A bronchoscopic cutter and positioning system

Abstract

The present invention provides a bronchoscopic cutter and positioning system, including: a preprocessing module, used to preprocess a medical examination image to obtain a preprocessed medical examination image; an image division module, used to divide the medical examination image into a plurality of sub-regions using the pixel values ​​of different pixel points on the medical examination image as an initial threshold; a pixel richness calculation module, used to calculate the pixel richness of each sub-region; an abnormal tissue segmentation module, used to determine the position of the abnormal tissue in the medical examination image according to the pixel richness of each sub-region; a cutter and positioning module, used to control the cutter to remove the abnormal tissue of the patient according to the position of the abnormal tissue in the medical examination image. The present invention can accurately identify and locate the abnormal tissue in the medical examination image by calculating the pixel richness of the divided medical image, thereby improving the accuracy of abnormal tissue removal and reducing damage to healthy tissue.

Description

Technical Field

[0001] The present invention relates to the technical field of bronchoscopes, and in particular to a bronchoscope cutter and a positioning system. Background Art

[0002] Bronchoscopy is an important medical method widely used in the diagnosis of respiratory diseases. Traditional bronchoscopy mainly relies on the physician's experience to perform tissue sampling and removal of abnormal tissue. However, existing technologies often face many challenges during operation, including unclear vision, inaccurate positioning, and incomplete removal, which makes it difficult to completely remove the lesions and increases the risk of re-treatment for patients.

[0003] With the continuous development of medical imaging technology, the clarity and resolution of bronchoscope images have been significantly improved, allowing doctors to more accurately observe abnormal tissues in the airway. However, although bronchoscopes provide real-time image feedback, doctors still have difficulties in accurately locating and precisely removing abnormal tissues under the complex airway anatomy. Summary of the invention

[0004] The object of the present invention is to provide a bronchoscope cutter and positioning system.

[0005] A bronchoscope cutter and positioning system, comprising:

[0006] A medical examination image acquisition module, used for acquiring medical examination images output by a bronchoscope;

[0007] A preprocessing module, used for preprocessing the medical examination image to obtain a preprocessed medical examination image;

[0008] An image division module, used to divide the medical examination image into a plurality of sub-areas using the pixel values ​​of different pixel points on the medical examination image as an initial threshold;

[0009] A pixel richness calculation module, used to calculate the pixel richness of each sub-region;

[0010] An abnormal tissue segmentation module is used to determine the location of abnormal tissue in the medical examination image based on the pixel richness of each sub-region;

[0011] The cutter and positioning module are used to control the cutter to remove the abnormal tissue of the patient according to the position of the abnormal tissue in the medical examination image.

[0012] Preferably, the image segmentation module comprises:

[0013] A mean and standard deviation calculation unit, used for calculating the mean and standard deviation of pixels of the medical examination image;

[0014] A distribution range determination unit, used to determine a normal distribution curve of pixels of the medical examination image based on a mean value and a standard deviation and to determine a distribution range of an initial threshold value according to the normal distribution curve;

[0015] The sub-region division module is used to divide the medical examination image into several sub-regions using an initial threshold; wherein the sub-region expression is as follows:

[0016]

[0017] Where W1 represents the pixel value distribution in the first sub-region, W2 represents the pixel value distribution in the second sub-region, and W j represents the pixel value distribution in the jth sub-region, W Q+1 represents the pixel value distribution in the Q+1th sub-region, g(x,y) represents the medical examination image, t1 represents the first initial threshold, t2 represents the second initial threshold, t3 represents the third initial threshold, t j represents the jth initial threshold, t k represents the kth initial threshold, and L represents the number of different pixel values ​​of the medical examination image.

[0018] Preferably, the pixel richness calculation module includes:

[0019] Using the formula:

[0020]

[0021] Calculate the pixel richness of each sub-region; where S1 represents the pixel richness in the first sub-region, S2 represents the pixel richness in the second sub-region, and S j represents the pixel richness in the jth sub-region, S Q+1 represents the pixel richness in the Q+1th sub-region, p i Indicates the probability of the pixel with pixel value i appearing.

[0022] Preferably, the abnormal tissue segmentation module comprises:

[0023] The objective function construction unit is used to construct an objective function with the maximum sum of pixel richness of all sub-regions as the goal; wherein the objective function is:

[0024]

[0025] Among them, S i represents the pixel richness in the i-th sub-region;

[0026] The solving unit is used for solving the objective function and taking the sub-region with the largest pixel richness as the position of the abnormal tissue in the medical examination image.

[0027] Preferably, the preprocessing module comprises:

[0028] A neighborhood matrix construction unit is used to take a local window centered on each pixel point on the medical examination image and convert the pixel points under the local window into a neighborhood matrix;

[0029] A similarity calculation unit, used for calculating the similarity between any two pixels based on a neighborhood matrix;

[0030] A denoising weight determination unit, used to calculate the denoising weight of each pixel according to the similarity;

[0031] The pixel preprocessing unit is used to perform denoising preprocessing on the pixels of the medical examination image by using the denoising weights of the pixels to obtain the preprocessed medical examination image.

[0032] Preferably, the calculating the similarity between any two pixels based on the neighborhood matrix includes:

[0033] Using the formula:

[0034]

[0035] Calculate the similarity between any two pixels; where d(i,j) represents the similarity between the i-th pixel and the j-th pixel, G a represents the Gaussian kernel matrix, v(N i ) represents the neighborhood matrix of the i-th pixel, v(N j ) represents the neighborhood matrix of the j-th pixel.

[0036] Preferably, calculating the denoising weight of each pixel according to the similarity includes:

[0037] Using the formula:

[0038]

[0039] Calculate the denoising weight of each pixel; where w(i,j) represents the denoising weight, Z(i) represents the normalization coefficient, I represents the set of all pixels on the medical examination image, and h represents the attenuation parameter.

[0040] Preferably, performing denoising preprocessing on the pixels of the medical examination image using the denoising weights of the pixels to obtain the preprocessed medical examination image includes:

[0041] The denoising weight of each pixel is used to perform weighted summation on each pixel to obtain the denoised pixel; the weighted summation formula is:

[0042]

[0043] in, represents the pixel after denoising, v(j) represents the jth pixel on the medical examination image;

[0044] The preprocessed medical examination images are regenerated using the denoised pixels.

[0045] The beneficial effect of a bronchoscope cutter and positioning system provided by the present invention is that, compared with the prior art, the present invention can accurately identify and locate abnormal tissue in medical examination images by calculating the pixel richness of the divided medical images, thereby improving the accuracy of abnormal tissue resection and reducing damage to healthy tissue.

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic diagram of a bronchoscope cutter and a positioning system provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0049] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0050] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0051] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] See also Figure 1 , a bronchoscope cutter and positioning system, comprising:

[0053] A medical examination image acquisition module, used for acquiring medical examination images output by a bronchoscope;

[0054] A preprocessing module, used for preprocessing the medical examination image to obtain a preprocessed medical examination image;

[0055] Furthermore, the preprocessing module includes:

[0056] A neighborhood matrix construction unit is used to take a local window centered on each pixel point on the medical examination image and convert the pixel points under the local window into a neighborhood matrix;

[0057] The similarity calculation unit is used to calculate the similarity between any two pixels based on the neighborhood matrix; wherein the similarity calculation formula is:

[0058]

[0059] Among them, d(i,j) represents the similarity between the i-th pixel and the j-th pixel, G a represents the Gaussian kernel matrix, v(N i ) represents the neighborhood matrix of the i-th pixel, v(N j ) represents the neighborhood matrix of the j-th pixel.

[0060] A denoising weight determination unit, used to calculate the denoising weight of each pixel according to the similarity;

[0061] Among them, the denoising weight calculation formula is:

[0062]

[0063] Among them, w(i,j) represents the denoising weight, Z(i) represents the normalization coefficient, I represents the set of all pixels on the medical examination image, and h represents the attenuation parameter.

[0064] The pixel preprocessing unit is used to perform denoising preprocessing on the pixels of the medical examination image by using the denoising weights of the pixels to obtain the preprocessed medical examination image.

[0065] In the pixel preprocessing unit, the present invention can use the denoising weight of the pixel point to perform weighted summation on each pixel point to obtain the denoised pixel point; the weighted summation formula is:

[0066]

[0067] in, represents the pixel after denoising, v(j) represents the jth pixel on the medical examination image;

[0068] The preprocessed medical examination images are regenerated using the denoised pixels.

[0069] Traditional local filtering methods, such as mean filtering, only take into account the influence of local neighborhood pixels. Therefore, the use of mean filtering usually results in a blurred image denoising effect. The denoising process of this application takes into account the pixel similarity of the entire image. By performing weighted averaging on multiple similar image areas, the visual quality of the image can be improved while suppressing noise.

[0070] An image division module, used to divide the medical examination image into a plurality of sub-areas using the pixel values ​​of different pixel points on the medical examination image as an initial threshold;

[0071] Furthermore, the image segmentation module includes:

[0072] A mean and standard deviation calculation unit, used for calculating the mean and standard deviation of pixels of the medical examination image;

[0073] A distribution range determination unit, used to determine a normal distribution curve of pixels of the medical examination image based on a mean value and a standard deviation and to determine a distribution range of an initial threshold value according to the normal distribution curve;

[0074] The sub-region division module is used to divide the medical examination image into several sub-regions using an initial threshold; wherein the sub-region expression is as follows:

[0075]

[0076] Where W1 represents the pixel value distribution in the first sub-region, W2 represents the pixel value distribution in the second sub-region, and W j represents the pixel value distribution in the jth sub-region, W Q+1 represents the pixel value distribution in the Q+1th sub-region, g(x,y) represents the medical examination image, t1 represents the first initial threshold, t2 represents the second initial threshold, t3 represents the third initial threshold, t jrepresents the jth initial threshold, t k represents the kth initial threshold, and L represents the number of different pixel values ​​of the medical examination image.

[0077] A pixel richness calculation module is used to calculate the pixel richness of each sub-region; in the pixel richness calculation module, the present invention can use the formula:

[0078]

[0079] Calculate the pixel richness of each sub-region; where S1 represents the pixel richness in the first sub-region, S2 represents the pixel richness in the second sub-region, and S j represents the pixel richness in the jth sub-region, S Q+1 represents the pixel richness in the Q+1th sub-region, p i Indicates the probability of the pixel with pixel value i appearing.

[0080] The present invention uses entropy in information theory to quantify the amount of information in an image, thereby helping to identify the complexity and detail richness of the image.

[0081] An abnormal tissue segmentation module is used to determine the location of abnormal tissue in the medical examination image based on the pixel richness of each sub-region;

[0082] Furthermore, the abnormal tissue segmentation module includes:

[0083] The objective function construction unit is used to construct an objective function with the maximum sum of pixel richness of all sub-regions as the goal; wherein the objective function is:

[0084]

[0085] Among them, S i represents the pixel richness in the i-th sub-region;

[0086] The solving unit is used for solving the objective function and taking the sub-region with the largest pixel richness as the position of the abnormal tissue in the medical examination image.

[0087] In actual medical examination images, normal tissues generally present single-color and smooth image features, while abnormal tissues usually present chaotic and irregular colors and high pixel richness. Therefore, this method can quickly screen out the target area.

[0088] The cutter and positioning module are used to control the cutter to remove the abnormal tissue of the patient according to the position of the abnormal tissue in the medical examination image.

[0089] The present invention can accurately identify and locate abnormal tissue in medical examination images by calculating the pixel richness of the divided medical images, thereby improving the accuracy of abnormal tissue resection and reducing damage to healthy tissue.

[0090] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A bronchoscopic cutter and positioning system, characterized in that: include: A medical examination image acquisition module, used for acquiring medical examination images output by a bronchoscope; A preprocessing module, used for preprocessing the medical examination image to obtain a preprocessed medical examination image; An image division module, used to divide the medical examination image into a plurality of sub-areas using the pixel values ​​of different pixel points on the medical examination image as an initial threshold; The image segmentation module comprises: A mean and standard deviation calculation unit, used for calculating the mean and standard deviation of pixels of the medical examination image; A distribution range determination unit, used to determine a normal distribution curve of pixels of the medical examination image based on a mean value and a standard deviation and to determine a distribution range of an initial threshold value according to the normal distribution curve; The sub-region division module is used to divide the medical examination image into several sub-regions using an initial threshold; wherein the sub-region expression is as follows: Where W1 represents the pixel value distribution in the first sub-region, W2 represents the pixel value distribution in the second sub-region, and W j represents the pixel value distribution in the jth sub-region, W Q+1 represents the pixel value distribution in the Q+1th sub-region, g(x,y) represents the medical examination image, t1 represents the first initial threshold, t2 represents the second initial threshold, t3 represents the third initial threshold, t j represents the jth initial threshold, t k represents the kth initial threshold, L represents the number of different pixel values ​​of the medical examination image; A pixel richness calculation module, used to calculate the pixel richness of each sub-region; The pixel richness calculation module includes: Using the formula: Calculate the pixel richness of each sub-region; where S1 represents the pixel richness in the first sub-region, S2 represents the pixel richness in the second sub-region, and S j represents the pixel richness in the jth sub-region, S Q+1 represents the pixel richness in the Q+1th sub-region, p i Indicates the probability of occurrence of a pixel with pixel value i; An abnormal tissue segmentation module is used to determine the location of abnormal tissue in the medical examination image based on the pixel richness of each sub-region; The abnormal tissue segmentation module comprises: The objective function construction unit is used to construct an objective function with the maximum sum of pixel richness of all sub-regions as the goal; wherein the objective function is: Among them, S i represents the pixel richness in the i-th sub-region; A solving unit, used for solving the objective function, and taking the sub-region with the largest pixel richness as the position of the abnormal tissue in the medical examination image; The cutter and positioning module are used to control the cutter to remove the abnormal tissue of the patient according to the position of the abnormal tissue in the medical examination image.

2. A bronchoscopic cutter and positioning system according to claim 1, characterized in that: The preprocessing module comprises: A neighborhood matrix construction unit is used to take a local window centered on each pixel point on the medical examination image and convert the pixel points under the local window into a neighborhood matrix; A similarity calculation unit, used for calculating the similarity between any two pixels based on a neighborhood matrix; A denoising weight determination unit, used to calculate the denoising weight of each pixel according to the similarity; The pixel preprocessing unit is used to perform denoising preprocessing on the pixels of the medical examination image by using the denoising weights of the pixels to obtain the preprocessed medical examination image.

3. A bronchoscope cutter and positioning system according to claim 2, characterized in that: The calculating the similarity between any two pixels based on the neighborhood matrix includes: Using the formula: Calculate the similarity between any two pixels; where d(i,j) represents the similarity between the i-th pixel and the j-th pixel, G a represents the Gaussian kernel matrix, v(N i ) represents the neighborhood matrix of the i-th pixel, v(N j ) represents the neighborhood matrix of the j-th pixel.

4. A bronchoscope cutter and positioning system according to claim 3, characterized in that: The denoising weight of each pixel is calculated based on the similarity, including: Using the formula: Calculate the denoising weight of each pixel; where w(i,j) represents the denoising weight, Z(i) represents the normalization coefficient, I represents the set of all pixels on the medical examination image, and h represents the attenuation parameter.

5. A bronchoscope cutter and positioning system according to claim 4, characterized in that: The pixels of the medical examination image are subjected to denoising preprocessing using the denoising weights of the pixels to obtain the preprocessed medical examination image, including: The denoising weight of each pixel is used to perform weighted summation on each pixel to obtain the denoised pixel; the weighted summation formula is: in, represents the pixel after denoising, v(j) represents the jth pixel on the medical examination image; The preprocessed medical examination images are regenerated using the denoised pixels.

Images