Kidney ultrasonic image lesion area segmentation method

Abstract

The invention relates to the technical field of region segmentation, in particular to a kidney ultrasonic image lesion region segmentation method. The method comprises the following steps: acquiring a tracking pixel sequence of feature points of a kidney region of an image to be analyzed, acquiring a cyst possible value according to the similarity of gray variation trends of each feature point and adjacent feature points and the length of the tracking pixel sequence, and further selecting cyst feature points in the kidney region; classifying the cyst feature points according to the distance between the pixel points at the same position in the tracking pixel sequence of any two cyst feature points and the similarity between the gray difference and the gray change trend; and according to the distance between each cyst feature point and the other cyst feature points of the category to which the cyst feature point belongs and the cyst possible value, obtaining a region growth threshold value, and taking the cyst feature points as seed points for region growth to obtain an actual cyst region. According to the scheme, the kidney cyst division precision is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of region segmentation, and in particular to a method for segmenting a kidney ultrasound image lesion region. Background Art

[0002] There are many kinds of kidney lesions, the most common of which is renal cyst. Renal cyst can cause infectious peritonitis, induce hypertension, cause renal failure and cancer. Segmentation of the lesion area in renal images can help to diagnose renal cysts and other common malignant cysts of the urinary system more quickly and accurately, which is of great significance for the early detection and prevention of kidney diseases.

[0003] Existing methods usually use regional segmentation algorithms and neural networks to extract renal tumor areas in kidney images. However, because the size, shape, number and location of renal cysts in the body are often different, and the images of renal cysts and surrounding renal cortical areas are relatively similar, the cyst edges are blurred, making it difficult to perform accurate segmentation, which in turn results in large errors in the lesion areas segmented from kidney images. Summary of the invention

[0004] In order to solve the technical problem that the tumor in the kidney is not fixed and the tumor edge is blurred, resulting in large errors in the segmentation of the cyst area in the kidney, the purpose of the present invention is to provide a method for segmenting the lesion area of ​​the kidney ultrasound image. The technical solution adopted is as follows: The present invention proposes a method for segmenting a renal ultrasound image lesion region, the method comprising: Acquire a plurality of consecutive frames of kidney images of the patient, and record the first frame of kidney image as the image to be analyzed; Acquire a kidney region of the image to be analyzed; select feature points from the kidney region, track each feature point in the kidney image, and form a tracking pixel sequence for each feature point by each feature point and its corresponding matching pixel points in the remaining kidney images except the image to be analyzed; According to the similarity of the grayscale change trend of each feature point in the kidney region and its neighboring feature points, and the length of the tracking pixel sequence of each feature point, the cyst possibility value of each feature point is obtained; and the cyst feature points in the kidney region are selected using the cyst possibility value; According to the distance, grayscale difference and similarity of grayscale change trend of the pixels at the same position in the tracking pixel sequence of any two cyst feature points, the cyst feature points are divided into different categories; According to the distance between each cyst feature point and the other cyst feature points of its category, and the cyst possible value of each cyst feature point, the regional growth threshold of each cyst feature point is obtained; based on the regional growth threshold, each type of cyst feature point is used as a seed point for regional growth to obtain the actual cyst area in the kidney area.

[0005] Furthermore, the method for acquiring the tracking pixel sequence of each feature point includes: Arranging all kidney images in time sequence to obtain an image sequence, wherein the first image in the image sequence is the image to be analyzed; For each feature point in the kidney region of the image to be analyzed, an initial target sequence of the feature point is set, and the elements in the initial target sequence are the feature points themselves; The feature points are respectively recorded as target points, and the second image in the image sequence is recorded as the target image; the target point is tracked in the target image using the optical flow algorithm, and when the target point has a corresponding matching pixel point in the target image, the corresponding matching pixel point of the target point in the target image is recorded as a new target point, the new target point is added to the target sequence, the target sequence is updated, and the next kidney image adjacent to the target image is recorded as a new target image, until the new target point has no corresponding matching pixel point in the new target image or the image sequence traversal is completed; when the new target point has no corresponding matching pixel point in the new target image or the image sequence traversal is completed, the target sequence is recorded as a tracking pixel sequence of the feature point.

[0006] Furthermore, the obtaining of the possible cyst value of each feature point includes: Using an optical flow algorithm to obtain an optical flow vector of each feature point in the kidney region of the image to be analyzed; Select any feature point as the analysis point, and record the cosine similarity between the analysis point and the optical flow vector of the feature point closest to it as the grayscale change similarity value of the analysis point; The cyst possibility value of the analysis point is obtained according to the gray value of the analysis point, the length of the tracking pixel sequence and the gray change similarity value; the gray value and the cyst possibility value are negatively correlated, and the length and the gray change similarity value are both positively correlated with the cyst possibility value.

[0007] Furthermore, the cyst feature points are divided into different categories, including: Using an optical flow algorithm to obtain the optical flow vectors of the remaining pixel points in the tracking pixel sequence of each cyst feature point except the last pixel point; Acquire characteristic fluctuation values ​​corresponding to the two cyst feature points according to the discrete degree of the distance between the pixel points at the same position in the tracking pixel sequence of any two cyst feature points, the discrete degree of the grayscale difference and the discrete degree of the similarity of the optical flow vector; According to the distance between the pixels at the same position in the tracking pixel sequence of any two cyst feature points, the grayscale difference, the similarity of the optical flow vector and the characteristic fluctuation value, the same cyst index corresponding to the two cyst feature points is obtained; The same cyst index is negatively correlated and mapped to obtain a characteristic distance between any two cyst feature points; all cyst feature points are clustered based on the characteristic distance to obtain a plurality of clusters; and the cyst feature points in each cluster are used as cyst feature points of the same category.

[0008] Furthermore, the method for obtaining the characteristic fluctuation value includes: Two cyst feature points are randomly selected as test points, and the pixel pairs of the two test points are formed by the pixel points at the same position in the tracking pixel sequences of the two test points; The distance between the two pixels in each pixel pair, the absolute value of the difference in grayscale values, and the cosine similarity of the optical flow vector are recorded as the conditional value of each pixel pair; The arithmetic mean difference of each condition value of all pixel pairs of the two points to be tested is obtained, and recorded as each condition fluctuation value of the two points to be tested; the product of all condition fluctuation values ​​of the two points to be tested is taken as the characteristic fluctuation value of the two points to be tested.

[0009] Furthermore, the method for obtaining the cyst index comprises: The average of the distances between the two pixels in all pixel pairs of the two test points is recorded as the overall distance between the two test points; The average of the absolute values ​​of the grayscale value differences between the two pixels in all the pixel pairs of the two test points is recorded as the overall grayscale difference between the two test points; The average of the cosine similarities of the optical flow vectors of the two pixel points in all pixel pairs of the two test points is recorded as the overall grayscale trend similarity value of the two test points; According to the overall distance, the overall grayscale difference and the overall grayscale trend similarity value, the same cyst initial values ​​of the two test points are obtained; the overall grayscale trend similarity value is positively correlated with the same cyst initial value, and the overall distance and the overall grayscale difference are negatively correlated with the same cyst initial value; The characteristic fluctuation value is negatively correlated and mapped, and the weighted result of the initial value of the same cyst is normalized by the mapping result to obtain the same cyst index of the two test points.

[0010] Furthermore, the step of obtaining the regional growth threshold of each cyst feature point includes: Obtain the arithmetic mean difference between the distances of each cyst feature point and the other cyst feature points of the category to which it belongs, and record it as the distance fluctuation value of each cyst feature point; Performing negative correlation mapping on the distance fluctuation value of each cyst feature point, normalizing the product of the mapping result and the cyst possible value, and obtaining the cyst area center value of each cyst feature point; The preset growth threshold is weighted based on the cyst region center value to obtain the region growth threshold of each cyst feature point.

[0011] Further, obtaining the kidney region of the image to be analyzed includes: The maximum inter-class variance method is used to obtain the segmentation threshold of the image to be analyzed; the pixel points whose grayscale values ​​in the image to be analyzed are less than or equal to the segmentation threshold are recorded as low grayscale points; For a connected domain formed by low-grayscale points in the image to be analyzed, the connected domain with non-low-grayscale points inside is recorded as a suspected renal cortex region, and the suspected renal cortex region has an outer edge; The largest suspected renal cortex region is recorded as the renal cortex region, and the closed region formed by the outer edge of the renal cortex region is taken as the kidney region of the image to be analyzed.

[0012] Furthermore, the selecting of cyst feature points in the kidney region includes: For the feature points in the kidney region, the feature points whose cyst possibility values ​​are greater than a preset threshold are recorded as cyst feature points in the kidney region.

[0013] Furthermore, the method for selecting feature points from the kidney region is a corner point detection algorithm.

[0014] The present invention has the following beneficial effects: Renal cysts usually appear in the renal cortex. Smaller renal cysts are easily confused with the renal cortex area. In addition, the number and size of cysts in the kidney area vary, making it difficult to extract the cyst area through common region segmentation algorithms and neural networks. In order to solve the above problems, firstly, the feature points of the kidney area are tracked in continuous frame images to obtain a tracking pixel sequence. The length of the tracking pixel sequence presents the morphological changes of the feature points in the continuous frame ultrasound images. Then, the morphological changes of renal cysts in continuous frame ultrasound images are smaller than those of other kidney areas. According to the similarity of the grayscale change trend of each feature point with its adjacent feature points and the length of the tracking pixel sequence of the feature point, the possibility of the feature point being in the cyst area is analyzed to obtain the cyst possibility value, and then the cyst feature points in the kidney area are selected. Since there may be multiple cysts in the kidney, the cyst feature points need to be classified; compared with the cyst feature points in different cyst areas, the grayscale performance of the cyst feature points in the same cyst area is less different and the grayscale change trend is more similar. Therefore, the cyst feature points can be accurately divided into different categories by combining the distance, grayscale difference and similarity of grayscale change trend of the pixels at the same position in the tracking pixel sequence of the cyst feature points. The distance between each cyst feature point and the other cyst feature points in its category, as well as the cyst possible value, can reflect the position of each cyst feature point in its cyst area. The two are used to adaptively obtain the regional growth threshold to achieve the segmentation of the cyst area, so as to solve the problem of inaccurate segmentation due to blurred tumor edges, which helps to improve the adaptability of the regional growing algorithm in different areas and ensure the accuracy of tumor area segmentation. 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 drawings required for use in the embodiments or the prior art descriptions are 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.

[0016] Figure 1 A flowchart of a method for segmenting a kidney ultrasound image lesion region provided by an embodiment of the present invention; Figure 2 A partial schematic diagram of a kidney image provided by an embodiment of the present invention; Figure 3 A flowchart of the steps of a method for classifying cyst feature points provided by an embodiment of the present invention; Figure 4 A system structure diagram of a kidney ultrasound image lesion region segmentation system provided by one embodiment of the present invention; Figure 5A schematic diagram of a computer device for segmenting a renal ultrasound image lesion region provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method for segmenting the lesion area of ​​a renal ultrasound image proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

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

[0019] The following is a detailed description of a method for segmenting renal ultrasound image lesion areas provided by the present invention in conjunction with the accompanying drawings.

[0020] Embodiment 1: The present invention proposes a method for segmenting the lesion area of ​​kidney ultrasound images. Figure 1 , which shows a flowchart of the steps of a method for segmenting a kidney ultrasound image lesion area provided by an embodiment of the present invention, the method comprising: Step S1: Acquire a plurality of consecutive frames of kidney images of the patient, and record the first frame of kidney image as the image to be analyzed.

[0021] In order to locate and segment the diseased area of ​​the kidney, it is necessary to obtain an ultrasound image of the patient's kidney area. The specific operation is as follows: First, during the test, the patient takes a supine or lateral position to better display the kidney area; second, select a curved probe ultrasound device to detect the patient's kidney area, and adjust the various parameters of the device to ensure that the kidney is clearly displayed on the display screen of the ultrasound device; then, place the curved probe on the patient's waist or abdomen, adjust the angle and pressure of the curved probe, so that the kidney is fully presented in the image; finally, the medical staff observes the real-time image on the display screen of the ultrasound device in real time during the test. When the kidney structure is clearly visible, press the acquisition key of the device continuously to capture and save multiple frames of images, and record these images as kidney images; Figure 2 A partial schematic diagram of a kidney image provided by an embodiment of the present invention.

[0022] It should be noted that this solution only detects a single kidney, and there is only one kidney area in the kidney image; the image acquired by ultrasound imaging is usually a grayscale image, and the kidney image is a grayscale image.

[0023] In order to facilitate subsequent analysis, the first frame of kidney image among the acquired multiple frames of kidney images is recorded as the image to be analyzed.

[0024] Step S2: Acquire the kidney region of the image to be analyzed; select feature points from the kidney region, track each feature point in the kidney image, and form a tracking pixel sequence for each feature point by each feature point and its corresponding matching pixel points in the remaining kidney images except the image to be analyzed.

[0025] In order to segment the lesion area in the kidney image, it is necessary to extract the kidney area in the kidney image.

[0026] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the kidney region includes: obtaining the segmentation threshold of the image to be analyzed by using the maximum inter-class variance method; recording the pixel points whose grayscale values ​​in the image to be analyzed are less than or equal to the segmentation threshold as low grayscale points; for the connected domain formed by the low grayscale points in the image to be analyzed, recording the connected domain with non-low grayscale points inside as the suspected renal cortex region, and the suspected renal cortex region has an outer edge; recording the suspected renal cortex region with the largest area as the renal cortex region, and taking the closed area formed by the outer edge of the renal cortex region as the kidney region of the image to be analyzed. Among them, the maximum inter-class variance method is a well-known technology for those skilled in the art and will not be repeated here.

[0027] Since the outer layer of the kidney is composed of cellulose, it shows high echo characteristics in the reflection of ultrasound, the renal cortex shows low echo characteristics, and the renal medulla shows high echo characteristics, and the inside of the kidney is mainly composed of the cortical area and the medulla area, then in the ultrasound image, the kidney appears as a group of bright areas wrapped in a circle of low-gray outer layer. Therefore, the connected domain composed of low-gray points with non-low-gray points inside is recorded as the suspected renal cortex area. The suspected renal cortex area is hollow inside and has an outer edge.

[0028] Since the environmental noise and the noise generated by the equipment acquisition process may also appear as a group of bright areas wrapped in a low-gray outer layer, but the area of ​​these low-gray outer layers is small, the largest suspected renal cortex area is the renal cortex area. Because the renal cortex is the outer part of the kidney, the closed area formed by the outer edge of the renal cortex area is taken as the kidney area.

[0029] Renal cysts usually appear in the outer part of the kidney, the renal cortex; in ultrasound images, the renal cortex is continuous with the overall structure of the kidney and exhibits low echo characteristics in the reflection of ultrasound waves. Cysts also exhibit low echo characteristics, making it easy for smaller renal cysts to be confused with the renal cortex area, making it difficult to distinguish and segment. Therefore, the morphological changes of renal cysts in continuous frame images are used to locate them.

[0030] First, feature points in the kidney region of the image to be analyzed are selected. In this embodiment, a corner point detection algorithm is used to extract feature points in the kidney region, and the feature points are equivalent to optical flow points. The corner point detection algorithm is a well-known technology for those skilled in the art and will not be described in detail here.

[0031] Afterwards, in order to analyze the morphological changes of renal cysts in continuous frame images, each feature point is tracked in the renal image; each feature point and its corresponding matching pixel points in the remaining renal images except the image to be analyzed constitute a tracking pixel sequence for each feature point.

[0032] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the tracking pixel sequence includes: arranging all kidney images in time sequence to obtain an image sequence, the first image in the image sequence is the image to be analyzed; for each feature point in the kidney area of ​​the image to be analyzed, setting an initial target sequence of the feature point, the element in the initial target sequence is the feature point itself; recording the feature points as target points respectively, and recording the second image in the image sequence as the target image; tracking the target point in the target image using an optical flow algorithm, when the target point has a corresponding matching pixel point in the target image, recording the corresponding matching pixel point of the target point in the target image as a new target point, adding the new target point to the target sequence, updating the target sequence, and recording the next adjacent kidney image of the target image as the new target image until the new target point has no corresponding matching pixel point in the new target image; when the new target point has no corresponding matching pixel point in the new target image or the image sequence traversal is completed, recording the target sequence as the tracking pixel sequence of the feature point.

[0033] As an example, suppose the image sequence ,in, All are kidney images; for feature point a in image A, the initial target sequence of feature point a is , use the optical flow algorithm to track pixel a in image B. When pixel a has a corresponding matching pixel b in image B, add pixel b to M0 to update the target sequence M0 and obtain the target sequence .

[0034] When pixel b has a corresponding matching pixel c in image C, pixel c is added to M1 to update the target sequence M1, and the target sequence is obtained. Image C is the last image in the image sequence P. After the image sequence is traversed, the target sequence Denoted as the tracking pixel sequence of feature point a.

[0035] When pixel b does not have a corresponding matching pixel c in image C, the target sequence Denoted as the tracking pixel sequence of feature point a.

[0036] It should be noted that the matching pixel point corresponding to the target point in the target image is equivalent to the most similar pixel point of the target point in the target image, and can also be regarded as the position of the target point in the target image. In this embodiment, the Lucas-Kanade optical flow algorithm is used to track the target point in the target image. Among them, the Lucas-Kanade optical flow algorithm is a well-known technology for those skilled in the art and will not be described in detail here.

[0037] Step S3: According to the similarity of the grayscale change trend between each feature point in the kidney region and its adjacent feature points, and the length of the tracking pixel sequence of each feature point, the cyst possibility value of each feature point is obtained; and the cyst feature points in the kidney region are selected using the cyst possibility value.

[0038] When there are multiple cysts in the patient's kidneys and the cysts are of different sizes, it is difficult to directly segment the cyst area using common region segmentation algorithms. This scheme uses the morphological change characteristics of renal cysts in continuous frame images to locate them.

[0039] When the kidneys are deeply breathed or pressed, they will slightly shift due to changes in abdominal pressure. The location and shape of renal cysts are more difficult to be clearly captured on ultrasound images. At the same time, the liquid properties of the cysts make their shape and position changes smaller. Therefore, the morphological changes of renal cysts in continuous frame ultrasound images are smaller than those of other renal areas.

[0040] Compared with the feature points in the non-cystic part of the kidney, the grayscale change trends of the feature points in the cystic area in the continuous frame ultrasound images are more similar; the length of the tracking pixel sequence of the feature points presents the morphological changes of the feature points in the continuous frame ultrasound images, and the possible value of the cyst is obtained by combining the similarity of the grayscale change trends of each feature point and its adjacent feature points.

[0041] Preferably, in an embodiment of the present invention, the method for obtaining the possible value of a cyst includes: using an optical flow algorithm to obtain an optical flow vector of each feature point in the kidney area of ​​the image to be analyzed; optionally recording a feature point as an analysis point, and recording the cosine similarity between the optical flow vector of the analysis point and the feature point closest to it as the grayscale change similarity value of the analysis point; obtaining the possible value of the cyst of the analysis point according to the grayscale value of the analysis point, the length of the tracking pixel sequence and the grayscale change similarity value.

[0042] Renal cysts are usually cystic structures filled with fluid. The fluid has a weak ability to transmit ultrasound waves, which makes the renal cysts show low echo characteristics in the reflection of ultrasound waves. The renal cortex is composed of dense renal tubules and blood vessels. Ultrasound waves will be strongly reflected when passing through these tissues, which makes the renal cortex show medium echo characteristics in the reflection of ultrasound waves. The renal medulla shows high echo characteristics. Therefore, the smaller the gray value of the feature point is, the more likely it is to be in the renal cyst area.

[0043] If the morphological changes of the feature points in the continuous frame ultrasound images are greater, it is easy to cause the optical flow algorithm to have matching errors, resulting in a greater possibility of interruption of the tracking of the feature points in the kidney image, and the shorter the length of the tracking pixel sequence of the feature points. It is known that the morphological changes of renal cysts in continuous frame ultrasound images are smaller than those of other kidney regions. When the length of the tracking pixel sequence of the feature points is longer, the feature points are more likely to be in the renal cyst region.

[0044] The grayscale change similarity value of the analysis point shows the similarity between the grayscale change trend of the analysis point and its nearest feature point. Compared with the feature points in the non-cystic part of the kidney, the grayscale change trend of the feature points in the cystic area in the continuous frame ultrasound image is more similar. The analysis point and its nearest feature point are in the same area. The larger the grayscale change similarity value, the greater the possibility that the analysis point is in the renal cyst area.

[0045] The greater the cyst possibility value, the greater the possibility that the analysis point is located at the location of the renal cyst. Therefore, the gray value of the analysis point is negatively correlated with the cyst possibility value, and the length of the tracking pixel sequence of the analysis point and the gray change similarity value are both positively correlated with the cyst possibility value. In the embodiment of the present invention, the gray value of the analysis point is negatively correlated, and the product of the mapping result, the length of the tracking pixel sequence of the analysis point and the gray change similarity value is normalized to obtain the cyst possibility value of the analysis point.

[0046] In the embodiment of the present invention, the gray value of the analysis point, the correlation between the length of the tracking pixel sequence and the gray value change similarity value and the cyst possibility value can also be constructed through other basic mathematical operations, which are not limited or elaborated here.

[0047] It should be noted that the present embodiment uses the Lucas-Kanade optical flow algorithm to obtain the optical flow vectors of the feature points in the kidney region; the length of the tracking pixel sequence is equal to the total number of elements in the sequence; if there are multiple feature points closest to the analysis point, then one feature point is selected from these feature points to calculate the grayscale change similarity value of the analysis point.

[0048] In a specific implementation of the embodiment of the present invention, assuming that the analysis point is the i-th characteristic point in the kidney region, the cyst possibility value of the analysis point is expressed by the formula: In the formula, is the possible value of cyst at the i-th feature point in the kidney region; is the length of the tracking pixel sequence of the i-th feature point in the kidney region; is the optical flow vector of the i-th feature point in the kidney area; is the optical flow vector of the feature point in the kidney region that is closest to the i-th feature point; is the similarity value of grayscale change of the i-th feature point in the kidney area; is the gray value of the i-th feature point in the kidney area; cos is the cosine function; exp is the exponential function with a natural constant as the base; Norm is the normalization function.

[0049] For the feature points in the kidney region, the feature points whose cyst possibility values ​​are greater than a preset threshold are recorded as cyst feature points in the kidney region.

[0050] It should be noted that the preset threshold in the embodiment of the present invention is an empirical value of 0.8, and the implementer can set it according to the specific situation. The method for obtaining the cyst possible value of all feature points in the kidney area of ​​the image to be analyzed is the same as the method for obtaining the cyst possible value of the analysis point.

[0051] Step S4: The cyst feature points are divided into different categories according to the distance between the pixels at the same position in the tracking pixel sequence of any two cyst feature points, the grayscale difference and the similarity of the grayscale change trend.

[0052] When there are multiple cysts in the patient's kidney, the cyst feature points acquired in the above step S3 are in different cyst regions, and the cyst feature points need to be classified, and the cyst feature points belonging to the same cyst region are divided into the same category.

[0053] Since the degree of pathological changes of different cysts is different, the grayscale performance and grayscale change trend of different cyst regions are quite different; therefore, compared with the cyst feature points in different cyst regions, the grayscale performance of the cyst feature points in the same cyst region is less different and the grayscale change trend is more similar. At the same time, the distance between the cyst feature points in the same cyst region is smaller than that between the cyst feature points in different cyst regions.

[0054] By analyzing the distance between pixels, grayscale difference and similarity of grayscale change trend between any two cyst feature points during the entire tracking process, the accuracy of the morphological and grayscale change analysis of the two cyst feature points during kidney movement is improved, and the cyst feature points belonging to different cyst areas are accurately divided.

[0055] See also Figure 3, which shows a flowchart of the steps of a method for classifying cyst feature points provided by an embodiment of the present invention, the method comprising: Step S410: using an optical flow algorithm to obtain optical flow vectors of the remaining pixel points in the tracking pixel sequence of each cyst feature point except the last pixel point.

[0056] It should be noted that, in this embodiment, the Lucas-Kanade optical flow algorithm is used to obtain the optical flow vector of the pixel points in the tracking pixel sequence of each cyst feature point; the kidney image where the last pixel point in the tracking pixel sequence is located has no adjacent next frame image, and tracking cannot be continued, resulting in the absence of an optical flow vector for the last pixel point in the tracking pixel sequence.

[0057] Step S420: Acquire characteristic fluctuation values ​​corresponding to two cyst feature points according to the discrete degree of distance between pixels at the same position in the tracking pixel sequence of any two cyst feature points, the discrete degree of grayscale difference and the discrete degree of similarity of optical flow vectors.

[0058] Compared with the differences in the degree of lesions of different renal cysts, the degree of lesions in different positions of the same renal cyst is closer, that is, different cyst feature points in the same cyst have the characteristics of closer grayscale, closer distance and similar grayscale change trend. The above characteristics of different cyst feature points in the same renal cyst can maintain high stability under continuous optical flow tracking.

[0059] The pixels at the same position in the tracking pixel sequence of the two cyst feature points represent the positions of the two cyst feature points under continuous optical flow tracking; the similarity of the optical flow vectors reflects the similarity of the grayscale change trends of the two pixels, and the distance and grayscale difference between the two pixels represent the distributed grayscale characteristics. The discrete degree of the above indicators presents the stability of the distributed grayscale characteristics of the two cyst feature points during the optical flow tracking process, thereby obtaining the characteristic fluctuation value.

[0060] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the characteristic fluctuation value includes: randomly selecting two cyst characteristic points as test points, and forming a pixel pair of the two test points by the pixel points at the same position in the tracking pixel sequence of the two test points; recording the distance between the pixel points of the two pixel points in each pixel pair, the absolute value of the difference in grayscale values, and the cosine similarity of the optical flow vector as the conditional value of each pixel pair; obtaining the arithmetic mean difference of each conditional value of all pixel pairs of the two test points, and recording it as each conditional fluctuation value of the two test points; and taking the product of all kinds of conditional fluctuation values ​​of the two test points as the characteristic fluctuation value of the two test points.

[0061] The arithmetic mean difference reflects the degree of discreteness of a set of data, and each conditional fluctuation value presents the degree of fluctuation of the distance, grayscale difference or similarity of grayscale change trend of the pixel points at the corresponding positions of two cyst feature points during continuous optical flow tracing.

[0062] Since the grayscale features of the cyst feature points in the same cyst are relatively close and the cyst is relatively stable, the grayscale features of the two cyst feature points in different ultrasound images under continuous optical flow tracing are relatively close. Therefore, the overall fluctuation degree of grayscale, distance and grayscale change trend of the two test points in the optical flow tracing process is obtained by analyzing the fluctuation values ​​of all conditions.

[0063] It should be noted that the total number of pixel pairs of the two points to be measured is equal to the minimum value of the total number of elements in the tracking pixel sequences of the two points to be measured.

[0064] In a specific implementation of the embodiment of the present invention, the characteristic fluctuation values ​​of the two points to be measured are expressed by the formula: Where, FJ is the characteristic fluctuation value of the two test points; N is the total number of pixel pairs of the two test points; is the distance between two pixels in the nth pixel pair of the two points to be measured. In this embodiment, the Euclidean distance is used to measure the distance between the pixels; is the mean distance between two pixels in all pixel pairs of the two points to be tested; is the absolute value of the difference in grayscale values ​​between two pixels in the nth pixel pair of the two points to be tested; is the mean of the absolute values ​​of the grayscale value differences between two pixels in all pixel pairs of the two test points; is the cosine similarity of the optical flow vectors of the two pixels in the nth pixel pair of the two test points; It is the mean value of the cosine similarity of the optical flow vectors of the two pixel points in the remaining pixel pairs of the two test points except the last pixel; , , They represent a conditional value of the nth pixel pair of two points to be tested, and there are three conditional values ​​in total; , , Respectively represent a conditional fluctuation value of two points to be tested; is the absolute value function.

[0065] It should be noted that if the characteristic fluctuation value FJ is smaller, it means that the grayscale difference, distance and grayscale change trend of the two test points in the corresponding positions of the kidney image in the continuous optical flow tracing process are more stable, then the possibility that the two test points are in the same cyst is greater, and the credibility of the distribution grayscale characteristics of the two test points in the corresponding positions of the kidney image in the continuous optical flow tracing process is greater.

[0066] It should be noted that, since there is no optical flow vector for the last pixel in the tracking pixel sequence, for the pixel pair consisting of the last pixel in the tracking pixel sequence of the test point corresponding to the minimum value of the total number of elements in the tracking pixel sequence and the pixel at the same position in the tracking pixel sequence of another test point, the pixel pair cannot obtain the conditional value of the cosine similarity of the optical flow vector, and the pixel pair does not participate in the process of obtaining the conditional fluctuation value of the cosine similarity of the optical flow vector.

[0067] Step S430: acquiring the same cyst index corresponding to the two cyst feature points according to the distance, grayscale difference, similarity of optical flow vectors and characteristic fluctuation value of the pixels at the same position in the tracking pixel sequence of any two cyst feature points.

[0068] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the same-cyst index includes: recording the mean of the distance between two pixel points in all pixel pairs of the two test points as the overall distance of the two test points; recording the mean of the absolute value of the difference in grayscale values ​​of the two pixel points in all pixel pairs of the two test points as the overall grayscale difference of the two test points; recording the mean of the cosine similarity of the optical flow vectors of the two pixel points in all pixel pairs of the two test points as the overall grayscale trend similarity value of the two test points; obtaining the same-cyst initial value of the two test points according to the overall distance, the overall grayscale difference and the overall grayscale trend similarity; the overall grayscale trend similarity value is positively correlated with the same-cyst initial value, and the overall distance and the overall grayscale difference are negatively correlated with the same-cyst initial value; performing negative correlation mapping on the characteristic fluctuation value, normalizing the mapping result with the weighted result of the same-cyst initial value, and obtaining the same-cyst index of the two test points.

[0069] In order to improve the accuracy of the analysis, the overall characteristics of the pixel points at the corresponding positions of the two test points in the kidney image during the continuous optical flow tracing process are considered; the overall distance reflects the overall level of the distance between the corresponding positions of the two test points in the continuous optical flow tracing process, the overall grayscale difference reflects the overall level of the grayscale difference between the corresponding positions of the two test points in the continuous optical flow tracing process, and the overall grayscale trend similarity value reflects the overall level of the similarity of the grayscale change trend of the corresponding positions of the two test points in the continuous optical flow tracing process.

[0070] Due to the differences in the degree of pathological changes of different cysts, the grayscale performance and grayscale change trends of different cyst regions are quite different; therefore, compared with the cyst feature points in different cyst regions, the grayscale performance of the cyst feature points in the same cyst region is less different and the grayscale change trends are more similar; and the distance between the cyst feature points in the same cyst region is smaller than the distance between the cyst feature points in different cyst regions. Therefore, the overall grayscale trend similarity value is positively correlated with the initial value of the same cyst, and the overall distance and the overall grayscale difference are negatively correlated with the initial value of the same cyst.

[0071] Because the smaller the characteristic fluctuation value, the greater the credibility of the distance between the corresponding pixel points, the grayscale difference and the similarity of the grayscale change trend between the two test points in the continuous tracking process, and the greater the possibility that the two test points are in the same cyst area, it is necessary to perform negative correlation mapping on the characteristic fluctuation value, and use the mapping result to weight the initial value of the same cyst to obtain the same cyst index, which is used to measure the possibility that the two test points are in the same cyst area.

[0072] In a specific implementation of the embodiment of the present invention, the cyst index is expressed by the formula: In the formula, JU is the same cyst index of the two points to be tested; It is the mean value of the cosine similarity of the optical flow vectors of the two pixel points in the remaining pixel pairs of the two test points except the last pixel; is the mean distance between two pixels in all pixel pairs of the two points to be tested; is the mean of the absolute value of the difference between the grayscale values ​​of the two pixels in all pixel pairs of the two test points; FJ is the characteristic fluctuation value of the two test points; It is a preset positive number with an empirical value of 0.1, which is used to prevent the denominator from being zero, making the fraction meaningless; exp is an exponential function with a natural constant as the base; Norm is a normalization function.

[0073] It should be noted that the larger the same cyst index of the two test points is, the greater the possibility that the two test points are in the same cyst area. The method for obtaining the same cyst index of any two cyst feature points is the same as the method for obtaining the same cyst index of the two test points.

[0074] Step S440: negatively correlate the same cyst index to obtain the characteristic distance between any two cyst feature points; cluster all cyst feature points based on the characteristic distance to obtain a number of clusters; and use the cyst feature points in each cluster as cyst feature points of the same category.

[0075] Since the larger the cyst index is, the more likely it is that the two cyst feature points are in the same cyst area, the smaller the distance between the two cyst feature points should be in the clustering process so that the two cyst feature points can be classified into the same category. Therefore, negative correlation mapping of the same cyst index is required.

[0076] In this embodiment, based on the characteristic distance between any two cyst characteristic points, the DBSCAN algorithm is used to cluster all cyst characteristic points in the kidney region to obtain different clusters. The DBSCAN algorithm is a well-known technology for those skilled in the art and will not be described in detail here.

[0077] It should be noted that, since the value range of the same cyst index is 0 to 1, this embodiment uses the difference between the constant 1 and the same cyst index as the characteristic distance between any two cyst feature points to achieve negative correlation mapping of the same cyst index. The number of clusters is equal to the number of cyst regions.

[0078] Step S5: Obtain the regional growth threshold of each cyst feature point according to the distance between each cyst feature point and the other cyst feature points of its category, and the cyst possible value of each cyst feature point; based on the regional growth threshold, use each type of cyst feature point as a seed point for regional growth to obtain the actual cyst area in the kidney area.

[0079] The distance between each cyst feature point and the other cyst feature points of its category and the cyst possible value reflect the position of each cyst feature point in the cyst area where it is located. The position of the cyst feature point in the cyst area is used to adjust the preset growth threshold to obtain the regional growth threshold of the cyst feature point.

[0080] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the regional growth threshold includes: obtaining the arithmetic mean difference of the distance between each cyst feature point and the remaining cyst feature points of the category to which it belongs, and recording it as the distance fluctuation value of each cyst feature point; performing negative correlation mapping on the distance fluctuation value of each cyst feature point, normalizing the mapping result and the product of the cyst possible value to obtain the cyst region center value of each cyst feature point; weighting the preset growth threshold based on the cyst region center value to obtain the regional growth threshold for each cyst feature point.

[0081] Since the boundary of the renal cyst is fuzzy, the grayscale change trend of the edge pixel of the renal cyst fluctuates more than that of the center pixel, so the cyst possibility value of the edge pixel of the renal cyst is smaller than that of the center pixel. Therefore, if the cyst possibility value is smaller, the cyst feature point is closer to the edge of the cyst area where it is located; conversely, the cyst feature point is closer to the center of the cyst area where it is located.

[0082] Compared with the distance between the cyst feature point near the edge of the cyst area and the other cyst feature points, the distance between the cyst feature point near the center of the cyst area and the other cyst feature points is closer, and the distance fluctuation is smaller. The arithmetic mean difference is used to reflect the degree of fluctuation of a set of data. If the distance fluctuation value is smaller, it means that the distance between each cyst feature point and the other cyst feature points of its category is closer, the fluctuation is smaller, and each cyst feature point is closer to the center of the cyst area where it is located.

[0083] Therefore, the cyst possibility value is positively correlated with the center value of the cyst area, and the distance fluctuation value is negatively correlated with the center value of the cyst area.

[0084] Since the grayscale changes in the edge area are larger and more complex, the seed points in the edge area need to be more precisely controlled to prevent other renal tumor areas from growing in by mistake, while the central area is usually more uniform, and the seed points in the central area can tolerate a larger threshold to adapt to relatively stable regional characteristics. The preset growth threshold is weighted by the center value of the cyst area, so that the threshold of the seed point at the center of the tumor area is larger, and the threshold of the seed point at the edge of the tumor area is smaller.

[0085] In a specific implementation of the embodiment of the present invention, the region growing threshold is expressed by the formula: Where QT is the regional growth threshold of each cyst feature point; is the preset growth threshold, with an empirical value of 10; UP is the possible cyst value of each cyst feature point; M is the total number of cyst feature points of the category to which each cyst feature point belongs; is the distance between each cyst feature point and the other m-th cyst feature points of its category; is the mean of the distances between each cyst feature point and the other cyst feature points of the category to which it belongs; is the distance fluctuation value of each cyst feature point; is the center value of the cyst area for each cyst feature point; Norm is the normalization function; exp is the exponential function with a natural constant as the base.

[0086] Based on the region growing threshold, each type of cyst feature point is used as a seed point, and a region growing algorithm is used to grow each type of cyst feature point to obtain an actual cyst region. The region growing algorithm is a well-known technology for those skilled in the art and will not be described in detail here.

[0087] It should be noted that, in the process of regional growth for each type of cyst feature point, each cyst feature point, i.e., seed point, is used as a growth point for regional growth, and the pixel point whose absolute value of the difference between the grayscale value of the growth point and the pixel points in its eight neighborhoods is less than or equal to the regional growth threshold of the cyst feature point at the initial growth position is used as a new growth point for regional growth, until the absolute value of the difference between the grayscale value of all new growth points and all pixel points in their eight neighborhoods is greater than the regional growth threshold of the cyst feature point of the initial growth point, to obtain an actual cyst region.

[0088] This scheme adaptively sets the region growing threshold according to the cyst features and positions represented by the cyst feature points to achieve segmentation of the cyst region, which helps to improve the adaptability of the region growing algorithm in different regions and ensure the accuracy of tumor region segmentation.

[0089] So far, the present invention is completed.

[0090] Embodiment 2: The present invention proposes a kidney ultrasound image lesion area segmentation system, please refer to Figure 4 , which shows a system structure diagram of a kidney ultrasound image lesion region segmentation system provided by an embodiment of the present invention, the system comprising: The data acquisition module 610 is used to acquire a plurality of consecutive frames of kidney images of the patient, and record the first frame of kidney image as the image to be analyzed; The feature point tracking module 620 is used to obtain the kidney region of the image to be analyzed; select feature points from the kidney region, track each feature point in the kidney image, and form a tracking pixel sequence for each feature point by each feature point and its corresponding matching pixel points in the remaining kidney images except the image to be analyzed; The cyst selection module 630 is used to obtain the cyst possibility value of each feature point according to the similarity of the grayscale change trend of each feature point in the kidney region and its adjacent feature points, and the length of the tracking pixel sequence of each feature point; and select the cyst feature points in the kidney region using the cyst possibility value; The cyst classification module 640 is used to classify the cyst feature points into different categories according to the distance between the pixels at the same position in the tracking pixel sequence of any two cyst feature points, the grayscale difference and the similarity of the grayscale change trend; The cyst region segmentation module 650 is used to obtain the region growth threshold of each cyst feature point based on the distance between each cyst feature point and the other cyst feature points of its category and the cyst possible value of each cyst feature point; based on the region growth threshold, each type of cyst feature point is used as a seed point for region growth to obtain the actual cyst region in the kidney region.

[0091] It should be noted that: the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the kidney ultrasound image lesion area segmentation system and the kidney ultrasound image lesion area segmentation method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0092] Embodiment 3: Figure 5 A computer device schematic diagram of a kidney ultrasound image lesion area segmentation device provided by an embodiment of the present invention. Figure 5 As shown, the computer device includes: a memory 701, a processor 702, and a computer program 703 stored in the memory 701 and running on the processor 702, wherein when the processor 702 executes the computer program 703, the computer device can execute any one of the kidney ultrasound image lesion area segmentation methods introduced above.

[0093] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a method for segmenting a renal ultrasound image lesion area provided in an embodiment of the present application.

[0094] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0095] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for segmenting the lesion area in kidney ultrasound images, and thus can achieve the same effect as the above-mentioned implementation method.

[0096] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the actions of the device. The storage module may be used to support the device to execute mutual program codes, etc.

[0097] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits included in the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0098] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages 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.

[0099] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for segmenting renal ultrasound image lesion areas, characterized in that: The method includes: Acquire a plurality of consecutive frames of kidney images of the patient, and record the first frame of kidney image as the image to be analyzed; Acquire a kidney region of the image to be analyzed; select feature points from the kidney region, track each feature point in the kidney image, and form a tracking pixel sequence for each feature point by each feature point and its corresponding matching pixel points in the remaining kidney images except the image to be analyzed; According to the similarity of the grayscale change trend of each feature point in the kidney region and its neighboring feature points, and the length of the tracking pixel sequence of each feature point, the cyst possibility value of each feature point is obtained; and the cyst feature points in the kidney region are selected using the cyst possibility value; According to the distance, grayscale difference and similarity of grayscale change trend of the pixels at the same position in the tracking pixel sequence of any two cyst feature points, the cyst feature points are divided into different categories; According to the distance between each cyst feature point and the other cyst feature points of the category to which it belongs, and the cyst possible value of each cyst feature point, a regional growth threshold of each cyst feature point is obtained; based on the regional growth threshold, each type of cyst feature point is used as a seed point for regional growth to obtain the actual cyst region in the kidney region; The obtaining of the possible cyst value of each feature point includes: Using an optical flow algorithm to obtain an optical flow vector of each feature point in the kidney region of the image to be analyzed; Select any feature point as the analysis point, and record the cosine similarity between the analysis point and the optical flow vector of the feature point closest to it as the grayscale change similarity value of the analysis point; According to the gray value of the analysis point, the length of the tracking pixel sequence and the gray change similarity value, the cyst possible value of the analysis point is obtained; the gray value and the cyst possible value are negatively correlated, and the length and the gray change similarity value are both positively correlated with the cyst possible value; The step of selecting cyst feature points in the kidney region includes: For the feature points in the kidney region, the feature points whose cyst possibility values ​​are greater than a preset threshold are recorded as cyst feature points in the kidney region.

2. The method for segmenting renal ultrasound lesion regions according to claim 1, characterized in that: The method for acquiring the tracking pixel sequence of each feature point comprises: Arranging all kidney images in time sequence to obtain an image sequence, wherein the first image in the image sequence is the image to be analyzed; For each feature point in the kidney region of the image to be analyzed, an initial target sequence of the feature point is set, and the elements in the initial target sequence are the feature points themselves; The feature points are respectively recorded as target points, and the second image in the image sequence is recorded as the target image; the target point is tracked in the target image using the optical flow algorithm, and when the target point has a corresponding matching pixel point in the target image, the corresponding matching pixel point of the target point in the target image is recorded as a new target point, the new target point is added to the target sequence, the target sequence is updated, and the next kidney image adjacent to the target image is recorded as a new target image, until the new target point has no corresponding matching pixel point in the new target image or the image sequence traversal is completed; when the new target point has no corresponding matching pixel point in the new target image or the image sequence traversal is completed, the target sequence is recorded as a tracking pixel sequence of the feature point.

3. The method for segmenting renal ultrasound image lesion area according to claim 1, characterized in that: The cyst feature points are divided into different categories, including: Using an optical flow algorithm to obtain the optical flow vectors of the remaining pixel points in the tracking pixel sequence of each cyst feature point except the last pixel point; Acquire characteristic fluctuation values ​​corresponding to the two cyst feature points according to the discrete degree of the distance between the pixel points at the same position in the tracking pixel sequence of any two cyst feature points, the discrete degree of the grayscale difference and the discrete degree of the similarity of the optical flow vector; According to the distance between the pixels at the same position in the tracking pixel sequence of any two cyst feature points, the grayscale difference, the similarity of the optical flow vector and the characteristic fluctuation value, the same cyst index corresponding to the two cyst feature points is obtained; The same cyst index is negatively correlated and mapped to obtain a characteristic distance between any two cyst feature points; all cyst feature points are clustered based on the characteristic distance to obtain a plurality of clusters; and the cyst feature points in each cluster are used as cyst feature points of the same category.

4. The method for segmenting renal ultrasound image lesion area according to claim 3, characterized in that: The method for obtaining the characteristic fluctuation value includes: Two cyst feature points are randomly selected as test points, and the pixel pairs of the two test points are formed by the pixel points at the same position in the tracking pixel sequences of the two test points; The distance between the two pixels in each pixel pair, the absolute value of the difference in grayscale values, and the cosine similarity of the optical flow vector are recorded as the conditional value of each pixel pair; The arithmetic mean difference of each condition value of all pixel pairs of the two points to be tested is obtained, and recorded as each condition fluctuation value of the two points to be tested; the product of all condition fluctuation values ​​of the two points to be tested is taken as the characteristic fluctuation value of the two points to be tested.

5. The method for segmenting renal ultrasound image lesion area according to claim 4, characterized in that: The method for obtaining the cyst index comprises: The average of the distances between the two pixels in all pixel pairs of the two test points is recorded as the overall distance between the two test points; The average of the absolute values ​​of the grayscale value differences between the two pixels in all the pixel pairs of the two test points is recorded as the overall grayscale difference between the two test points; The average of the cosine similarities of the optical flow vectors of the two pixel points in all pixel pairs of the two test points is recorded as the overall grayscale trend similarity value of the two test points; According to the overall distance, the overall grayscale difference and the overall grayscale trend similarity value, the same cyst initial values ​​of the two test points are obtained; the overall grayscale trend similarity value is positively correlated with the same cyst initial value, and the overall distance and the overall grayscale difference are negatively correlated with the same cyst initial value; The characteristic fluctuation value is negatively correlated and mapped, and the weighted result of the initial value of the same cyst is normalized by the mapping result to obtain the same cyst index of the two test points.

6. The method for segmenting renal ultrasound image lesion area according to claim 1, characterized in that: The step of obtaining the regional growth threshold of each cyst feature point includes: Obtain the arithmetic mean difference between the distances of each cyst feature point and the other cyst feature points of the category to which it belongs, and record it as the distance fluctuation value of each cyst feature point; Performing negative correlation mapping on the distance fluctuation value of each cyst feature point, normalizing the product of the mapping result and the cyst possible value, and obtaining the cyst area center value of each cyst feature point; The preset growth threshold is weighted based on the cyst region center value to obtain the region growth threshold of each cyst feature point.

7. The method for segmenting renal ultrasound image lesion area according to claim 1, characterized in that: The step of obtaining the kidney region of the image to be analyzed includes: The maximum inter-class variance method is used to obtain the segmentation threshold of the image to be analyzed; the pixel points whose grayscale values ​​in the image to be analyzed are less than or equal to the segmentation threshold are recorded as low grayscale points; For a connected domain formed by low-grayscale points in the image to be analyzed, the connected domain with non-low-grayscale points inside is recorded as a suspected renal cortex region, and the suspected renal cortex region has an outer edge; The largest suspected renal cortex region is recorded as the renal cortex region, and the closed region formed by the outer edge of the renal cortex region is taken as the kidney region of the image to be analyzed.

8. The method for segmenting renal ultrasound lesion regions according to claim 1, characterized in that: The method for selecting feature points from the kidney region is a corner point detection algorithm.

Images