An intelligent processing method for obstetric images

Abstract

The present invention relates to the technical field of fetal ultrasound image enhancement, and specifically relates to an intelligent processing method for obstetric images. The present invention collects fetal ultrasound images; according to the regional gray-scale features and gradient features of brain tissue, heart tissue, and abdominal tissue in the images respectively, and combining the gray-scale distribution and gradient distribution of pixel points in a preset direction, the brain probability factor, heart probability factor, and abdominal probability factor of the pixel points are obtained, and then the brain region, heart region, and abdominal region are obtained; according to the probability factor differences and position distributions in different images, the image matching degree is obtained, and then the image is enhanced. The present invention can better restore the true morphology of the key feature regions of the fetus, reduce the influence of interference factors on the image accuracy, and enable relevant personnel to diagnose the fetal condition more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of fetal ultrasound image enhancement, and particularly relates to an intelligent processing method for obstetric images. Background Art

[0002] In the field of medical image processing, the processing of obstetric images has always been an important research direction. As the most common imaging examination method in obstetrics, ultrasound examination can obtain many key information about the fetus and pregnant women in the early and middle stages of pregnancy, including embryonic development, organ health, amniotic fluid volume, placental function, etc. Although ultrasound examination has the advantages of non-invasiveness, convenience, real-time, etc., its imaging quality is often affected by various factors, and the obtained ultrasound images have low resolution, noise and artifacts, and certain image processing operations are also required to enhance the image quality.

[0003] Using ultrasound images to diagnose whether a fetus has developmental abnormalities is one of its important functions. However, poor image quality is very likely to result in unclear imaging of some tissues or structures of the fetus, making it difficult for doctors to make accurate judgments. Non-local means filtering is a commonly used method for ultrasound image enhancement. This method uses the pixel values in similar regions of the image to perform weighted averaging on each pixel, thereby effectively removing noise and retaining the details of the image. This method has certain advantages in ultrasound image enhancement. However, when applied to fetal ultrasound images, since this algorithm will blur the edge structure to a certain extent and the filtering effect on complex regions is not strong, some fine structures become too blurred or distorted, ultimately resulting in misdiagnosis and missed diagnosis when relevant personnel analyze key fetal features (such as ventricle size, heart shape, etc.), and the processing effect is not ideal. Summary of the Invention

[0004] In order to solve the technical problem that when using the non-local means filtering algorithm to enhance fetal ultrasound images, the edge structure will be blurred, making some fine structures too blurred or distorted, and ultimately leading to misdiagnosis and missed diagnosis when relevant personnel analyze the key features of the fetus, and the processing effect is not ideal, the purpose of the present invention is to provide an intelligent processing method for obstetric images, and the specific technical solution adopted is as follows: An intelligent processing method for obstetric images, the method includes: collecting a preset number of fetal ultrasound images; all the fetal ultrasound images form a fetal ultrasound image set; arbitrarily selecting any pixel point in any one of the fetal ultrasound images as the reference pixel point of the reference fetal image; obtaining the brain probability factor of the reference pixel point belonging to the brain tissue, the heart probability factor of the reference pixel point belonging to the heart tissue, and the abdominal probability factor of the reference pixel point belonging to the abdominal tissue according to the regional gray level features and regional gradient features of the brain tissue, heart tissue and abdominal tissue in the reference fetal image, as well as the gradient distribution and gray level distribution of the reference pixel point in all preset directions; obtaining the brain region, heart region and abdominal region in each fetal ultrasound image according to the brain probability factor, the heart probability factor and the abdominal probability factor of each pixel point in each fetal ultrasound image; the brain region, heart region and abdominal region are used as the key feature regions in the fetal ultrasound image; obtaining the image matching degree between the reference fetal image and each other fetal ultrasound image according to the position distribution difference of the key feature regions in the reference fetal image and each other fetal ultrasound image, as well as the differences in the brain probability factor, heart probability factor and abdominal probability factor of the pixel points in the key feature regions; enhancing the reference fetal image according to the image matching degree between the reference fetal image and each other fetal ultrasound image.

[0005] Further, the method for obtaining the brain probability factor includes: obtaining the possible degree that each preset direction of the reference pixel point can cross the edge of the brain tissue according to the gradient distribution of the reference pixel point in each preset direction; taking the preset direction with the possible degree of crossing the edge of the brain tissue greater than the preset first threshold as the brain tissue judgment direction; counting the number of brain tissue judgment directions in the preset directions; obtaining the brain probability factor according to the brain probability factor calculation formula, and the brain probability factor calculation formula is as follows: In the formula, represents the brain probability factor of the reference pixel point belonging to the brain tissue; represents the number of brain tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the th preset number of pixels of the pixel point in the th preset direction of the reference pixel point; the gray difference between the th pixel in a preset direction and the next pixel.

[0006] Furthermore, the method for obtaining the possibility degree that each preset direction of the reference pixel can cross the edge of the brain tissue includes: obtaining the possibility degree according to the possibility degree calculation formula, and the possibility degree calculation formula is as follows: In the formula, represents the possibility degree that the th preset direction of the reference pixel can cross the edge of the brain tissue; represents the maximum gradient value in the th preset direction of the reference pixel; represents the second largest gradient value in the th preset direction of the reference pixel; represents the maximum gradient value on the reference fetal image; represents the distance between the pixel corresponding to the maximum gradient value and the pixel corresponding to the second largest gradient value in the th preset direction of the reference pixel; represents the normalization function.

[0007] Furthermore, the method for obtaining the cardiac probability factor includes: calculating the possibility degree that each preset direction of the reference pixel can cross the edge of the cardiac tissue; obtaining the cardiac tissue judgment direction of the reference pixel according to the possibility degree that each preset direction of the reference pixel can cross the edge of the cardiac tissue; taking the midpoint of the two pixels corresponding to the maximum gradient values in each preset direction of the reference pixel as the symmetric center point of the reference pixel in each preset direction; obtaining the reference symmetric point of the reference pixel in each preset direction according to the position of the reference pixel and the symmetric center point in each preset direction; obtaining the cardiac tissue judgment direction of the reference symmetric point according to the possibility degree that each preset direction of the reference symmetric point can cross the edge of the cardiac tissue; obtaining the cardiac probability factor according to the cardiac probability factor calculation formula, and the cardiac probability factor calculation formula is as follows: In the formula, represents the cardiac probability factor that the reference pixel belongs to the cardiac tissue; represents the number of cardiac tissue judgment directions of the reference pixel; represents the number of preset directions of the reference pixel; represents the number of cardiac tissue judgment directions in the th preset direction of the reference symmetric point.

[0008] Further, the method for obtaining the abdominal probability factor includes: obtaining the abdominal tissue judgment direction of the reference pixel point according to the possibility of crossing the edge of the abdominal tissue in each preset direction of the reference pixel point; using Otsu's method to perform binary segmentation on the preset area of the reference pixel point to obtain all high-gray-value areas; obtaining the abdominal probability factor according to the abdominal probability factor calculation formula, and the abdominal probability factor calculation formula is as follows: In the formula, represents the abdominal probability factor that the reference pixel point belongs to the abdominal tissue; represents the number of abdominal tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the number of high-gray-value areas in the preset area of the reference pixel point; represents the number of pixel points in each high-gray-value area in the preset area of the reference pixel point; represents the th high-gray-value area in the preset area of the reference pixel point, and the th pixel point; represents the maximum area of the high-gray-value areas in the preset area of the reference pixel point.

[0009] Further, the method for obtaining the key feature area includes: taking the pixel points with the brain probability factor greater than the preset second threshold as brain tissue pixel points; taking the pixel points with the heart probability factor greater than the preset second threshold as heart tissue pixel points; taking the pixel points with the abdominal probability factor greater than the preset second threshold as abdominal tissue pixel points; taking the area composed of all brain tissue pixel points as the brain area; taking the area composed of all heart tissue pixel points as the heart area; taking the area composed of all abdominal tissue pixel points as the abdominal area; taking the brain area, the heart area and the abdominal area as the key feature area.

[0010] Further, the method for obtaining the image matching degree includes: taking any fetal ultrasound image other than the reference fetal image as a comparison fetal image; obtaining the key feature similarity between the reference fetal image and the comparison fetal image according to the differences in brain probability factors, heart probability factors, and abdominal probability factors of the pixel points in the key feature area between the reference fetal image and the comparison fetal image; obtaining the body structure similarity between the reference fetal image and the comparison fetal image according to the difference in the position distribution of the key feature areas between the reference fetal image and the comparison fetal image; collectively referring to the brain probability factor, heart probability factor, and abdominal probability factor in the key feature area as probability factors; calculating the mean value of the probability factors of all pixel points in all key feature areas of the reference fetal image; obtaining the image matching degree according to the image matching degree calculation formula, and the image matching degree calculation formula is as follows: In the formula, represents the image matching degree between the reference fetal image and the comparison fetal image; represents the key feature similarity between the reference fetal image and the comparison fetal image; represents the mean value of the probability factors of all pixel points in all key feature areas of the reference fetal image; represents a preset second threshold; represents the body structure similarity between the reference fetal image and the comparison fetal image.

[0011] Further, the method for obtaining the key feature similarity includes: calculating the difference in the mean value of the brain probability factors of the pixel points in the brain area of the reference fetal image and the comparison fetal image, calculating the difference in the mean value of the heart probability factors of the pixel points in the heart area of the reference fetal image and the comparison fetal image, and calculating the difference in the mean value of the abdominal probability factors of the pixel points in the abdominal area of the reference fetal image and the comparison fetal image; averaging the differences in the mean value of the brain probability factors, the mean value of the heart probability factors, and the mean value of the abdominal probability factors between the reference fetal image and the comparison fetal image, and performing a negative correlation normalization operation to obtain the key feature similarity between the reference fetal image and the comparison fetal image.

[0012] Further, the method for obtaining the similarity of the body structure includes: obtaining the center of gravity points of the brain region, the heart region, and the abdominal region of the reference fetal image and the comparison fetal image; in each fetal ultrasound image, obtaining the line connecting the center of gravity point of the brain region and the center of gravity point of the heart region as the first line, and obtaining the line connecting the center of gravity point of the heart region and the center of gravity point of the abdominal region as the second line; taking the angle between the first line and the second line as the first angle; obtaining the similarity of the body structure according to the formula for calculating the similarity of the body structure between the reference fetal image and the comparison fetal image, and the formula for calculating the similarity of the body structure is as follows: In the formula, represents the similarity of the body structure between the reference fetal image and the comparison fetal image; represents the length of the first line in the reference fetal image; represents the length of the second line in the reference fetal image; represents the length of the first line in the comparison fetal image; represents the length of the second line in the comparison fetal image; represents the first angle in the reference fetal image; represents the first angle in the comparison fetal image.

[0013] Further, according to the degree of image matching between the reference fetal image and each other fetal ultrasound image, the reference fetal image is enhanced, including: calculating the degree of image matching between the reference fetal image and each other fetal ultrasound image in the fetal ultrasound image set; selecting a preset first number of other fetal ultrasound images with the largest degree of image matching as the reference filtering images; performing non-local mean filtering on the reference fetal image according to the preset first number of reference filtering images to obtain an enhanced fetal image.

[0014] The present invention has the following beneficial effects: The present invention collects a preset number of fetal ultrasound images. Since in fetal ultrasound images, the brain, heart, spine, and gastrointestinal regions of the fetus are important image areas for detecting potential abnormalities in the fetus and are very important for relevant personnel to accurately judge the condition of the fetus, it is necessary to accurately extract the brain region, heart region, and abdominal region in the fetal ultrasound image and use them as key feature regions. Since the brain region, heart region, and abdominal region each have obvious regional gray-scale features and regional gradient features, the gradient distribution and gray-scale distribution of pixels in all preset directions are combined to obtain the brain probability factor of the reference pixel belonging to brain tissue, the heart probability factor of the reference pixel belonging to heart tissue, and the abdominal probability factor of the reference pixel belonging to abdominal tissue. Since the conventional non-local mean filtering algorithm will blur the important anatomical structures of the fetus with a large number of significant edges and make them difficult to identify, similar fetal ultrasound images are matched in the fetal ultrasound image set through the key feature regions of the reference fetal image to achieve non-local mean filtering of multiple images. And the similarity of the fetal body shape is calculated according to the ratio and angle of the line segments formed by the centers of these three regions, and at the same time, the comprehensive probability factor of each region is combined to obtain the image performance similarity of the three key feature regions, and finally the image matching degree between every two fetal images is obtained. The present invention can better restore the true shape of the key feature regions of the fetus, reduce the influence of interference factors on the image accuracy, and enable relevant personnel to more accurately diagnose the condition of the fetus. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of an intelligent processing method for obstetric images provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in combination with the accompanying drawings and preferred embodiments, detail the specific implementation manners, structures, features, and effects of an intelligent processing method for obstetric images proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0019] The following specifically describes the specific solution of an intelligent processing method for obstetric images provided by the present invention in conjunction with the accompanying drawings.

[0020] Please refer to Figure 1 , which shows an intelligent processing method for obstetric images provided by an embodiment of the present invention. The method includes: Step S1: Collect a preset number of fetal ultrasound images; all fetal ultrasound images form a fetal ultrasound image set.

[0021] The embodiment of the present invention is mainly applied to the scenario of fetal ultrasound image enhancement. Therefore, the fetal ultrasound images of the parturient are first obtained; in order to facilitate the subsequent enhancement of fetal images through similar structures in different fetal ultrasound images, the embodiment of the present invention collects a preset number of fetal ultrasound images.

[0022] In one embodiment of the present invention, a ultrasonic probe is used to obtain fetal ultrasound images of different parturients, and upload them to the image processing module in the ultrasonic device for processing, and finally store them in the corresponding image storage module. It should be noted that the preset number is set to 100, and the preset number can be set by oneself, and no limitation is made here.

[0023] Step S2: Arbitrarily select any pixel point in any one of the fetal ultrasound images as the reference pixel point of the reference fetal image; according to the regional gray-scale features and regional gradient features of the brain tissue, heart tissue and abdominal tissue in the reference fetal image respectively, and the gradient distribution and gray-scale distribution of the reference pixel point in all preset directions, obtain the brain probability factor of the reference pixel point belonging to the brain tissue, the heart probability factor of the reference pixel point belonging to the heart tissue, and the abdominal probability factor of the reference pixel point belonging to the abdominal tissue; according to the brain probability factor, heart probability factor and abdominal probability factor of each pixel point in each fetal ultrasound image, obtain the brain region, heart region and abdominal region in each fetal ultrasound image; the brain region, heart region and abdominal region are used as the key feature regions in the fetal ultrasound image.

[0024] In fetal ultrasound images, the brain, heart, spine and gastrointestinal parts of the fetus are important image regions for detecting potential abnormalities of the fetus, and it is very important for relevant personnel to accurately judge the condition of the fetus. Therefore, it is necessary to accurately extract the brain region, heart region and abdominal region in the fetal ultrasound image.

[0025] In the brain region of a fetus, the intraventricular fluid (such as cerebrospinal fluid) has a weak reflection to ultrasonic waves, so it appears as a region with a lower gray level in the fetal ultrasound image; while the brain tissue is mainly composed of water and soft tissue, and ultrasonic waves have more reflections and scatterings in these regions, thus appearing as a region with a higher gray level in the fetal ultrasound image. In addition, the acoustic properties of the intraventricular fluid are relatively uniform, and the pixel distribution is more consistent; while there are more details (such as gyri and sulci) on the surface of the brain tissue, and the pixel distribution is more abundant. Therefore, in the embodiments of the present invention, the brain probability factor of a reference pixel point belonging to the brain tissue can be obtained according to the regional gray level feature and regional gradient feature of the brain tissue in the reference fetal image, as well as the gradient distribution and gray level distribution of the reference pixel point in all preset directions.

[0026] Preferably, in an embodiment of the present invention, the method for obtaining the brain probability factor includes: obtaining the possibility degree that each preset direction of the reference pixel point can cross the edge of the brain tissue according to the gradient distribution of the reference pixel point in each preset direction; in an embodiment of the present invention, the preset directions are set as the four directions of up, down, left, and right of the reference pixel point, and the preset directions can be set by oneself and are not limited herein. The formula for the possibility degree is as follows: In the formula, represents the possibility degree that the th preset direction of the reference pixel point can cross the edge of the brain tissue; represents the maximum gradient value in the th preset direction of the reference pixel point; represents the second largest gradient value in the th preset direction of the reference pixel point; represents the maximum gradient value on the reference fetal image; represents the distance between the pixel point corresponding to the maximum gradient value and the pixel point corresponding to the second largest gradient value in the th preset direction of the reference pixel point; represents the normalization function.

[0027] In the formula for the possibility degree, the maximum gradient value and the second largest gradient value in the th preset direction of the reference pixel point respectively correspond to the outer edge of the brain tissue and the inner wall edge of the ventricle, and the gradient values of the pixel points on both edges are close to the maximum gradient value in the fetal ultrasound image. Therefore, the larger, and the smaller, it indicates that the pixels of the chain are closer to the distance between the outer edge of the brain tissue and the inner wall edge of the ventricle in the real situation, indicating that the possibility of crossing the edge of the brain tissue in the th preset direction is greater.

[0028] Take the preset direction that may cross the edge of the brain tissue and is greater than the preset first threshold as the brain tissue judgment direction; in an embodiment of the present invention, the preset first threshold is set to 0.7. It should be noted that the preset first threshold can be set by oneself and is not limited here.

[0029] Count the number of brain tissue judgment directions in the preset direction; obtain the brain probability factor according to the brain probability factor calculation formula, and the brain probability factor calculation formula is as follows: In the formula, represents the brain probability factor that the reference pixel point belongs to the brain tissue; represents the number of brain tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the th preset first number of pixels on the th preset direction of the reference pixel point; represents the th pixel and the gray difference between the next pixel on the

[0030] In the brain probability factor calculation formula, the larger the average gray change value in the th preset direction, the richer the gray change of the reference pixel point in the th preset direction. Analyze the average gray change values of all preset directions to obtain , The larger it is, the richer the gray change of the reference pixel point in all preset directions. At this time, the reference pixel point is more likely to be located in the brain tissue; the larger the proportion of the number of brain tissue judgment directions of the reference pixel point, the more likely the positioning of the reference pixel point is located within the brain tissue; at this time, the brain probability factor that the reference pixel point belongs to the brain tissue is larger.

[0031] The heart of the fetus is relatively small in area compared to the brain and is usually located in the middle of the whole body. The gray distribution in the heart area has great similarities with the brain. The myocardium layer outside the heart shows a clear boundary and has a higher gray level. The inside is mainly composed of four chambers (ventricles and atria), and the gray level is lower. However, the heart chambers have the characteristic of being pairwise symmetric, and adjacent chambers are basically symmetric in position and size. Therefore, in the embodiment of the present invention, according to the regional gray characteristics and regional gradient characteristics of the heart tissue in the reference fetal image, and the gradient distribution and gray distribution of the reference pixel point in all preset directions, the heart probability factor that the reference pixel point belongs to the heart tissue is obtained.

[0032] Preferably, in one embodiment of the present invention, the method for obtaining the cardiac probability factor includes: calculating, according to the same calculation steps of the above-mentioned brain probability factor, the possibility degree that each preset direction of the reference pixel point can cross the edge of the cardiac tissue; taking the preset direction with the possibility degree of crossing the edge of the cardiac tissue greater than a preset first threshold as the cardiac tissue judgment direction of the reference pixel point.

[0033] Taking the midpoint of the two gradient maximum corresponding pixels of the reference pixel point in each preset direction as the symmetric center point of the reference pixel point in each preset direction; obtaining the reference symmetric point of the reference pixel point in each preset direction according to the positions of the reference pixel point and the symmetric center point in each preset direction; obtaining the cardiac tissue judgment direction of the reference symmetric point according to the possibility degree that the reference symmetric point in each preset direction can cross the edge of the cardiac tissue; the cardiac tissue judgment direction of the reference symmetric point is obtained according to the same screening method.

[0034] Obtaining the cardiac probability factor according to the cardiac probability factor calculation formula, and the cardiac probability factor calculation formula is as follows: In the formula, represents the cardiac probability factor that the reference pixel point belongs to the cardiac tissue; represents the number of cardiac tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the th number of cardiac tissue judgment directions of the reference symmetric point in the

[0035] In the abdominal probability factor calculation formula, if the number of cardiac tissue judgment directions of the reference pixel point is more, it indicates that the reference pixel point is more likely to be in the cardiac chamber; at the same time, if the number of cardiac tissue judgment directions of the reference symmetric point in the th preset direction is more, it indicates that the reference symmetric point in the th preset direction is more likely to be in the cardiac chamber. Analyzing the reference symmetric points of the reference pixel point in all preset directions, obtaining , The larger it is, it indicates that the reference symmetric points of the reference pixel point in all preset directions are likely to be in the cardiac chamber. At this time, the reference pixel point is more likely to be in the cardiac chamber, and the cardiac probability factor that the reference pixel point belongs to the cardiac tissue is larger.

[0036] The abdomen is located in the lower part of the fetal body, and the lower part of the abdomen is mainly covered by the intestines. Therefore, the fetal intestines are identified to represent the lower part of the whole body. The intestines in the ultrasound image also have similar characteristics to the brain and heart, that is, the outer periphery is the intestinal wall with a high gray value, and the inner part is the amniotic fluid or other liquids with a low gray value. In addition, during fetal development, the intestines may accumulate a certain amount of gas, and the echo of the gas is strong. Therefore, the intestinal area will show many high gray value areas with irregular shapes, interspersed in the low gray value liquid area. Therefore, in the embodiments of the present invention, according to the regional gray characteristics and regional gradient characteristics of the abdominal tissue in the reference fetal image, as well as the gradient distribution and gray distribution of the reference pixel point in all preset directions, the abdominal probability factor of the reference pixel point belonging to the abdominal tissue is obtained.

[0037] Preferably, in an embodiment of the present invention, the method for obtaining the abdominal probability factor includes: according to the same calculation steps of the above-mentioned brain probability factor, calculating the possibility that each preset direction of the reference pixel point can cross the edge of the abdominal tissue; taking the preset direction with the possibility of crossing the edge of the abdominal tissue greater than the preset first threshold as the judgment direction of the abdominal tissue of the reference pixel point.

[0038] Using the Otsu method to perform binary segmentation on the preset area of the reference pixel point can divide all areas of the reference fetal image into two types of areas. Among them, the type area with a higher gray value is used as the high gray value area, and the type area with a lower gray value is used as the low gray value area, so as to obtain all high gray value areas; in the embodiments of the present invention, the preset area is set to be centered on the reference pixel point, of the rectangular area, and the preset area can be set by itself and is not limited here. Among them, the Otsu method is a well-known technical means in the art and will not be elaborated here.

[0039] Obtain the abdominal probability factor according to the abdominal probability factor calculation formula. The abdominal probability factor calculation formula is as follows: In the formula, represents the abdominal probability factor of the reference pixel point belonging to the abdominal tissue; represents the number of judgment directions of the abdominal tissue of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the number of high gray value areas in the preset area of the reference pixel point; represents the number of pixel points of each high gray value area in the preset area of the reference pixel point; represents the th high gray value area in the preset area of the reference pixel point and the th pixel point's gray value; represents the maximum value of the area of the high gray value area in the preset area of the reference pixel point.

[0040] In the abdominal probability factor calculation formula, if the number of abdominal tissue judgment directions of the reference pixel point is larger, it indicates that the reference pixel point is more likely to be in the abdominal area. At this time, the abdominal probability factor of the reference pixel point belonging to the abdominal tissue is larger; since the gray value of the gas area in the fetal intestine is very high, the more high-gray-value areas in the preset area, that is the larger, it indicates that the gray value of the high-gray-value area is larger. At this time, it is more likely that intestinal gas exists in the preset area of the reference pixel point. At this time, the reference pixel point is more likely to be in the abdominal area, that is, the abdominal probability factor of the reference pixel point belonging to the abdominal tissue is larger; using the product of the number of high-gray-value areas and the maximum area of the high-gray-value areas indicates that the number of high-gray-value areas where the reference pixel point is not located in the brain area is small at this time, and the maximum area of the high-gray-value area indicates that the reference pixel point is not a high-brightness noise pixel point, so the larger, it indicates that the abdominal probability factor of the reference pixel point belonging to the abdominal tissue is larger.

[0041] Preferably, in an embodiment of the present invention, the method for obtaining the key feature area includes: regarding the pixel points with a brain probability factor greater than a preset second threshold as brain tissue pixel points; regarding the pixel points with a heart probability factor greater than a preset second threshold as heart tissue pixel points; regarding the pixel points with an abdominal probability factor greater than a preset second threshold as abdominal tissue pixel points; in an embodiment of the present invention, the preset second threshold is set to 0.8, and the preset second threshold can be set by itself and is not limited herein.

[0042] Regarding the area composed of all brain tissue pixel points as the brain area; regarding the area composed of all heart tissue pixel points as the heart area; regarding the area composed of all abdominal tissue pixel points as the abdominal area; regarding the brain area, the heart area and the abdominal area as the key feature areas.

[0043] Step S3: Obtain the image matching degree between the reference fetal image and each other fetal ultrasound image according to the position distribution difference of the key feature areas in the reference fetal image and each other fetal ultrasound image, as well as the differences in the brain probability factor, heart probability factor and abdominal probability factor of the pixel points in the key feature areas; enhance the reference fetal image according to the image matching degree between the reference fetal image and each other fetal ultrasound image.

[0044] Since the conventional non - local mean filtering algorithm uses the regions of pixels with similar gray levels in the same fetal ultrasound image to filter each other to achieve the denoising effect, this method will blur and make it difficult to identify the important anatomical structures of the fetus with a large number of significant edges. Therefore, after initially locating the key feature regions of the reference fetal image, similar fetal ultrasound images are matched in the fetal ultrasound image set through the key feature regions of the reference fetal image to achieve non - local mean filtering of multiple images. It is known that the brain, heart, and abdomen respectively represent the upper, middle, and lower parts of the fetal body. Therefore, the similarity of the fetal body is calculated based on the ratio and angle of the line segments formed by the centers of these three regions, and the image performance similarity of the three key feature regions is obtained by combining the comprehensive probability factors of each region. Finally, the image matching degree between every two fetal images is obtained.

[0045] Preferably, in an embodiment of the present invention, the method for obtaining the image matching degree includes: using any fetal ultrasound image other than the reference fetal image as the comparison fetal image.

[0046] Calculate the mean difference of the brain probability factors of the pixels in the brain region between the reference fetal image and the comparison fetal image, calculate the mean difference of the heart probability factors of the pixels in the heart region between the reference fetal image and the comparison fetal image, and calculate the mean difference of the abdominal probability factors of the pixels in the abdominal region between the reference fetal image and the comparison fetal image; average the mean differences of the brain probability factors, heart probability factors, and abdominal probability factors between the reference fetal image and the comparison fetal image, and perform a negative - correlation normalization operation to obtain the key feature similarity between the reference fetal image and the comparison fetal image. In an embodiment of the present invention, the formula for calculating the key feature similarity is as follows: In the formula, represents the key feature similarity between the reference fetal image and the comparison fetal image; represents the mean difference of the brain probability factors of the pixels in the brain region between the reference fetal image and the comparison fetal image; represents the mean difference of the heart probability factors of the pixels in the heart region between the reference fetal image and the comparison fetal image; represents the mean difference of the abdominal probability factors of the pixels in the abdominal region between the reference fetal image and the comparison fetal image.

[0047] In the formula for calculating the key feature similarity, the smaller the mean differences of the brain probability factors, heart probability factors, and abdominal probability factors between the reference fetal image and the comparison fetal image, the higher the similarity of the key feature regions of the two images, that is, the greater the key feature similarity between the reference fetal image and the comparison fetal image.

[0048] Obtain the centroid points of the brain region, the centroid point of the heart region, and the centroid point of the abdominal region for the reference fetal image and the comparison fetal image; in each fetal ultrasound image, obtain the line connecting the centroid point of the brain region and the centroid point of the heart region as the first line, and obtain the line connecting the centroid point of the heart region and the centroid point of the abdominal region as the second line; take the angle between the first line and the second line as the first angle.

[0049] Obtain the morphological structure similarity according to the morphological structure similarity calculation formula between the reference fetal image and the comparison fetal image. The morphological structure similarity calculation formula is as follows: In the formula, represents the morphological structure similarity between the reference fetal image and the comparison fetal image; represents the length of the first line in the reference fetal image; represents the length of the second line in the reference fetal image; represents the length of the first line in the comparison fetal image; represents the length of the second line in the comparison fetal image; represents the first angle in the reference fetal image; represents the first angle in the comparison fetal image.

[0050] In the morphological structure similarity calculation formula, the ratio between the first line and the second line in the reference fetal image, and the ratio between the first line and the second line in the comparison fetal image, the smaller the difference between them, the greater the similarity in the overall fetal body proportion between the reference fetal image and the comparison fetal image. At this time, the morphological structure similarity between the reference fetal image and the comparison fetal image is greater; the smaller the difference in the first angle between the reference fetal image and the comparison fetal image, the more similar the relative positions of the reference fetal image and the comparison fetal image in the key feature regions. At this time, the morphological structure similarity between the reference fetal image and the comparison fetal image is greater.

[0051] Collectively refer to the brain probability factor, the heart probability factor, and the abdominal probability factor in the key feature regions as probability factors; calculate the mean value of the probability factors of all pixel points in all key feature regions in the reference fetal image.

[0052] Obtain the image matching degree according to the image matching degree calculation formula. The image matching degree calculation formula is as follows: In the formula, represents the image matching degree between the reference fetal image and the comparison fetal image; represents the key feature similarity between the reference fetal image and the comparison fetal image; represents the mean value of the probability factors of all pixel points in all key feature regions in the reference fetal image; represents a preset second threshold; represents the similarity of the physical structure between the reference fetal image and the comparison fetal image.

[0053] In the image matching degree calculation formula, represents the proportion of the part where the average probability factor exceeds the preset second threshold to the maximum value that can be exceeded, that is The larger the proportion between, the stronger the regional feature performance of the fetus in the key feature area of the reference fetal image. At this time, the greater the weight should be given to the key feature similarity between the reference fetal image and the comparison fetal image, and the smaller the weight should be given to the similarity of the physical structure between the reference fetal image and the comparison fetal image, that is the smaller, so is used to represent the image matching degree between the reference fetal image and the comparison fetal image.

[0054] Preferably, in an embodiment of the present invention, according to the image matching degree between the reference fetal image and each other fetal ultrasound image, the reference fetal image is enhanced, including: calculating the image matching degree between the reference fetal image and each other fetal ultrasound image in the fetal ultrasound image set; selecting the other fetal ultrasound images with the largest preset first number of image matching degrees as reference filtering images; in the embodiment of the present invention, the preset first number is set to 3. It should be noted that the preset first number can be set by itself and is not limited here.

[0055] Perform non-local mean filtering on the reference fetal image according to the preset first number of reference filtering images, expand the matching range to 3 similar fetal ultrasound images, and perform window search on 4 fetal ultrasound images when filtering each pixel point of the reference fetal image, so that each pixel point can search for a window with a high similarity, thereby improving the denoising effect and better retaining details, and being able to handle large-scale noise problems such as artifacts, so as to obtain an enhanced fetal image.

[0056] Visualize the enhanced fetal image into a display device to help relevant personnel better analyze the fetal development status.

[0057] In summary, a preset number of fetal ultrasound images are collected; all the fetal ultrasound images form a fetal ultrasound image set; an arbitrary pixel point in an arbitrary fetal ultrasound image is selected as the reference pixel point of the reference fetal image; according to the regional gray-scale features and regional gradient features of the brain tissue, heart tissue, and abdominal tissue in the reference fetal image, as well as the gradient distribution and gray-scale distribution of the reference pixel point in all preset directions, the brain probability factor of the reference pixel point belonging to the brain tissue, the heart probability factor of the reference pixel point belonging to the heart tissue, and the abdominal probability factor of the reference pixel point belonging to the abdominal tissue are obtained; according to the brain probability factor, heart probability factor, and abdominal probability factor of each pixel point in each fetal ultrasound image, the brain region, heart region, and abdominal region in each fetal ultrasound image are obtained; the brain region, heart region, and abdominal region are used as the key feature regions in the fetal ultrasound image; according to the difference in the position distribution of the key feature regions in the reference fetal image and each other fetal ultrasound image, as well as the differences in the brain probability factor, heart probability factor, and abdominal probability factor of the pixel points in the key feature regions, the image matching degree between the reference fetal image and each other fetal ultrasound image is obtained; according to the image matching degree between the reference fetal image and each other fetal ultrasound image, the reference fetal image is enhanced.

[0058] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. An intelligent processing method for obstetric images, characterized in that, The method includes: collecting a preset number of fetal ultrasound images; all the fetal ultrasound images form a fetal ultrasound image set; arbitrarily selecting any pixel point in any one of the fetal ultrasound images as the reference pixel point of the reference fetal image; obtaining the brain probability factor of the reference pixel point belonging to the brain tissue, the heart probability factor of the reference pixel point belonging to the heart tissue, and the abdominal probability factor of the reference pixel point belonging to the abdominal tissue according to the regional gray-scale features and regional gradient features of the brain tissue, heart tissue, and abdominal tissue in the reference fetal image, as well as the gradient distribution and gray-scale distribution of the reference pixel point in all preset directions; obtaining the brain region, heart region, and abdominal region in each fetal ultrasound image according to the brain probability factor, the heart probability factor, and the abdominal probability factor of each pixel point in each fetal ultrasound image; the brain region, heart region, and abdominal region are used as the key feature regions in the fetal ultrasound image; obtaining the image matching degree between the reference fetal image and each other fetal ultrasound image according to the difference in the position distribution of the key feature regions in the reference fetal image and each other fetal ultrasound image, as well as the differences in the brain probability factor, heart probability factor, and abdominal probability factor of the pixel points in the key feature regions; the method for obtaining the image matching degree includes: taking any one of the fetal ultrasound images other than the reference fetal image as the comparison fetal image; obtaining the image matching degree according to the image matching degree calculation formula, and the image matching degree calculation formula is as follows: In the formula, represents the image matching degree between the reference fetal image and the comparison fetal image; represents the key feature similarity between the reference fetal image and the comparison fetal image; represents the average value of the probability factors of all pixel points in all key feature regions in the reference fetal image; represents a preset second threshold; represents the body structure similarity between the reference fetal image and the comparison fetal image; enhancing the reference fetal image according to the image matching degree between the reference fetal image and each other fetal ultrasound image, specifically including: calculating the image matching degree between the reference fetal image and each other fetal ultrasound image in the fetal ultrasound image set; selecting a preset first number of other fetal ultrasound images with the largest image matching degree as the reference filtering images; performing non-local mean filtering on the reference fetal image according to the preset first number of reference filtering images to obtain the enhanced fetal image.

2. The intelligent processing method for an obstetric image according to claim 1, wherein The method for obtaining the brain probability factor includes: obtaining the possibility that each preset direction of a reference pixel point can cross the edge of brain tissue according to the gradient distribution of the reference pixel point in each preset direction; taking the preset directions with the possibility of crossing the edge of brain tissue greater than a preset first threshold as the brain tissue judgment directions; counting the number of brain tissue judgment directions in the preset directions; and obtaining the brain probability factor according to the brain probability factor calculation formula, and the brain probability factor calculation formula is as follows: In the formula, represents the brain probability factor that the reference pixel point belongs to brain tissue; represents the number of brain tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the th preset number of pixels of the pixel point in the th preset direction of the reference pixel point; represents the gray difference between the th pixel point and the next pixel point in the th preset direction of the reference pixel point.

3. The intelligent processing method for an obstetric image according to claim 2, characterized in that, The method for obtaining the possible degree that each preset direction of the reference pixel point can cross the edge of the brain tissue includes: obtaining the possible degree according to the possible degree calculation formula, and the possible degree calculation formula is as follows: In the formula, represents the possible degree that the th preset direction of the reference pixel point can cross the edge of the brain tissue; represents the maximum gradient value in the th preset direction of the reference pixel point; represents the second largest gradient value in the th preset direction of the reference pixel point; represents the maximum gradient value on the reference fetal image; represents the distance between the pixel point corresponding to the maximum gradient value and the pixel point corresponding to the second largest gradient value in the th preset direction of the reference pixel point; represents the pixel point number corresponding to the maximum gradient value in each preset direction of the reference pixel point; represents the pixel point number corresponding to the second largest gradient value in each preset direction of the reference pixel point; represents the normalization function.

4. The intelligent processing method for obstetric images according to claim 1, wherein The method for obtaining the cardiac probability factor includes: calculating the possibility that each preset direction of a reference pixel point can cross the edge of the cardiac tissue; obtaining the cardiac tissue judgment direction of the reference pixel point according to the possibility that each preset direction of the reference pixel point can cross the edge of the cardiac tissue; taking the midpoint of the two gradient maximum corresponding pixel points of the reference pixel point in each preset direction as the symmetric center point of the reference pixel point in each preset direction; obtaining the reference symmetric point of the reference pixel point in each preset direction according to the positions of the reference pixel point and the symmetric center point in each preset direction; obtaining the cardiac tissue judgment direction of the reference symmetric point according to the possibility that each preset direction of the reference symmetric point can cross the edge of the cardiac tissue; obtaining the cardiac probability factor according to the cardiac probability factor calculation formula, and the cardiac probability factor calculation formula is as follows: In the formula, represents the cardiac probability factor that the reference pixel point belongs to the cardiac tissue; represents the number of cardiac tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the th number of cardiac tissue judgment directions in the preset direction of the reference symmetric point.

5. The intelligent processing method of an obstetric image according to claim 1, characterized in that The method for obtaining the abdominal probability factor includes: obtaining the abdominal tissue judgment direction of the reference pixel point according to the possibility of crossing the edge of the abdominal tissue in each preset direction of the reference pixel point; using the Otsu method to perform binary segmentation on the preset area of the reference pixel point to obtain all high-gray-value areas; obtaining the abdominal probability factor according to the abdominal probability factor calculation formula, and the abdominal probability factor calculation formula is as follows: In the formula, represents the abdominal probability factor that the reference pixel point belongs to the abdominal tissue; represents the number of abdominal tissue judgment directions of the reference pixel point; represents the number of preset directions of the reference pixel point; represents the number of high-gray-value areas in the preset area of the reference pixel point; represents the number of pixel points in each high-gray-value area in the preset area of the reference pixel point; represents the th high-gray-value area in the preset area of the reference pixel point, and the th pixel point's gray value; represents the maximum value of the area of the high-gray-value areas in the preset area of the reference pixel point.

6. The intelligent processing method of an obstetric image according to claim 1, wherein The method for obtaining the key feature regions includes: taking the pixel points with the brain probability factor greater than a preset second threshold as brain tissue pixel points; taking the pixel points with the heart probability factor greater than a preset second threshold as heart tissue pixel points; taking the pixel points with the abdomen probability factor greater than a preset second threshold as abdomen tissue pixel points; taking the region composed of all brain tissue pixel points as the brain region; taking the region composed of all heart tissue pixel points as the heart region; taking the region composed of all abdomen tissue pixel points as the abdomen region; taking the brain region, the heart region and the abdomen region as the key feature regions.

7. An intelligent processing method for obstetric images according to claim 1, characterized in that, The method for obtaining the image matching degree further includes: taking any fetal ultrasound image other than the reference fetal image as the comparison fetal image; obtaining the key feature similarity between the reference fetal image and the comparison fetal image according to the differences in the brain probability factor, the heart probability factor and the abdomen probability factor of the pixel points in the key feature regions between the reference fetal image and the comparison fetal image; obtaining the body structure similarity between the reference fetal image and the comparison fetal image according to the difference in the position distribution of the key feature regions between the reference fetal image and the comparison fetal image; collectively referring to the brain probability factor, the heart probability factor and the abdomen probability factor in the key feature regions as the probability factor; calculating the mean value of the probability factors of all pixel points in all key feature regions of the reference fetal image.

8. The intelligent processing method for an obstetric image according to claim 7, characterized in that, The method for obtaining the key feature similarity includes: calculating the difference in the mean value of the brain probability factor of the pixel points in the brain region between the reference fetal image and the comparison fetal image, calculating the difference in the mean value of the heart probability factor of the pixel points in the heart region between the reference fetal image and the comparison fetal image, calculating the difference in the mean value of the abdomen probability factor of the pixel points in the abdomen region between the reference fetal image and the comparison fetal image; averaging the differences in the mean value of the brain probability factor, the mean value of the heart probability factor and the mean value of the abdomen probability factor between the reference fetal image and the comparison fetal image, and performing a negative correlation normalization operation to obtain the key feature similarity between the reference fetal image and the comparison fetal image.

9. The intelligent processing method of an obstetric image according to claim 7, characterized in that The method for obtaining the similarity of the body structure includes: obtaining the center of gravity points of the brain region, the heart region, and the abdominal region of the reference fetal image and the comparison fetal image; in each fetal ultrasound image, obtaining the line connecting the center of gravity point of the brain region and the center of gravity point of the heart region as the first line, and obtaining the line connecting the center of gravity point of the heart region and the center of gravity point of the abdominal region as the second line; taking the angle between the first line and the second line as the first angle; obtaining the similarity of the body structure according to the formula for calculating the similarity of the body structure between the reference fetal image and the comparison fetal image, and the formula for calculating the similarity of the body structure is as follows: In the formula, represents the similarity of the body structure between the reference fetal image and the comparison fetal image; represents the length of the first line in the reference fetal image; represents the length of the second line in the reference fetal image; represents the length of the first line in the comparison fetal image; represents the length of the second line in the comparison fetal image; represents the first angle in the reference fetal image; represents the first angle in the comparison fetal image.

Images