Ultrasonic image processing method for swallowing function examination

Abstract

The invention discloses an ultrasonic image processing method for swallowing function examination, and mainly relates to the technical field of ultrasonic image processing. Comprising the following steps: arranging an ultrasonic probe according to a preset placement position and a placement angle, and capturing a dynamic ultrasonic image frame sequence; obtaining an enhanced dynamic ultrasonic image frame sequence; obtaining a separation ridge line set sequence; obtaining an enhanced dynamic ultrasonic image frame neighborhood contour recognition result sequence; extracting a lingual bone-thyroid cartilage distance to obtain a lingual bone-thyroid cartilage distance set; and obtaining the shortening rate of the distance between the target tongue bone and the thyroid cartilage, and taking the shortening rate of the distance between the target tongue bone and the thyroid cartilage as an ultrasonic image processing result. The technical problems that in the prior art, the ultrasonic image processing quality for swallowing function examination is poor, and the reliability of the processing result is low are solved. The method has the beneficial effects that the ultrasonic image processing reliability is improved, and the recognition accuracy of the shortening rate of the distance between the tongue bone and the thyroid cartilage is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic image processing, and in particular to an ultrasonic image processing method for swallowing function examination. Background Art

[0002] Swallowing function examination mainly observes and evaluates the swallowing process through imaging technology to determine the patient's swallowing ability and possible obstacles. Ultrasound imaging, as a commonly used imaging examination method, has the advantages of being non-invasive, real-time, and convenient, and can reflect the swallowing movements in the oral and laryngeal phases. In ultrasound imaging, the positional relationship between the hyoid bone and the thyroid cartilage is an important basis for judging swallowing function. However, existing ultrasound image processing methods usually use simple image filtering or contrast adjustment to improve image quality, which cannot effectively remove noise, resulting in blurred image details, especially the small movements during swallowing cannot be clearly captured.

[0003] The prior art has technical problems such as poor quality of ultrasonic image processing for swallowing function examination and low reliability of processing results. Summary of the invention

[0004] The present application provides an ultrasonic image processing method for swallowing function examination, which is used to solve the technical problems of poor quality of ultrasonic image processing for swallowing function examination and low reliability of processing results in the prior art.

[0005] In view of the above problems, the present application provides an ultrasonic image processing method for swallowing function examination, the method comprising:

[0006] The ultrasound probe is deployed according to a preset placement position and placement angle, and a dynamic ultrasound image of the target inspection subject swallowing a preset milliliter of water at one time is captured by using the deployed ultrasound probe to obtain a dynamic ultrasound image frame sequence;

[0007] Introducing a noise function and performing image enhancement processing on the dynamic ultrasound image frame sequence in combination with a pre-trained denoising function to obtain an enhanced dynamic ultrasound image frame sequence;

[0008] The pixel value of each pixel point is simulated as the height of a simulated hillside, and the enhanced dynamic ultrasound image frame sequence is traversed to perform slope simulation to obtain a simulated slope sequence;

[0009] The positions of the minimum hillside heights of the simulated slope sequence are respectively used as water injection points, water is injected into the simulated slope sequence, and as the water level rises, the dividing ridge line of the simulated slope sequence is identified according to a preset hillside height difference threshold, so as to obtain a dividing ridge line set sequence;

[0010] Based on the position of the dividing ridge line in the dividing ridge line set sequence, performing neighborhood contour recognition on the enhanced dynamic ultrasound image frame sequence corresponding to the simulated slope sequence to obtain an enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence;

[0011] Traversing the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence to extract the hyoid bone-thyroid cartilage distance, and obtaining a hyoid bone-thyroid cartilage distance set;

[0012] Based on the size of the hyoid bone-thyroid cartilage distance in the hyoid bone-thyroid cartilage distance set, the hyoid bone-thyroid cartilage distance shortening rate is identified to obtain the target hyoid bone-thyroid cartilage distance shortening rate, and the target hyoid bone-thyroid cartilage distance shortening rate is used as the ultrasonic image processing result.

[0013] One or more technical solutions provided in the present application have at least the following technical effects or advantages: the present application deploys ultrasonic probes according to preset placement positions and placement angles, and uses the deployed ultrasonic probes to capture dynamic ultrasonic images of the target inspection object swallowing preset milliliters of water at one time, to obtain a dynamic ultrasonic image frame sequence, and then introduces a noise function, and combines the pre-trained denoising function to perform image enhancement processing on the dynamic ultrasonic image frame sequence to obtain an enhanced dynamic ultrasonic image frame sequence, and then simulates the pixel value of each pixel point as the height of a simulated hillside, traverses the enhanced dynamic ultrasonic image frame sequence to perform slope simulation, and obtains a simulated slope sequence, and respectively uses the positions of the minimum hillside heights of the simulated slope sequence as water injection points, and injects water into the simulated slope sequence. As the water level rises, the separation ridge line of the simulated slope sequence is identified according to the preset hillside height difference threshold, and the separation ridge line set sequence is obtained. Then, based on the position of the separation ridge line in the separation ridge line set sequence, the neighborhood contour of the enhanced dynamic ultrasound image frame sequence corresponding to the simulated slope sequence is identified to obtain the neighborhood contour identification result sequence of the enhanced dynamic ultrasound image frame. The neighborhood contour identification result sequence of the enhanced dynamic ultrasound image frame is traversed to extract the hyoid bone-thyroid cartilage distance to obtain the hyoid bone-thyroid cartilage distance set. Based on the size of the hyoid bone-thyroid cartilage distance in the hyoid bone-thyroid cartilage distance set, the hyoid bone-thyroid cartilage distance shortening rate is identified to obtain the target hyoid bone-thyroid cartilage distance shortening rate, and the target hyoid bone-thyroid cartilage distance shortening rate is used as the ultrasound image processing result. The technical effect of significantly improving the reliability of ultrasound image processing in swallowing function examination and improving the accuracy of hyoid bone-thyroid cartilage distance measurement is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Attached Figure 1 It is a flow chart of an ultrasonic image processing method for swallowing function examination provided by an embodiment of the present invention.

[0015] Attached Figure 2It is a flow chart of obtaining a separation ridge line set sequence in an ultrasonic image processing method for swallowing function examination provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0017] Examples, such as Figure 1 As shown, the present application provides an ultrasonic image processing method for swallowing function examination, wherein the method comprises:

[0018] S100: deploying ultrasound probes according to preset placement positions and placement angles, and using the deployed ultrasound probes to capture dynamic ultrasound images of the target inspection subject swallowing preset milliliters of water at one time, to obtain a dynamic ultrasound image frame sequence;

[0019] In an embodiment of the present application, the ultrasonic probe is placed in the throat area of ​​the patient according to the preset placement position and placement angle set by a technician in this field according to the actual situation of the target monitored object, so as to clearly capture the process of swallowing action. When the target object (subject) swallows a preset milliliter (such as 5 milliliters) of water at one time, the swallowing action is captured by an ultrasonic device in real time to obtain the dynamic ultrasonic image sequence. The dynamic ultrasonic image sequence refers to a series of continuous image frames captured by the ultrasonic probe, and each frame represents a certain moment in the swallowing process. Since the dynamic ultrasonic image sequence is continuous, it can capture rapid changes in the swallowing process.

[0020] By obtaining the dynamic ultrasound image frame sequence, the technical effect of providing raw data for subsequent image enhancement, noise removal and structural analysis, capturing subtle physiological changes during swallowing, and providing basic data for the measurement of the hyoid bone-thyroid cartilage distance is achieved.

[0021] S200: introducing a noise function and performing image enhancement processing on the dynamic ultrasound image frame sequence in combination with a pre-trained denoising function to obtain an enhanced dynamic ultrasound image frame sequence;

[0022] Further, a noise function is introduced, and the image enhancement processing is performed on the dynamic ultrasound image frame sequence in combination with a pre-trained denoising function to obtain an enhanced dynamic ultrasound image frame sequence. Step S200 of the embodiment of the present application further includes:

[0023] Obtain a noise function, wherein the noise function is:

[0024] x i =α t y i +(1-α t )·∈ t ;

[0025] Among them, x i is the i-th training sample noisy ultrasound image frame in the training sample noisy ultrasound image frame set, y i is the i-th training sample ultrasound image frame in the training sample ultrasound image frame set, α t is the preset diffusion intensity, ∈ t is the preset random noise;

[0026] The dynamic ultrasonic image frame sequence is forward diffused based on the noise function, and the dynamic ultrasonic image frame sequence after the forward diffusion is reverse diffused using the pre-trained denoising function to obtain the enhanced dynamic ultrasonic image frame sequence.

[0027] Furthermore, step S200 of the embodiment of the present application further includes:

[0028] Acquire a training sample initial ultrasound image frame set, perform noise diffusion processing on the sample ultrasound image frame set based on the noise function, and obtain a training sample noise ultrasound image frame set, wherein the training sample ultrasound image frames correspond to the training sample noise ultrasound image frames one by one;

[0029] Obtaining the image after image enhancement of the initial ultrasound image frame set of the training sample to obtain the enhanced ultrasound image frame set of the training sample;

[0030] Based on the training sample ultrasound image frame set, the noise function, the training sample noise ultrasound image frame set and the training sample enhanced ultrasound image frame set, coefficient fitting is performed on the pre-constructed denoising function to obtain the pre-trained denoising function according to the solution result.

[0031] Furthermore, step S200 of the embodiment of the present application further includes:

[0032] Obtain a pre-built denoising function, wherein the pre-built denoising function is:

[0033]

[0034] in, is the i-th training sample enhanced ultrasound image frame in the training sample enhanced ultrasound image frame set, x i is the i-th training sample noisy ultrasound image frame in the training sample noisy ultrasound image frame set, y iis the i-th training sample ultrasound image frame in the training sample ultrasound image frame set, σ t is the noise function, and ε is the denoising coefficient.

[0035] In a possible embodiment, the noise function is a mathematical function used to simulate the effect of noise in an image. The noise function is used to combine noise with a dynamic ultrasound image frame sequence to generate a noisy image, and then a pre-trained denoising function is used to perform image enhancement processing on the noisy image, thereby obtaining a clearer and higher quality enhanced dynamic ultrasound image frame sequence. The technical effect of providing data support for subsequent image contour recognition is achieved.

[0036] In a possible embodiment, the noise function is:

[0037] x i =α t y i +(1-α t )·∈ t ;

[0038] Among them, x i is the i-th training sample noisy ultrasound image frame in the training sample noisy ultrasound image frame set, y i is the i-th training sample ultrasound image frame in the training sample ultrasound image frame set, α t is the preset diffusion intensity, ∈ t The default random noise.

[0039] Optionally, the preset random noise can be Gaussian noise, which represents random disturbances in the image. The preset diffusion intensity is a diffusion intensity pre-set by a person skilled in the art, which is used to control the intensity of the noise. Forward diffusion refers to the process of gradually converting a clear image into a noisy image by adding noise in image processing. In this step, a noise function is used to forward diffuse the image to simulate the influence of noise. Reverse diffusion is a process opposite to forward diffusion, and its purpose is to remove noise and restore the image to its original state. In this step, a pre-trained denoising function is used to reverse the forward diffusion process to restore a clear image from a noisy image. The pre-trained denoising function is an image processing function used to restore a clear image from a noisy image. It can effectively process image noise by learning the features of noise removal on a large amount of training data.

[0040] In one embodiment, the training sample initial ultrasound image frame set is a set of real, noise-free ultrasound image frames, which are used to train the denoising model during the training process. The training sample enhanced ultrasound image frame set is an image frame obtained by a person skilled in the art after performing image enhancement based on the training sample initial ultrasound image frame set. The training sample noisy ultrasound image frame set is an image frame obtained after adding noise to the image frames in the sample ultrasound image frame set based on the noise function.

[0041] Get the pre-built denoising function. The pre-built denoising function is:

[0042]

[0043] in, is the i-th training sample enhanced ultrasound image frame in the training sample enhanced ultrasound image frame set, x i is the i-th training sample noisy ultrasound image frame in the training sample noisy ultrasound image frame set, y i is the i-th training sample ultrasound image frame in the training sample ultrasound image frame set, σ t is the noise function, and ε is the denoising coefficient.

[0044] Optionally, the denoising coefficient is used to adjust the denoising effect. It is the square of the Euclidean distance, which indicates the difference between the training sample noisy ultrasound image frame and the training sample ultrasound image frame.

[0045] The training sample ultrasound image frame set, the noise function, the training sample noise ultrasound image frame set and the training sample enhanced ultrasound image frame set are input into the pre-constructed denoising function for fitting analysis to obtain the solved denoising coefficient. According to the solved denoising coefficient, the pre-trained denoising function is obtained. Through training, the combination of the noise function and the denoising function is optimized to improve the quality of image enhancement.

[0046] S300: simulating the pixel value of each pixel point as the height of a simulated hillside, traversing the enhanced dynamic ultrasound image frame sequence to perform slope simulation, and obtaining a simulated slope sequence;

[0047] S400: taking the positions of the minimum hillside heights of the simulated slope sequence as water injection points, injecting water into the simulated slope sequence, and identifying the dividing ridge lines of the simulated slope sequence according to a preset hillside height difference threshold as the water level rises, to obtain a dividing ridge line set sequence;

[0048] Further, as attached Figure 2As shown, the positions of the minimum hillside heights of the simulated slope sequence are respectively used as water injection points, and water is injected into the simulated slope sequence. As the water level rises, the separation ridge line of the simulated slope sequence is identified according to a preset hillside height difference threshold, and a separation ridge line set sequence is obtained. Step S400 of the embodiment of the present application also includes:

[0049] Extracting a first simulated slope from the simulated slope sequence, and using the minimum slope height of the first simulated slope as a reference for threshold determination;

[0050] Water is injected based on the water injection point of the first simulated slope, and as the water level rises, when the water surface covers a simulated hillside, a first water surface covers the simulated hillside;

[0051] Determine whether the difference in slope height between the simulated slope submerged by the first water surface and the water injection point of the first simulated slope is greater than or equal to a preset slope height difference threshold; if not, continue to inject water, and identify the dividing ridge line based on the minimum slope height and the preset slope height difference threshold;

[0052] If so, a dividing ridge line is generated at the place where the first water surface covers the simulated hillside, and water injection is continued to obtain a first dividing ridge line set, wherein the dividing ridge line rises as the water surface rises;

[0053] The positions of the minimum hillside heights of the simulated slope sequence are respectively taken as water injection points, and water is injected into the simulated slope sequence. During the rising process of the water level, the dividing ridge lines of the simulated slope sequence are identified based on the preset hillside height difference threshold to obtain a dividing ridge line set sequence.

[0054] Further, if so, a dividing ridge line is generated at the place where the first water surface covers the simulated hillside, and water injection is continued to obtain a first dividing ridge line set. Step S400 of the embodiment of the present application further includes:

[0055] The height of the simulated hillside submerged by the first water surface is updated as a reference for threshold determination;

[0056] When the water surface covers a simulated slope again, a second water surface covers the simulated slope;

[0057] Determine whether the difference in height between the simulated hillside height submerged by the second water surface and the simulated hillside height submerged by the first water surface is greater than or equal to a preset hillside height difference threshold; if so, generate a dividing ridge line at the place where the second water surface submerges the simulated hillside, and update the height of the simulated hillside height submerged by the second water surface as a reference for threshold judgment, continue to inject water to identify the dividing ridge line, and stop injecting water when the water surface submerges the highest point of the first simulated slope to obtain the first dividing ridge line set.

[0058] In one possible embodiment, the pixel value of each pixel point is associated with the height of the hillside to form a model that is analogous to the hillside. This simulated hillside height reflects the intensity of the pixel values ​​in the image (such as grayscale values), and higher pixel values ​​may represent higher hillsides, while lower pixel values ​​represent lower hillsides. By analogizing the pixel value of each pixel with the height of the hillside, the enhanced dynamic ultrasound image frame sequence is converted into a simulated slope sequence. This process simulates each pixel value in the image as the height of the "hillside", making the analysis of the entire image more structured and facilitating subsequent more complex analysis.

[0059] In the simulated hillside terrain, water injection is to simulate the liquid rising from the bottom of the hillside, reflecting the important areas or key points in the image. Preferably, the water injection process is similar to "filling" the image, which can help identify different areas. In the simulated slope, the dividing ridge line is a boundary defined by the water injection process and the rise of the water level. These dividing lines help to divide different areas, thereby realizing the recognition and analysis of the image structure. The preset hillside height difference threshold is the maximum hillside height difference that can be divided into an area, which is pre-set by a person skilled in the art. By obtaining the dividing ridge line set sequence, the technical effect of paving the way for the subsequent neighborhood contour recognition of the enhanced dynamic ultrasound image frame sequence is achieved.

[0060] Preferably, a first simulated slope is extracted from the simulated slope sequence, and the minimum hillside height of the first simulated slope is used as a basis for threshold judgment. The first simulated slope is a sub-area extracted from the simulated slope sequence, which is used for further water injection and hillside height difference judgment.

[0061] Water is injected into the slope from the water injection point of the first simulated slope, and the simulated liquid starts to rise from the bottom of the hillside. As the water level rises, when the water level submerges a simulated hillside, the first water surface submerges the simulated hillside. Then, it is determined whether the difference in hillside height between the first water surface submerging the simulated hillside and the water injection point of the first simulated slope is greater than or equal to the preset hillside height difference threshold. If not, it indicates that the difference between the first simulated slope and the first water surface submerging the simulated hillside is not large, and they can be divided into a neighborhood without the need for ridge line separation. Continue to inject water, and identify the separation ridge line based on the minimum hillside height and the preset hillside height difference threshold.

[0062] If so, it indicates that the difference between the first simulated slope and the first simulated hillside submerged by the water surface is large, and it is necessary to generate a dividing ridge line at the place where the first water surface submerges the simulated hillside, continue to inject water, and update the hillside height of the first simulated hillside submerged by the water surface as the reference for threshold judgment. When the water surface submerges a simulated slope again, the second simulated hillside submerged by the water surface is obtained. Further, it is determined whether the height difference between the hillside height of the second simulated hillside submerged by the water surface and the hillside height of the first simulated hillside submerged by the water surface is greater than or equal to the preset hillside height difference threshold. If so, a dividing ridge line is generated at the place where the second simulated hillside submerged by the water surface, and the hillside height of the second simulated hillside submerged by the water surface is updated as the reference for threshold judgment. Continue to inject water to identify the dividing ridge line until the water surface submerges the highest point of the first simulated slope, stop injecting water, summarize the dividing ridge lines obtained during the water injection process, and obtain the first dividing ridge line set. Among them, the dividing ridge line rises as the water surface rises.

[0063] Based on the same principle as that of obtaining the first dividing ridge line set, the positions of the minimum hillside heights of the simulated slope sequence are respectively used as water injection points, and water is injected into the simulated slope sequence. During the rising process of the water level, the dividing ridge lines of the simulated slope sequence are identified based on the preset hillside height difference threshold to obtain a dividing ridge line set sequence.

[0064] By taking the minimum hillside height of the simulated slope sequence as the water injection point, we start to "inject water" into the slope. As the water level rises, the separation ridge line (similar to the regional boundary in the image) is identified according to the set hillside height difference threshold. This process simulates how to identify areas with key features in the image. In this way, the system can gradually identify and separate different areas through the rise of water level, thereby helping to extract important information in the image, such as structural features such as the distance between the hyoid bone and the thyroid cartilage.

[0065] This method effectively transforms the image segmentation problem into a terrain analysis problem, using the "water injection" process to identify key areas in the image by simulating hillsides, thereby improving the accuracy and reliability of image processing in swallowing function examinations.

[0066] S500: Based on the position of the dividing ridge line in the dividing ridge line set sequence, performing neighborhood contour recognition on the enhanced dynamic ultrasound image frame sequence corresponding to the simulated slope sequence to obtain a neighborhood contour recognition result sequence of the enhanced dynamic ultrasound image frame;

[0067] In one possible embodiment, neighborhood contour recognition is performed by analyzing the relationship between adjacent pixels in the image to identify and extract important contours in the image (such as the edge of an object). In step S500, neighborhood contour recognition is based on the position of the separation ridge line, and the contours of the area containing key information are respectively identified in the enhanced dynamic ultrasound image frame.

[0068] Preferably, according to the position of the separation ridge line in the separation ridge line set sequence, the separation ridge lines in a separation ridge line set are connected to each other, and the contour of the neighborhood area is extracted, so as to obtain the neighborhood of different structures (for example, the neighborhood of the hyoid bone or the thyroid cartilage) for further analysis, thereby achieving the technical effect of providing support for the subsequent hyoid bone-thyroid cartilage distance measurement.

[0069] S600: traversing the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence to extract the hyoid bone-thyroid cartilage distance, and obtaining a hyoid bone-thyroid cartilage distance set;

[0070] Further, the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence is traversed to extract the hyoid bone-thyroid cartilage distance to obtain a hyoid bone-thyroid cartilage distance set. Step S600 of the embodiment of the present application further includes:

[0071] Acquire multiple sample enhanced dynamic ultrasound image frame neighborhood contour recognition results, and perform manual marking based on the multiple sample enhanced dynamic ultrasound image frame neighborhood contour recognition results to obtain multiple sample hyoid bone-thyroid cartilage distances, wherein each hyoid bone-thyroid cartilage distance corresponds to one sample enhanced dynamic ultrasound image frame neighborhood contour recognition result;

[0072] The framework constructed based on the convolutional neural network is supervised by using the plurality of sample enhanced dynamic ultrasound image frame neighborhood contour recognition results and the plurality of sample hyoid bone-thyroid cartilage distances to train the framework, learn the one-to-one mapping relationship between the sample enhanced dynamic ultrasound image frame neighborhood contour recognition results and the hyoid bone-thyroid cartilage distance, until the training converges, and obtain the distance extractor;

[0073] The spacing extractor is used to extract the hyoid bone-thyroid cartilage spacing from the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence to obtain the hyoid bone-thyroid cartilage spacing set.

[0074] In the embodiments of the present application, the hyoid-thyroid cartilage distance refers to the distance between the hyoid bone and the thyroid cartilage. In the swallowing function test, the change of this distance is of great significance for evaluating the functional state of the swallowing process. By measuring this distance, it is possible to evaluate whether the swallowing action is normal and whether the hyoid bone and the thyroid cartilage have appropriate displacement.

[0075] The enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence is the contour information (such as the hyoid bone and thyroid cartilage regions) of each key region in the enhanced dynamic ultrasound image frame sequence obtained in the previous step.

[0076] Obtain multiple sample enhanced dynamic ultrasound image frame neighborhood contour recognition results, and have an expert or operator manually mark the hyoid bone-thyroid cartilage distance in each image frame to obtain multiple sample hyoid bone-thyroid cartilage distances. This process is to generate training data for subsequent machine learning algorithm training. Among them, each hyoid bone-thyroid cartilage distance corresponds to a sample enhanced dynamic ultrasound image frame neighborhood contour recognition result.

[0077] The framework constructed based on the convolutional neural network is supervised and trained using the multiple sample enhanced dynamic ultrasound image frame neighborhood contour recognition results and multiple sample hyoid bone-thyroid cartilage distances to learn the one-to-one mapping relationship between the sample enhanced dynamic ultrasound image frame neighborhood contour recognition results and the hyoid bone-thyroid cartilage distance until the training converges to obtain a distance extractor. The convolutional neural network (CNN) is a deep learning model widely used in image processing and recognition tasks. Here, CNN is used to learn the relationship between the enhanced dynamic ultrasound image frame in the sample and the corresponding hyoid bone-thyroid cartilage distance. The distance extractor is a model obtained by CNN training, which is used to automatically extract the hyoid bone-thyroid cartilage distance from the enhanced dynamic ultrasound image frame neighborhood contour recognition results.

[0078] Through supervised training of CNN, the model (distance extractor) can learn to automatically extract the hyoid bone-thyroid cartilage distance from the image. This process is the core part of automated recognition, which greatly improves the efficiency and accuracy of swallowing function examination. Finally, using the trained distance extractor, the hyoid bone-thyroid cartilage distance can be automatically extracted from the new enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence, thereby obtaining the hyoid bone-thyroid cartilage distance set. The technical effect of improving the efficiency and accuracy of ultrasound image processing is achieved.

[0079] S700: Based on the size of the hyoid bone-thyroid cartilage distance in the hyoid bone-thyroid cartilage distance set, identify the hyoid bone-thyroid cartilage distance shortening rate, obtain the target hyoid bone-thyroid cartilage distance shortening rate, and use the target hyoid bone-thyroid cartilage distance shortening rate as the ultrasonic image processing result.

[0080] Further, based on the size of the hyoid bone-thyroid cartilage distance in the hyoid bone-thyroid cartilage distance set, the hyoid bone-thyroid cartilage distance shortening rate is identified to obtain the target hyoid bone-thyroid cartilage distance shortening rate. In the embodiment of the present application, step S700 further includes:

[0081] Extracting the maximum value of the hyoid bone-thyroid cartilage distance and the minimum value of the hyoid bone-thyroid cartilage distance from the hyoid bone-thyroid cartilage distance set;

[0082] The difference between the maximum hyoid bone-thyroid cartilage distance and the minimum hyoid bone-thyroid cartilage distance is calculated, and the ratio of the calculated result to the maximum hyoid bone-thyroid cartilage distance is used as the target hyoid bone-thyroid cartilage distance shortening rate.

[0083] In one embodiment, the hyoid-thyroid distance set refers to the set of distance values ​​between the hyoid bone and the thyroid cartilage in all image frames extracted by the aforementioned steps. This set contains the actual distance data between the hyoid bone and the thyroid cartilage in each frame of the image. The maximum and minimum values ​​of the hyoid-thyroid distance refer to the maximum and minimum distances among all measured values ​​in the hyoid-thyroid distance set. Through these extreme values, the relative position changes of the hyoid bone and the thyroid cartilage during swallowing can be quantified. The target hyoid-thyroid distance shortening rate is an indicator to measure the relative distance change between the hyoid bone and the thyroid cartilage during the swallowing action, which is specifically calculated as the ratio of the difference between the maximum distance and the minimum distance to the maximum distance. The larger this ratio is, the more significant the relative movement between the hyoid bone and the thyroid cartilage is, which helps to evaluate the effectiveness of the swallowing function.

[0084] By analyzing all the data in the hyoid-thyroid cartilage distance set, the maximum and minimum values, that is, the maximum and minimum distances between the hyoid bone and the thyroid cartilage, are first extracted. Then, the difference between the two values ​​is calculated, and the ratio is calculated with the maximum value to obtain the shortening rate of the distance between the hyoid bone and the thyroid cartilage. This indicator is used to reflect the relative movement between the hyoid bone and the thyroid cartilage during swallowing, and then evaluate whether the swallowing function is normal. If the shortening rate is small, it may mean that there is an abnormality in the swallowing function, suggesting that further examination or intervention is needed. Therefore, the shortening rate of the distance between the hyoid bone and the thyroid cartilage, as the final result of ultrasound image processing, is one of the key outputs of this method. The technical effect of improving the reliability of ultrasound image processing has been achieved.

[0085] In summary, the embodiments of the present application have at least the following technical effects:

[0086] This application can effectively remove noise and blur through image enhancement, making the distance between the hyoid bone and the thyroid cartilage during swallowing clearer and measurable. By simulating slopes and water injection operations, each pixel value of the image is compared to the height of the hillside, which can simulate the structural changes in the image from a more fine-grained level, providing a good foundation for subsequent ridge line recognition. Based on the position of the ridge line, through neighborhood contour recognition, the dynamic distance between the hyoid bone and the thyroid cartilage during swallowing can be accurately extracted, thereby improving the recognition accuracy of the distance shortening rate. The technical effect of significantly improving the reliability of ultrasonic image processing in swallowing function examinations has been achieved.

[0087] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, 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.

[0088] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0089] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An ultrasonic image processing method for swallowing function examination, characterized in that: The method comprises: The ultrasound probe is deployed according to a preset placement position and placement angle, and a dynamic ultrasound image of the target inspection subject swallowing a preset milliliter of water at one time is captured by using the deployed ultrasound probe to obtain a dynamic ultrasound image frame sequence; Introducing a noise function and performing image enhancement processing on the dynamic ultrasound image frame sequence in combination with a pre-trained denoising function to obtain an enhanced dynamic ultrasound image frame sequence; The pixel value of each pixel point is simulated as the height of a simulated hillside, and the enhanced dynamic ultrasound image frame sequence is traversed to perform slope simulation to obtain a simulated slope sequence; The positions of the minimum hillside heights of the simulated slope sequence are respectively used as water injection points, water is injected into the simulated slope sequence, and as the water level rises, the dividing ridge line of the simulated slope sequence is identified according to a preset hillside height difference threshold, so as to obtain a dividing ridge line set sequence; Based on the position of the dividing ridge line in the dividing ridge line set sequence, performing neighborhood contour recognition on the enhanced dynamic ultrasound image frame sequence corresponding to the simulated slope sequence to obtain an enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence; Traversing the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence to extract the hyoid bone-thyroid cartilage distance, and obtaining a hyoid bone-thyroid cartilage distance set; Based on the size of the hyoid bone-thyroid cartilage distance in the hyoid bone-thyroid cartilage distance set, the hyoid bone-thyroid cartilage distance shortening rate is identified to obtain the target hyoid bone-thyroid cartilage distance shortening rate, and the target hyoid bone-thyroid cartilage distance shortening rate is used as the ultrasonic image processing result.

2. The ultrasonic image processing method for swallowing function examination according to claim 1, characterized in that: Introducing a noise function and combining it with a pre-trained denoising function to perform image enhancement processing on the dynamic ultrasound image frame sequence to obtain an enhanced dynamic ultrasound image frame sequence, including: Obtain a noise function, wherein the noise function is: x i =a t y i +(1-a t )·∈ t ; Among them, x i is the i-th training sample noisy ultrasound image frame in the training sample noisy ultrasound image frame set, y i is the i-th training sample ultrasound image frame in the training sample ultrasound image frame set, α t is the preset diffusion intensity, ∈ t is the preset random noise; The dynamic ultrasonic image frame sequence is forward diffused based on the noise function, and the dynamic ultrasonic image frame sequence after the forward diffusion is reverse diffused using the pre-trained denoising function to obtain the enhanced dynamic ultrasonic image frame sequence.

3. The ultrasonic image processing method for swallowing function examination according to claim 2, characterized in that: include: Acquire a training sample initial ultrasound image frame set, perform noise diffusion processing on the sample ultrasound image frame set based on the noise function, and obtain a training sample noise ultrasound image frame set, wherein the training sample ultrasound image frames correspond to the training sample noise ultrasound image frames one by one; Obtaining the image after image enhancement of the initial ultrasound image frame set of the training sample to obtain the enhanced ultrasound image frame set of the training sample; Based on the training sample ultrasound image frame set, the noise function, the training sample noise ultrasound image frame set and the training sample enhanced ultrasound image frame set, coefficient fitting is performed on the pre-constructed denoising function to obtain the pre-trained denoising function according to the solution result.

4. The ultrasonic image processing method for swallowing function examination according to claim 3, characterized in that: include: Obtain a pre-built denoising function, wherein the pre-built denoising function is: in, is the i-th training sample enhanced ultrasound image frame in the training sample enhanced ultrasound image frame set, x i is the i-th training sample noisy ultrasound image frame in the training sample noisy ultrasound image frame set, y i is the i-th training sample ultrasound image frame in the training sample ultrasound image frame set, σ t is the noise function, and ε is the denoising coefficient.

5. The ultrasonic image processing method for swallowing function examination according to claim 1, characterized in that: The positions of the minimum hillside heights of the simulated slope sequence are respectively used as water injection points, water is injected into the simulated slope sequence, and as the water level rises, the dividing ridge line of the simulated slope sequence is identified according to a preset hillside height difference threshold, to obtain a dividing ridge line set sequence, including: Extracting a first simulated slope from the simulated slope sequence, and using the minimum slope height of the first simulated slope as a reference for threshold determination; Water is injected based on the water injection point of the first simulated slope, and as the water level rises, when the water surface covers a simulated hillside, a first water surface covers the simulated hillside; Determine whether the difference in slope height between the simulated slope submerged by the first water surface and the water injection point of the first simulated slope is greater than or equal to a preset slope height difference threshold; if not, continue to inject water, and identify the dividing ridge line based on the minimum slope height and the preset slope height difference threshold; If so, a dividing ridge line is generated at the place where the first water surface covers the simulated hillside, and water injection is continued to obtain a first dividing ridge line set, wherein the dividing ridge line rises as the water surface rises; The positions of the minimum hillside heights of the simulated slope sequence are respectively taken as water injection points, and water is injected into the simulated slope sequence. During the rising process of the water level, the dividing ridge lines of the simulated slope sequence are identified based on the preset hillside height difference threshold to obtain a dividing ridge line set sequence.

6. The ultrasonic image processing method for swallowing function examination according to claim 5, characterized in that: If so, a dividing ridge line is generated at the place where the first water surface covers the simulated hillside, and water injection is continued to obtain the first dividing ridge line set, including: The height of the simulated hillside submerged by the first water surface is updated as a reference for threshold determination; When the water surface covers a simulated slope again, a second water surface covers the simulated slope; Determine whether the difference in height between the simulated hillside height submerged by the second water surface and the simulated hillside height submerged by the first water surface is greater than or equal to a preset hillside height difference threshold; if so, generate a dividing ridge line at the place where the second water surface submerges the simulated hillside, and update the height of the simulated hillside height submerged by the second water surface as a reference for threshold judgment, continue to inject water to identify the dividing ridge line, and stop injecting water when the water surface submerges the highest point of the first simulated slope to obtain the first dividing ridge line set.

7. The ultrasonic image processing method for swallowing function examination according to claim 1, characterized in that: Traversing the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence to extract the hyoid bone-thyroid cartilage distance, and obtaining the hyoid bone-thyroid cartilage distance set, including: Acquire multiple sample enhanced dynamic ultrasound image frame neighborhood contour recognition results, and perform manual marking based on the multiple sample enhanced dynamic ultrasound image frame neighborhood contour recognition results to obtain multiple sample hyoid bone-thyroid cartilage distances, wherein each hyoid bone-thyroid cartilage distance corresponds to one sample enhanced dynamic ultrasound image frame neighborhood contour recognition result; The framework constructed based on the convolutional neural network is supervised by using the plurality of sample enhanced dynamic ultrasound image frame neighborhood contour recognition results and the plurality of sample hyoid bone-thyroid cartilage distances to train the framework, learn the one-to-one mapping relationship between the sample enhanced dynamic ultrasound image frame neighborhood contour recognition results and the hyoid bone-thyroid cartilage distance, until the training converges, and obtain the distance extractor; The spacing extractor is used to extract the hyoid bone-thyroid cartilage spacing from the enhanced dynamic ultrasound image frame neighborhood contour recognition result sequence to obtain the hyoid bone-thyroid cartilage spacing set.

8. The ultrasonic image processing method for swallowing function examination according to claim 1, characterized in that: Based on the size of the hyoid bone-thyroid cartilage distance in the hyoid bone-thyroid cartilage distance set, the hyoid bone-thyroid cartilage distance shortening rate is identified to obtain the target hyoid bone-thyroid cartilage distance shortening rate, including: Extracting the maximum value of the hyoid bone-thyroid cartilage distance and the minimum value of the hyoid bone-thyroid cartilage distance from the hyoid bone-thyroid cartilage distance set; The difference between the maximum hyoid bone-thyroid cartilage distance and the minimum hyoid bone-thyroid cartilage distance is calculated, and the ratio of the calculated result to the maximum hyoid bone-thyroid cartilage distance is used as the target hyoid bone-thyroid cartilage distance shortening rate.

Images