Method and apparatus for quantifying softness of gastric mucosa and related devices

Abstract

This application provides a method, apparatus, and related equipment for quantifying the softness of the gastric mucosa. The method includes: determining the height change rate of a first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction based on a second time-series simulated image set; determining the width change rate, lateral movement rate, and brightness change rate of a target region in a second target mucosa based on a third time-series simulated image set; and quantifying the softness of the gastric mucosa based on the height change rate, the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction, the width change rate, the lateral movement rate, and the brightness change rate of the target region. The embodiments of this application achieve efficient and accurate quantification of the softness of the gastric mucosa, assisting endoscopists in assessing the health status of the gastric mucosa and aiding in disease diagnosis.

Description

Technical Field

[0001] This application relates to the field of assistive medical technology, specifically to a method, device, and related equipment for quantifying the softness of the gastric mucosa. Background Technology

[0002] Upper gastrointestinal endoscopy is one of the most direct methods for detecting lesions in the gastric cavity. An endoscopist manipulates the endoscope, using real-time images returned by a high-definition camera at the end of the endoscope to identify and determine whether any abnormalities exist in the gastric mucosa within the current field of view.

[0003] The inventors of this application have discovered a correlation between the softness of the gastric mucosa under endoscopy and its health status, and that this softness is indicative of disease prediction. However, existing technologies cannot accurately and efficiently quantify the softness of the gastric mucosa.

[0004] Therefore, how to accurately and efficiently quantify the softness of the gastric mucosa is a technical problem that urgently needs to be solved in the field of auxiliary medical technology. Summary of the Invention

[0005] This application provides a method, apparatus, and related equipment for quantifying the softness of the gastric mucosa, aiming to solve the technical problem of how to accurately and efficiently quantify the softness of the gastric mucosa.

[0006] On the one hand, this application provides a method for quantifying the softness of the gastric mucosa, the method comprising:

[0007] Acquire a set of first-time-series simulated images of a pre-constructed 3D model of the patient's stomach taken simultaneously from multiple perspectives within a preset time period;

[0008] Identify a second set of time-series simulated images taken along a first target viewpoint targeting the first target mucosa of the stomach from the plurality of first time-series simulated image sets, and a third set of time-series simulated images taken along a second target viewpoint targeting the second target mucosa of the stomach from the second target viewpoint, wherein the first target viewpoint is a side viewpoint and the second target viewpoint is a top viewpoint;

[0009] Based on the second time-series simulated image set, the height change rate of the first target mucosa along the first preset direction and the lateral movement rate of the first target mucosa along the second preset direction are determined.

[0010] Based on the third time-series simulated image set, the width change rate, lateral movement speed and brightness change rate of the target region in the second target mucosa are determined, and the target region is the bright region corresponding to the third time-series simulated image after being converted into the HSV color space.

[0011] The mucosal softness of the stomach is quantified based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate.

[0012] In one possible implementation of this application, determining the width change rate, lateral movement speed, and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set includes:

[0013] The RGB color space of all images in the third time-series simulated image set is converted to the HSV color space to obtain the fourth time-series simulated image set;

[0014] Two time-series simulation images are selected from the fourth time-series simulation image set to obtain the third target time-series simulation image and the third time-series time corresponding to the third target time-series simulation image, and the fourth time-series simulation image and the fourth time-series time corresponding to the fourth target time-series simulation image, wherein the third time-series time is the same as the first time-series time, and the fourth time-series time is the same as the second time-series time;

[0015] Based on a pre-trained highlight region target detection model, the H channels of the third target time-series simulated image and the fourth target time-series simulated image are identified respectively to obtain the coordinates of the highlight regions of the third target time-series simulated image and the fourth target time-series simulated image;

[0016] Based on the coordinates of the highlighted regions in the third target time-series simulation image and the fourth target time-series simulation image, the width change rate and lateral movement speed of the highlighted regions are determined.

[0017] Based on the average brightness of the bright region and the average brightness of the non-bright region in the third target time-series simulation image and the fourth target time-series simulation image, as well as the third time-series time and the fourth time-series time, the brightness change rate of the bright region is determined.

[0018] In one possible implementation of this application, determining the height change rate of the first target mucosa along a first preset direction based on the second time-series simulated image set includes:

[0019] Based on the second time-series simulated image set, a reference plane for the first target mucosa is determined, wherein the reference plane is the plane corresponding to the flat position of the first target mucosa;

[0020] Two time-series simulation images are selected from the second time-series simulation image set to obtain the first target time-series simulation image and the first time-series time corresponding to the first target time-series simulation image, and the second target time-series simulation image and the second time-series time corresponding to the second target time-series simulation image;

[0021] Based on the reference plane and the first target time-series simulation image, determine the first height data of the first target mucosa bulging at the first time-series moment;

[0022] Based on the reference plane and the second target time-series simulation image, determine the second height data of the first target mucosa bulging at the second time-series moment;

[0023] Based on the first height data, the second height data, the first time step, and the second time step, the height change rate of the first target mucosa along the first preset direction is determined.

[0024] In one possible implementation of this application, determining the lateral movement speed of the first target mucosa along a second preset direction based on the second time-series simulated image set includes:

[0025] Based on the first target time-series simulation image and the second time-series simulation image, determine the lateral movement distance of the first target mucosa along the second preset direction;

[0026] Based on the lateral movement distance, the first time step, and the second time step, the lateral movement speed of the first target mucosa along the second preset direction is determined.

[0027] In one possible implementation of this application, quantifying the mucosal softness of the stomach based on the height change rate, the lateral movement speed of the first target mucosa along a second preset direction, the width change rate of the target region, the lateral movement speed, and the brightness change rate includes:

[0028] The height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate are fitted to obtain fitting parameters.

[0029] The softness of the gastric mucosa is quantified based on the fitting parameters and the preset threshold.

[0030] In one possible implementation of this application, the acquisition of a set of multiple first temporal simulated images of a pre-constructed three-dimensional model of the patient's stomach taken simultaneously from multiple viewpoints within a preset time period includes:

[0031] Acquire the initial set of endoscopic images of the patient's stomach within a preset time period;

[0032] Based on a pre-trained observation distance recognition model, the initial endoscopic image set is filtered to obtain a second endoscopic image set that meets the preset distance requirements;

[0033] Based on the second endoscopic image set, a three-dimensional model of the stomach is constructed;

[0034] Obtain a set of multiple first-time-series simulated images of the three-dimensional model taken simultaneously from multiple viewpoints.

[0035] In one possible implementation of this application, constructing a three-dimensional model of the stomach based on the second endoscopic image set includes:

[0036] Obtain the similarity of each second endoscope image in the second endoscope image set;

[0037] Based on the similarity of each second endoscopic image and a preset similarity threshold, a target endoscopic image that meets the preset similarity requirement is determined.

[0038] A three-dimensional model of the stomach is constructed based on the target endoscopic image.

[0039] On the other hand, this application provides a device for quantifying the softness of the gastric mucosa, the device comprising:

[0040] The first acquisition unit is used to acquire a set of first temporal simulated images of a three-dimensional model of the patient’s stomach that is pre-constructed within a preset time period, taken simultaneously from multiple perspectives.

[0041] The first identification unit is used to identify a second set of time-series simulated images taken from the plurality of first time-series simulated image sets along the first target viewpoint targeting the first target mucosa of the stomach, and a third set of time-series simulated images taken from the second target viewpoint targeting the second target mucosa of the stomach, wherein the first target viewpoint is a side viewpoint and the second target viewpoint is a top viewpoint.

[0042] The first determining unit is used to determine the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a second preset direction based on the second time-series simulated image set.

[0043] The second determining unit is used to determine the width change rate, lateral movement speed and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set, wherein the target region is the bright region corresponding to the third time-series simulated image after being converted into the HSV color space.

[0044] The first quantification unit is used to quantify the softness of the gastric mucosa based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate.

[0045] In one possible implementation of this application, the second determining unit is specifically used for:

[0046] The RGB color space of all images in the third time-series simulated image set is converted to the HSV color space to obtain the fourth time-series simulated image set;

[0047] Two time-series simulation images are selected from the fourth time-series simulation image set to obtain the third target time-series simulation image and the third time-series time corresponding to the third target time-series simulation image, and the fourth time-series simulation image and the fourth time-series time corresponding to the fourth target time-series simulation image, wherein the third time-series time is the same as the first time-series time, and the fourth time-series time is the same as the second time-series time;

[0048] Based on a pre-trained highlight region target detection model, the H channels of the third target time-series simulated image and the fourth target time-series simulated image are identified respectively to obtain the coordinates of the highlight regions of the third target time-series simulated image and the fourth target time-series simulated image;

[0049] Based on the coordinates of the highlighted regions in the third target time-series simulation image and the fourth target time-series simulation image, the width change rate and lateral movement speed of the highlighted regions are determined.

[0050] Based on the average brightness of the bright region and the average brightness of the non-bright region in the third target time-series simulation image and the fourth target time-series simulation image, as well as the third time-series time and the fourth time-series time, the brightness change rate of the bright region is determined.

[0051] In one possible implementation of this application, the first determining unit is specifically used for:

[0052] Based on the second time-series simulated image set, a reference plane for the first target mucosa is determined, wherein the reference plane is the plane corresponding to the flat position of the first target mucosa;

[0053] Two time-series simulation images are selected from the second time-series simulation image set to obtain the first target time-series simulation image and the first time-series time corresponding to the first target time-series simulation image, and the second target time-series simulation image and the second time-series time corresponding to the second target time-series simulation image;

[0054] Based on the reference plane and the first target time-series simulation image, determine the first height data of the first target mucosa bulging at the first time-series moment;

[0055] Based on the reference plane and the second target time-series simulation image, determine the second height data of the first target mucosa bulging at the second time-series moment;

[0056] Based on the first height data, the second height data, the first time step, and the second time step, the height change rate of the first target mucosa along the first preset direction is determined.

[0057] In one possible implementation of this application, the first determining unit is further configured to:

[0058] Based on the first target time-series simulation image and the second time-series simulation image, determine the lateral movement distance of the first target mucosa along the second preset direction;

[0059] Based on the lateral movement distance, the first time step, and the second time step, the lateral movement speed of the first target mucosa along the second preset direction is determined.

[0060] In one possible implementation of this application, the first quantization unit is specifically used for:

[0061] The height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate are fitted to obtain fitting parameters.

[0062] The softness of the gastric mucosa is quantified based on the fitting parameters and the preset threshold.

[0063] In one possible implementation of this application, the first acquisition unit specifically includes:

[0064] The second acquisition unit is used to acquire an initial set of endoscopic images of the patient's stomach within a preset time period;

[0065] The first screening unit is used to screen the initial endoscopic image set based on a pre-trained observation distance recognition model to obtain a second endoscopic image set that meets the preset distance requirements.

[0066] The first construction unit is used to construct a three-dimensional model of the stomach based on the second endoscopic image set;

[0067] The third acquisition unit is used to acquire a set of multiple first time-series simulated images of the three-dimensional model taken simultaneously from multiple viewpoints.

[0068] In one possible implementation of this application, the first building unit is specifically used for:

[0069] Obtain the similarity of each second endoscope image in the second endoscope image set;

[0070] Based on the similarity of each second endoscopic image and a preset similarity threshold, a target endoscopic image that meets the preset similarity requirement is determined.

[0071] A three-dimensional model of the stomach is constructed based on the target endoscopic image.

[0072] On the other hand, this application also provides a computer device, the computer device comprising:

[0073] One or more processors;

[0074] Memory; and

[0075] 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 method for quantifying the gastric mucosal softness.

[0076] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the method for quantifying the softness of the gastric mucosa.

[0077] This application embodiment acquires multiple sets of first temporal simulated images of a pre-constructed 3D model of a patient's stomach taken simultaneously from multiple perspectives within a preset time period; identifies a second set of temporal simulated images taken from a first target perspective of the stomach's first target mucosa, and a third set of temporal simulated images taken from the second target perspective of the stomach's second target mucosa. The first target perspective is a side view, and the second target perspective is a top view. Based on the second set of temporal simulated images, the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction are determined. Based on the third set of temporal simulated images, the width change rate, lateral movement rate, and brightness change rate of the target region in the second target mucosa are determined. The target region is the bright area corresponding to the third temporal simulated image after conversion to the HSV color space. Based on the height change rate, the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction, the width change rate, lateral movement rate, and brightness change rate of the target region, the softness of the gastric mucosa is quantified. It enables efficient and accurate quantification of the softness of the gastric mucosa, assisting endoscopists in assessing the health status of the gastric mucosa and aiding in disease diagnosis. Attached Figure Description

[0078] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0079] Figure 1 This is a schematic diagram of a scenario for the gastric mucosal softness quantification system provided in an embodiment of this application;

[0080] Figure 2 This is a schematic flowchart of an embodiment of the method for quantifying the softness of the gastric mucosa provided in this application.

[0081] Figure 3 This is a schematic flowchart of an embodiment of the change of the first target mucosal elevation over time provided in this application;

[0082] Figure 4 This is a schematic flowchart of an embodiment of the change in brightness of the second target mucosal bulge over time, provided in this application.

[0083] Figure 5 This is a schematic diagram of an embodiment of the gastric mucosal softness quantification device provided in this application.

[0084] Figure 6 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0085] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0086] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0087] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0088] This application provides a method, apparatus, and related equipment for quantifying the softness of the gastric mucosa, which will be described in detail below.

[0089] like Figure 1 As shown, Figure 1 This is a schematic diagram of a gastric mucosal softness quantification system provided in an embodiment of this application. The gastric mucosal softness quantification system may include a computer device 100, which integrates a gastric mucosal softness quantification device, such as... Figure 1 Computer equipment 100.

[0090] In this embodiment, the computer device 100 is mainly used to acquire multiple sets of first temporal simulated images of a pre-constructed three-dimensional model of a patient's stomach taken simultaneously from multiple perspectives within a preset time period; identify a second set of second temporal simulated images taken from a first target perspective of the stomach's first target mucosa within the multiple sets of first temporal simulated images, and a third set of third temporal simulated images taken from a second target perspective of the stomach's second target mucosa, wherein the first target perspective is a side view and the second target perspective is a top view; based on the second temporal simulated image set, determine the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction; based on the third temporal simulated image set, determine the width change rate, lateral movement rate, and brightness change rate of the target area in the second target mucosa, wherein the target area is the bright area corresponding to the third temporal simulated image after conversion to the HSV color space; and quantify the softness of the gastric mucosa based on the height change rate, the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction, the width change rate, the lateral movement rate, and the brightness change rate of the target area.

[0091] In this embodiment, the computer device 100 can be a terminal or a server. When the computer device 100 is a server, it can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, computers, network hosts, single network servers, multiple sets of network servers, or cloud servers constructed from multiple servers. The cloud server is constructed from a large number of computers or network servers based on cloud computing.

[0092] It is understood that when the computer device 100 in this embodiment is a terminal, the terminal used can be a device that includes both receiving and transmitting hardware, that is, a device with receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices, which have a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may also be one of a mobile phone, tablet computer, laptop computer, medical auxiliary instrument, etc.

[0093] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario for the solution in this application and is not intended to limit the application scenario of the solution in this application. Other application environments may include more than one. Figure 1 The number of computer devices shown is more or less, for example Figure 1Only one computer device is shown in the diagram. It is understood that the gastric mucosal softness quantification system may also include one or more other computer devices, which are not specified here.

[0094] In addition, such as Figure 1 As shown, the gastric mucosal softness quantification system may also include a memory 200 for storing data, such as storing a first time-series simulated image set of the patient and gastric mucosal softness quantification data, such as gastric mucosal softness quantification data during the operation of the gastric mucosal softness quantification system.

[0095] It should be noted that, Figure 1 The schematic diagram of the gastric mucosal softness quantification system shown is merely an example. The gastric mucosal softness quantification system and scenarios described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of the gastric mucosal softness quantification system and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0096] Next, we will introduce the method for quantifying the softness of the gastric mucosa provided in the embodiments of this application.

[0097] In this embodiment of the method for quantifying gastric mucosal softness, a gastric mucosal softness quantification device is used as the execution subject. For simplicity and ease of description, this execution subject will be omitted in subsequent method embodiments. The gastric mucosal softness quantification device is applied to a computer device. The method includes: acquiring multiple first temporal simulated image sets taken simultaneously from multiple perspectives along a pre-constructed three-dimensional model of the patient's stomach within a preset time period; identifying a second temporal simulated image set taken from a first target perspective at a first target mucosa of the stomach, and a third temporal simulated image set taken from the multiple first temporal simulated image sets at a second target perspective at a second target mucosa of the stomach, wherein the first target perspective is a side view. The second target perspective is a top-down view. Based on the second time-series simulated image set, the height change rate of the first target mucosa along the first preset direction and the lateral movement speed of the first target mucosa along the direction perpendicular to the first preset direction are determined. Based on the third time-series simulated image set, the width change rate, lateral movement speed, and brightness change rate of the target region in the second target mucosa are determined. The target region is the bright area corresponding to the third time-series simulated image after conversion to the HSV color space. Based on the height change rate, the lateral movement speed of the first target mucosa along the direction perpendicular to the first preset direction, the width change rate, lateral movement speed, and brightness change rate of the target region, the softness of the gastric mucosa is quantified.

[0098] Please see Figures 2 to 6 , Figure 2This is a schematic flowchart of an embodiment of the gastric mucosal softness quantification method provided in this application. The gastric mucosal softness quantification method includes:

[0099] 201. Obtain a set of first-time-series simulated images of a pre-constructed 3D model of the patient's stomach taken simultaneously from multiple perspectives within a preset time period;

[0100] The multiple perspectives can include side views, top views, and other perspectives. Other perspectives can include top-down tilted views and bottom-up tilted views. The preset time period can be set according to actual needs; for example, it can be set to 10 seconds, 30 seconds, 3 minutes, or 10 minutes. Alternatively, a preset time period can be selected from a specific time frame, such as a 30-second time-series image set within a 10-minute period.

[0101] In some embodiments of this application, the step of obtaining multiple first time-series simulated image sets of a pre-constructed three-dimensional model of a patient's stomach taken simultaneously from multiple perspectives within a preset time period includes: obtaining an initial endoscopic image set of the patient's stomach within a preset time period; filtering the initial endoscopic image set based on a pre-trained observation distance recognition model to obtain a second endoscopic image set that meets preset distance requirements, wherein the network structure of the observation distance recognition model is preferably ResNet50, and the dataset used in its training process is gastric white light images, labeled as near distance, medium distance, and far distance; constructing a three-dimensional model of the stomach based on the second endoscopic image set; and obtaining multiple first time-series simulated image sets of the three-dimensional model taken simultaneously from multiple perspectives. Specifically, this may include, but is not limited to, using computer-preset recording software to adjust the image to multiple perspectives for simultaneous shooting, thereby obtaining multiple first time-series simulated image sets.

[0102] In some embodiments of this application, constructing a three-dimensional model of the stomach based on the second endoscopic image set includes: obtaining the similarity of each second endoscopic image in the second endoscopic image set; specifically, the image similarity can be calculated using the Euclidean distance between images, and the specific calculation method can be based on publicly available methods, which will not be elaborated here; determining a target endoscopic image that meets the preset similarity requirement based on the similarity of each second endoscopic image and a preset similarity threshold; the similarity threshold can be set according to actual needs, and in this embodiment of the application, the similarity threshold is preferably set to 90%. The similarity requirement is that the similarity of each second endoscopic image must be greater than the preset similarity threshold. For example, if the similarity of the second endoscopic image is greater than 90%, then it meets the preset similarity requirement; and constructing a three-dimensional model of the stomach based on the target endoscopic image.

[0103] 202. Identify a set of second time-series simulated images taken from a first target perspective at the first target mucosa of the stomach, and a set of third time-series simulated images taken from a second target perspective at the second target mucosa of the stomach, wherein the first target perspective is a side view and the second target perspective is a top view.

[0104] In this embodiment, a preset viewing angle recognition model can be used to identify a second set of simulated images taken from a first target viewpoint at the first target mucosa of the stomach, and a third set of simulated images taken from a second target viewpoint at the second target mucosa of the stomach, within the plurality of first temporal simulated image sets. The network structure of this viewing angle recognition model is preferably ResNet50, and the dataset used in its training process consists of gastric white light images labeled as other viewpoints, side viewpoints, and top viewpoints.

[0105] 203. Based on the second time-series simulated image set, determine the height change rate of the first target mucosa along the first preset direction and the lateral movement rate of the first target mucosa along the second preset direction;

[0106] Among them, combined with the following Figure 3 The first preset direction is the upward bulge direction of the first target mucosa; the second preset direction is the forward direction perpendicular to the first preset direction. It can be understood that the first preset direction and the second preset direction are the two decomposition directions when the first target mucosa peristalsis.

[0107] Wherein, the height change rate is the distance the first target mucosa moves longitudinally along the first preset direction per unit time; while the lateral movement rate is the distance the first target mucosa moves laterally along the direction perpendicular to the first preset direction per unit time.

[0108] In some embodiments of this application, determining the height change rate of the first target mucosa along a first preset direction based on the second time-series simulated image set includes: determining a reference plane of the first target mucosa based on the second time-series simulated image set, wherein the reference plane is the plane corresponding to the flat position of the first target mucosa. Specifically, all images in the second time-series simulated image set can be compared and analyzed to mark the reference plane of the first target mucosa; selecting two time-series simulated images from the second time-series simulated image set to obtain the first time-series simulated image of the first target and the first time-series simulated image corresponding to the first time-series simulated image, and the second time-series simulated image of the second target and the second time-series simulated image corresponding to the second time-series simulated image. The first and second time-series simulated images can be any two time-series simulated images selected from the second time-series simulated image set. However, for ease of observation and calculation, two images of the first target mucosa within the same peristaltic cycle can be selected. Generally, the first time-series simulated image is earlier than the second time-series simulated image. For details, please refer to the following... Figure 3 For example, the first time series time corresponds to t0 in the figure below, and the second time series time corresponds to t1 in the figure below; based on the reference plane and the first target time series simulation image, the first height data of the bulge of the first target mucosa at the first time series time is determined. Specifically, the first height data of the bulge of the first target mucosa at the first time series time can be obtained through preset distance measurement software or program. This first height data is... Figure 3 h0 in the reference plane; based on the reference plane and the second target time-series simulation image, determine the second height data of the bulge of the first target mucosa at the second time-series moment. For example, this second height data corresponds to the following... Figure 3 h1 in the first time series; based on the first height data, the second height data, the first time series time, and the second time series time, determine the height change rate of the first target mucosa along the first preset direction.

[0109] For easier understanding, please refer to the following. Figure 3 At time t0, the height of the first target mucosa along the first preset direction is h0, and at time t1, the height of the first target mucosa along the first preset direction changes from h0 at time t0 to h1. Therefore, the rate of change of the height of the first target mucosa along the first preset direction during the time period from t0 to t1 can be calculated according to the following formula:

[0110]

[0111] In some embodiments of this application, determining the lateral movement speed of the first target mucosa along a second preset direction based on the second time-series simulated image set includes: selecting two time-series simulated images from the second time-series simulated image set to obtain a first time-series simulated image of the first target and a corresponding first time-series simulated image, and a second time-series simulated image of the second target and a corresponding second time-series simulated image. The first and second target time-series simulated images can be any two time-series simulated images selected from the second time-series simulated image set. However, for ease of observation and calculation, two images of the first target mucosa within the same peristaltic cycle are preferred. Generally, the first time-series simulated image is earlier than the second time-series simulated image. For details, please refer to the following... Figure 3 For example, the first time step corresponds to t0 in the figure below, and the second time step corresponds to t1 in the figure below; obtain the lateral movement distance of the first target mucosa along the second preset direction. Specifically, this can be obtained through preset distance measurement software or program, such as the lateral movement distance of the first target mucosa at the first time step from the distance of the first target mucosa at the second time step, as follows. Figure 3 d in h Based on the lateral movement distance of the first target mucosa along the second preset direction, the first time step, and the second time step, the lateral movement speed of the first target mucosa along the second preset direction is determined.

[0112] For example, during the time period from t0 to t1, the lateral movement distance of the first target mucosa along the second preset direction is d. h Therefore, the lateral movement speed of the first target mucosa along the second preset direction during the time period from t0 to t1 can be calculated according to the following formula:

[0113]

[0114] 204. Based on the third time-series simulated image set, determine the width change rate, lateral movement speed and brightness change rate of the target region in the second target mucosa. The target region is the bright region corresponding to the third time-series simulated image after conversion to HSV color space.

[0115] Among them, the width change rate is the amount of change in the width of the target area per unit time, the lateral movement speed is the distance the target area moves laterally per unit time, and the brightness change rate is the amount of change in the brightness of the target area per unit time.

[0116] In some embodiments of this application, determining the width change rate, lateral movement speed, and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set includes: converting the RGB color space of all images in the third time-series simulated image set to the HSV color space to obtain a fourth time-series simulated image set; selecting two time-series simulated images from the fourth time-series simulated image set to obtain the third time-series simulated image of the third target and the third time-series simulated image corresponding to the third target time-series simulated image, and the fourth time-series simulated image of the fourth target and the fourth time-series simulated image corresponding to the fourth target time-series simulated image, wherein the third time-series simulated image is the same as the first time-series simulated image, and the fourth time-series simulated image is the same as the second time-series simulated image; and performing the detection of the target in the third target time-series simulated image and the fourth target time-series simulated image based on a pre-trained high-brightness region target detection model. The H channel of the image is used for identification to obtain the coordinates of the highlighted regions in the third and fourth target time-series simulated images. The network structure of the highlighted region target detection model is preferably YOLOv3, and the training dataset used is gastric white light images. The labels are created by professional endoscopists who mark the highlighted regions with rectangular boxes. Based on the coordinates of the highlighted regions in the third and fourth target time-series simulated images, the width change rate and lateral movement speed of the highlighted regions are determined. Based on the average brightness of the bright regions and the average brightness of the non-bright regions in the third and fourth target time-series simulated images, as well as the third and fourth time-series times, the brightness change rate of the highlighted regions is determined. The non-bright regions are the areas in the third and fourth target time-series simulated images other than the bright regions.

[0117] In one specific implementation, the following is true: Figure 4 As shown, based on the coordinates of the highlighted regions in the third target time-series simulation image and the fourth target time-series simulation image, the width change rate and lateral movement speed of the highlighted regions are determined, including determining the coordinates of the highlighted regions in the third target time-series simulation image as (x...). 00 y 00 x 01 y 01 Then calculate the width w0 of the highlighted area at this time, w0 = x 01 -x 00 Calculate the center line coordinates of the highlighted area at this time: x0 = (x 01 +x 00 ) / 2; The coordinates of the highlighted area in the fourth target time-series simulation image are (x) / 2; 10 y 10 x 11 y 11Then calculate the width w0 of the highlighted area at this time, w0 = x 11 -x 10 Calculate the center line coordinates of the highlighted area at this time: x1 = (xx 11 +x 10 If the ratio is 1 / 2, then the calculation method for the rate of change of the width of the highlighted area is as follows;

[0118]

[0119] The horizontal movement speed of the highlighted area is calculated as follows:

[0120]

[0121] In one specific implementation, the brightness change rate of the bright region is determined based on the average brightness of the bright region and the average brightness of the non-bright region in the third target time-series simulated image and the fourth target time-series simulated image, as well as the third time-series time and the fourth time-series time. This includes: calculating the average brightness l0 of the bright region at time t0, and the average brightness l of other regions in the top view excluding the bright region. 01 Calculate the brightness contrast ratio: k0 = l0 / l 01 Calculate the average brightness l1 of the highlighted area at time t1, and the average brightness l of the other areas in the top view excluding the highlighted area. 11 Calculate the brightness contrast ratio: k1 = l1 / l 11 The calculation method for the brightness change rate of the highlighted area is as follows:

[0122]

[0123] 205. The softness of the gastric mucosa is quantified based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate.

[0124] In some embodiments of this application, quantifying the mucosal softness of the stomach based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate includes: fitting the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate to obtain fitting parameters; and quantifying the mucosal softness of the stomach based on the fitting parameters and a preset threshold.

[0125] In some embodiments of this application, the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target region, the lateral movement speed, and the brightness change rate are fitted to obtain fitting parameters. Specifically, a gradient boosting tree can be used for feature fitting, as shown in the following formula:

[0126]

[0127] Among them, v h It is the velocity of height change of the first target mucosa along the first preset direction, v d It is the lateral movement speed of the first target mucosa along the second preset direction, v w It is the rate of change of the width of the highlighted area, v ld It is the lateral movement speed of the highlighted area, v l It represents the rate of change of brightness in the bright area. α1, α2, α3, and α4 are obtained by training machine learning models such as decision trees and random forests.

[0128] In some embodiments of this application, the preset thresholds include a first threshold, a second threshold, and a third threshold. Based on the fitting parameters and the preset thresholds, the softness of the gastric mucosa is quantified, including: if the fitting parameters are less than or equal to the first threshold, the gastric mucosa is determined to be hard; if the fitting parameters are greater than the first threshold and less than or equal to the second threshold, the gastric mucosa is determined to be semi-soft; if the fitting parameters are greater than the second threshold and less than or equal to the third threshold, the gastric mucosa is determined to be soft. The first, second, and third thresholds can be adjusted according to actual needs. Preferably, the first, second, and third thresholds are 0.2, 0.5, and 1, respectively.

[0129] This application embodiment acquires multiple sets of first temporal simulated images of a pre-constructed 3D model of a patient's stomach taken simultaneously from multiple perspectives within a preset time period; identifies a second set of temporal simulated images taken from a first target perspective of the stomach's first target mucosa, and a third set of temporal simulated images taken from the second target perspective of the stomach's second target mucosa. The first target perspective is a side view, and the second target perspective is a top view. Based on the second set of temporal simulated images, the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction are determined. Based on the third set of temporal simulated images, the width change rate, lateral movement rate, and brightness change rate of the target region in the second target mucosa are determined. The target region is the bright area corresponding to the third temporal simulated image after conversion to the HSV color space. Based on the height change rate, the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction, the width change rate, lateral movement rate, and brightness change rate of the target region, the softness of the gastric mucosa is quantified. It enables efficient and accurate quantification of the softness of the gastric mucosa, assisting endoscopists in assessing the health status of the gastric mucosa and aiding in disease diagnosis.

[0130] To better implement the gastric mucosal softness quantification method in the embodiments of this application, based on the gastric mucosal softness quantification method, the embodiments of this application also provide a gastric mucosal softness quantification device, such as... Figure 5 As shown, the gastric mucosal softness quantification device 500 includes:

[0131] The first acquisition unit 501 is used to acquire a set of multiple first temporal simulated images of a three-dimensional model of the patient’s stomach that is pre-constructed within a preset time period, taken simultaneously from multiple perspectives.

[0132] The first identification unit 502 is used to identify a second time-series simulated image set taken along a first target viewpoint targeting the first target mucosa of the stomach from the plurality of first time-series simulated image sets, and a third time-series simulated image set taken along a second target viewpoint targeting the second target mucosa of the stomach from the second target viewpoint, wherein the first target viewpoint is a side viewpoint and the second target viewpoint is a top viewpoint.

[0133] The first determining unit 503 is used to determine the height change rate of the first target mucosa along the first preset direction and the lateral movement rate of the first target mucosa along the second preset direction based on the second time-series simulated image set.

[0134] The second determining unit 504 is used to determine the width change rate, lateral movement speed and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set, wherein the target region is the bright region corresponding to the third time-series simulated image after being converted into the HSV color space.

[0135] The first quantification unit 505 is used to quantify the softness of the gastric mucosa based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate.

[0136] In some embodiments of this application, the second determining unit 504 is specifically used for:

[0137] The RGB color space of all images in the third time-series simulated image set is converted to the HSV color space to obtain the fourth time-series simulated image set;

[0138] Two time-series simulation images are selected from the fourth time-series simulation image set to obtain the third target time-series simulation image and the third time-series time corresponding to the third target time-series simulation image, and the fourth time-series simulation image and the fourth time-series time corresponding to the fourth target time-series simulation image, wherein the third time-series time is the same as the first time-series time, and the fourth time-series time is the same as the second time-series time;

[0139] Based on a pre-trained highlight region target detection model, the H channels of the third target time-series simulated image and the fourth target time-series simulated image are identified respectively to obtain the coordinates of the highlight regions of the third target time-series simulated image and the fourth target time-series simulated image;

[0140] Based on the coordinates of the highlighted regions in the third target time-series simulation image and the fourth target time-series simulation image, the width change rate and lateral movement speed of the highlighted regions are determined.

[0141] Based on the average brightness of the bright region and the average brightness of the non-bright region in the third target time-series simulation image and the fourth target time-series simulation image, as well as the third time-series time and the fourth time-series time, the brightness change rate of the bright region is determined.

[0142] In some embodiments of this application, the first determining unit 503 is specifically used for:

[0143] Based on the second time-series simulated image set, a reference plane for the first target mucosa is determined, wherein the reference plane is the plane corresponding to the flat position of the first target mucosa;

[0144] Two time-series simulation images are selected from the second time-series simulation image set to obtain the first target time-series simulation image and the first time-series time corresponding to the first target time-series simulation image, and the second target time-series simulation image and the second time-series time corresponding to the second target time-series simulation image;

[0145] Based on the reference plane and the first target time-series simulation image, determine the first height data of the first target mucosa bulging at the first time-series moment;

[0146] Based on the reference plane and the second target time-series simulation image, determine the second height data of the first target mucosa bulging at the second time-series moment;

[0147] Based on the first height data, the second height data, the first time step, and the second time step, the height change rate of the first target mucosa along the first preset direction is determined.

[0148] In some embodiments of this application, the first determining unit 503 is further configured to:

[0149] Based on the first target time-series simulation image and the second time-series simulation image, determine the lateral movement distance of the first target mucosa along the second preset direction;

[0150] Based on the lateral movement distance, the first time step, and the second time step, the lateral movement speed of the first target mucosa along the second preset direction is determined.

[0151] In some embodiments of this application, the first quantization unit 505 is specifically used for:

[0152] The height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate are fitted to obtain fitting parameters.

[0153] The softness of the gastric mucosa is quantified based on the fitting parameters and the preset threshold.

[0154] In some embodiments of this application, the first acquisition unit 501 specifically includes:

[0155] The second acquisition unit is used to acquire an initial set of endoscopic images of the patient's stomach within a preset time period;

[0156] The first screening unit is used to screen the initial endoscopic image set based on a pre-trained observation distance recognition model to obtain a second endoscopic image set that meets the preset distance requirements.

[0157] The first construction unit is used to construct a three-dimensional model of the stomach based on the second endoscopic image set;

[0158] The third acquisition unit is used to acquire a set of multiple first time-series simulated images of the three-dimensional model taken simultaneously from multiple viewpoints.

[0159] In some embodiments of this application, the first building unit is specifically used for:

[0160] Obtain the similarity of each second endoscope image in the second endoscope image set;

[0161] Based on the similarity of each second endoscopic image and a preset similarity threshold, a target endoscopic image that meets the preset similarity requirement is determined.

[0162] A three-dimensional model of the stomach is constructed based on the target endoscopic image.

[0163] This embodiment of the application uses a first acquisition unit 501 to acquire multiple sets of first temporal simulated images of a pre-constructed three-dimensional model of a patient's stomach taken simultaneously from multiple viewpoints within a preset time period; a first identification unit 502 to identify a second set of temporal simulated images taken from a first target viewpoint of the stomach at a first target mucosa, and a third set of temporal simulated images taken from a second target viewpoint of the stomach at a second target mucosa, within the multiple sets of first temporal simulated images, wherein the first target viewpoint is a side viewpoint and the second target viewpoint is a top viewpoint; and a first determination unit 503 to determine, based on the second temporal simulated image set, the first target mucosa along a first preset time period. The system includes a height change rate and a lateral movement rate of the first target mucosa along a second preset direction; a second determining unit 504, used to determine the width change rate, lateral movement rate, and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set, wherein the target region is the bright area corresponding to the third time-series simulated image after conversion to HSV color space; and a first quantization unit 505, used to quantify the mucosal softness of the stomach based on the height change rate, the lateral movement rate of the first target mucosa along the second preset direction, the width change rate, the lateral movement rate, and the brightness change rate of the target region. This achieves efficient and accurate quantification of the mucosal softness of the stomach, assisting endoscopists in assessing the health status of the gastric mucosa and aiding in disease diagnosis.

[0164] In addition to the methods and apparatus for quantifying gastric mucosal softness described above, embodiments of this application also provide a computer device that integrates any of the gastric mucosal softness quantification devices provided in the embodiments of this application. The computer device includes:

[0165] One or more processors;

[0166] Memory; and

[0167] One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to perform operations of any of the methods described in any of the embodiments of the above-described methods for quantifying gastric mucosal softness.

[0168] This application also provides a computer device that integrates any of the gastric mucosal softness quantification devices provided in this application. For example... Figure 6 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0169] The computer device may include components such as a processor 601 with one or more processing cores, a storage unit 602 with one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will understand that... Figure 6 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0170] The processor 601 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the storage unit 602, and by calling data stored in the storage unit 602, thereby providing overall monitoring of the computer device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601.

[0171] Storage unit 602 can be used to store software programs and modules. Processor 601 executes various functional applications and data processing by running the software programs and modules stored in storage unit 602. Storage unit 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, storage unit 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage unit 602 may also include a memory controller to provide processor 601 with access to storage unit 602.

[0172] The computer device also includes a power supply 603 that supplies power to the various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0173] The computer device may also include an input unit 604, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0174] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processor 601 in the computer device loads the executable files corresponding to the processes of one or more applications into the storage unit 602 according to the following instructions, and the processor 601 runs the applications stored in the storage unit 602 to realize various functions, as follows:

[0175] The system acquires multiple sets of first-time-series simulated images of a pre-constructed 3D model of a patient's stomach taken simultaneously from multiple viewpoints within a preset time period. It then identifies a second-time-series simulated image set taken from a first target viewpoint of the stomach's first target mucosa, and a third-time-series simulated image set taken from the second target viewpoint of the stomach's second target mucosa. The first target viewpoint is a side view, and the second target viewpoint is a top view. Based on the second-time-series simulated image set, it determines the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction. Based on the third-time-series simulated image set, it determines the width change rate, lateral movement rate, and brightness change rate of the target region within the second target mucosa. The target region is the highlighted area corresponding to the third-time-series simulated image after conversion to the HSV color space. Finally, it quantifies the softness of the gastric mucosa based on the height change rate, the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction, and the width change rate, lateral movement rate, and brightness change rate of the target region.

[0176] The embodiments of this application enable efficient and accurate quantification of the softness of the gastric mucosa, assisting endoscopists in assessing the health status of the gastric mucosa and aiding in disease diagnosis.

[0177] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. The computer-readable storage medium stores multiple instructions, which can be loaded by a processor to execute the steps in any of the gastric mucosal softness quantification methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0178] The system acquires multiple sets of first-time-series simulated images of a pre-constructed 3D model of a patient's stomach taken simultaneously from multiple viewpoints within a preset time period. It then identifies a second-time-series simulated image set taken from a first target viewpoint of the stomach's first target mucosa, and a third-time-series simulated image set taken from the second target viewpoint of the stomach's second target mucosa. The first target viewpoint is a side view, and the second target viewpoint is a top view. Based on the second-time-series simulated image set, it determines the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction. Based on the third-time-series simulated image set, it determines the width change rate, lateral movement rate, and brightness change rate of the target region within the second target mucosa. The target region is the highlighted area corresponding to the third-time-series simulated image after conversion to the HSV color space. Finally, it quantifies the softness of the gastric mucosa based on the height change rate, the lateral movement rate of the first target mucosa along a direction perpendicular to the first preset direction, and the width change rate, lateral movement rate, and brightness change rate of the target region.

[0179] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0180] The above provides a detailed description of a method, apparatus, and related equipment for quantifying gastric mucosal softness according to embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for quantifying the softness of the gastric mucosa, characterized in that, The method includes: Acquire a set of first-time-series simulated images of a pre-constructed 3D model of the patient's stomach taken simultaneously from multiple perspectives within a preset time period; Identify a second set of time-series simulated images taken along a first target viewpoint targeting the first target mucosa of the stomach from the plurality of first time-series simulated image sets, and a third set of time-series simulated images taken along a second target viewpoint targeting the second target mucosa of the stomach from the second target viewpoint, wherein the first target viewpoint is a side viewpoint and the second target viewpoint is a top viewpoint; Based on the second time-series simulated image set, the height change rate of the first target mucosa along the first preset direction and the lateral movement rate of the first target mucosa along the second preset direction are determined. Based on the third time-series simulated image set, the width change rate, lateral movement speed and brightness change rate of the target region in the second target mucosa are determined, and the target region is the bright region corresponding to the third time-series simulated image after being converted into the HSV color space. The mucosal softness of the stomach is quantified based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate. The quantification of the gastric mucosal softness based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target region, the lateral movement speed, and the brightness change rate includes: The height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate are fitted to obtain fitting parameters. The softness of the gastric mucosa is quantified based on the fitting parameters and the preset threshold.

2. The method for quantifying the softness of the gastric mucosa according to claim 1, characterized in that, The step of determining the height change rate of the first target mucosa along a first preset direction based on the second time-series simulated image set includes: Based on the second time-series simulated image set, a reference plane for the first target mucosa is determined, wherein the reference plane is the plane corresponding to the flat position of the first target mucosa; Two time-series simulation images are selected from the second time-series simulation image set to obtain the first target time-series simulation image and the first time-series time corresponding to the first target time-series simulation image, and the second target time-series simulation image and the second time-series time corresponding to the second target time-series simulation image; Based on the reference plane and the first target time-series simulation image, determine the first height data of the first target mucosa bulging at the first time-series moment; Based on the reference plane and the second target time-series simulation image, determine the second height data of the first target mucosa bulging at the second time-series moment; Based on the first height data, the second height data, the first time step, and the second time step, the height change rate of the first target mucosa along the first preset direction is determined.

3. The method for quantifying the softness of the gastric mucosa according to claim 2, characterized in that, Determining the lateral movement speed of the first target mucosa along a second preset direction based on the second time-series simulated image set includes: Based on the first target time-series simulation image and the second time-series simulation image, determine the lateral movement distance of the first target mucosa along the second preset direction; Based on the lateral movement distance, the first time step, and the second time step, the lateral movement speed of the first target mucosa along the second preset direction is determined.

4. The method for quantifying the softness of the gastric mucosa according to claim 3, characterized in that, The step of determining the width change rate, lateral movement speed, and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set includes: The RGB color space of all images in the third time-series simulated image set is converted to the HSV color space to obtain the fourth time-series simulated image set; Two time-series simulation images are selected from the fourth time-series simulation image set to obtain the third target time-series simulation image and the third time-series time corresponding to the third target time-series simulation image, and the fourth time-series simulation image and the fourth time-series time corresponding to the fourth target time-series simulation image, wherein the third time-series time is the same as the first time-series time, and the fourth time-series time is the same as the second time-series time; Based on a pre-trained highlight region target detection model, the H channels of the third target time-series simulated image and the fourth target time-series simulated image are identified respectively to obtain the coordinates of the highlight regions of the third target time-series simulated image and the fourth target time-series simulated image; Based on the coordinates of the highlighted regions in the third target time-series simulation image and the fourth target time-series simulation image, the width change rate and lateral movement speed of the highlighted regions are determined. Based on the average brightness of the bright region and the average brightness of the non-bright region in the third target time-series simulation image and the fourth target time-series simulation image, as well as the third time-series time and the fourth time-series time, the brightness change rate of the bright region is determined.

5. The method for quantifying the softness of the gastric mucosa according to claim 1, characterized in that, The acquisition of a set of multiple first-time-series simulated images of a pre-constructed 3D model of the patient's stomach taken simultaneously from multiple perspectives within a preset time period includes: Acquire the initial set of endoscopic images of the patient's stomach within a preset time period; Based on a pre-trained observation distance recognition model, the initial endoscopic image set is filtered to obtain a second endoscopic image set that meets the preset distance requirements; Based on the second endoscopic image set, a three-dimensional model of the stomach is constructed; Obtain a set of multiple first-time-series simulated images of the three-dimensional model taken simultaneously from multiple viewpoints.

6. The method for quantifying the softness of the gastric mucosa according to claim 5, characterized in that, Based on the second endoscopic image set, a three-dimensional model of the stomach is constructed, including: Obtain the similarity of each second endoscope image in the second endoscope image set; Based on the similarity of each second endoscopic image and a preset similarity threshold, a target endoscopic image that meets the preset similarity requirement is determined. A three-dimensional model of the stomach is constructed based on the target endoscopic image.

7. A device for quantifying the softness of gastric mucosa, characterized in that, The device includes: The first acquisition unit is used to acquire a set of first temporal simulated images of a three-dimensional model of the patient’s stomach that is pre-constructed within a preset time period, taken simultaneously from multiple perspectives. The first identification unit is used to identify a second set of time-series simulated images taken from the plurality of first time-series simulated image sets along the first target viewpoint targeting the first target mucosa of the stomach, and a third set of time-series simulated images taken from the second target viewpoint targeting the second target mucosa of the stomach, wherein the first target viewpoint is a side viewpoint and the second target viewpoint is a top viewpoint. The first determining unit is used to determine the height change rate of the first target mucosa along a first preset direction and the lateral movement rate of the first target mucosa along a second preset direction based on the second time-series simulated image set. The second determining unit is used to determine the width change rate, lateral movement speed and brightness change rate of the target region in the second target mucosa based on the third time-series simulated image set, wherein the target region is the bright region corresponding to the third time-series simulated image after being converted into the HSV color space. The first quantification unit is used to quantify the softness of the gastric mucosa based on the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate. The first quantization unit is further configured to fit the height change rate, the lateral movement speed of the first target mucosa along the second preset direction, the width change rate of the target area, the lateral movement speed, and the brightness change rate to obtain fitting parameters; and to quantify the mucosal softness of the stomach based on the fitting parameters and a preset threshold.

8. A computer device, characterized in that, The computer device includes: One or more processors; 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 method for quantifying the gastric mucosal softness as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to perform the steps in the method for quantifying the softness of the gastric mucosa as described in any one of claims 1 to 6.

Images