CN-122023503-A - Method, device, equipment and storage medium for estimating size of polyp of digestive tract

CN122023503ACN 122023503 ACN122023503 ACN 122023503ACN-122023503-A

Abstract

The application provides a dimension estimation method, a dimension estimation device and a computer storage medium for polyps of digestive tracts. The size estimation method comprises the steps of obtaining an image of a digestive tract polyp acquired by a capsule endoscope, obtaining marking information in the image of the digestive tract polyp, wherein the marking information comprises polyp boundary point coordinates, determining the distance from a polyp boundary point to a visual field boundary and the angle between polyp boundary points according to the marking information, determining the radial distance of the polyp according to the distance from the polyp boundary point to the visual field 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 the size estimation method, high-precision measurement of the polyp of the digestive tract is realized.

Inventors

ZHANG JIARUI
HU FENG
WU JIACHENG

Assignees

浙江势通机器人科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A method of estimating the size of a polyp of the digestive tract, the method comprising: Acquiring an image of the polyp of the digestive tract acquired by the capsule endoscope; Acquiring marking information in the digestive tract polyp image, wherein the marking information comprises polyp boundary point coordinates; Determining the distance from the polyp boundary point to the visual field boundary and the angle between the polyp boundary points according to the marking information; determining the radial distance of the polyp according to the distance from the polyp boundary point to the visual field 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.
2. The method of size estimation according to claim 1, wherein, The size estimation method further includes: according to the simulation experiment result of the acquisition lens, determining a magnification table based on object distance and field angle; Mathematical modeling is carried out on a polyp shooting scene, and the mathematical relationship among the radial length from an image point to a visual field boundary, the distance from the image point to a capsule front cover and the visual field angle corresponding to the image point is determined; Converting the magnification table into the radial distance table according to the mathematical relationship; wherein the radial distance table records a relationship of a pixel distance of each image point to a radial length of the image point to a field of view boundary.
3. The method of size estimation according to claim 2, wherein, Said converting said magnification table into said radial distance table according to said mathematical relationship, comprising: According to the visual field angle range of the capsule endoscope, the inner diameter of the alimentary canal establishes a first mathematical relationship between the visual field angle corresponding to the image point and the radial length from the image point to the visual field boundary; according to the field angle range of the capsule endoscope and the distance from the spherical shell of the optical front cover to the capsule, the inner diameter of the alimentary canal establishes a second mathematical relationship between the distance from the image point to the capsule front cover and the radial length from the image point to the field boundary; According to the field angle range of the capsule endoscope and the distance from the spherical shell of the optical front cover to the capsule, establishing a third mathematical relationship between the field angle corresponding to the image point and the distance from the image point to the capsule front cover by the inner diameter of the alimentary canal; And reducing the dimension of the amplification factor table according to the first mathematical relationship, the second mathematical relationship and the third mathematical relationship, and converting the amplification factor table into the radial distance table.
4. A size estimation method according to claim 3, wherein, The dimension reduction of the magnification table according to the first mathematical relationship, the second mathematical relationship and the third mathematical relationship is performed, and the dimension reduction is converted into the radial distance table, including: Establishing an interpolation function according to the first mathematical relationship, the second mathematical relationship and the third mathematical relationship; determining calibration information of adjacent calibration points of the target calibration point machine according to the magnification ratio table; substituting the calibration information into the interpolation function, calculating the relation between the distance from the image point to the capsule front cover and the amplification factor, and establishing an amplification factor function; establishing an average magnification model of each image point according to the magnification function; and solving the relation between the pixel distance of each image point and the radial length from the image point to the visual field boundary according to the average magnification model, and establishing the radial distance table.
5. The method of size estimation according to claim 1, wherein, The determining the distance from the polyp boundary point to the view boundary and the angle between the polyp boundary points according to the marking information comprises: Determining a first polyp boundary point, a second polyp boundary point and an image center point according to the marking information; calculating a first distance from the first polyp boundary point to a visual field boundary according to the coordinates of the first polyp boundary point and the coordinates of the image center point; calculating a second distance from the second polyp boundary point to the view boundary according to the coordinates of the second polyp boundary point and the coordinates of the image center point; And calculating the angle crossed by the first polyp boundary point and the second polyp boundary point according to the coordinates of the first polyp boundary point, the coordinates of the second polyp boundary point and the image center point.
6. The method of size estimation according to claim 5, wherein, The determining the total length of the polyp according to the radial distance and the circumferential length of the polyp comprises: determining the total length of the polyp according to the radial distance, the circumferential length and the influence parameters of the polyp; wherein the influencing parameter is determined according to the type of polyp.
7. The method of size estimation according to claim 1, wherein, The determining the circumferential length of the polyp according to the angle between the polyp boundary points comprises: Determining the circumferential length of the polyp based on the angle between the polyp boundary points and the internal diameter of the digestive tract.
8. A dimension estimation device of an alimentary canal polyp is characterized by comprising an acquisition module, a marking module and a calculation module, wherein, The acquisition module is used for acquiring the digestive tract polyp image acquired by the capsule endoscope; The marking module is used for acquiring marking information in the digestive tract polyp image, wherein the marking information comprises polyp boundary point coordinates; the calculation module is used for determining the distance from the polyp boundary point to the visual field boundary and the angle between the polyp boundary points according to the marking information; the calculation module is used for determining the radial distance of the polyp according to the distance from the polyp boundary point to the visual field boundary and a pre-stored radial distance table; the calculation module is used for determining the circumferential length of the polyp according to the angle between the polyp boundary points; The calculation module is used for determining the total length of the polyp according to the radial distance and the circumferential length of the polyp.
9. A size estimation device for polyps of the digestive tract, the size estimation device comprising a memory and a processor coupled to the memory; wherein the memory is for storing program data and the processor is for executing the program data to implement the size estimation method according to any one of claims 1 to 7.
10. A computer storage medium for storing program data which, when executed by a computer, is adapted to carry out the size estimation method according to any one of claims 1 to 7.

Description

Method, device, equipment and storage medium for estimating size of polyp of digestive tract Technical Field The present application relates to the technical field of medical image processing, and in particular, to a size estimation method, a size estimation device, a size estimation apparatus, and a computer storage medium for polyps of the digestive tract. Background Digestive tract diseases are a common health problem worldwide, and digestive tract polyps are a critical type of lesions where there is a potential risk of malignant changes. The size is an important basis for assessing risk of malignant changes and determining subsequent treatment regimens (e.g., excision or follow-up). In conventional gastroenteroscopy, a physician typically relies on visual inspection or comparison to instruments of known dimensions (e.g., biopsies) to estimate polyp size, which is highly subjective, poorly reproducible, and has a large error, especially in the face of small or irregular polyps. Capsule endoscopes are increasingly used in digestive tract examinations as a painless, noninvasive examination apparatus. However, as the capsule is free to move within the alimentary canal, the imaging distance and viewing angle continue to dynamically change, resulting in nonlinear fluctuations in magnification of the target in the image. The existing pixel size changing algorithm (such as the method proposed by Kim et al) based on the fixed magnification assumption has significant errors in this dynamic environment, which can exceed 40%. While the method based on binocular stereoscopic vision or deep learning (such as StereoNet proposed by Mahmood and the like) can improve the precision, the method is limited by hardware constraints such as miniaturization, low power consumption, disposable use and the like of the capsule endoscope, and is difficult to integrate an additional camera or a high-power module, and the clinical deployment cost is high. Therefore, how to realize high-precision, self-adaptive and automatic polyp size estimation without additional hardware under the dynamic imaging condition of a monocular capsule endoscope becomes a technical problem to be solved currently. ‌ A Disclosure of Invention In order to solve the technical problems, the application provides a size estimation method, a size estimation device and a computer storage medium for digestive tract polyps. In order to solve the technical problem, the application provides a dimension estimation method of polyp of digestive tract, which comprises the following steps: Acquiring an image of the polyp of the digestive tract acquired by the capsule endoscope; Acquiring marking information in the digestive tract polyp image, wherein the marking information comprises polyp boundary point coordinates; Determining the distance from the polyp boundary point to the visual field boundary and the angle between the polyp boundary points according to the marking information; determining the radial distance of the polyp according to the distance from the polyp boundary point to the visual field 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. The size estimation method further comprises the following steps: according to the simulation experiment result of the acquisition lens, determining a magnification table based on object distance and field angle; Mathematical modeling is carried out on a polyp shooting scene, and the mathematical relationship among the radial length from an image point to a visual field boundary, the distance from the image point to a capsule front cover and the visual field angle corresponding to the image point is determined; Converting the magnification table into the radial distance table according to the mathematical relationship; wherein the radial distance table records a relationship of a pixel distance of each image point to a radial length of the image point to a field of view boundary. Wherein said converting said magnification table into said radial distance table according to said mathematical relationship comprises: According to the visual field angle range of the capsule endoscope, the inner diameter of the alimentary canal establishes a first mathematical relationship between the visual field angle corresponding to the image point and the radial length from the image point to the visual field boundary; according to the field angle range of the capsule endoscope and the distance from the spherical shell of the optical front cover to the capsule, the inner diameter of the alimentary canal establishes a second mathematical relationship between the distance from the image point to the capsule front cover and the radial length from the image point to the field boundary; According to the field angle range