Dimension estimation method, device and equipment of alimentary canal polyp and storage medium

Abstract

The invention provides a size estimation method, a size estimation device and size estimation equipment of alimentary canal polyp and a computer storage medium. The size estimation method comprises the following steps: acquiring an alimentary canal polyp image acquired by a capsule endoscope; mark information in the alimentary canal polyp image is obtained, and the mark information comprises polyp boundary point coordinates; determining the distance from the polyp boundary points to the view boundary and the angle between the polyp boundary points according to the mark information; determining the radial distance of the polyp according to the distance from the polyp boundary point to the view boundary and a pre-stored radial distance table; determining the circumferential length of the polyp according to the angle between the polyp boundary points; and determining the total length of the polyp according to the radial distance and the circumferential length of the polyp. By means of the size estimation method, high-precision measurement of the polyp of the digestive tract is achieved.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, device, equipment, and computer storage medium for estimating the size of digestive tract polyps. Background Technology

[0002] Gastrointestinal diseases are common health problems worldwide, and gastrointestinal polyps are a key type of lesion with a potential risk of malignancy. Their size is an important basis for assessing the risk of malignancy and determining subsequent treatment plans (such as resection or follow-up). In traditional gastroscopy, doctors usually rely on visual estimation or comparison with instruments of known size (such as biopsy forceps) to estimate polyp size. This method is highly subjective, has poor repeatability, and is particularly prone to error when dealing with small or irregular polyps.

[0003] Capsule endoscopy, as a painless and non-invasive examination device, is increasingly widely used in gastrointestinal examinations. However, due to the free movement of the capsule within the digestive tract, the imaging distance and viewing angle continuously change dynamically, leading to nonlinear fluctuations in the magnification of targets in the image. Existing pixel size conversion algorithms based on the assumption of fixed magnification (such as the method proposed by Kim et al.) exhibit significant errors in this dynamic environment, exceeding 40%. While methods based on binocular stereo vision or deep learning (such as StereoNet proposed by Mahmood et al.) can improve accuracy, they are limited by hardware constraints such as the miniaturization, low power consumption, and disposable nature of capsule endoscopes, making it difficult to integrate additional cameras or high-computing modules, resulting in high clinical deployment costs.

[0004] Therefore, achieving high-precision, adaptive, and hardware-free automatic estimation of polyp size under dynamic imaging conditions using a monocular capsule endoscope has become a pressing technical challenge. Summary of the Invention

[0005] To address the aforementioned technical problems, this application proposes a method, device, equipment, and computer storage medium for estimating the size of digestive tract polyps.

[0006] To address the aforementioned technical problems, this application proposes a method for estimating the size of digestive tract polyps, the method comprising: To acquire images of digestive tract polyps obtained by capsule endoscopy; Obtain the marking information in the image of the digestive tract polyp, wherein the marking information includes the coordinates of the polyp boundary points; The distance from the polyp boundary point to the visual field boundary, and the angle between the polyp boundary points are determined based on the marking information. The radial distance of the polyp is determined based on the distance from the boundary point of the polyp to the boundary of the field of view, and a pre-stored radial distance table. The circumferential length of the polyp is determined based on the angle between the boundary points of the polyp. The total length of the polyp is determined based on its radial distance and circumferential length.

[0007] The size estimation method further includes: Based on the simulation results of the acquisition lens, a magnification table based on object distance and field of view was determined; Mathematical modeling was performed on the polyp imaging scenario to determine the mathematical relationship between the radial length of the image point to the boundary of the field of view, the distance of the image point to the capsule front cover, and the field of view angle corresponding to the image point. The magnification table is converted into the radial distance table based on the mathematical relationship. The radial distance table records the relationship between the pixel distance of each image point and the radial length from the image point to the view boundary.

[0008] The step of converting the magnification table into the radial distance table based on the mathematical relationship includes: Based on the field of view range of the capsule endoscope, a first mathematical relationship is established between the field of view angle corresponding to the image point and the radial length from the image point to the boundary of the field of view. Based on the field of view of the capsule endoscope and the distance between the optical front cover spherical shell and the capsule, a second mathematical relationship is established between the distance from the image point to the capsule front cover and the radial length from the image point to the boundary of the field of view. Based on the field of view of the capsule endoscope and the distance between the optical front cover and the capsule, a third mathematical relationship is established between the field of view corresponding to the image point and the distance from the image point to the capsule front cover. The magnification table is reduced in dimensionality based on the first mathematical relation, the second mathematical relation, and the third mathematical relation, and transformed into the radial distance table.

[0009] The step of reducing the dimensionality of the magnification table and transforming it into the radial distance table based on the first mathematical relation, the second mathematical relation, and the third mathematical relation includes: An interpolation function is established based on the first mathematical relation, the second mathematical relation, and the third mathematical relation; The calibration information of adjacent calibration points of the target calibration point machine is determined according to the magnification table. Substitute the calibration information into the interpolation function to calculate the relationship between the distance from the image point to the capsule front cover and the magnification, and establish the magnification function; Establish an average magnification model for each image point based on the magnification function; The relationship between the pixel distance of each image point and the radial length from the image point to the field of view boundary is solved based on the average magnification model, and the radial distance table is established.

[0010] The step of determining the distance from the polyp boundary point to the visual field boundary, and the angle between the polyp boundary points, based on the marking information, includes: The first polyp boundary point, the second polyp boundary point, and the image center point are determined based on the marked information; Calculate the first distance from the first polyp boundary point to the field of view boundary based on the coordinates of the first polyp boundary point and the coordinates of the image center point; Calculate the second distance from the boundary of the second polyp to the boundary of the field of view based on the coordinates of the boundary point of the second polyp and the coordinates of the center point of the image; The angle between the first polyp boundary point and the second polyp boundary point is calculated based on the coordinates of the first polyp boundary point, the coordinates of the second polyp boundary point, and the center point of the image.

[0011] The step of determining the total length of the polyp based on its radial distance and circumferential length includes: The total length of the polyp is determined based on its radial distance, circumferential length, and influencing parameters. The influencing parameters are determined based on the type of polyp.

[0012] The step of determining the circumferential length of the polyp based on the angle between the polyp boundary points includes: The circumferential length of the polyp is determined based on the angle between the boundary points of the polyp and the inner diameter of the digestive tract.

[0013] To address the aforementioned technical problems, this application also proposes a size estimation device for digestive tract polyps, the size estimation device comprising: a data acquisition module, a marking module, and a calculation module; wherein, The acquisition module is used to acquire images of digestive tract polyps obtained by capsule endoscopy; The marking module is used to acquire marking information in the image of the digestive tract polyps, wherein the marking information includes the coordinates of the polyp boundary points; The calculation module is used to determine the distance from the polyp boundary point to the field of view boundary, and the angle between the polyp boundary points, based on the marking information. The calculation module is used to determine the radial distance of the polyp based on the distance from the polyp boundary point to the field of view boundary and a pre-stored radial distance table. The calculation module is used to determine the circumferential length of the polyp based on the angle between the boundary points of the polyp. The calculation module is used to determine the total length of the polyp based on its radial distance and circumferential length.

[0014] To address the aforementioned technical problems, this application also proposes a size estimation device for digestive tract polyps, the size estimation device comprising a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the size estimation method as described above.

[0015] To address the aforementioned technical problems, this application also proposes a computer storage medium for storing program data, which, when executed by a computer, is used to implement the aforementioned size estimation method.

[0016] Compared with existing technologies, the advantages of this application are as follows: This application is entirely based on the existing imaging system of monocular capsule endoscopy, without the need for any additional cameras, sensors, or deep learning acceleration hardware. High-precision measurement can be achieved solely through software algorithm upgrades, greatly reducing the hardware modification costs and technical barriers for clinical deployment. This application provides an automated size quantification process, replacing the traditional method that relies on doctors' subjective visual assessment, eliminating judgment bias caused by differences in personal experience, and providing objective and repeatable quantitative standards for the screening, diagnosis, and follow-up of gastrointestinal polyps. Attached Figure Description

[0017] 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.

[0018] in: Figure 1 This is a schematic flowchart of an embodiment of the method for estimating the size of digestive tract polyps provided in this application; Figure 2 This is a schematic flowchart of another embodiment of the method for estimating the size of digestive tract polyps provided in this application; Figure 3 This is a schematic diagram of an embodiment of the digestive tract polyp size estimation device provided in this application; Figure 4 This is a schematic diagram of an embodiment of the digestive tract polyp size estimation device provided in this application; Figure 5 This is a schematic diagram of the structure of an embodiment of the computer storage medium provided in this application. Detailed Implementation

[0019] 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 a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0020] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] To address the aforementioned shortcomings, this invention aims to provide a high-precision, adaptive, and hardware-friendly method for estimating the size of gastrointestinal polyps, particularly suitable for the dynamic imaging environment of monocular capsule endoscopy. The specific objectives are as follows: 1. Overcome measurement errors caused by dynamic changes in magnification in monocular imaging: By constructing a priori magnification model based on capsule endoscope geometric parameters (such as lens focal length and sensor size) and historical motion data, this invention quantifies the magnification distribution of polyps under different imaging distances and viewing angles. It also introduces integral operations to calculate the average magnification of the polyp image region, effectively compensating for the distance-angle coupling effect. Compared to existing pixel-swapping algorithms that rely solely on static parameters of a single frame, this method achieves dynamic magnification correction during the free movement of the capsule, controlling the size estimation error within ±10%, and significantly improving measurement robustness in complex digestive tract environments.

[0022] 2. Achieve lightweight and accurate measurements without additional hardware: This invention fully utilizes existing capsule endoscopy imaging systems (single camera) and historical data, and correlates polyp location information (image coordinates), angle information, and size equations through a mathematical model, avoiding the introduction of binocular devices or deep learning modules. This method can be seamlessly integrated into the capsule image processing workflow, requiring only a software upgrade to run, reducing clinical deployment costs. It also addresses the infeasibility of traditional subjective estimation methods in capsule scenarios, providing objective and reliable quantitative evidence for early polyp screening.

[0023] The core innovation of this invention lies in combining prior knowledge with the concept of integration to fundamentally solve the problem of size distortion in dynamic imaging of capsule endoscopy, promote the development of gastrointestinal polyp assessment towards automation and standardization, and provide more accurate technical support for clinical diagnosis and treatment.

[0024] This invention relates to a method for estimating the size of digestive tract polyps based on prior magnification integration. This method, using a monocular camera, can achieve high-precision polyp size estimation based on existing anatomical information within the digestive tract and the size information of a capsule endoscope. Please refer to the details below. Figure 1 , Figure 1 This is a schematic flowchart of an embodiment of the method for estimating the size of digestive tract polyps provided in this application.

[0025] The dimension estimation method of this application is applied to a dimension estimation device, which can be a server, a terminal device, or a system in which the server and the terminal device cooperate with each other. Accordingly, the various parts of the dimension estimation device, such as each unit, subunit, module, and submodule, can all be set in the server, all in the terminal device, or separately in the server and the terminal device.

[0026] Furthermore, the aforementioned server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules, such as software or software modules used to provide distributed server functionality, or as a single software program or software module; no specific limitations are made here.

[0027] like Figure 1 As shown, the specific steps are as follows: Step S11: Obtain images of digestive tract polyps captured by capsule endoscopy.

[0028] In this embodiment, the subject orally ingests a capsule endoscope device, which is advanced axially along the digestive tract driven by physiological peristalsis. A built-in miniature imaging system, aided by a ring-shaped LED, continuously captures a sequence of images with a clear temporal relationship within the digestive tract lumen, transmitting the data in real-time to a data logger worn by the patient for storage. After the capsule completes a full digestive tract examination and is naturally excreted, the clinical operator removes the data logger and imports the complete image sequence into a workstation computer, providing the raw data foundation for subsequent analysis.

[0029] Step S12: Obtain the marking information in the image of the digestive tract polyp, wherein the marking information includes the coordinates of the polyp boundary points.

[0030] In the embodiments of this application, the size estimation device first systematically evaluates the quality of the acquired images during the image screening and polyp information marking stage, selects high-quality images with excellent clarity, uniform illumination distribution and no motion artifacts for image enhancement, and uses sharpening methods to magnify the details of the images, which is more conducive to doctors distinguishing the contours of lesions.

[0031] Then, the size estimation device provides a verification function, which is manually reviewed by professional physicians to accurately identify candidate scenes containing polyp lesions. Images meeting the "ideal hollow scene" standard are then rigorously selected—that is, the capsule is located in the central region of the digestive tract lumen, the lens optical axis is parallel to the long axis of the digestive tract, and the supplemental lighting forms a uniform ring illumination. Based on the selection results, physicians use interactive tools to precisely delineate the polyp boundaries and systematically quantify its radial and circumferential pixel feature parameters, providing reliable input for size estimation.

[0032] Specifically, the image screening process provided in this application implements a three-level progressive screening mechanism to ensure the clinical reliability of the input data. First, gradient amplitude analysis quantifies image sharpness (focusing on edge sharpness features), histogram equalization assesses the uniformity of illumination distribution (identifying overexposed or underexposed areas), and optical flow is used to detect motion artifacts (excluding blurred frames caused by gastrointestinal peristalsis). This process efficiently eliminates low-quality images, retaining a candidate image set that meets the criteria of excellent sharpness, uniform illumination, and no dynamic distortion. Next, adaptive sharpening processing is applied to the selected high-quality images. A nonlinear filtering algorithm enhances high-frequency details of the mucosal texture, highlighting the microstructural features of the polyp edges (such as the morphology of surface gland openings), significantly improving the visual recognizability of the lesion outline and providing an optimized basis for subsequent manual interpretation. Then, the images are reviewed by certified physicians in a professional viewing environment. They identify image frames containing polyp lesions and, for specific polyps, select the images that best fit the "ideal hollow scene" for polyp information labeling.

[0033] Furthermore, in the polyp information labeling stage, it is necessary to standardize and quantify the parameters of the polyp. A professional doctor marks the two boundary points of the polyp to be estimated on the image and records the coordinates. , .

[0034] Step S13: Determine the distance from the polyp boundary point to the field of view boundary, and the angle between the polyp boundary points, based on the marking information.

[0035] In this embodiment of the application, the coordinates of the image center are denoted as... Calculate the distances from the two boundary points to the view boundary: ; .

[0036] And calculate the angle traced by the two polyp boundary points using the vector angle: .

[0037] Step S14: Determine the radial distance of the polyp based on the distance from the polyp boundary point to the field of view boundary and a pre-stored radial distance table.

[0038] In this embodiment, a pre-stored radial distance table records the relationship between the pixel distance of each image point and the radial length from the image point to the viewpoint boundary. Therefore, the size estimation device determines the distance from the polyp boundary point to the viewpoint boundary according to step S13, that is, determines the pixel distance of the polyp boundary point. The size estimation device can query the radial distance corresponding to the pixel distance of the polyp boundary point from the radial distance table. This allows us to determine the radial distance of the polyp: .

[0039] Furthermore, this application also provides a scheme for constructing the radial distance table; please refer to [link / reference needed]. Figure 2 , Figure 2 This is a schematic flowchart of another embodiment of the method for estimating the size of digestive tract polyps provided in this application.

[0040] like Figure 2 As shown, the specific steps are as follows: Step S21: Based on the simulation results of the acquisition lens, determine the magnification table based on object distance and field of view.

[0041] In this embodiment, the size estimation device performs a priori magnification calculation and obtains a magnification table based on object distance and field of view through simulation experiments. This calibration scheme systematically calibrates the hemispherical optical front cover integrated at the front of the lens (whose center is located at the center of the lens, forming a transparent medium interface with a radius of curvature of 5mm). The core objective is to quantify the spatial magnification characteristics under different object distances and field of view positions.

[0042] This calibration scheme constructs a physical simulation environment for capsule endoscopy imaging based on ray tracing theory. A complete optical path model, including a hemispherical optical cover, is established using Zemax optical design software, and the original parameters related to the lens are input. A systematic scan is performed within an object distance range of 5-25mm (covering typical distances within the digestive tract lumen) and a field of view range of 0° to the maximum field of view. The position of the test calibration plate is changed in 1mm increments, while the incident ray angle is adjusted at 3° intervals. For each object distance-field of view combination, the unit length (1) on the calibration plate is precisely calculated. The pixel span formed on the image sensor is used to derive the spatial magnification value—a value that characterizes the conversion ratio between physical size and pixel size under specific imaging conditions.

[0043] Step S22: Perform mathematical modeling on the polyp imaging scene to determine the mathematical relationship between the radial length from the image point to the boundary of the field of view, the distance from the image point to the capsule front cover, and the field of view angle corresponding to the image point.

[0044] Step S23: Convert the magnification table into the radial distance table according to the mathematical relationship.

[0045] In this embodiment, the size estimation device performs radial interpolation table calculation, and calculates the radial distance interpolation table using a polyp imaging model.

[0046] Specifically, given that this length can be estimated from the difference in radial distances from its proximal and distal ends to the field of view boundary, the size estimation device calculates the radial distance from any point in the image to the field of view boundary. First, a mathematical model of the polyp imaging scene is needed, and then the radial length from that point to the field of view edge is found analytically. The distance from this point to the front cover of the capsule The field of view angle corresponding to this point The mathematical relationship.

[0047] Then use and The relationship transforms the magnification table into a magnification table with respect to a single variable. The table; then, using and The relationship between the two points is analyzed by integrating the average magnification from the field of view boundary to the point. Finally, by calculating the pixel distance from the point to the field of view boundary in the imaging result, the true distance can be calculated using the magnification. The true distances corresponding to points at distances from 10 to 200 pixels are calculated separately, and then the radial distance of the polyp is obtained by subtracting the distances from both ends of the polyp to the field of view boundary.

[0048] Specifically, for a point on the digestive tract wall, first establish the radial length from that point to the edge of the field of view. The distance from this point to the front cover of the capsule The field of view angle corresponding to this point The mathematical relationship. Assume the general radius of the digestive tract is R, and the field of view of the capsule endoscope is... The distance r between the optical front cover spherical shell and the capsule used for calibrating the object distance. By extracting the mathematical model, the corresponding field of view angle at this point can be obtained as: .

[0049] The corresponding distance to the front cover of the capsule for: .

[0050] Similarly, there are also and Relationship: .

[0051] According to the above formulas (1) to (3), the size estimation device can reduce the dimension of the magnification table in step S21 and reduce the integral equation to be solved to a univariate equation.

[0052] Specifically, the size estimation device adjusts the magnification Q calibrated in step S21 with respect to the object distance. and field of view The corresponding table is calculated using a bilinear interpolation process. Then, in equation (3) and Substituting the relational expression into In the middle, we obtained .

[0053] The specific calculation process is as follows: For a point within the calibration range Find the four nearest calibration points. , , , Then calculate the corresponding value at that point: ; in, and It is the relative position of the point within the grid cell, i.e. ; ; Subsequently, substituting equations (5) and (6) into the interpolation function reduces the dimension of the magnification relationship, transforming it into the magnification corresponding to the range traced by the target point. .

[0054] Furthermore, the size estimation device is suitable for radial lengths of... The range drawn from the edge of the field of view to a given point can be obtained through a mathematical model. ,in, Distance from the edge of the field of view Let this be the distance from the point to the optical front cover; therefore, the average magnification can be calculated by integrating the data. .

[0055] For a specific capsule lens, the size estimation device can obtain the width h of each pixel calibrated from the manufacturer, so for a radial length of... By identifying the point, we can obtain its pixel length P in the image, and then solve for its radial length in the image. Therefore, the average magnification over this radial distance can be calculated: .

[0056] By solving the two equations simultaneously, we can obtain the solution for the radial length. The equation: .

[0057] The size estimation device solves this equation to obtain the radial distance from the point to the boundary of the field of view. Calculate the radial distances corresponding to points from 10 to 200 pixels, and create a radial distance table. Then, based on the subsequent polyp location information, calculate the distances from both ends of the polyp to the field of view boundary, and subtract them to obtain the radial length of the polyp.

[0058] Step S15: Determine the circumferential length of the polyp based on the angle between the boundary points of the polyp.

[0059] In this embodiment of the application, the size estimation device uses the angle between the polyp boundary points determined in step S13. To calculate the circumferential length of the polyp, a circumferential scaling function is established based on the cylindrical topological characteristics of the digestive tract lumen, using the included angle... The circumferential length of the polyp is estimated by its proportion of the entire circumference. The specific formula is as follows: .

[0060] Step S16: Determine the total length of the polyp based on its radial distance and circumferential length.

[0061] In this embodiment, since the surface of the polyp is not perfectly flat, the radial and circumferential lengths are not strictly perpendicular in the coordinate system. Therefore, the size estimation device uses a morphology-aware intelligent coupling method to represent the total length of the polyp as follows: ; in, It was used to describe the effect of local curvature of the digestive tract on measurements.

[0062] if This indicates that the polyp is concave inwards, and circumferential stretching will cause the radial measurement value to be smaller. Therefore, it is necessary to set... Provide compensation; similarly, if This indicates that the polyp is more likely to be a spherical polyp, and we need to set... Make corrections.

[0063] In real-world scenarios, doctors can dynamically control the condition based on the type of polyp. The size of the circumferential and radial lengths can be intelligently coupled by setting parameters that are closer together.

[0064] In summary, the size estimation device can achieve high-precision, adaptive, and zero-hardware-dependent quantitative assessment of the size of gastrointestinal polyps in monocular capsule endoscopy scenarios.

[0065] This application utilizes a simulation-based calibration process for the optical front cover geometry parameters and a method for generating a magnification lookup table under the coupling effect of object distance and field of view, ensuring high-fidelity modeling of magnification characteristics in uncontrolled motion scenarios. The core innovation lies in establishing a precise mapping relationship between object distance, field of view, and magnification through systematic simulation experiments, specifically addressing the unique hemispherical optical front cover geometry of capsule endoscopes (with a fixed radius of curvature and lens position). This model overcomes the limitations of traditional single-point estimation, transforming nonlinear magnification changes in dynamic imaging environments into a quantifiable prior knowledge base, providing a theoretical foundation for subsequent size correction.

[0066] This application presents a mathematical transformation method that converts magnification tables into univariate functions (object distance), and a core algorithm for calculating the average magnification through radial distance integration, forming a key technological barrier for dynamically compensating for magnification nonlinearity. This method innovatively introduces the concept of integration, associating the radial position information of the polyp in the image (pixel distance to the field of view boundary) with the prior magnification model, and calculating the average magnification from the field of view boundary to the polyp point through path integration. This mechanism effectively eliminates dimensional distortion caused by distance fluctuations and viewing angle shifts in monocular imaging, significantly improving measurement robustness.

[0067] This application proposes a construction logic for a radial distance interpolation table, a geometric derivation method for circumferential dimensions, a morphology-aware intelligent coupling method, and a multi-dimensional physical dimension comprehensive calculation process based on average magnification, forming an integrated solution for high-precision polyp quantification. This method achieves accurate fusion of polyp physical dimensions through the collaborative calculation of radial interpolation tables and circumferential geometric relationships: radial pixel dimensions are converted into true lengths based on average magnification, and the three-dimensional scale is derived through a morphology-aware intelligent coupling method combined with circumferential pixel parameters. This framework avoids the one-sidedness of traditional single-dimensional estimation, ensuring the completeness and clinical applicability of size assessment in complex digestive tract environments.

[0068] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0069] To implement the above-mentioned method for estimating the size of digestive tract polyps, this application also proposes a device for estimating the size of digestive tract polyps, for details please refer to [link / reference needed]. Figure 3 , Figure 3 This is a schematic diagram of an embodiment of the digestive tract polyp size estimation device provided in this application.

[0070] The size estimation device 500 in this embodiment includes: a data acquisition module 51, a marking module 52, and a calculation module 53.

[0071] The acquisition module 51 is used to acquire images of digestive tract polyps obtained by capsule endoscopy.

[0072] The marking module 52 is used to acquire marking information in the image of the digestive tract polyp, wherein the marking information includes the coordinates of the polyp boundary points.

[0073] The calculation module 53 is used to determine the distance from the polyp boundary point to the field of view boundary, and the angle between the polyp boundary points, based on the marking information.

[0074] The calculation module 53 is used to determine the radial distance of the polyp based on the distance from the polyp boundary point to the field of view boundary and a pre-stored radial distance table.

[0075] The calculation module 53 is used to determine the circumferential length of the polyp based on the angle between the boundary points of the polyp.

[0076] The calculation module 53 is used to determine the total length of the polyp based on the radial distance and circumferential length of the polyp.

[0077] To implement the above-mentioned method for estimating the size of gastrointestinal polyps, this application also proposes a device for estimating the size of gastrointestinal polyps, for details please refer to [link / reference needed]. Figure 4 , Figure 4 This is a schematic diagram of an embodiment of the digestive tract polyp size estimation device provided in this application.

[0078] The size estimation device 400 in this embodiment includes a processor 41, a memory 42, an input / output device 43, and a bus 44.

[0079] The processor 41, memory 42, and input / output device 43 are respectively connected to the bus 44. The memory 42 stores program data, and the processor 41 is used to execute the program data to implement the size estimation method described in the above embodiments.

[0080] In this embodiment, processor 41 can also be referred to as a CPU (Central Processing Unit). Processor 41 may be an integrated circuit chip with signal processing capabilities. Processor 41 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor, or processor 41 can be any conventional processor.

[0081] This application also provides a computer storage medium; please refer to the following: Figure 5 , Figure 5 This is a schematic diagram of a computer storage medium according to an embodiment of the present application. The computer storage medium 600 stores a computer program 61, which, when executed by a processor, is used to implement the size estimation method of the above embodiment.

[0082] When the embodiments of this application are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0083] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for estimating the size of digestive tract polyps, characterized in that, The size estimation method includes: To acquire images of digestive tract polyps obtained by capsule endoscopy; Obtain the marking information in the image of the digestive tract polyp, wherein the marking information includes the coordinates of the polyp boundary points; The distance from the polyp boundary point to the visual field boundary, and the angle between the polyp boundary points are determined based on the marking information. The radial distance of the polyp is determined based on the distance from the boundary point of the polyp to the boundary of the field of view, and a pre-stored radial distance table. The circumferential length of the polyp is determined based on the angle between the boundary points of the polyp. The total length of the polyp is determined based on its radial distance and circumferential length.

2. The size estimation method according to claim 1, characterized in that, The size estimation method further includes: Based on the simulation results of the acquisition lens, a magnification table based on object distance and field of view was determined; Mathematical modeling was performed on the polyp imaging scenario to determine the mathematical relationship between the radial length of the image point to the boundary of the field of view, the distance of the image point to the capsule front cover, and the field of view angle corresponding to the image point. The magnification table is converted into the radial distance table based on the mathematical relationship. The radial distance table records the relationship between the pixel distance of each image point and the radial length from the image point to the view boundary.

3. The size estimation method according to claim 2, characterized in that, The step of converting the magnification table into the radial distance table based on the mathematical relationship includes: Based on the field of view range of the capsule endoscope, a first mathematical relationship is established between the field of view angle corresponding to the image point and the radial length from the image point to the boundary of the field of view. Based on the field of view of the capsule endoscope and the distance between the optical front cover spherical shell and the capsule, a second mathematical relationship is established between the distance from the image point to the capsule front cover and the radial length from the image point to the boundary of the field of view. Based on the field of view of the capsule endoscope and the distance between the optical front cover and the capsule, a third mathematical relationship is established between the field of view corresponding to the image point and the distance from the image point to the capsule front cover. The magnification table is reduced in dimensionality based on the first mathematical relation, the second mathematical relation, and the third mathematical relation, and transformed into the radial distance table.

4. The size estimation method according to claim 3, characterized in that, The step of reducing the dimensionality of the magnification table and transforming it into the radial distance table based on the first mathematical relation, the second mathematical relation, and the third mathematical relation includes: An interpolation function is established based on the first mathematical relation, the second mathematical relation, and the third mathematical relation; The calibration information of adjacent calibration points of the target calibration point machine is determined according to the magnification table. Substitute the calibration information into the interpolation function to calculate the relationship between the distance from the image point to the capsule front cover and the magnification, and establish the magnification function; Establish an average magnification model for each image point based on the magnification function; The relationship between the pixel distance of each image point and the radial length from the image point to the field of view boundary is calculated based on the average magnification model, and the radial distance table is established.

5. The size estimation method according to claim 1, characterized in that, Determining the distance from the polyp boundary point to the visual field boundary, and the angle between the polyp boundary points, based on the marked information, includes: The first polyp boundary point, the second polyp boundary point, and the image center point are determined based on the marked information; Calculate the first distance from the first polyp boundary point to the field of view boundary based on the coordinates of the first polyp boundary point and the coordinates of the image center point; Calculate the second distance from the boundary of the second polyp to the boundary of the field of view based on the coordinates of the boundary point of the second polyp and the coordinates of the center point of the image; The angle between the first polyp boundary point and the second polyp boundary point is calculated based on the coordinates of the first polyp boundary point, the coordinates of the second polyp boundary point, and the center point of the image.

6. The size estimation method according to claim 5, characterized in that, Determining the total length of the polyp based on its radial distance and circumferential length includes: The total length of the polyp is determined based on its radial distance, circumferential length, and influencing parameters. The influencing parameters are determined based on the type of polyp.

7. The size estimation method according to claim 1, characterized in that, Determining the circumferential length of the polyp based on the angle between the polyp boundary points includes: The circumferential length of the polyp is determined based on the angle between the boundary points of the polyp and the inner diameter of the digestive tract.

8. A device for estimating the size of digestive tract polyps, characterized in that, The size estimation device includes: a data acquisition module, a marking module, and a calculation module; wherein, The acquisition module is used to acquire images of digestive tract polyps obtained by capsule endoscopy; The marking module is used to acquire marking information in the image of the digestive tract polyps, wherein the marking information includes the coordinates of the polyp boundary points; The calculation module is used to determine the distance from the polyp boundary point to the field of view boundary, and the angle between the polyp boundary points, based on the marking information. The calculation module is used to determine the radial distance of the polyp based on the distance from the polyp boundary point to the field of view boundary and a pre-stored radial distance table. The calculation module is used to determine the circumferential length of the polyp based on the angle between the boundary points of the polyp. The calculation module is used to determine the total length of the polyp based on its radial distance and circumferential length.

9. A device for estimating the size of digestive tract polyps, characterized in that, The size estimation device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the size estimation method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium is used to store program data, which, when executed by the computer, is used to implement the size estimation method as described in any one of claims 1 to 7.

Images