image sets corresponding to a plurality of preset types of parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a type blocked by foreign matters, a gastroscope image set in a normal type and a gastroscope image set in a mucosa crimp type; determining a foreign matter shielding area ratio parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter shielding type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval. Compare in traditional mode, when endoscopy, can only simply carry out the foreign matter to the stomach and clear away, can't carry out the background of quantization to the visual degree of gastric mucosa entirely, the visual degree of mucosa that this application creative proposition leads to owing to the foreign matter shelters from is poor through bringing into, with mucosa crimp, the visual degree of mucosa that the fold leads to is poor these two kinds of circumstances carry out integrated analysis and calculation, in order to quantify the visual degree of whole gastric mucosa, the emergence of the false retrieval condition that has reduced because the foreign matter shelters from, mucosa crimp, the fold leads to, improve the comprehensiveness of gastroscope inspection, inspection quality, and the accuracy of inspection.
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 has stored therein a plurality of instructions that can be loaded by a processor to perform the steps of any one of the methods for quantifying the degree of gastric mucosa visualization provided in the embodiments of the present application. For example, the instructions may perform the steps of:
acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts; classifying gastroscope image sets corresponding to a plurality of preset type parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type; determining a foreign matter shielding area ratio parameter set corresponding to a first type part set in a gastroscope image set of a foreign matter shielding type; determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in a gastroscope image set of a mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to a plurality of preset type parts; determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to a plurality of preset types of parts; and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
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, the terminal and the readable storage medium for quantifying the visualization degree of the gastric mucosa provided by the embodiments of the present application are described in detail above, and specific examples are applied herein to illustrate the principles and embodiments of the present application, and the description of the embodiments above is only used to help understand the method and the core ideas of the present 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 (10)

1. A method for quantifying the degree of visualization of the gastric mucosa, the method comprising:
acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of parts of preset types and corresponds to the parts;
classifying the gastroscope image sets corresponding to the preset types of parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type;
determining a foreign matter shielding area ratio parameter set corresponding to a first type part set included in the gastroscope image set of the foreign matter shielding type;
determining a mucosa occlusion area ratio parameter set corresponding to a second type part set included in the gastroscope image set of the mucosa contracture type, wherein the total number of parts corresponding to a third type part set included in the gastroscope image set of the first type part set, the second type part set and the normal type part set is the same as the total number of parts corresponding to the preset type parts;
determining an average visual mucous membrane proportion parameter of the whole gastric mucous membrane based on the foreign matter shielding area ratio parameter set, the mucous membrane shielding area proportion parameter set and the part quantity parameters corresponding to the preset types of parts;
and quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
2. The method for quantifying visual degree of gastric mucosa according to claim 1, wherein the determining the foreign object occlusion area ratio parameter set corresponding to the first type site set included in the gastroscope image set of the foreign object occlusion type comprises:
acquiring a first mucosa total area parameter set corresponding to each type part in the first type part set based on the gastroscope image set of the type blocked by the foreign matter;
dividing the foreign matters of each type part in the first type part set to obtain a foreign matter ratio area parameter set;
and determining a foreign matter shielding area ratio parameter set corresponding to each type part in the first type part set based on the first mucosa total area parameter set and the foreign matter ratio area parameter set.
3. The method for quantifying degree of gastric mucosa visualization according to claim 1, wherein the determining a mucosa occlusion area ratio parameter set corresponding to a second type site set included in the gastroscopic image set of mucosa flinching type comprises:
acquiring a second set of mucosal total area parameters for each type of site in the second set of sites based on the set of gastroscopic images of the mucosal contracture type;
acquiring a hidden area parameter set of mucosa bulges corresponding to each type of part in the second type of part set based on a preset three-dimensional reconstruction model;
determining a mucosal occlusion area ratio parameter set corresponding to each type of site in the second type of site set based on the second mucosal total area parameter set and the hidden area parameter set of the mucosal prominence.
4. The method for quantifying visualization degree of gastric mucosa according to claim 1, wherein the acquiring of the gastroscope image set corresponding to the plurality of preset types of parts and meeting the preset lens distance requirement comprises:
acquiring a second gastroscope image set meeting the requirement of the preset lens distance from the first gastroscope image set on the basis of a preset lens distance identification model;
and acquiring a gastroscope image set comprising a plurality of preset types of parts corresponding to the parts from the second gastroscope image set based on a gastroscope image part identification model.
5. The method for quantifying visual degree of gastric mucosa according to claim 4, wherein before acquiring the second gastroscopic image set satisfying the preset lens distance requirement from the first gastroscopic image set based on the preset lens distance identification model, the method further comprises:
decoding the gastroscope image video to obtain an initial gastroscope image set;
and carrying out size normalization processing on the images in the initial gastroscope image set to obtain a first gastroscope image set.
6. The method for quantifying visual degree of gastric mucosa according to claim 4, wherein before acquiring a gastroscopic image set comprising a plurality of preset types of parts from the first gastroscopic image set based on a gastroscopic image part identification model, the method further comprises:
identifying an invalid image in the first gastroscope image set by adopting a preset invalid image identification model;
the invalid image is removed from the first set of gastroscopic images.
7. The method for quantifying the visualization degree of the gastric mucosa according to claim 1, wherein the quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval comprises:
if the average visualized mucous membrane proportion parameter is between the preset visualized mucous membrane proportion threshold intervals, determining the visualization degree of the whole gastric mucous membrane;
if the average visualized mucous membrane proportion parameter is larger than a larger boundary value of the preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is good;
and if the average visualized mucous membrane proportion parameter is smaller than the smaller boundary value of the preset visualized mucous membrane proportion threshold interval, determining that the visualized degree of the whole gastric mucous membrane is poor.
8. A gastric mucosa visualization degree quantifying device, characterized in that the device comprises:
the gastroscope image acquisition device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring a gastroscope image set which meets the requirement of a preset lens distance and comprises a plurality of preset type parts;
the first classification unit is used for classifying the gastroscope image sets corresponding to the preset types of parts based on a preset gastric mucosa visualization degree classification model to respectively obtain a gastroscope image set in a foreign matter shielding type, a gastroscope image set in a normal type and a gastroscope image set in a mucosa curling type;
the first determining unit is used for determining a foreign matter shielding area proportion parameter set corresponding to a first type part set included in the gastroscope image set of the foreign matter shielding type;
a second determining unit, configured to determine a mucosa occlusion area ratio parameter set corresponding to a second type of region set included in the gastroscope image set of the mucosa contracture type, where a total number of regions corresponding to a third type of region set included in the gastroscope image set of the first type, the second type, and the normal type is the same as a total number of regions corresponding to the preset types of regions;
a third determining unit, configured to determine an average visualized mucosa proportion parameter of the entire gastric mucosa based on the foreign object occlusion area proportion parameter set, the mucosa occlusion area proportion parameter set, and the number of locations parameters corresponding to the multiple preset types of locations;
and the first quantification unit is used for quantifying the visualization degree of the whole gastric mucosa based on the average visualization mucosa proportion parameter and a preset visualization mucosa proportion threshold interval.
9. A terminal, characterized in that the terminal 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 gastric mucosa visualization degree quantifying method of any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps of the method for quantifying the degree of visualization of the gastric mucosa according to any one of claims 1 to 7.
CN202210328705.0A 2022-03-31 2022-03-31 Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium Active CN114419050B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210328705.0A CN114419050B (en) 2022-03-31 2022-03-31 Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210328705.0A CN114419050B (en) 2022-03-31 2022-03-31 Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium

Publications (2)

Publication Number Publication Date
CN114419050A CN114419050A (en) 2022-04-29
CN114419050B true CN114419050B (en) 2022-06-21

Family

ID=81263947

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210328705.0A Active CN114419050B (en) 2022-03-31 2022-03-31 Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium

Country Status (1)

Country Link
CN (1) CN114419050B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117974668A (en) * 2024-04-02 2024-05-03 青岛美迪康数字工程有限公司 Novel gastric mucosa visibility scoring quantification method, device and equipment based on AI

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016094367A2 (en) * 2014-12-08 2016-06-16 The Johns Hopkins University Endoscopic gastric mucosal ablation/resection/exclusion (a/r/e) as a minimally invasive weight loss approach
CN206007678U (en) * 2016-07-20 2017-03-15 四川大学华西第二医院 A kind of baby's gastrointestinal decompression
EP3237391A2 (en) * 2014-12-22 2017-11-01 Farmington Pharma Development Creatine prodrugs, compositions and methods of use thereof
CN111127426A (en) * 2019-12-23 2020-05-08 山东大学齐鲁医院 Gastric mucosa cleanliness evaluation method and system based on deep learning
CN111128396A (en) * 2019-12-20 2020-05-08 山东大学齐鲁医院 Digestive tract disease auxiliary diagnosis system based on deep learning
CN113129287A (en) * 2021-04-22 2021-07-16 武汉楚精灵医疗科技有限公司 Automatic lesion mapping method for upper gastrointestinal endoscope image
CN113538344A (en) * 2021-06-28 2021-10-22 河北省中医院 Image recognition system, device and medium for distinguishing atrophic gastritis and gastric cancer
CN113539476A (en) * 2021-06-02 2021-10-22 复旦大学 Stomach endoscopic biopsy Raman image auxiliary diagnosis method and system based on artificial intelligence
CN113822897A (en) * 2021-11-22 2021-12-21 武汉楚精灵医疗科技有限公司 Blood vessel segmentation method, terminal and computer-readable storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016094367A2 (en) * 2014-12-08 2016-06-16 The Johns Hopkins University Endoscopic gastric mucosal ablation/resection/exclusion (a/r/e) as a minimally invasive weight loss approach
EP3237391A2 (en) * 2014-12-22 2017-11-01 Farmington Pharma Development Creatine prodrugs, compositions and methods of use thereof
CN206007678U (en) * 2016-07-20 2017-03-15 四川大学华西第二医院 A kind of baby's gastrointestinal decompression
CN111128396A (en) * 2019-12-20 2020-05-08 山东大学齐鲁医院 Digestive tract disease auxiliary diagnosis system based on deep learning
CN111127426A (en) * 2019-12-23 2020-05-08 山东大学齐鲁医院 Gastric mucosa cleanliness evaluation method and system based on deep learning
CN113129287A (en) * 2021-04-22 2021-07-16 武汉楚精灵医疗科技有限公司 Automatic lesion mapping method for upper gastrointestinal endoscope image
CN113539476A (en) * 2021-06-02 2021-10-22 复旦大学 Stomach endoscopic biopsy Raman image auxiliary diagnosis method and system based on artificial intelligence
CN113538344A (en) * 2021-06-28 2021-10-22 河北省中医院 Image recognition system, device and medium for distinguishing atrophic gastritis and gastric cancer
CN113822897A (en) * 2021-11-22 2021-12-21 武汉楚精灵医疗科技有限公司 Blood vessel segmentation method, terminal and computer-readable storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
新型鼻胃镜辅助法留置经鼻型肠梗阻导管的应用价值;钱晶瑶等;《天津医药》;20191115(第11期);第1179-1182页 *
胶囊内镜在不明原因消化道出血中的诊断价值及结果分析;刘晓兵等;《中国药物与临床》;20200715(第13期);第2238-2240页 *

Also Published As

Publication number Publication date
CN114419050A (en) 2022-04-29

Similar Documents

Publication Publication Date Title
CN113573654A (en) AI system for detecting and determining lesion size
WO2020259453A1 (en) 3d image classification method and apparatus, device and storage medium
CN114419050B (en) Gastric mucosa visualization degree quantification method and device, terminal and readable storage medium
CN114417037B (en) Image processing method, device, terminal and readable storage medium
CN114419521B (en) Method and device for monitoring intestinal endoscopy
CN113643299B (en) Method and device for quantifying degree of bending of microvessels, and computer-readable storage medium
CN115393356B (en) Target part abnormal form recognition method and device and computer readable storage medium
CN113823400A (en) Method and device for monitoring speed of endoscope withdrawal of intestinal tract and computer readable storage medium
CN114464316B (en) Stomach abnormal risk grade prediction method, device, terminal and readable storage medium
CN114387320B (en) Medical image registration method, device, terminal and computer-readable storage medium
CN113344926B (en) Method, device, server and storage medium for recognizing biliary-pancreatic ultrasonic image
CN115511885B (en) Method and device for detecting success rate of cecum intubation
CN114494406B (en) Medical image processing method, device, terminal and computer readable storage medium
CN113706536B (en) Sliding mirror risk early warning method and device and computer readable storage medium
CN114511045B (en) Image processing method, device, terminal and computer readable storage medium
US20220110505A1 (en) Information processing apparatus, control method, and non-transitory storage medium
CN114419041B (en) Method and device for identifying focus color
CN114419135B (en) Pancreas marker size quantification method and device, terminal and readable storage medium
CN114359280B (en) Gastric mucosa image boundary quantification method, device, terminal and storage medium
CN115035153B (en) Medical image processing method, device and related equipment
CN115690060A (en) Method and device for determining abnormality of eye ultrasonic image and related equipment
CN115393230B (en) Ultrasonic endoscope image standardization method and device and related device thereof
CN116168000A (en) Gastric mucosa image positioning method, device, computer equipment and storage medium
CN115908452A (en) Method and device for identifying esophageal endoscope video abnormality
CN113793334B (en) Equipment monitoring method and equipment monitoring device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant