WO2019062842A1 - Ultrasound image processing method and device, ultrasonic diagnosis device, and storage medium

Info

Abstract

Description

Claims

WO2019062842A1

Publication number: WO2019062842A1
Application number: PCT/CN2018/108295
Authority: WO
Inventors: 廖静秋; 黄子殷; 曹锡华; 许龙
Original assignee: 深圳开立生物医疗科技股份有限公司
Priority date: 2017-09-30
Filing date: 2018-09-28
Publication date: 2019-04-04
Also published as: CN107518920A; CN107518920B

An ultrasound image processing method and device, an ultrasonic diagnosis device, and a computer-readable storage medium, relating to the field of image processing. The ultrasound image processing method comprises: acquiring an ultrasound image of an amniotic fluid pocket; identifying an amniotic fluid opaque area corresponding to the amniotic fluid pocket in the ultrasound image; and measuring the greatest vertical depth of the amniotic fluid pocket according to the greatest vertical depth of the amniotic fluid opaque area. The method and related device can avoid the impact of human factors on a measurement result of an amniotic fluid volume as far as possible and improve the accuracy of an amniotic fluid detection result, and are beneficial to reduction in misdiagnoses.

Ultrasonic image processing method and device, ultrasonic diagnostic device and storage medium

This application claims the priority of the Chinese Patent Application filed on September 30, 2017, the Chinese Patent Office, the application number is 201710923233.2, and the invention name is "ultrasonic image processing method and device, ultrasonic diagnostic device and storage medium", the entire contents of which are The citations are incorporated herein by reference.

Technical field

The present invention relates to the field of ultrasonic diagnostic technology devices, and in particular, to an ultrasonic image processing method and device, an ultrasonic diagnostic device, and a computer readable storage medium.

Background technique

The abnormality of amniotic fluid volume is closely related to the normal development of fetal development, and has become an important test content in pregnancy. Due to the limitation of the inspection time, the ultrasound should not be too long for the fetal radiation time and limited by the professional level and the function of the ultrasonic instrument. At present, it is not possible to diagnose each abnormality in a short time for each pregnant woman. Therefore, abnormal amniotic fluid volume has become a reminder of the discovery of high-risk conditions, and its detection and judgment is particularly important. It can prompt the testing doctor to conduct a detailed examination of the fetus in time.

At present, the B-mode scan is usually performed by using an ultrasonic probe to image the amniotic cavity of the pregnant woman to obtain a B-ultrasound image, and the sheep pool is expressed as a liquid dark area in the B-ultrasound image. The liquid dark area refers to the dark area where the liquid is concentrated when the human body is in the B-ultrasound examination because it is not easy to transmit ultrasonic waves. Liquids in human body such as effusion, empyema, amniotic fluid, blood, etc. can all appear as liquid dark areas in B-ultrasound images.

At present, the methods and standards for commonly used ultrasonic testing of amniotic fluid include: 1 measuring the vertical depth of the largest sheep pool, called deepest vertical pool (DVP), generally used in early pregnancy and middle pregnancy, the normal range of DVP is 2cm ~ 7.9 Cm; 2 measurement of amniotic fluid index (AFI), generally used in late pregnancy, AFI is divided into four upper quadrants, upper right, lower left and lower right quadrant, measuring amniotic fluid depth DVP in each quadrant, the four quadrants obtained The sum of DVP is AFI, and the normal range of AFI is 6cm to 19.9cm.

In the prior art, the ultrasonic testing process for the amount of amniotic fluid in a pregnant woman is usually: first, the doctor finds the largest sheep pool of the pregnant woman by moving the ultrasonic probe, and freezes the current image; after that, the doctor determines in the liquid dark area of the current image according to subjective judgment. The position with the largest vertical depth, and manually inserting the line segment at the position, the length of the line segment represents the vertical depth of the liquid dark area at the position; after the ultrasonic image processing device obtains the line segment inserted by the doctor, the current image is calculated according to the length of the line segment. The maximum vertical depth of the sheep pool and serves as the DVP result for the pregnant woman. Similarly, the maximum vertical depth of the sheep pool in the four quadrants of the pregnant woman's womb can be calculated, and the AFI result of the pregnant woman can be obtained after the summation.

Both DVP and AFI measurements are based on the measurement of the maximum vertical depth of the sheep pool in the ultrasound image. However, the prior art measurement of the maximum vertical depth requires the physician to determine the maximum vertical depth in the dark region of the amniotic fluid in the frozen ultrasound image based on subjective judgment. Position, and insert a line segment representing the maximum vertical depth at the position, and finally determine the maximum vertical depth according to the length of the line segment. It can be seen that the measurement results of DVP and AFI are largely affected by human factors, that is, different doctors Differences in professional skill level, subjectivity, and errors in manual measurement can result in different test results for the same test subject, resulting in lower accuracy of amniotic fluid test results, and prone to false negative or false positive results of amniotic fluid measurements, thus giving Pregnant women and the fetus cause unnecessary misdiagnosis.

Summary of the invention

The invention provides an ultrasonic image processing method and device, an ultrasonic diagnostic device and a computer readable storage medium, which are used for solving the problem of low accuracy of the existing amniotic fluid detection result.

An aspect of an embodiment of the present invention provides an ultrasonic image processing method, including:

Obtain an ultrasound image of the sheep pool;

Identifying a dark area of amniotic fluid corresponding to the sheep pool in the ultrasonic image;

The maximum vertical depth of the sheep pool is measured based on the maximum vertical depth of the amniotic fluid dark zone.

In conjunction with the first aspect, in a first possible implementation manner of the first aspect, the identifying the dark region of the amniotic fluid corresponding to the sheep pool in the ultrasonic image includes:

Traversing the ultrasound image using a sliding window of a target scale, the target scale comprising a first scale, a second scale, and a third scale;

Performing image segmentation on the current sliding window region according to the gray value distribution of the current sliding window region, to obtain a first region and a second region, wherein the gray value of the first region is smaller than the gray value of the second region;

Marking pixels in the first area as amniotic dark areas, and marking pixels in the second area as non-amphibious dark areas;

Converting the ultrasonic image into a binary image at a target scale according to a mark of the pixel, respectively obtaining binary images at the first scale, the second scale, and the third scale;

Determining, by using the binary image of the first scale, the second scale, and the third scale, a value of each pixel in the ultrasonic image to generate a composite binary image;

Performing noise smoothing processing on the synthesized binary image;

The amniotic fluid dark area in the ultrasonic image is determined according to the denoised synthetic binary image.

With reference to the first possible implementation of the first aspect, in a second possible implementation manner of the first aspect, after the pixels in the first area and the pixels in the second area are marked, Before converting the ultrasound pattern to a binary image at a target scale, the method further includes:

The Doppler signal of the blood flow is used to determine the pixel corresponding to the color blood flow, and is marked as a non-amniotic dark area.

In conjunction with the first aspect, the first possible implementation of the first aspect, and the second possible implementation of the first aspect, in a third possible implementation of the first aspect Measuring the maximum vertical depth of the sheep pool according to the maximum vertical depth of the amniotic fluid dark area includes:

Dividing target pixels having the same abscissa and continuous ordinates into a group, wherein the target pixels are pixels marked as amniotic dark areas in the ultrasonic image;

Calculating the number of pixels in each group, and selecting the group with the largest number of pixels as the target group;

Calculating a maximum vertical depth of the sheep pool according to the number of pixels of the target group.

In combination with the first aspect, the first possible implementation of the first aspect, the second possible implementation of the first aspect, and the third possible implementation of the first aspect, in a first aspect In a fourth possible implementation manner, after measuring the maximum vertical depth of the sheep pool according to the maximum vertical depth of the amniotic fluid dark area in the amniotic fluid depth DVP measurement mode, the method further includes:

The obtained maximum vertical depth of the sheep pool is displayed as a measurement result of DVP;

Determining whether the measurement result of the DVP is within a preset range;

If yes, the test result of the DVP is normal;

If not, the test result of the DVP is abnormal.

Combining the first aspect, the first possible implementation of the first aspect, the second possible implementation of the first aspect, the third possible implementation of the first aspect, and the fourth possible aspect of the first aspect In any one of the implementation manners, in the fifth possible implementation manner of the first aspect, in the measurement mode of the amniotic fluid index AFI, acquiring the ultrasonic image of the sheep pool includes:

Obtaining ultrasonic images of four quadrants of the sheep pool respectively;

After measuring the maximum vertical depth of the sheep pool according to the maximum vertical depth of the amniotic fluid dark area, the method further includes:

The maximum vertical depths of the four quadrants of the sheep pool are summed to obtain the AFI measurement results and displayed;

Determining whether the measurement result of the AFI is within a preset range;

If yes, it indicates that the measurement result of the AFI is normal;

If not, it indicates that the measurement result of the AFI is abnormal.

A second aspect of the embodiments of the present invention provides an ultrasonic image processing apparatus, including:

Obtaining a module for acquiring an ultrasonic image of a sheep pool;

An identification module, configured to identify a dark area of amniotic fluid corresponding to the sheep pool in the ultrasonic image;

And a measuring module for measuring a maximum vertical depth of the sheep pool according to a maximum vertical depth of the amniotic fluid dark area.

In conjunction with the second aspect, in a first possible implementation of the second aspect, the device further includes:

a first display module, configured to display, in a measurement mode of the DVP, a maximum vertical depth of the obtained sheep pool as a measurement result of the DVP;

a first determining module, configured to determine whether the measurement result of the DVP is within a preset range;

a first prompting module, configured to: when the first determining module determines that the measurement result of the DVP is within a preset range, prompting that the test result of the DVP is normal, when the first determining module determines the measurement of the DVP When the result is not within the preset range, the test result of the DVP is abnormal, and the corresponding medical treatment prompt is displayed.

With reference to the second aspect, or the first possible implementation manner of the second aspect, in the second possible implementation manner of the second aspect, the acquiring module includes:

Obtaining a subunit for respectively acquiring ultrasonic images of four quadrants of the sheep pool;

The ultrasonic image processing apparatus further includes:

a calculation module for summing the maximum vertical depths of the four quadrants of the sheep pool in the AFI measurement mode to obtain the AFI measurement result;

a second display module, configured to display the measurement result of the AFI;

a second determining module, configured to determine whether the measurement result of the AFI is within a preset range;

a second prompting module, configured to: when the second determining module determines that the measurement result of the AFI is within a preset range, prompting that the measurement result of the AFI is normal, and when the second determining module determines the measurement of the AFI When the result is not within the preset range, the measurement result of the AFI is abnormal, and the corresponding medical treatment prompt is displayed.

A third aspect of the embodiments of the present invention provides an ultrasonic diagnostic apparatus, wherein the ultrasonic diagnostic apparatus includes a host computer and an ultrasonic probe;

The host computer includes a processor for performing the steps of the method of any of claims 1-6 when executing the computer program stored in the memory.

A fourth aspect of the embodiments of the present invention provides a computer readable storage medium having stored thereon a computer program, wherein the computer program is executed by a processor to implement any one of the first aspect or the first aspect A possible implementation step.

It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

The invention can obtain the ultrasonic image of the sheep pool, identify the dark area of the amniotic fluid corresponding to the sheep pool in the ultrasonic image, and measure the maximum vertical depth of the sheep pool according to the maximum vertical depth of the dark area of the amniotic fluid, thereby avoiding the measurement result of the artificial factors on the amniotic fluid. The effect of improving the accuracy of amniotic fluid test results is conducive to reducing misdiagnosis.

DRAWINGS

1 is a schematic diagram of an embodiment of an ultrasonic image processing method of the present invention;

2 is a schematic view showing an embodiment of a method for identifying a dark region of amniotic fluid in an ultrasonic image according to the present invention;

3 is a schematic view showing another embodiment of a method for identifying a dark region of amniotic fluid in an ultrasonic image according to the present invention;

4 is a schematic view showing an embodiment of a method for measuring a maximum vertical depth of a sheep pool according to the present invention;

Figure 5 is a schematic view of a binary image of the present invention;

Figure 6 is a schematic view showing another embodiment of the ultrasonic image processing method of the present invention;

Figure 7 is a schematic view showing another embodiment of the ultrasonic image processing method of the present invention;

Figure 8 is a schematic view showing an embodiment of an ultrasonic image processing apparatus of the present invention;

Figure 9 is a schematic view showing another embodiment of the ultrasonic image processing apparatus of the present invention;

Figure 10 is a schematic view showing another embodiment of the ultrasonic image processing apparatus of the present invention;

Figure 11 is a schematic view showing an embodiment of the ultrasonic diagnostic apparatus of the present invention.

Detailed ways

The embodiment of the invention provides an ultrasonic image processing method and device, an ultrasonic diagnostic device and a computer readable storage medium, which are used for reducing human factors in the amniotic fluid measurement process and improving the accuracy of the amniotic fluid detection result.

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is an embodiment of the invention, but not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of the present invention.

The terms "first", "second", "third", "fourth", etc. (if present) in the specification and claims of the present invention and the above figures are used to distinguish similar objects without having to use To describe a specific order or order. It is to be understood that the data so used may be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than what is illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

For ease of understanding, the specific process in the embodiment of the present invention is described below. Referring to FIG. 1, an embodiment of the method for processing an ultrasonic image in the embodiment of the present invention includes:

101. Obtain an ultrasonic image of a sheep pool;

The ultrasonic image to be measured can be obtained first, and since the present invention is used for amniocentesis measurement, the ultrasonic image includes a sheep pool.

102. Identify a dark area of the amniotic fluid corresponding to the sheep pool in the ultrasonic image;

Since the gray scale of the amniotic fluid dark area is low and connected, after the ultrasonic image is acquired, the connected area with lower gray level can be identified from the ultrasonic image according to the gray value of the pixel as the dark area of the amniotic fluid.

103. Measure the maximum vertical depth of the sheep pool according to the maximum vertical depth of the dark area of the amniotic fluid.

After identifying the dark area of the amniotic fluid corresponding to the sheep pool in the ultrasound image, the maximum vertical depth of the sheep pool can be measured according to the maximum vertical depth of the dark area of the amniotic fluid. Based on the measured maximum vertical depth of the sheep pool, indicators representing amniotic fluid volume, such as amniotic fluid depth DVP and amniotic fluid index AFI, can be further obtained.

After obtaining the ultrasonic image to be measured, the invention can automatically identify the dark region of the amniotic fluid in the ultrasonic image, and measure the maximum vertical depth of the sheep pool. Compared with the prior art, the influence of the human factor on the measurement result is excluded. Improve the accuracy of amniotic fluid test results and reduce misdiagnosis.

In the corresponding embodiment of FIG. 1, after acquiring the ultrasonic image of the sheep pool, it is first necessary to identify the dark region of the amniotic fluid in the ultrasonic image, and an optional method for identifying the dark region of the amniotic fluid in the ultrasonic image is provided below. 2. An embodiment of the method for identifying a dark region of amniotic fluid in an ultrasound image according to the present invention comprises:

201. Traversing the ultrasonic image by using a sliding window of a target scale;

When measuring the amniotic fluid index, the B-mode scan is usually performed by using an ultrasonic probe to image the amniotic cavity of the pregnant woman, and the B-ultrasound image is obtained as a grayscale image. In order to identify the dark area of amniotic fluid in the ultrasound image, the ultrasound image needs to be segmented into at least two parts - the dark area of amniotic fluid and the dark area of non-amniotic water. Compared with the dark area of non-amniotic water, the dark area of amniotic fluid is lower in gray scale. Connected area ultrasound image. In order to improve the accuracy of image segmentation, the sliding window of the target scale can be used to traverse the ultrasonic image, and the image in each sliding window region is separately segmented during the traversal process.

202, determining whether the current sliding window area belongs to the amniotic fluid dark area, if it belongs, step 203 is performed, if not, step 204 is performed;

The current sliding window area may be determined to belong to the amniotic fluid dark area according to the gray value distribution of the current sliding window area. If yes, step 203 is performed, and if not, step 204 is performed. As an example, the method for determining whether the current sliding window area belongs to the amniotic fluid dark area according to the gray value distribution of the current sliding window area may be:

1) calculating the mean and mean square error of the gray values of all pixels in the current sliding window area;

2) If the mean value of the gray value is smaller than the first mean threshold, and the mean square error is smaller than the first difference threshold, it indicates that the gray value of the current sliding window area is evenly distributed, and is a dark area, and the current sliding window area can be determined at this time. To belong to the dark area of amniotic fluid;

3) If the mean value of the gray value is greater than the first mean threshold, or the mean square error is greater than the first difference threshold, it may be determined that the current sliding window area does not belong to the amniotic fluid dark area.

203, mark the pixel in the current sliding window area as 1;

If it is determined that the current sliding window area belongs to the amniotic fluid dark area, the pixels in the current sliding window area are marked to indicate that the pixels in the current sliding window area belong to the amniotic fluid dark area. For example, the pixels in the current sliding window area may be marked as 1.

204, determining whether the current sliding window area belongs to a non-amniotic dark area, if it is, then executing step 205; if not, executing step 206;

If the current sliding window area does not belong to the amniotic fluid dark area, it indicates that the current sliding window area has uneven distribution of gray values, or the gray value is evenly distributed and high. If the gray value is evenly distributed and high, the current sliding window is displayed. The pixels in the area belong to the non-amniotic dark area. Therefore, it can be determined whether the current sliding window area belongs to the non-amniotic dark area. If yes, step 205 is performed; if not, step 206 is performed.

As an example, the method for determining whether the current sliding window region belongs to a non-amphibious dark region according to the pixel value distribution of the current sliding window region may be:

The calculation result of step 202 can be directly utilized.

2) If the mean value of the gray value is greater than the second mean threshold, and the mean square error is smaller than the second difference threshold, indicating that the gray value of the current sliding window area is evenly distributed and is a bright area, and the current sliding window area can be directly determined. It belongs to the dark area of non-amniotic water;

3) If the mean value of the gray value is less than the second mean threshold, or the mean square error is greater than the second difference threshold, it indicates that the gray value of the current sliding window area is unevenly distributed, or the mean value of the gray value is centered, and the current sliding window area is determined not to be It belongs to the dark area of amniotic fluid, and does not belong to the dark area of non-amniotic water. That is to say, all pixels in the current sliding window area cannot be uniformly determined to belong to the dark area of amniotic fluid or the dark area of non-amniotic water.

It should be noted that the second mean threshold is greater than or equal to the first mean threshold. Preferably, the first mean threshold, the second mean threshold, the first difference threshold, and the second difference threshold may be set according to the gray histogram of the ultrasound image.

205. Mark the current sliding window area as 0;

If it is determined that the current sliding window area belongs to the non-amniotic dark area, the pixels in the current sliding window area are marked to indicate that the pixels in the current sliding window area belong to the non-amphibious dark area, for example, the pixels in the current sliding window area may be Marked as 0.

206. Perform image segmentation on the current sliding window region to obtain a first region and a second region, where the gray value of the first region is smaller than the second region;

If it is determined that the current sliding window area does not belong to the non-amniotic dark area, it indicates that the current sliding window area is neither a amniotic fluid dark area nor a non-amphibious water dark area, and all pixels in the current sliding window area cannot be uniformly classified as belonging to The amniotic fluid dark area or the non-amniotic water dark area. At this time, the current sliding window area may be image-divided according to the gray value distribution of the current sliding window area, and the first area and the second area are obtained, and the gray value of the first area is smaller than the first Two areas.

The OTSU algorithm can be used to segment the current sliding window region. The OTSU algorithm is also called the maximum inter-class variance method. According to the grayscale characteristics of the image, the image is divided into two parts: the background and the foreground. The larger the variance between the background and the foreground, the greater the difference between the two parts of the image. When part of the foreground is misclassified into the background, or part of the background is divided into the foreground, the difference between the two parts will be reduced. The segmentation with the largest variance means that the probability of misclassification is the smallest, so the segmentation threshold corresponding to the segment with the largest variance between classes is called the optimal grayscale threshold. In this step, the OTSU algorithm first determines an optimal gray threshold according to the gray value distribution of the current sliding window region, and then divides the current sliding window region according to the optimal gray threshold to obtain two regions—the first region. And the second area. The gradation of the pixel belonging to the first region is smaller than the optimal gradation threshold, the gradation of the pixel belonging to the second region is greater than the optimal gradation threshold, and the pixel whose gradation is equal to the optimal gradation threshold may be determined to belong to the first region. It can also be determined to belong to the second area, and is not specifically limited herein.

In actual use, other algorithms may also be used to perform image segmentation on the current sliding window region, and no exclusive limitation is made here.

207, the pixel in the first area is marked as 1, and the pixel in the second area is marked as 0;

After image segmentation of the current sliding window region according to the gray value distribution of the current sliding window region to obtain the first region and the second region, the first region and the second region may be respectively marked to indicate that the first region is a dark region of amniotic fluid The second area is a dark area other than amniotic fluid. For example, a pixel in the first region can be marked as 1 and a pixel in the second region can be marked as 0.

In actual use, step 202 to step 205 may not be performed, but image segmentation is directly performed on each sliding window region of the ultrasonic image, but the efficiency is low due to the large amount of calculation of image segmentation. In addition, step 204 may be performed to determine whether the current sliding window area belongs to the non-amniotic dark area. If it does not belong to the non-amniotic dark area, step 202 is performed to determine whether the current sliding window area belongs to the amniotic fluid dark area.

208, using the Doppler signal of the blood flow to determine the pixel corresponding to the color blood flow, and marking it as 0;

Because of the measurement of amniotic fluid volume, the area with the most amniotic fluid should be selected, and there is no structure such as carcass or umbilical cord inside. In the B-ultrasound image, the umbilical cord can also be expressed as liquid dark area like amniotic fluid. It is often necessary to image the uterus of a pregnant woman by means of a color Doppler ultrasound mode. The color Doppler image quantizes the Doppler signal of the bloodstream and performs color coding, and the real-time overlay is displayed on the B-ultrasound image. Therefore, in the color Doppler image, the umbilical cord region appears as a color blood flow, and The dark area of amniotic fluid still appears as a liquid dark area, which can be distinguished from the dark area of amniotic fluid in color. Therefore, when the ultrasonic measurement mode is the color Doppler ultrasound mode, the Doppler signal of the blood flow can be used to determine the pixels in the region where the color blood flow is located in the ultrasonic image, and the pixel corresponding to the color blood flow is marked as non-amniotic water. In dark areas, for example, pixels corresponding to color blood flow can be marked as 0.

In actual use, the color Doppler ultrasound mode may not be turned on during the measurement of the amniotic fluid index. At this time, step 208 is not performed after step 207.

209. Convert the ultrasonic image into a binary image according to the mark of each pixel;

After step 202 to step 208, the marking of each pixel in the ultrasonic image is completed. According to the marking, it can be determined whether any pixel belongs to the amniotic fluid dark area or the non-amphibious water dark area, and the ultrasonic image can be converted into a binary image according to the marking of each pixel. In other words, any pixel has only two selectable values. In the embodiment of the present invention, after the ultrasonic image is converted into a binary image, the value of any one pixel is either 1 or 0.

210. Perform noise smoothing processing on the binary image to obtain a denoised binary image;

Since the dark region of amniotic fluid should be a connected region, the binary image obtained by image segmentation often includes noise, such as a small number of 1-value pixels surrounded by 0-value pixels, or a small number of 0-value pixels surrounded by 1-value pixels. Therefore, preferably, the binary image can be subjected to noise smoothing processing, for example, morphological expansion etching can be used to eliminate noise. Morphological expansion is to enlarge the boundary of each 1 pixel connection component in the binary image, filling the edge or the hole inside the 0 pixel; morphological corrosion is to remove the boundary point of each 1 pixel connection component in the binary image to reduce one Layer, you can extract the backbone information, remove the glitch, and remove the isolated 0 pixels.

211. Determine a dark region of amniotic fluid in the ultrasonic image according to the denoised binary image.

After the denoised binary image is obtained, the pixels belonging to the dark region of the amniotic fluid in the ultrasonic image can be determined, and the dark water regions of the amniotic fluid are composed of the pixels, and the dark region of the amniotic fluid in the ultrasonic image can be determined according to the coordinate positions of the pixels. In the embodiment of the present invention, the amniotic fluid dark area is composed of pixels having a value of 1.

The dark areas of amniotic fluid obtained by selecting different sliding window scales usually have some differences. In order to reduce the error caused by different sliding window scales, refer to steps 201 to 211 to determine the dark areas of amniotic fluid in the ultrasonic images corresponding to the sliding windows of other scales. For example, the dark region of the amniotic fluid in the second ultrasonic image corresponding to the sliding window of the second scale and the third amniotic dark region in the ultrasonic image corresponding to the sliding window of the third scale may be determined, and then multiple scale slidings may be integrated. The dark area of the amniotic fluid in the ultrasound image corresponding to the window determines the dark area of the amniotic fluid in the final ultrasound image. Referring to FIG. 3, another embodiment of the amniotic fluid dark area in the ultrasonic image of the present invention includes:

301, respectively, setting a target scale to a first scale, a second scale, and a third scale, and converting the ultrasonic image into a binary image at the first scale, the second scale, and the third scale;

The target scale may be set to the first scale, the second scale, and the third scale, respectively, and the ultrasonic images are respectively converted into binary images at the first scale, the second scale, and the third scale. Specifically, the target scale may be set to the first scale, and steps 201 to 209 are performed to obtain the binary image at the first scale; the target scale is set to the second scale, and steps 201 to 209 are performed to obtain the second scale. The binary image is set to the third scale, and steps 201 to 209 are performed to obtain the binary image at the third scale. These three processes can be performed in parallel or serially. The timing between the three processes is not specifically defined here.

302. Determine, by using a binary image at the first scale, the second scale, and the third scale, a value of each pixel in the ultrasonic image to generate a composite binary image;

The binary image at the first scale, the second scale and the third scale can be used to determine the value of each pixel in the ultrasonic image to generate a composite binary image, and the composite binary image is obtained by comprehensively considering the binary image at different scales. Any pixel in the ultrasonic image corresponds to a value in the binary image at each scale. For convenience of description, the corresponding value in the binary image of the pixel at a certain scale is called the pixel. An alternative value is selected, and the candidate value of the pixel having a higher frequency appears in the candidate value of each scale as the value of the pixel in the synthesized binary image.

Specifically, as an example, a composite binary image may be generated by using a voting mechanism, and the voter is each pixel in the ultrasonic image, and the voting party is the first amniocentetics dark zone, the second amniotic fluid dark zone, and the third amniotic fluid dark zone. Traverse each pixel in the ultrasonic image to vote for each pixel. When the first amniocentetic dark area votes for the current pixel, if the current pixel belongs to the first amniocentetic dark area, a ticket is added for the current pixel, otherwise, the current pixel is not added. Number of votes; when the second amniotic fluid dark area is the current pixel vote, if the current pixel belongs to the second amniotic fluid dark area, then one ticket is added for the current pixel; otherwise, the current pixel number is not increased; the third amniotic fluid dark area is the current pixel voting time. If the current pixel belongs to the third amniotic dark area, a ticket is added for the current pixel; otherwise, the number of votes of the current pixel is not increased. Accumulate the voting result of the first amniotic fluid dark zone, the second amniotic fluid dark zone and the third amniotic fluid dark zone to the current pixel as the total number of votes of the current pixel. The threshold of the number of votes belonging to the dark area of the amniotic fluid can be preset. For example, it can be set to 2 votes. Then, the pixels with the total number of votes in the ultrasonic image greater than or equal to 2 can be determined to belong to the dark area of the amniotic fluid and marked as the dark area of the amniotic fluid. If the number of voters is greater than three, then the number of votes will increase accordingly, at least greater than the median of the number of voters.

303. Perform noise smoothing processing on the synthesized binary image to obtain a synthesized binary image after denoising;

304. Determine a dark region of amniotic fluid in the ultrasonic image according to the synthesized binary image after denoising.

Steps 303 to 304 are the same as steps 210 to 211 in the embodiment corresponding to FIG. 2, and details are not described herein again.

In the corresponding embodiment of FIG. 1, after identifying the dark region of the amniotic fluid in the ultrasonic image, the maximum vertical depth of the sheep pool can be measured. Since the ultrasonic image is composed of pixels of the same size and arranged in rows and columns, it represents the pool of sheep. The target line segment of the maximum vertical depth can be considered to be composed of a part of consecutive pixels in a certain column of pixels. Therefore, the maximum vertical depth of the sheep pool can be calculated according to the number of pixels corresponding to the target line segment. An optional method of measuring the maximum vertical depth of a sheep pond is provided below. Referring to Figure 4, one embodiment of the method of measuring the maximum vertical depth of a sheep pond of the present invention includes:

401. The target pixels with the same abscissa and continuous ordinate are grouped into one group, and the target pixel is a pixel marked as a dark region of the amniotic fluid in the ultrasonic image;

Since the ultrasonic image is composed of pixels of the same size and distributed in rows and columns, the number of the column in which the pixel is located can represent the abscissa of the pixel, and the number of the row in which the pixel is located represents the ordinate of the pixel. After the dark region of the amniotic fluid in the ultrasonic image is identified, the pixels marked as the dark region of the amniotic fluid in the ultrasonic image can be counted. For convenience of description, the pixel marked as the dark region of the amniotic fluid in the ultrasonic image is referred to as the target pixel. The target pixels having the same abscissa and continuous ordinates may be grouped into one group, that is, the target pixels of the continuous distribution in the same column in the ultrasonic image are grouped.

402. Calculate the number of pixels in each group, and select a group with the largest number of pixels as the target group;

After grouping the target pixels, the number of pixels of the target pixel in each group can be calculated, and a group having a large number of pixels is selected as the target group.

403. Calculate a maximum vertical depth of the sheep pool according to the number of pixels in the target group, and determine a target line segment corresponding to the maximum vertical depth.

The target line segment composed of the target pixels in the target group corresponds to the maximum vertical depth of the sheep pool, and the maximum vertical depth of the sheep pool can be calculated according to the number of pixels in the target group. There is a certain proportional relationship between the size of the ultrasonic image and the size of the object to be photographed, and the sizes of all the pixels constituting the ultrasonic image are the same, and all the pixels are evenly distributed in the ultrasonic image, and therefore, the corresponding pixel can be calculated according to the number of pixels. The size occupied by the ultrasonic image can further calculate the corresponding size of the corresponding pixel on the subject.

The target line segment is determined to highlight the target line segment in the ultrasound image displayed to the doctor, so that the doctor can determine the maximum vertical depth corresponding to the line segment in the ultrasonic image, and judge whether the target line segment is selected according to experience, in actual use, if There is no need to highlight the target line segment or determine the target line segment.

For ease of understanding and implementation, a more specific method of measuring the maximum vertical depth of a sheep pool is provided below:

After identifying the dark region of the amniotic fluid in the ultrasound image, the ultrasound image can be converted into a binary image, that is, any pixel in the ultrasound image can only be selected from two values, one value represents the dark region of the amniotic fluid, and the other value represents For non-amniotic dark areas, for example, "1" can be used to represent the dark area of amniotic fluid, and "0" is used to represent the dark area of non-amniotic water. If the value of any pixel in the ultrasonic image is not "0", it is "1". As shown in FIG. 5, it is a schematic diagram of a binary image, the large square represents the entire binary image, and each small square in the large square represents one pixel, and the pixel coordinates of the upper left corner are (1, 1), and the lower right corner is The pixel coordinates are (8,8), and the pixels filled with dark colors have a value of "0", which belongs to the non-amniotic dark area. The pixels filled with white have a value of "1", belonging to the dark area of amniotic fluid, and the dark area of amniotic fluid is A connected area that includes some non-amniotic dark areas.

The voting idea may be adopted, and the voting item is the abscissa of the dark region of the amniotic fluid. In the embodiment of the present invention, the voting items are 2, 3, 4, 5, 6, and 7, respectively, and then the entire amniotic dark area in FIG. 5 is traversed line by line. And all the pixels inside it (that is, all the pixels inside the dotted line in Fig. 5), according to whether the pixel belongs to the amniotic fluid dark area to vote on the voting item corresponding to the abscissa of the pixel, and in an array of 3 rows and 6 columns set in advance Record the voting data. The 6 columns in the array correspond to 6 voting items respectively, and the row a in the array records consecutive current votes, that is, when the current pixel belongs to the amniotic dark area, the count corresponding to the abscissa of the current pixel in row a is increased by one vote. If the current pixel belongs to a non-amniotic dark area, the count corresponding to the abscissa of the current pixel in row a is cleared; the row b in the array records the maximum number of consecutive votes, that is, an item in line a, such as In vote 2, before the corresponding count is cleared, the count corresponding to vote 2 of line b remains the same as the count of vote 2 of line a, and when the count corresponding to vote 2 of line a is cleared, line b The count corresponding to the voting item 2 is unchanged until the count corresponding to the voting item 2 of the row a exceeds the count corresponding to the voting item 2 of the row b. At this time, the count corresponding to the voting item 2 of the row b is re-held with the voting item of the row a. 2 The corresponding count is the same; the row c in the array records that the row b and the row a remain the same (excluding the case where all are 0), and the last count increases the ordinate of the corresponding pixel.

After traversing the first row of pixels inside the dotted line in Figure 5, the data recorded by the array is as shown in Table 1:

Table 1

After traversing the second row of pixels inside the dotted line in Figure 5, the data recorded by the array is as shown in Table 2:

Table 2

And so on, after traversing the second row of pixels inside the dotted line in Figure 5, the data recorded by the array is as shown in Table 3:

table 3

After the traversal, the maximum count result of row b is used to calculate the maximum vertical depth of the sheep pool, with the maximum count result of row b as the target segment length, the abscissa of the maximum count result item as the abscissa of the lower endpoint of the target segment, The target line segment can be determined in the ultrasonic image by using the corresponding ordinate of the horizontal coordinate in the row c as the ordinate of the lower end point of the target line segment, wherein the target line segment is an ultrasonic image or a binary image representing the sheep pool The line segment of the maximum vertical depth. Taking the binary image of FIG. 5 as an example, the maximum counting result of row b is 6, and the abscissa of the maximum counting result item is 2 and 6, and one of them can be taken. For example, a smaller abscissa 2 and an abscissa can be taken. 2 The corresponding ordinate in row c is 7, and since the length of the target segment corresponds to 6 pixels, the coordinates of the lower endpoint of the target segment are (2, 7) and the coordinates of the upper endpoint are (2, 2).

Based on the corresponding embodiments of FIG. 1 to FIG. 5, the maximum vertical depth of the sheep pool in the ultrasonic image can be measured. On this basis, the amniotic fluid index can be obtained, such as DVP or AFI, and the following are respectively for DVP and AFI. The measurement process is described.

First, the measurement process of DVP:

Referring to FIG. 6, another embodiment of the ultrasonic image processing method in the embodiment of the present invention includes:

601. Obtain an ultrasonic image of the sheep pool;

In the early pregnancy or mid-pregnancy ultrasound amniocentesis, because the fetus is small, the amniotic fluid is more, at this time, the doctor can obtain the different horizontal positions in the uterus by changing the detection position of the ultrasonic probe on the pregnant woman's belly surface within the entire uterus of the pregnant woman. In the ultrasonic preview image corresponding to the cross section in the vertical direction, the doctor gives an instruction to freeze the current ultrasonic preview image when the ultrasonic preview image including the deepest sheep pool is determined according to the experience comparison, and the ultrasonic image processing apparatus can acquire the frozen ultrasonic image. The ultrasound image includes the deepest sheep pool.

It should be noted that two or more ultrasonic images can also be acquired in actual use. For example, when doctors compare the depths of the sheep pools in multiple ultrasound preview images, it is difficult to accurately determine which of the ultrasound preview images has the largest vertical depth of the sheep pool by visual contrast. Therefore, the doctor can give the sheep pool. The plurality of ultrasonic preview images having a large depth are frozen, and the ultrasonic image processing apparatus can acquire the frozen plurality of ultrasonic images, and then the plurality of acquired ultrasonic images can be processed in series or in parallel. Alternatively, it is also possible to obtain three-dimensional ultrasonic image information of the pregnant woman's uterus, which is equivalent to freezing a large number of ultrasonic preview images at a time, and then processing a large number of acquired ultrasonic images in series or in parallel.

602. Identify a dark area of amniotic fluid corresponding to the sheep pool in the ultrasonic image;

Since the gray value of the dark region of the amniotic fluid is low and is a connected region, after the ultrasonic image is acquired, the connected region with a lower gray value can be identified from the ultrasonic image according to the grayscale difference as the dark region of the amniotic fluid.

For the method of identifying the dark region of the amniotic fluid in the ultrasonic image, refer to the method of the embodiment corresponding to FIG. 2 or FIG. 3, and details are not described herein again.

603. Measure the maximum vertical depth of the sheep pool as the measurement result of the amniotic fluid depth DVP measured this time, and determine the target line segment;

For the method of measuring the maximum vertical depth of the sheep pool and the method for determining the target line segment, please refer to the corresponding embodiment of FIG. 4 or FIG. 5, and details are not described herein again.

If the ultrasonic image acquired in step 601 is one, then only one maximum vertical depth measurement result and its corresponding line segment are obtained in this step, and this measurement result is directly used as the measurement result of the amniotic fluid depth DVP measured this time. The corresponding line segment is used as the target line segment.

If step 601 acquires two or more ultrasound images, then this step can obtain a corresponding number of maximum vertical depth measurements and corresponding corresponding number of line segments, for example, a total of three ultrasound images are acquired, then The maximum vertical depths d1, d2, and d3 of the sheep pools of the three ultrasonic images are respectively obtained, and the line segments l1 corresponding to d1, the line segments l2 corresponding to d2, and the line segments l3 corresponding to d3. The maximum value (assumed to be d1) is selected from d1, d2, and d3 as the amniotic fluid depth DVP of this measurement, and then the line segment l1 corresponding to d1 is determined as the target line segment.

604. Display a measurement result of the DVP, and identify a target line segment in the ultrasonic image.

After the DVP is measured and the target line segment is determined, the DVP result can be displayed to the user, and the target line segment is highlighted in the displayed ultrasonic image, so that the doctor can determine the corresponding vertical line depth in the ultrasonic image, and judge the target line segment according to experience. Is it reasonable? Highlighting a target segment highlights all pixels on the target segment, or you can highlight both endpoints of the target segment.

605, determining whether the measurement result of the DVP is within a preset range, and if so, executing step 606, if not, executing step 607;

After the measurement result of the DVP is obtained, it can be determined whether the measurement result of the DVP is within a preset range. If yes, step 606 is performed, and if no, step 607 is performed. Clinically, the preset range of DVP is usually set to [2,8). When DVP≥8cm, the amount of amniotic fluid is considered to be too much. When DVP<2cm, the amount of amniotic fluid is considered to be too small.

Considering that not all regions and units have the same DVP criteria, a preset range setting option can be added to the DVP test system, and the user can set the preset range as needed.

In actual use, step 605 may also be performed before step 604, or may be performed simultaneously with step 604, that is, as long as it is performed after step 603, the timing is not uniquely defined herein.

606. The DVP test result is normal;

If it is determined that the DVP is within the preset range, it can be determined that the DVP detection result is normal, and the DVP test result can be prompted to be normal.

607. The DVP test result is abnormal, and the corresponding medical treatment prompt is displayed.

If it is determined that the DVP is not within the preset range, it may be determined that the DVP detection result is abnormal, and the DVP test result may be prompted to be abnormal, and the corresponding medical treatment prompt is displayed. Specifically, if DVP ≥ 8cm, the amount of amniotic fluid can be indicated too much. If DVP < 2cm, the amount of amniotic fluid can be indicated to be too small. The abnormal amniotic fluid volume is closely related to the normal development of fetal development. The excessive amniotic fluid may be related to fetal digestive tract obstruction, central nervous system abnormality, intrauterine infection and other causes. The oligohydramnios may be associated with fetal growth restriction and fetal congenital urinary tract. System malformations and other related. In order to assist the doctor to make a correct diagnosis based on the test results, screening for diseases that may cause abnormal amniotic fluid, when the system has determined that the amniotic fluid is abnormal, it can display the diagnosis and treatment tips related to amniotic fluid abnormalities, for example, when the amniotic fluid is indicated When there are few, you can suggest "Possible causes include: fetal growth restriction, fetal congenital urinary system malformation, etc."; when the amount of amniotic fluid is too much, you may be prompted "probable causes include: fetal digestive tract obstruction, central nervous system abnormalities, palace Cavity infection, etc.".

Second, the measurement process of AFI:

Referring to FIG. 7, another embodiment of the ultrasonic image processing method in the embodiment of the present invention includes:

701. Obtain an ultrasonic image of four quadrants of the sheep pool;

During the ultrasound examination in the late pregnancy, or when the DVP<3cm, the AFI method is needed to retest the amniotic fluid, the sheep pool is divided into four quadrants: the upper left, the lower left, the upper right, and the lower right, respectively, to obtain ultrasonic images of the four quadrants of the sheep pool. Then, the maximum vertical depth of the sheep pool in each quadrant is measured separately, and then the maximum vertical depth of the four quadrants is added to obtain the amniotic fluid index AFI, and the maximum value among the maximum vertical depths of the four quadrants is used as the DVP value. In order to more fully reflect the distribution of amniotic fluid in the entire uterine cavity. After the ultrasound doctor freezes the ultrasound preview images of the four quadrants in the upper left, lower left, upper right, and lower right quadrants respectively, the ultrasonic image processing apparatus can acquire the ultrasonic images of the four quadrants of the sheep pool.

702. Identify dark areas of amniotic fluid in the ultrasonic images of the respective quadrants;

Since the gray value of the dark region of the amniotic fluid is low and is a connected region, after acquiring the ultrasonic images of the respective quadrants, for each ultrasonic image of the quadrant, the gray value can be recognized from the image according to the grayscale difference. Low connected area, as a dark area of amniotic fluid.

For the method of identifying the dark area of the amniotic fluid in the ultrasonic image of each quadrant, please refer to the method of the embodiment corresponding to FIG. 2 or FIG. 3, and details are not described herein again.

703. Measure a maximum vertical depth of each sheep pool separately, and determine a target line segment in the ultrasonic image of each quadrant;

For the amniotic fluid dark area in the ultrasound image of each quadrant, the maximum vertical depth can be measured separately, and the target line segments corresponding to the maximum vertical depth are respectively determined.

704: summing the maximum vertical depths corresponding to the ultrasonic images of the four quadrants, and obtaining the measurement result of the AFI;

After obtaining the maximum vertical depth corresponding to the ultrasonic image of the four quadrants, the maximum vertical depth corresponding to the ultrasonic images of the four quadrants can be summed to obtain the measurement result of the AFI.

705. Select a maximum value of a maximum vertical depth corresponding to the ultrasonic image of the four quadrants as a measurement result of the DVP;

After obtaining the maximum vertical depth corresponding to the ultrasonic image of the four quadrants, the maximum value can be selected as the measurement result of the DVP.

706. Display measurement results of AFI and DVP, and highlight corresponding target line segments in the ultrasonic images of the respective quadrants;

After measuring the measurement results of AFI and DVP, the measurement results can be displayed, and the respective target line segments are highlighted in the ultrasonic images of each quadrant to facilitate the doctor to determine the maximum vertical depth corresponding to the line segment in the ultrasonic image, and according to experience Determine whether the selection of the target line segment is reasonable. Highlighting a target segment highlights all pixels on the target segment, or it can highlight both endpoints of the target segment.

707, determine whether the measurement result of AFI and DVP is within a preset range, and if so, step 708 is performed, and if not, step 709 is performed;

After the measurement results of AFI and DVP are obtained, whether the measurement results of AFI and DVP are respectively determined to be within a preset range, if yes, step 708 is performed, and if not, step 709 is performed. Clinically, the preset range of DVP is usually set to [2,8). When DVP≥8cm, the amount of amniotic fluid is considered too much. When DVP<2cm, the amount of amniotic fluid is considered too small; the preset range of AFI is usually set to [ 6,20), when AFI ≥ 20cm, it is considered that the amount of amniotic fluid is too much. When AFI <6cm, the amount of amniotic fluid is considered to be too small. When the measurement results of AFI and DVP are both within the preset range, it is determined that the measurement results of AFI and DVP are within a preset range, and step 708 is performed; when the measurement result of AFI is not within the preset range, or the measurement of DVP When the result is not within the preset range, it is determined that the measurement results of AFI and DVP are not within the preset range, and step 709 is performed.

Considering that not all regions and units have the same criteria for AFI and DVP, a preset range setting option can be added to the AFI test system. Users can set the preset range of AFI and DVP as needed.

708. The AFI test result is normal;

If it is determined that the measurement results of AFI and DVP are within the preset range, it can be determined that the AFI measurement result is normal, and the AFI test result can be prompted to be normal.

709. The AFI test result is abnormal, and the corresponding medical prompt is displayed.

If it is determined that the measurement results of AFI and DVP are not within the preset range, it may be determined that the AFI detection result is abnormal, and the AFI test result may be abnormal at this time, and the corresponding medical treatment prompt is displayed. Specifically, if DVP ≥ 8cm, or AFI ≥ 20cm, you can indicate excessive amniotic fluid. If DVP < 2cm, or AFI <6cm, you can indicate that the amount of amniotic fluid is too small. The abnormal amniotic fluid volume is closely related to the normal development of fetal development. The excessive amniotic fluid may be related to fetal digestive tract obstruction, central nervous system abnormality, intrauterine infection and other causes. The oligohydramnios may be associated with fetal growth restriction and fetal congenital urinary tract. System malformations and other related. In order to assist the doctor to make a correct diagnosis based on the test results, screening for diseases that may cause abnormal amniotic fluid, when the system has determined that the amniotic fluid is abnormal, it can display the diagnosis and treatment tips related to amniotic fluid abnormalities, for example, when the amniotic fluid is indicated When there are few, you can suggest "Possible causes include: fetal growth restriction, fetal congenital urinary system malformation, etc."; when the amount of amniotic fluid is too much, you may be prompted "probable causes include: fetal digestive tract obstruction, central nervous system abnormalities, palace Cavity infection, etc.".

In actual use, in the AFI measurement mode, DVP can also be measured and displayed.

The embodiment corresponding to FIG. 6 and FIG. 7 can greatly simplify the operation flow of the user in measuring the amniotic fluid index AFI and DVP, and significantly improve the working efficiency of the doctor.

The method in the embodiment of the present invention has been described above, and the device in the embodiment of the present invention is described below.

Referring to FIG. 8, an embodiment of an ultrasonic image processing apparatus in an embodiment of the present invention includes:

The obtaining module 801 is configured to acquire an ultrasonic image of the sheep pool;

The identification module 802 is configured to identify a dark area of the amniotic fluid corresponding to the sheep pool in the ultrasonic image;

The measuring module 803 is configured to measure the maximum vertical depth of the sheep pool according to the maximum vertical depth of the dark region of the amniotic fluid.

Preferably, the identification module 802 can include:

a traversing unit for traversing the ultrasonic image by using a sliding window of a target scale, the target scale comprising a first scale, a second scale, and a third scale;

a dividing unit, configured to perform image segmentation on the current sliding window region according to the gray value distribution of the current sliding window region, to obtain a first region and a second region, wherein the gray value of the first region is smaller than the gray value of the second region;

a first marking unit, configured to mark pixels in the first area as amniotic dark areas, and pixels in the second area as non-amphibious dark areas;

a conversion unit, configured to convert the ultrasonic image into a binary image at a target scale according to the mark of the pixel, and obtain binary images at the first scale, the second scale, and the third scale, respectively;

a first determining unit, configured to determine a value of each pixel in the ultrasonic image by using the binary image at the first scale, the second scale, and the third scale to generate a synthesized binary image;

a smoothing unit for performing noise smoothing on the synthesized binary image;

And a second determining unit, configured to determine a dark region of the amniotic fluid in the ultrasonic image according to the synthesized binary image after denoising.

Preferably, the identification module 802 can further include:

a third determining unit, configured to determine a pixel corresponding to the color blood flow by using a Doppler signal of the blood flow;

And a second marking unit, configured to mark the third determining unit to identify the hungry pixel as a non-amniotic dark area.

Preferably, the measurement module 803 comprises:

a grouping unit for dividing a target pixel having the same abscissa and a continuous ordinate into a group, wherein the target pixel is a pixel marked as a dark region of the amniotic fluid in the ultrasonic image;

a first calculating unit, configured to calculate a number of pixels of each group, and select a group with the largest number of pixels as the target group;

And a second calculating unit, configured to calculate a maximum vertical depth of the sheep pool according to the number of pixels of the target group.

Referring to FIG. 9, another embodiment of the ultrasonic image processing apparatus in the embodiment of the present invention includes:

The obtaining module 901 is configured to acquire an ultrasonic image of the sheep pool;

The identification module 902 is configured to identify a dark area of the amniotic fluid corresponding to the sheep pool in the ultrasonic image;

a measuring module 903, configured to measure a maximum vertical depth of the sheep pool according to a maximum vertical depth of the dark region of the amniotic fluid;

The first display module 904 is configured to display the maximum vertical depth of the obtained sheep pool as a measurement result of the DVP in the DVP measurement mode;

The first determining module 905 is configured to determine whether the measurement result of the DVP is within a preset range;

The first prompting module 906 is configured to: when the first determining module determines that the measurement result of the DVP is within the preset range, the test result of the DVP is normal, when the first determining module determines that the measurement result of the DVP is not within the preset range, The test result of DVP is abnormal, and the corresponding medical tips are displayed.

Referring to FIG. 10, another embodiment of the ultrasonic image processing apparatus in the embodiment of the present invention includes:

The obtaining module 1001 is configured to acquire an ultrasonic image of the sheep pool, and the obtaining module includes an acquiring subunit for respectively acquiring ultrasonic images of four quadrants of the sheep pool;

The identification module 1002 is configured to identify a dark region of the amniotic fluid corresponding to the sheep pool in the ultrasonic image;

a measuring module 1003, configured to measure a maximum vertical depth of the sheep pool according to a maximum vertical depth of the dark region of the amniotic fluid;

The calculating module 1004 is configured to sum the maximum vertical depths of the four quadrants of the sheep pool in the AFI measurement mode to obtain the AFI measurement result;

The second display module 1005 is configured to display the measurement result of the AFI;

The second determining module 1006 is configured to determine whether the measurement result of the AFI is within a preset range;

The second prompting module 1007 is configured to: when the second determining module determines that the measurement result of the AFI is within the preset range, prompting the measurement result of the AFI to be normal, and when the second determining module determines that the measurement result of the AFI is not within the preset range, The AFI measurement results are abnormal and the corresponding medical tips are displayed.

The embodiment of the present invention further provides an ultrasonic diagnostic apparatus 11 as shown in FIG. 11. For the convenience of description, only parts related to the embodiment of the present invention are shown. For details of the technical disclosure, please refer to the embodiment of the present invention. Method part. The ultrasonic diagnostic apparatus includes a host computer 11-1 and an ultrasonic probe 11-2. The host computer 11-1 can be a terminal device with signal processing capability such as a tablet computer or a desktop computer, and the host computer 11-1 is connected to the ultrasonic probe 11-2. The ultrasonic image can be acquired based on the output data of the ultrasonic probe 11-2.

Referring to FIG. 11, the host computer 11-1 includes a power source 1110, a memory 1120, a display unit 1130, a processor 1140, and a computer program stored in the memory and operable on the processor. The processor 1140 implements the steps in the various method embodiments described above when executing a computer program, such as steps 101 through 103 shown in FIG. Alternatively, the processor implements the functions of the modules or units in the various apparatus embodiments described above when the computer program is executed.

Illustratively, the computer program can be partitioned into one or more modules/units that are stored in the memory and executed by the processor to perform the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing a particular function, the instruction segments being used to describe the execution of the computer program in the host computer 11-1. For example, referring to the corresponding embodiment of FIG. 8, the computer program may be divided into an obtaining module 81, an identifying module 82, and a measuring module 83. The specific functions of each module are as follows:

The obtaining module 81 is configured to acquire an ultrasonic image of the sheep pool;

The identification module 82 is configured to identify a dark area of the amniotic fluid corresponding to the sheep pool in the ultrasonic image;

The measuring module 83 is configured to measure the maximum vertical depth of the sheep pool according to the maximum vertical depth of the dark region of the amniotic fluid.

It will be understood by those skilled in the art that the structure shown in FIG. 11 does not constitute a limitation to the ultrasonic diagnostic apparatus 11, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements, For example, the host computer 11-1 may further include an input/output device, a network access device, a bus, and the like.

The so-called processor can be a central processing unit (CPU), or other general-purpose processor, digital signal processor (DSP), application specific integrated circuit (ASIC), ready-made Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor is a control center of the upper computer 11-1, and connects the entire upper computer 11 by using various interfaces and lines. The various parts of 1.

The memory can be used to store the computer program and/or module, the processor implementing the upper level by running or executing a computer program and/or module stored in the memory, and recalling data stored in the memory Various functions of the machine 11-1. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored. Data created based on the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include a high-speed random access memory, and may also include non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC), and a Secure Digital (SD) card. , Flash Card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

The computer-integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the foregoing embodiments, and may also be completed by a computer program to instruct related hardware. The computer program may be stored in a computer readable storage medium. The steps of the various method embodiments described above may be implemented when the program is executed by the processor. Wherein, the computer program comprises computer program code, which may be in the form of source code, object code form, executable file or some intermediate form. The computer readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM). , random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable media Does not include electrical carrier signals and telecommunication signals.

A person skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the system, the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments described, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of cells is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that The technical solutions described in the examples are modified, or equivalent to some of the technical features, and the modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

投票项 Voting item

An ultrasonic image processing method, comprising:

Obtain an ultrasound image of the sheep pool;

Identifying a dark area of amniotic fluid corresponding to the sheep pool in the ultrasonic image;

The maximum vertical depth of the sheep pool is measured based on the maximum vertical depth of the amniotic fluid dark zone.
The ultrasonic image processing method according to claim 1, wherein the identification of the amniotic fluid dark area corresponding to the sheep pool in the ultrasonic image comprises:

Traversing the ultrasound image using a sliding window of a target scale, the target scale comprising a first scale, a second scale, and a third scale;

Performing image segmentation on the current sliding window region according to the gray value distribution of the current sliding window region, to obtain a first region and a second region, wherein the gray value of the first region is smaller than the gray value of the second region;

Marking pixels in the first area as amniotic dark areas, and marking pixels in the second area as non-amphibious dark areas;

Converting the ultrasonic image into a binary image at a target scale according to a mark of the pixel, respectively obtaining binary images at the first scale, the second scale, and the third scale;

Determining, by using the binary image of the first scale, the second scale, and the third scale, a value of each pixel in the ultrasonic image to generate a composite binary image;

Performing noise smoothing processing on the synthesized binary image;

The amniotic fluid dark area in the ultrasonic image is determined according to the denoised synthetic binary image.
The ultrasonic image processing method according to claim 2, wherein after the pixels in the first area and the pixels in the second area are marked, the ultrasonic pattern is converted to a target scale Before the binary image, the method further includes:

The Doppler signal of the blood flow is used to determine the pixel corresponding to the color blood flow, and is marked as a non-amniotic dark area.
The ultrasonic image processing method according to claim 1, wherein measuring the maximum vertical depth of the sheep pool according to the maximum vertical depth of the amniotic fluid dark area comprises:

Dividing target pixels having the same abscissa and continuous ordinates into a group, wherein the target pixels are pixels marked as amniotic dark areas in the ultrasonic image;

Calculating the number of pixels in each group, and selecting the group with the largest number of pixels as the target group;

Calculating a maximum vertical depth of the sheep pool according to the number of pixels of the target group.
The ultrasonic image processing method according to any one of claims 1 to 4, characterized in that, in the measurement mode of the amniotic fluid depth DVP, the maximum vertical depth of the sheep pool is measured according to the maximum vertical depth of the amniotic fluid dark area Thereafter, the method further includes:

The obtained maximum vertical depth of the sheep pool is displayed as a measurement result of DVP;

Determining whether the measurement result of the DVP is within a preset range;

If yes, the test result of the DVP is normal;

If not, the test result of the DVP is abnormal.
The ultrasonic image processing method according to any one of claims 1 to 4, characterized in that, in the measurement mode of the amniotic fluid index AFI, acquiring the ultrasonic image of the sheep pool comprises:

Obtaining ultrasonic images of four quadrants of the sheep pool respectively;

After measuring the maximum vertical depth of the sheep pool according to the maximum vertical depth of the amniotic fluid dark area, the method further includes:

The maximum vertical depths of the four quadrants of the sheep pool are summed to obtain the AFI measurement results and displayed;

Determining whether the measurement result of the AFI is within a preset range;

If yes, it indicates that the measurement result of the AFI is normal;

If not, it indicates that the measurement result of the AFI is abnormal.
An ultrasonic image processing apparatus, comprising:

Obtaining a module for acquiring an ultrasonic image of a sheep pool;

An identification module, configured to identify a dark area of amniotic fluid corresponding to the sheep pool in the ultrasonic image;

And a measuring module for measuring a maximum vertical depth of the sheep pool according to a maximum vertical depth of the amniotic fluid dark area.
The ultrasonic image processing apparatus according to claim 7, wherein the apparatus further comprises:

a first display module, configured to display, in a measurement mode of the DVP, a maximum vertical depth of the obtained sheep pool as a measurement result of the DVP;

a first determining module, configured to determine whether the measurement result of the DVP is within a preset range;

a first prompting module, configured to: when the first determining module determines that the measurement result of the DVP is within a preset range, prompting that the test result of the DVP is normal, when the first determining module determines the measurement of the DVP When the result is not within the preset range, the test result of the DVP is abnormal, and the corresponding medical treatment prompt is displayed.
The ultrasonic image processing apparatus according to claim 7, wherein the acquisition module comprises:

Obtaining a subunit for respectively acquiring ultrasonic images of four quadrants of the sheep pool;

The ultrasonic image processing apparatus further includes:

a calculation module for summing the maximum vertical depths of the four quadrants of the sheep pool in the AFI measurement mode to obtain the AFI measurement result;

a second display module, configured to display the measurement result of the AFI;

a second determining module, configured to determine whether the measurement result of the AFI is within a preset range;

a second prompting module, configured to: when the second determining module determines that the measurement result of the AFI is within a preset range, prompting that the measurement result of the AFI is normal, and when the second determining module determines the measurement of the AFI When the result is not within the preset range, the measurement result of the AFI is abnormal, and the corresponding medical treatment prompt is displayed.
An ultrasonic diagnostic apparatus, comprising: an upper computer and an ultrasonic probe;

The host computer includes a processor for performing the steps of the method of any of claims 1-6 when executing the computer program stored in the memory.
A computer readable storage medium having stored thereon a computer program, wherein the computer program is executed by a processor to perform the steps of the method of any of claims 1-6.