Ultrasound image-based abdominal breathing monitoring method and system, device, and medium

Abstract

Disclosed are an ultrasound image-based abdominal breathing monitoring method and system, a device, and a storage medium. The method comprises: obtaining abdominal ultrasound images of a user at the end of quiet breathing and at abdominal breathing; according to the abdominal ultrasound images, identifying corresponding external oblique muscles, internal oblique muscles and transverse abdominis muscles; calculating the thicknesses of the external oblique muscles, the internal oblique muscles and the transverse abdominis muscles; according to the thicknesses of the external oblique muscles, the internal oblique muscles and the transverse abdominis muscles, calculating the external oblique muscle recruitment intensity, the internal oblique muscle recruitment intensity and the transverse abdominis muscle recruitment intensity; comparing the external oblique muscle recruitment intensity, the internal oblique muscle recruitment intensity and the transverse abdominis muscle recruitment intensity with corresponding preset target values to obtain a monitoring result. The present invention can implement real-time monitoring of abdominal breathing, which is convenient for self-monitoring of abdominal breathing training, and satisfies user requirements for home rehabilitation.

Description

Abdominal respiration monitoring method, system, device and medium based on ultrasound image Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to an abdominal respiration monitoring method, system, device and medium based on ultrasonic images. Background Art

[0002] Abdominal breathing is the best way to improve respiratory function and activate the inner core myocardium. High-quality abdominal breathing requires the participation of the deep abdominal muscles. Non-invasive, real-time monitoring of deep abdominal muscle activity and effective activation are key to ensuring high-quality abdominal breathing. Ultrasound images obtained through musculoskeletal ultrasound can reflect muscle thickness and, therefore, muscle contraction capacity, making it a non-invasive method for assessing muscle function.

[0003] However, existing ultrasound monitoring methods usually require doctors to hold an ultrasound probe and guide the user's breathing throughout the entire process. In addition, the images used for monitoring abdominal breathing training are all professional ultrasound images. The training must be completed under the full supervision of medical staff, which has high labor costs. In addition, the calculation method of muscle recruitment intensity requires manual measurement by professional doctors, which is complicated to operate and difficult for users to self-test. Summary of the Invention

[0004] The purpose of the present invention is to provide an abdominal breathing monitoring method, system, device and medium based on ultrasound images, which can realize real-time monitoring of abdominal breathing and facilitate self-monitoring of abdominal breathing training conditions.

[0005] A first aspect of the present invention provides an ultrasound image-based abdominal respiration monitoring method, comprising:

[0006] Acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images of the user during abdominal breathing;

[0007] performing image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle; performing image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle;

[0008] Calculating the thicknesses of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, the thickness of the first transverse abdominal muscle, the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle;

[0009] Calculating the external oblique muscle recruitment strength according to the thickness of the first external oblique muscle and the second external oblique muscle, calculating the internal oblique muscle recruitment strength according to the thickness of the first internal oblique muscle and the second internal oblique muscle, and calculating the transverse abdominal muscle recruitment strength according to the thickness of the first transverse abdominal muscle and the second transverse abdominal muscle;

[0010] The external oblique muscle recruitment strength, internal oblique muscle recruitment strength, and transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images are compared with corresponding preset target values ​​to obtain a monitoring result.

[0011] In some embodiments, performing image recognition on the first abdominal ultrasound image to identify the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle includes:

[0012] Preprocessing the first abdominal ultrasound image to obtain a first preprocessed image;

[0013] According to the pixel values ​​of the first preprocessed image, the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation are identified in sequence. The abdominal muscle between the first layer of fascia of quiet exhalation and the second layer of fascia of quiet exhalation is the first external abdominal oblique muscle, the abdominal muscle between the second layer of fascia of quiet exhalation and the third layer of fascia of quiet exhalation is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation is the first transverse abdominal muscle.

[0014] In some embodiments, calculating the thickness of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, and the thickness of the first transverse abdominal muscle comprises:

[0015] Constructing line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia;

[0016] dividing the line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia into a plurality of sub-line segments;

[0017] Selecting the points with the largest and smallest slopes in the sub-segments corresponding to the first layer of fascia during quiet exhalation, the second layer of fascia during quiet exhalation, the third layer of fascia during quiet exhalation, and the fourth layer of fascia during quiet exhalation as key points;

[0018] Selecting, from the key points on the second layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the first layer of fascia during quiet exhalation to form corresponding first key point pairs, and calculating the average of the distances of the first key point pairs to obtain the thickness of the first external oblique muscle;

[0019] Selecting, from the key points on the third layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the second layer of fascia during quiet exhalation to form corresponding second key point pairs, and calculating the average of the distances of the second key point pairs to obtain the thickness of the first internal abdominal oblique muscle;

[0020] Among the key points on the fourth layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the third layer of fascia during quiet exhalation are selected to form corresponding third key point pairs. The average value of the distances of the third key point pairs is calculated to obtain the thickness of the first transverse abdominal muscle.

[0021] In some embodiments, performing image recognition on each of the second abdominal ultrasound images to identify the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle includes:

[0022] preprocessing the second abdominal ultrasound image to obtain a second preprocessed image;

[0023] According to the pixel values ​​of the second preprocessed image, the first layer of abdominal respiration fascia, the second layer of abdominal respiration fascia, the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia arranged in sequence are identified; the second external abdominal oblique muscle is between the first layer of abdominal respiration fascia and the second layer of abdominal respiration fascia, the second internal abdominal oblique muscle is between the second layer of abdominal respiration fascia and the third layer of abdominal respiration fascia, and the second transverse abdominal muscle is between the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia.

[0024] In some embodiments, calculating the thickness of the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle comprises:

[0025] Constructing line segment models corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia to obtain corresponding line segments;

[0026] dividing the line segments corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia into a plurality of sub-line segments;

[0027] Selecting points with the largest and smallest slopes in each sub-segment corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia as key points;

[0028] Selecting the key points on the second layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the first layer of abdominal breathing fascia to form corresponding fourth key point pairs, and calculating the average value of the distances of the fourth key point pairs to obtain the thickness of the second external abdominal oblique muscle;

[0029] Selecting the key points on the third layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the second layer of abdominal breathing fascia to form corresponding fifth key point pairs, and calculating the average value of the distances of the fifth key point pairs to obtain the thickness of the second internal abdominal oblique muscle;

[0030] Among the key points on the fourth layer of fascia for abdominal breathing, the key points with the shortest absolute distance to the key points on the third layer of fascia for abdominal breathing are selected to form a corresponding sixth key point pair, and the average value of the distance of the sixth key point pair is calculated to obtain the thickness of the second transverse abdominal muscle.

[0031] In some embodiments, calculating the external oblique muscle recruitment strength based on the first external oblique muscle thickness and the second external oblique muscle thickness, calculating the internal oblique muscle recruitment strength based on the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculating the transverse abdominal muscle recruitment strength based on the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness comprises:

[0032] The recruitment strength calculation formula is used to calculate the recruitment strength of the external oblique muscle, the internal oblique muscle, and the transverse abdominal muscle. The recruitment strength calculation formula is:

[0033] ,

[0034] Wherein, Q represents the recruitment intensity, h2 represents the muscle thickness at the end of abdominal breathing, and h1 represents the muscle thickness at the end of quiet exhalation;

[0035] The thickness of the first external oblique muscle is defined as h1, and the thickness of the second external oblique muscle is defined as h2. Substitute the recruitment strength calculation formula to obtain the recruitment strength of the external oblique muscle, and use the thickness of the first internal oblique muscle as h1 and the thickness of the second internal oblique muscle as Substitute the recruitment strength calculation formula to obtain the internal oblique muscle recruitment strength, and use the thickness of the first transverse abdominal muscle as h1 and the thickness of the second transverse abdominal muscle as Substitute into the recruitment strength calculation formula to obtain the transverse abdominal muscle recruitment strength.

[0036] A second aspect of the present invention provides an ultrasound image-based abdominal respiration monitoring system, comprising:

[0037] An ultrasound image acquisition module, configured to acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images of the user in a state of abdominal breathing;

[0038] an abdominal muscle recognition module, configured to perform image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle, and to perform image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle;

[0039] an abdominal muscle thickness calculation module, configured to calculate the thickness of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle, and obtain the thickness of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle;

[0040] a recruitment strength calculation module, configured to calculate the external abdominal oblique muscle recruitment strength based on the thickness of the first external abdominal oblique muscle and the second external abdominal oblique muscle, calculate the internal abdominal oblique muscle recruitment strength based on the thickness of the first internal abdominal oblique muscle and the second internal abdominal oblique muscle, and calculate the transverse abdominal muscle recruitment strength based on the thickness of the first transverse abdominal muscle and the second transverse abdominal muscle;

[0041] The comparison module is used to compare the external oblique muscle recruitment strength, internal oblique muscle recruitment strength and transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images with the corresponding preset target values ​​to obtain a monitoring result.

[0042] In some embodiments, the abdominal muscle identification module includes:

[0043] a preprocessing unit, configured to preprocess the first abdominal ultrasound image to obtain a first preprocessed image;

[0044] an identification unit, configured to identify, in sequence, a first layer of fascia during quiet exhalation, a second layer of fascia during quiet exhalation, a third layer of fascia during quiet exhalation, and a fourth layer of fascia during quiet exhalation based on pixel values ​​of the first preprocessed image, wherein the abdominal muscle between the first layer of fascia during quiet exhalation and the second layer of fascia during quiet exhalation is the first external abdominal oblique muscle, the abdominal muscle between the second layer of fascia during quiet exhalation and the third layer of fascia during quiet exhalation is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of fascia during quiet exhalation and the fourth layer of fascia during quiet exhalation is the first transverse abdominal muscle.

[0045] A third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0046] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0047] The technical solution provided by the present invention has the following advantages and effects: by obtaining a first abdominal ultrasound image and multiple second abdominal ultrasound images, real-time monitoring of abdominal breathing is achieved, the abdominal muscle thickness and recruitment intensity are calculated, and the recruitment intensity is compared with the preset target value to obtain monitoring results, so that the user can monitor the abdominal breathing training situation by himself and meet the user's home rehabilitation needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] FIG1 is a schematic flow chart of an ultrasonic image-based abdominal respiration monitoring method provided by the present invention;

[0049] FIG2 is a schematic diagram of a first abdominal ultrasound image of a user at the end of quiet exhalation provided by the present invention;

[0050] FIG3 is a schematic diagram of line segments corresponding to a first abdominal ultrasound image of a user at the end of quiet exhalation provided by the present invention;

[0051] FIG4 is a schematic diagram of key points corresponding to a first abdominal ultrasound image of a user at the end of quiet exhalation provided by the present invention;

[0052] FIG5 is a schematic diagram of a second abdominal ultrasound image of a user during abdominal exhalation provided by the present invention;

[0053] FIG6 is a schematic diagram of line segments corresponding to a second abdominal ultrasound image of a user during abdominal exhalation provided by the present invention;

[0054] FIG7 is a schematic diagram of key points corresponding to a second abdominal ultrasound image during abdominal exhalation provided by the present invention;

[0055] FIG8 is a block diagram of the abdominal respiration monitoring system based on ultrasound images provided by the present invention;

[0056] FIG9 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention.

[0057] Description of reference numerals:

[0058] 100. The first layer of fascia for calm exhalation; 200. The second layer of fascia for calm exhalation; 300. The third layer of fascia for calm exhalation; 400. The fourth layer of fascia for calm exhalation; 500. The first layer of fascia for abdominal breathing; 600. The second layer of fascia for abdominal breathing; 700. The third layer of fascia for abdominal breathing; 800. The fourth layer of fascia for abdominal breathing. DETAILED DESCRIPTION

[0059] To facilitate understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0060] Unless otherwise specified or defined, the "first, second..." used in this article is only used to distinguish names and does not represent a specific quantity or order.

[0061] Unless stated otherwise or defined otherwise, the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0062] It should be noted that, in this document, “fixed to” or “connected to” may mean directly fixing or connecting to an element, or indirectly fixing or connecting to an element.

[0063] As shown in FIG1 , this embodiment provides an ultrasound image-based abdominal respiration monitoring method, including:

[0064] Step 1: Acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images during abdominal breathing.

[0065] In actual applications, a user can hold a wireless ultrasound probe to measure abdominal muscles. The wireless ultrasound probe and a terminal are connected via Bluetooth. The terminal can be a mobile terminal such as a mobile phone, a tablet computer, etc.

[0066] Specifically, at the end of the user's calm exhalation, a wireless ultrasound probe is used to collect the user's abdominal ultrasound image to obtain a first abdominal ultrasound image. During the user's abdominal breathing, the user's abdominal ultrasound images are continuously collected to obtain multiple second abdominal ultrasound images. When collecting the abdominal ultrasound image by using the wireless ultrasound probe, the wireless ultrasound probe is placed at the intersection of the anterior axillary line and the umbilicus line. The wireless ultrasound probe is parallel to the anterior axillary line. During measurement, the wireless ultrasound probe can move slightly at the intersection with the breathing to ensure that the collected abdominal ultrasound image can collect the external oblique abdominal muscles, internal oblique abdominal muscles and transverse abdominal muscles, and the fascia of each layer of abdominal muscles are kept as parallel as possible. At the same time, a sufficient amount of coupling agent needs to be applied, and there is no gap between the wireless ultrasound probe and the skin. The wireless ultrasound probe needs to be gently pressed against the skin, and the abdomen should not be excessively squeezed to cause the abdominal muscles to be flattened.

[0067] Step 2: Perform image recognition on the first abdominal ultrasound image to identify the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle; perform image recognition on each of the second abdominal ultrasound images to identify the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle.

[0068] Specifically, performing image recognition on the first abdominal ultrasound image to identify the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle includes:

[0069] Preprocessing the first abdominal ultrasound image to obtain a first preprocessed image;

[0070] According to the pixel values ​​of the first preprocessed image, the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation are identified in sequence. The abdominal muscle between the first layer of fascia of quiet exhalation and the second layer of fascia of quiet exhalation is the first external abdominal oblique muscle, the abdominal muscle between the second layer of fascia of quiet exhalation and the third layer of fascia of quiet exhalation is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation is the first transverse abdominal muscle.

[0071] In practical applications, the first abdominal ultrasound image is preprocessed, including: grayscale and normalizing the first abdominal ultrasound image to obtain a first preprocessed image, the pixel value of the first preprocessed image is the grayscale value of the first preprocessed image, in this embodiment, the pixel points in the first preprocessed image whose pixel values ​​are greater than the first preset threshold are recorded as first fascia points to obtain multiple first fascia areas, and the adjacent first fascia areas with a spacing within the preset spacing are connected to obtain the first connected area, the second connected area, the third connected area, and the fourth connected area arranged in sequence, and the average pixel value of the first connected area, the second connected area, the third connected area, and the fourth connected area is calculated, and the connected area with an average pixel value greater than the second preset threshold is used as the first layer of fascia of quiet exhalation, as shown in Figure 2. If the first connected area is the first layer of fascia 100 of quiet exhalation, then the second connected area is the first layer of fascia 100 of quiet exhalation. The second layer of fascia 200, the third connected area is the third layer of fascia 300 for quiet exhalation, and the fourth connected area is the fourth layer of fascia 400 for quiet exhalation. If the fourth connected area is the first layer of fascia for quiet exhalation, then the third connected area is the second layer of fascia for quiet exhalation, the second connected area is the third layer of fascia for quiet exhalation, and the first connected area is the fourth layer of fascia for quiet exhalation. According to physiological knowledge, the abdominal muscles between the first layer of fascia for quiet exhalation and the second layer of fascia for quiet exhalation are taken as the first external abdominal oblique muscle, the abdominal muscles between the second layer of fascia for quiet exhalation and the third layer of fascia for quiet exhalation are taken as the first internal abdominal oblique muscle, and the abdominal muscles between the third layer of fascia for quiet exhalation and the fourth layer of fascia for quiet exhalation are taken as the first transverse abdominal muscle. In other embodiments, an abdominal muscle recognition model can also be established based on deep learning, and the first preprocessed image can be input into the model to identify the first external abdominal oblique muscle, the first internal abdominal oblique muscle and the first transverse abdominal muscle.

[0072] Specifically, performing image recognition on each of the second abdominal ultrasound images to identify the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle includes:

[0073] preprocessing the second abdominal ultrasound image to obtain a second preprocessed image;

[0074] According to the pixel values ​​of the second preprocessed image, the first layer of abdominal respiration fascia, the second layer of abdominal respiration fascia, the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia arranged in sequence are identified; the second external abdominal oblique muscle is between the first layer of abdominal respiration fascia and the second layer of abdominal respiration fascia, the second internal abdominal oblique muscle is between the second layer of abdominal respiration fascia and the third layer of abdominal respiration fascia, and the second transverse abdominal muscle is between the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia.

[0075] In practical applications, the preprocessing of the second abdominal ultrasound image is the same as that of the first abdominal ultrasound image, that is, the second abdominal ultrasound image is grayscaled and normalized to obtain a second preprocessed image, and the second preprocessed image is processed in the same way as the first preprocessed image to identify the second external oblique muscle, the second internal oblique muscle and the second transverse abdominal muscle. Specifically, the pixel points in the second preprocessed image whose pixel values ​​are greater than the first preset threshold are recorded as second fascia points to obtain multiple second fascia areas, and the adjacent second fascia areas with a spacing within the preset spacing are connected to obtain the fifth connected area, the sixth connected area, the seventh connected area, and the eighth connected area arranged in sequence, and the average pixel values ​​of the fifth connected area, the sixth connected area, the seventh connected area, and the eighth connected area are calculated, and the connected area with an average pixel value greater than the second preset threshold is used as the first layer of fascia for abdominal breathing. As shown in Figure 5, the fifth connected area is the first layer of fascia for abdominal breathing. Membrane 500, the sixth connected area is the second layer of abdominal respiration fascia 600, the seventh connected area is the third layer of abdominal respiration fascia 700, and the eighth connected area is the fourth layer of abdominal respiration fascia 800. If the eighth connected area is the first layer of abdominal respiration fascia, the seventh connected area is the second layer of abdominal respiration fascia, the sixth connected area is the third layer of abdominal respiration fascia, and the fifth connected area is the fourth layer of abdominal respiration fascia. According to physiological knowledge, the abdominal muscles between the first layer of abdominal respiration fascia and the second layer of abdominal respiration fascia are regarded as the second external abdominal oblique muscle, the abdominal muscles between the second layer of abdominal respiration fascia and the third layer of abdominal respiration fascia are regarded as the second internal abdominal oblique muscle, and the abdominal muscles between the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia are regarded as the second transverse abdominal muscle. Similarly, an abdominal muscle recognition model can be established based on deep learning, and the second preprocessed image can be input into the model to identify the second external abdominal oblique muscle, the second internal abdominal oblique muscle and the second transverse abdominal muscle.

[0076] Step 3: Calculate the thicknesses of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, the thickness of the first transverse abdominal muscle, the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle.

[0077] Specifically, calculating the thickness of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, and the thickness of the first transverse abdominal muscle includes:

[0078] constructing line segment models corresponding to the first layer of fascia during quiet exhalation, the second layer of fascia during quiet exhalation, the third layer of fascia during quiet exhalation, and the fourth layer of fascia during quiet exhalation to obtain corresponding line segments;

[0079] dividing the line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia into a plurality of sub-line segments;

[0080] Selecting the points with the largest and smallest slopes in the sub-segments corresponding to the first layer of fascia during quiet exhalation, the second layer of fascia during quiet exhalation, the third layer of fascia during quiet exhalation, and the fourth layer of fascia during quiet exhalation as key points;

[0081] Selecting, from the key points on the second layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the first layer of fascia during quiet exhalation to form corresponding first key point pairs, and calculating the average of the distances of the first key point pairs to obtain the thickness of the first external oblique muscle;

[0082] Selecting, from the key points on the third layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the second layer of fascia during quiet exhalation to form corresponding second key point pairs, and calculating the average of the distances of the second key point pairs to obtain the thickness of the first internal abdominal oblique muscle;

[0083] Among the key points on the fourth layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the third layer of fascia during quiet exhalation are selected to form corresponding third key point pairs. The average value of the distances of the third key point pairs is calculated to obtain the thickness of the first transverse abdominal muscle.

[0084] In actual applications, after obtaining the first connected area, second connected area, third connected area and fourth connected area corresponding to the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation, the curve fitting model in the prior art is used to fit each pixel point in the first connected area, the second connected area, the third connected area and the fourth connected area, as shown in Figure 3, to obtain the line segments corresponding to the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation, determine the direction of each line segment according to the starting point and the end point of each line segment, and divide each line segment evenly along the direction according to the preset number of sub-segments to obtain multiple corresponding sub-segments. The preset number of sub-segments is set according to actual conditions. The more preset sub-segments, the higher the measurement accuracy.

[0085] In this embodiment, as shown in FIG4 , the points with the largest and smallest slopes in each sub-segment corresponding to the first layer of fascia during quiet exhalation are selected as key points to obtain all key points corresponding to the first layer of fascia during quiet exhalation. The same method as that for the first layer of fascia during quiet exhalation is used to obtain all key points corresponding to the second layer of fascia during quiet exhalation, all key points corresponding to the third layer of fascia during quiet exhalation, and all key points corresponding to the fourth layer of fascia during quiet exhalation, so as to facilitate subsequent acquisition of all first key point pairs, all second key point pairs, and all third key point pairs. The Euclidean distances between the key points corresponding to all first key point pairs, the Euclidean distances between the key points corresponding to all second key point pairs, and the Euclidean distances between the key points corresponding to all third key point pairs are calculated, and the average value of the Euclidean distances of all first key point pairs is calculated to obtain the thickness of the first external oblique muscle, the average value of the Euclidean distances of all second key point pairs is calculated to obtain the thickness of the first internal oblique muscle, and the average value of the Euclidean distances of all third key point pairs is calculated to obtain the thickness of the first transverse abdominal muscle. This helps to smooth local fluctuations. The use of local average (Local Average) in the present invention is helpful to smooth local fluctuations. Averaging is a method used to smooth the data to reduce abrupt changes or unnecessary details and make the data more readable.

[0086] Specifically, calculating the thickness of the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle includes:

[0087] Constructing line segment models corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia to obtain corresponding line segments;

[0088] dividing the line segments corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia into a plurality of sub-line segments;

[0089] Selecting points with the largest and smallest slopes in each sub-segment corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia as key points;

[0090] Selecting the key points on the second layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the first layer of abdominal breathing fascia to form corresponding fourth key point pairs, and calculating the average value of the distances of the fourth key point pairs to obtain the thickness of the second external abdominal oblique muscle;

[0091] Selecting the key points on the third layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the second layer of abdominal breathing fascia to form corresponding fifth key point pairs, and calculating the average value of the distances of the fifth key point pairs to obtain the thickness of the second internal abdominal oblique muscle;

[0092] Among the key points on the fourth layer of fascia for abdominal breathing, the key points with the shortest absolute distance to the key points on the third layer of fascia for abdominal breathing are selected to form a corresponding sixth key point pair, and the average value of the distance of the sixth key point pair is calculated to obtain the thickness of the second transverse abdominal muscle.

[0093] In actual applications, after obtaining the fifth connected area, sixth connected area, seventh connected area and eighth connected area corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia and the fourth layer of abdominal breathing fascia, the curve fitting model in the prior art is used to fit the various pixel points in the fifth connected area, the sixth connected area, the seventh connected area and the eighth connected area, as shown in Figure 6, to obtain the line segments corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia and the fourth layer of abdominal breathing fascia, determine the direction of each line segment according to the starting point and the end point of each line segment, and divide each line segment evenly along the direction according to the preset number of sub-line segments to obtain multiple corresponding sub-line segments. The preset number of sub-line segments is set according to actual conditions. The more preset sub-line segments, the higher the measurement accuracy.

[0094] In this embodiment, the points with the largest and smallest slopes in each sub-segment corresponding to the first layer of fascia of abdominal breathing are selected as key points to obtain all key points corresponding to the first layer of fascia of abdominal breathing, as shown in Figure 7. The same method as that for the first layer of fascia of abdominal breathing is used to obtain all key points corresponding to the second layer of fascia of abdominal breathing, all key points corresponding to the third layer of fascia of abdominal breathing, and all key points corresponding to the fourth layer of fascia of abdominal breathing, so as to subsequently obtain all fourth key point pairs, all fifth key point pairs, and all sixth key point pairs. The Euclidean distances between the key points corresponding to all fourth key point pairs, the Euclidean distances between the key points corresponding to all fifth key point pairs, and the Euclidean distances between the key points corresponding to all sixth key point pairs are calculated, and the average value of the Euclidean distances of all fourth key point pairs is calculated to obtain the thickness of the second external abdominal oblique muscle, the average value of the Euclidean distances of all fifth key point pairs is calculated to obtain the thickness of the second internal abdominal oblique muscle, and the average value of the Euclidean distances of all sixth key point pairs is calculated to obtain the thickness of the second transverse abdominal muscle, which helps to smooth local fluctuations.

[0095] Step 4: Calculate the external oblique muscle recruitment strength based on the first external oblique muscle thickness and the second external oblique muscle thickness, calculate the internal oblique muscle recruitment strength based on the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculate the transverse abdominal muscle recruitment strength based on the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness.

[0096] Specifically, calculating the external oblique muscle recruitment strength according to the first external oblique muscle thickness and the second external oblique muscle thickness, calculating the internal oblique muscle recruitment strength according to the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculating the transverse abdominal muscle recruitment strength according to the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness includes:

[0097] The recruitment strength calculation formula is used to calculate the recruitment strength of the external oblique muscle, the internal oblique muscle, and the transverse abdominal muscle. The recruitment strength calculation formula is:

[0098] ,

[0099] Wherein, Q represents the recruitment intensity, h2 represents the muscle thickness at the end of abdominal breathing, and h1 represents the muscle thickness at the end of quiet exhalation;

[0100] The thickness of the first external oblique muscle is defined as h1, and the thickness of the second external oblique muscle is defined as h2. Substitute the recruitment strength calculation formula to obtain the recruitment strength of the external oblique muscle, and use the thickness of the first internal oblique muscle as h1 and the thickness of the second internal oblique muscle as Substitute the recruitment strength calculation formula to obtain the internal oblique muscle recruitment strength, and use the thickness of the first transverse abdominal muscle as h1 and the thickness of the second transverse abdominal muscle as Substitute into the recruitment strength calculation formula to obtain the transverse abdominal muscle recruitment strength.

[0101] In actual application, the recruitment intensity of the external oblique muscles, the internal oblique muscles and the transverse abdominal muscles during the user's abdominal breathing are calculated according to the recruitment intensity calculation formula. Through this method, the thickness of the transverse abdominal muscles, the internal oblique muscles and the external oblique muscles during the user's abdominal breathing can be measured in real time, and the corresponding recruitment intensity can be calculated. The recruitment intensity of the external oblique muscles, the internal oblique muscles and the transverse abdominal muscles can be converted into a histogram, and the height of the histogram can change in real time according to the abdominal muscle activity, providing visual feedback to the user.

[0102] Step 5: Compare the external oblique muscle recruitment strength, internal oblique muscle recruitment strength, and transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images with the corresponding preset target values ​​to obtain a monitoring result.

[0103] In actual application, the preset target values ​​include: a preset external oblique muscle target value, a preset internal oblique muscle target value and a preset transverse abdominal muscle target value. The preset external oblique muscle target value, the preset internal oblique muscle target value and the preset transverse abdominal muscle target value can be the external oblique muscle recruitment strength reference value, the internal oblique muscle recruitment strength reference value and the transverse abdominal muscle recruitment strength reference value given by the doctor according to the user's own physical condition. The preset target values ​​are pre-input by the user. The external oblique muscle recruitment strength, the internal oblique muscle recruitment strength and the transverse abdominal muscle recruitment strength corresponding to each second abdominal ultrasound image are compared with the corresponding preset target values. Only when the external oblique muscle recruitment strength, the internal oblique muscle recruitment strength and the transverse abdominal muscle recruitment strength reach the corresponding preset target values, is it determined that the user's abdominal breathing is correct, thereby realizing monitoring of the user's abdominal breathing process and improving the training quality. The doctor can also provide breathing training guidance or change the breathing training prescription based on the measured external oblique muscle recruitment strength, internal oblique muscle recruitment strength and transverse abdominal muscle recruitment strength to ensure the effectiveness of abdominal breathing training.

[0104] The ultrasonic image-based abdominal breathing monitoring method of the present invention realizes real-time monitoring of abdominal breathing, calculates abdominal muscle thickness and recruitment intensity, and compares the recruitment intensity with a preset target value to obtain monitoring results, so that users can monitor their own abdominal breathing training status and meet their home rehabilitation needs.

[0105] As shown in FIG4 , an embodiment of the present invention further provides an ultrasound image-based abdominal respiration monitoring system, comprising:

[0106] An ultrasound image acquisition module 10 is configured to acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images of the user during abdominal breathing;

[0107] an abdominal muscle recognition module 20 configured to perform image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle, and to perform image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle;

[0108] an abdominal muscle thickness calculation module 30, configured to calculate the thicknesses of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle, and obtain the thicknesses of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle;

[0109] a recruitment strength calculation module 40, configured to calculate the external abdominal oblique muscle recruitment strength based on the first external abdominal oblique muscle thickness and the second external abdominal oblique muscle thickness, calculate the internal abdominal oblique muscle recruitment strength based on the first internal abdominal oblique muscle thickness and the second internal abdominal oblique muscle thickness, and calculate the transverse abdominal muscle recruitment strength based on the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness;

[0110] The comparison module 50 is configured to compare the external oblique muscle recruitment strength, the internal oblique muscle recruitment strength, and the transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images with corresponding preset target values ​​to obtain a monitoring result.

[0111] In one embodiment, the abdominal muscle identification module includes:

[0112] a preprocessing unit, configured to preprocess the first abdominal ultrasound image to obtain a first preprocessed image;

[0113] an identification unit, configured to identify, in sequence, a first layer of fascia during quiet exhalation, a second layer of fascia during quiet exhalation, a third layer of fascia during quiet exhalation, and a fourth layer of fascia during quiet exhalation based on pixel values ​​of the first preprocessed image, wherein the abdominal muscle between the first layer of fascia during quiet exhalation and the second layer of fascia during quiet exhalation is the first external abdominal oblique muscle, the abdominal muscle between the second layer of fascia during quiet exhalation and the third layer of fascia during quiet exhalation is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of fascia during quiet exhalation and the fourth layer of fascia during quiet exhalation is the first transverse abdominal muscle.

[0114] The specific structure of the abdominal respiration monitoring system based on ultrasound images can be found in the structure of the abdominal respiration monitoring method based on ultrasound images described above, and will not be repeated here. The various modules of the above-mentioned abdominal respiration monitoring system based on ultrasound images can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0115] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG5 . The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for monitoring abdominal respiration based on ultrasound images is implemented.

[0116] Those skilled in the art will understand that the structure shown in FIG5 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0117] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0118] Acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images of the user during abdominal breathing;

[0119] performing image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle; performing image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle;

[0120] Calculating the thicknesses of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, the thickness of the first transverse abdominal muscle, the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle;

[0121] Calculating the external oblique muscle recruitment strength according to the thickness of the first external oblique muscle and the second external oblique muscle, calculating the internal oblique muscle recruitment strength according to the thickness of the first internal oblique muscle and the second internal oblique muscle, and calculating the transverse abdominal muscle recruitment strength according to the thickness of the first transverse abdominal muscle and the second transverse abdominal muscle;

[0122] The external oblique muscle recruitment strength, internal oblique muscle recruitment strength, and transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images are compared with corresponding preset target values ​​to obtain a monitoring result.

[0123] In one embodiment, performing image recognition on the first abdominal ultrasound image to identify the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle includes:

[0124] Preprocessing the first abdominal ultrasound image to obtain a first preprocessed image;

[0125] According to the pixel values ​​of the first preprocessed image, the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation are identified in sequence. The abdominal muscle between the first layer of fascia of quiet exhalation and the second layer of fascia of quiet exhalation is the first external abdominal oblique muscle, the abdominal muscle between the second layer of fascia of quiet exhalation and the third layer of fascia of quiet exhalation is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation is the first transverse abdominal muscle.

[0126] In one embodiment, calculating the thickness of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, and the thickness of the first transverse abdominal muscle includes:

[0127] Constructing line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia;

[0128] dividing the line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia into a plurality of sub-line segments;

[0129] Selecting the points with the largest and smallest slopes in the sub-segments corresponding to the first layer of fascia during quiet exhalation, the second layer of fascia during quiet exhalation, the third layer of fascia during quiet exhalation, and the fourth layer of fascia during quiet exhalation as key points;

[0130] Selecting, from the key points on the second layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the first layer of fascia during quiet exhalation to form corresponding first key point pairs, and calculating the average of the distances of the first key point pairs to obtain the thickness of the first external oblique muscle;

[0131] Selecting, from the key points on the third layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the second layer of fascia during quiet exhalation to form corresponding second key point pairs, and calculating the average of the distances of the second key point pairs to obtain the thickness of the first internal abdominal oblique muscle;

[0132] Among the key points on the fourth layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the third layer of fascia during quiet exhalation are selected to form corresponding third key point pairs. The average value of the distances of the third key point pairs is calculated to obtain the thickness of the first transverse abdominal muscle.

[0133] In one embodiment, performing image recognition on each of the second abdominal ultrasound images to identify the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle includes:

[0134] preprocessing the second abdominal ultrasound image to obtain a second preprocessed image;

[0135] According to the pixel values ​​of the second preprocessed image, the first layer of abdominal respiration fascia, the second layer of abdominal respiration fascia, the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia arranged in sequence are identified; the second external abdominal oblique muscle is between the first layer of abdominal respiration fascia and the second layer of abdominal respiration fascia, the second internal abdominal oblique muscle is between the second layer of abdominal respiration fascia and the third layer of abdominal respiration fascia, and the second transverse abdominal muscle is between the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia.

[0136] In one embodiment, calculating the thickness of the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle includes:

[0137] Constructing line segment models corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia to obtain corresponding line segments;

[0138] dividing the line segments corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia into a plurality of sub-line segments;

[0139] Selecting points with the largest and smallest slopes in each sub-segment corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia as key points;

[0140] Selecting the key points on the second layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the first layer of abdominal breathing fascia to form corresponding fourth key point pairs, and calculating the average value of the distances of the fourth key point pairs to obtain the thickness of the second external abdominal oblique muscle;

[0141] Selecting the key points on the third layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the second layer of abdominal breathing fascia to form corresponding fifth key point pairs, and calculating the average value of the distances of the fifth key point pairs to obtain the thickness of the second internal abdominal oblique muscle;

[0142] Among the key points on the fourth layer of fascia for abdominal breathing, the key points with the shortest absolute distance to the key points on the third layer of fascia for abdominal breathing are selected to form a corresponding sixth key point pair, and the average value of the distance of the sixth key point pair is calculated to obtain the thickness of the second transverse abdominal muscle.

[0143] In one embodiment, calculating the external oblique muscle recruitment strength according to the first external oblique muscle thickness and the second external oblique muscle thickness, calculating the internal oblique muscle recruitment strength according to the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculating the transverse abdominal muscle recruitment strength according to the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness includes:

[0144] The recruitment strength calculation formula is used to calculate the recruitment strength of the external oblique muscle, the internal oblique muscle, and the transverse abdominal muscle. The recruitment strength calculation formula is:

[0145] ,

[0146] Wherein, Q represents the recruitment intensity, h2 represents the muscle thickness at the end of abdominal breathing, and h1 represents the muscle thickness at the end of quiet exhalation;

[0147] The thickness of the first external oblique muscle is defined as h1, and the thickness of the second external oblique muscle is defined as h2. Substitute the recruitment strength calculation formula to obtain the recruitment strength of the external oblique muscle, and use the thickness of the first internal oblique muscle as h1 and the thickness of the second internal oblique muscle as Substitute the recruitment strength calculation formula to obtain the internal oblique muscle recruitment strength, and use the thickness of the first transverse abdominal muscle as h1 and the thickness of the second transverse abdominal muscle as Substitute into the recruitment strength calculation formula to obtain the transverse abdominal muscle recruitment strength.

[0148] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0149] Acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images of the user during abdominal breathing;

[0150] performing image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle; performing image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle;

[0151] Calculating the thicknesses of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, the first transverse abdominal muscle, the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, the thickness of the first transverse abdominal muscle, the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle;

[0152] Calculating the external oblique muscle recruitment strength according to the thickness of the first external oblique muscle and the second external oblique muscle, calculating the internal oblique muscle recruitment strength according to the thickness of the first internal oblique muscle and the second internal oblique muscle, and calculating the transverse abdominal muscle recruitment strength according to the thickness of the first transverse abdominal muscle and the second transverse abdominal muscle;

[0153] The external oblique muscle recruitment strength, internal oblique muscle recruitment strength, and transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images are compared with corresponding preset target values ​​to obtain a monitoring result.

[0154] In one embodiment, performing image recognition on the first abdominal ultrasound image to identify the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle includes:

[0155] Preprocessing the first abdominal ultrasound image to obtain a first preprocessed image;

[0156] According to the pixel values ​​of the first preprocessed image, the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation are identified in sequence. The abdominal muscle between the first layer of fascia of quiet exhalation and the second layer of fascia of quiet exhalation is the first external abdominal oblique muscle, the abdominal muscle between the second layer of fascia of quiet exhalation and the third layer of fascia of quiet exhalation is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation is the first transverse abdominal muscle.

[0157] In one embodiment, calculating the thickness of the first external abdominal oblique muscle, the first internal abdominal oblique muscle, and the first transverse abdominal muscle to obtain the thickness of the first external abdominal oblique muscle, the thickness of the first internal abdominal oblique muscle, and the thickness of the first transverse abdominal muscle includes:

[0158] Constructing line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia;

[0159] dividing the line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia into a plurality of sub-line segments;

[0160] Selecting the points with the largest and smallest slopes in the sub-segments corresponding to the first layer of fascia during quiet exhalation, the second layer of fascia during quiet exhalation, the third layer of fascia during quiet exhalation, and the fourth layer of fascia during quiet exhalation as key points;

[0161] Selecting, from the key points on the second layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the first layer of fascia during quiet exhalation to form corresponding first key point pairs, and calculating the average of the distances of the first key point pairs to obtain the thickness of the first external oblique muscle;

[0162] Selecting, from the key points on the third layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the second layer of fascia during quiet exhalation to form corresponding second key point pairs, and calculating the average of the distances of the second key point pairs to obtain the thickness of the first internal abdominal oblique muscle;

[0163] Among the key points on the fourth layer of fascia during quiet exhalation, the key points with the shortest absolute distances to the key points on the third layer of fascia during quiet exhalation are selected to form corresponding third key point pairs. The average value of the distances of the third key point pairs is calculated to obtain the thickness of the first transverse abdominal muscle.

[0164] In one embodiment, performing image recognition on each of the second abdominal ultrasound images to identify the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle includes:

[0165] preprocessing the second abdominal ultrasound image to obtain a second preprocessed image;

[0166] According to the pixel values ​​of the second preprocessed image, the first layer of abdominal respiration fascia, the second layer of abdominal respiration fascia, the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia arranged in sequence are identified; the second external abdominal oblique muscle is between the first layer of abdominal respiration fascia and the second layer of abdominal respiration fascia, the second internal abdominal oblique muscle is between the second layer of abdominal respiration fascia and the third layer of abdominal respiration fascia, and the second transverse abdominal muscle is between the third layer of abdominal respiration fascia and the fourth layer of abdominal respiration fascia.

[0167] In one embodiment, calculating the thickness of the second external abdominal oblique muscle, the second internal abdominal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the second external abdominal oblique muscle, the thickness of the second internal abdominal oblique muscle, and the thickness of the second transverse abdominal muscle includes:

[0168] Constructing line segment models corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia to obtain corresponding line segments;

[0169] dividing the line segments corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia into a plurality of sub-line segments;

[0170] Selecting points with the largest and smallest slopes in each sub-segment corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia as key points;

[0171] Selecting the key points on the second layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the first layer of abdominal breathing fascia to form corresponding fourth key point pairs, and calculating the average value of the distances of the fourth key point pairs to obtain the thickness of the second external abdominal oblique muscle;

[0172] Selecting the key points on the third layer of abdominal breathing fascia that have the shortest absolute distances to the key points on the second layer of abdominal breathing fascia to form corresponding fifth key point pairs, and calculating the average value of the distances of the fifth key point pairs to obtain the thickness of the second internal abdominal oblique muscle;

[0173] Among the key points on the fourth layer of fascia for abdominal breathing, the key points with the shortest absolute distance to the key points on the third layer of fascia for abdominal breathing are selected to form a corresponding sixth key point pair, and the average value of the distance of the sixth key point pair is calculated to obtain the thickness of the second transverse abdominal muscle.

[0174] In one embodiment, calculating the external oblique muscle recruitment strength according to the first external oblique muscle thickness and the second external oblique muscle thickness, calculating the internal oblique muscle recruitment strength according to the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculating the transverse abdominal muscle recruitment strength according to the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness includes:

[0175] The recruitment strength calculation formula is used to calculate the recruitment strength of the external oblique muscle, the internal oblique muscle, and the transverse abdominal muscle. The recruitment strength calculation formula is:

[0176] ,

[0177] Wherein, Q represents the recruitment intensity, h2 represents the muscle thickness at the end of abdominal breathing, and h1 represents the muscle thickness at the end of quiet exhalation;

[0178] The thickness of the first external oblique muscle is defined as h1, and the thickness of the second external oblique muscle is defined as h2. Substitute the recruitment strength calculation formula to obtain the recruitment strength of the external oblique muscle, and use the thickness of the first internal oblique muscle as h1 and the thickness of the second internal oblique muscle as Substitute the recruitment strength calculation formula to obtain the internal oblique muscle recruitment strength, and use the thickness of the first transverse abdominal muscle as h1 and the thickness of the second transverse abdominal muscle as Substitute into the recruitment strength calculation formula to obtain the transverse abdominal muscle recruitment strength.

[0179] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0180] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. An abdominal respiration monitoring method based on ultrasound images, characterized in that: include: Acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images of the user in a condition of abdominal breathing; Performing image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle, and performing image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle; Calculating the thickness of the first external oblique muscle, the first internal oblique muscle, the first transverse abdominal muscle, the second external oblique muscle, the second internal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the first external oblique muscle, the thickness of the first internal oblique muscle, the thickness of the first transverse abdominal muscle, the thickness of the second external oblique muscle, the thickness of the second internal oblique muscle, and the thickness of the second transverse abdominal muscle; Calculate the external oblique muscle recruitment strength according to the first external oblique muscle thickness and the second external oblique muscle thickness, calculate the internal oblique muscle recruitment strength according to the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculate the transverse abdominal muscle recruitment strength according to the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness; The external oblique muscle recruitment strength, the internal oblique muscle recruitment strength and the transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images are compared with corresponding preset target values ​​to obtain a monitoring result.

2. The method for monitoring abdominal respiration based on ultrasound images according to claim 1, characterized in that: The performing image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle includes: Preprocessing the first abdominal ultrasound image to obtain a first preprocessed image; According to the pixel values ​​of the first preprocessed image, the first layer of fascia of quiet exhalation, the second layer of fascia of quiet exhalation, the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation are identified in sequence. The abdominal muscle between the first layer of fascia of quiet exhalation and the second layer of fascia of quiet exhalation is the first external oblique abdominal muscle, the abdominal muscle between the second layer of fascia of quiet exhalation and the third layer of fascia of quiet exhalation is the first internal oblique abdominal muscle, and the abdominal muscle between the third layer of fascia of quiet exhalation and the fourth layer of fascia of quiet exhalation is the first transverse abdominal muscle.

3. The abdominal respiration monitoring method based on ultrasound images as claimed in claim 2, characterized in that: The step of calculating the thickness of the first external oblique muscle, the first internal oblique muscle, and the first transverse abdominal muscle to obtain the thickness of the first external oblique muscle, the thickness of the first internal oblique muscle, and the thickness of the first transverse abdominal muscle comprises: Constructing line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia and the fourth layer of quiet exhalation fascia; dividing the line segments corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia and the fourth layer of quiet exhalation fascia into a plurality of sub-line segments; Selecting the points with the largest and smallest slopes in each sub-segment corresponding to the first layer of quiet exhalation fascia, the second layer of quiet exhalation fascia, the third layer of quiet exhalation fascia, and the fourth layer of quiet exhalation fascia as key points; Selecting the key points on the second layer of fascia during quiet exhalation with the shortest absolute distance from each key point on the first layer of fascia during quiet exhalation to form a corresponding first key point pair, calculating the average value of the distances of the first key point pair to obtain the first external oblique muscle thickness; Selecting the key points on the third layer of fascia during quiet exhalation with the shortest absolute distance from each key point on the second layer of fascia during quiet exhalation to form corresponding second key point pairs, calculating the average of the distances of the second key point pairs, and obtaining the thickness of the first internal oblique muscle; Among the key points on the fourth layer of fascia during quiet exhalation, the key points with the shortest absolute distance to the key points on the third layer of fascia during quiet exhalation are selected to form corresponding third key point pairs, and the average value of the distances of the third key point pairs is calculated to obtain the thickness of the first transverse abdominal muscle.

4. The method for monitoring abdominal respiration based on ultrasound images according to claim 1, characterized in that: The performing image recognition on each of the second abdominal ultrasound images to identify the second external oblique muscle, the second internal oblique muscle, and the second transverse abdominal muscle comprises: preprocessing the second abdominal ultrasound image to obtain a second preprocessed image; According to the pixel values ​​of the second preprocessed image, the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia and the fourth layer of abdominal breathing fascia arranged in sequence are identified; the second external oblique muscle is between the first layer of abdominal breathing fascia and the second layer of abdominal breathing fascia, the second internal oblique muscle is between the second layer of abdominal breathing fascia and the third layer of abdominal breathing fascia, and the second transverse abdominal muscle is between the third layer of abdominal breathing fascia and the fourth layer of abdominal breathing fascia.

5. The method for monitoring abdominal respiration based on ultrasound images as claimed in claim 4, characterized in that: Calculating the thickness of the second external oblique muscle, the second internal oblique muscle, and the second transverse abdominal muscle to obtain the thickness of the second external oblique muscle, the thickness of the second internal oblique muscle, and the thickness of the second transverse abdominal muscle comprises: Constructing line segment models corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia and the fourth layer of abdominal breathing fascia to obtain corresponding line segments; Divide the line segments corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia and the fourth layer of abdominal breathing fascia into a plurality of sub-line segments; Selecting points with the largest and smallest slopes in each sub-segment corresponding to the first layer of abdominal breathing fascia, the second layer of abdominal breathing fascia, the third layer of abdominal breathing fascia, and the fourth layer of abdominal breathing fascia as key points; Select the key points on the second layer of abdominal breathing fascia that have the shortest absolute distance to the key points on the first layer of abdominal breathing fascia to form corresponding fourth key point pairs, calculate the average value of the distances of the fourth key point pairs, and obtain the thickness of the second external oblique muscle; Select the key points on the third layer of abdominal breathing fascia with the shortest absolute distance from each key point on the second layer of abdominal breathing fascia to form a corresponding fifth key point pair, calculate the average value of the distance of the fifth key point pair, and obtain the thickness of the second abdominal internal oblique muscle; Among the key points on the fourth layer of fascia of abdominal breathing, the key points with the shortest absolute distance to the key points on the third layer of fascia of abdominal breathing are selected to form the corresponding sixth key point pair, and the average value of the distance of the sixth key point pair is calculated to obtain the thickness of the second transverse abdominal muscle.

6. The method for monitoring abdominal respiration based on ultrasound images according to claim 1, characterized in that: Calculating the external oblique muscle recruitment strength according to the first external oblique muscle thickness and the second external oblique muscle thickness, calculating the internal oblique muscle recruitment strength according to the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculating the transverse abdominal muscle recruitment strength according to the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness, comprises: The recruitment strength calculation formula is used to calculate the recruitment strength of the external oblique muscle, the internal oblique muscle and the transverse abdominal muscle, wherein the recruitment strength calculation formula is: ， Wherein, Q represents the recruitment intensity, h2 represents the muscle thickness at the end of abdominal breathing, and h1 represents the muscle thickness at the end of quiet exhalation; The thickness of the first external oblique muscle is taken as h1, and the thickness of the second external oblique muscle is taken as Substitute the recruitment strength calculation formula to obtain the external oblique muscle recruitment strength, and use the thickness of the first internal oblique muscle as h1 and the thickness of the second internal oblique muscle as h2. Substitute the recruitment strength calculation formula to obtain the internal oblique muscle recruitment strength, and use the first transverse abdominal muscle thickness as h1 and the second transverse abdominal muscle thickness as h2. Substitute into the recruitment strength calculation formula to obtain the transverse abdominal muscle recruitment strength.

7. An abdominal respiration monitoring system based on ultrasound images, characterized in that: include: An ultrasound image acquisition module, used to acquire a first abdominal ultrasound image of the user at the end of quiet exhalation and a plurality of second abdominal ultrasound images in a case of abdominal breathing; an abdominal muscle recognition module, configured to perform image recognition on the first abdominal ultrasound image to identify a first external abdominal oblique muscle, a first internal abdominal oblique muscle, and a first transverse abdominal muscle, and to perform image recognition on each of the second abdominal ultrasound images to identify a second external abdominal oblique muscle, a second internal abdominal oblique muscle, and a second transverse abdominal muscle; an abdominal muscle thickness calculation module, used to calculate the thickness of the first external oblique muscle, the first internal oblique muscle, the first transverse abdominal muscle, the second external oblique muscle, the second internal oblique muscle, and the second transverse abdominal muscle, and obtain the thickness of the first external oblique muscle, the first internal oblique muscle, the first transverse abdominal muscle, the second external oblique muscle, the second internal oblique muscle, and the second transverse abdominal muscle; a recruitment strength calculation module, configured to calculate the external oblique muscle recruitment strength according to the first external oblique muscle thickness and the second external oblique muscle thickness, calculate the internal oblique muscle recruitment strength according to the first internal oblique muscle thickness and the second internal oblique muscle thickness, and calculate the transverse abdominal muscle recruitment strength according to the first transverse abdominal muscle thickness and the second transverse abdominal muscle thickness; The comparison module is used to compare the external oblique muscle recruitment strength, the internal oblique muscle recruitment strength and the transverse abdominal muscle recruitment strength corresponding to each of the second abdominal ultrasound images with the corresponding preset target values ​​to obtain a monitoring result.

8. The abdominal respiration monitoring system based on ultrasound images as claimed in claim 7, characterized in that: The abdominal muscle recognition module comprises: A preprocessing unit, configured to preprocess the first abdominal ultrasound image to obtain a first preprocessed image; The identification unit is used to identify the first layer of calm exhalation fascia, the second layer of calm exhalation fascia, the third layer of calm exhalation fascia and the fourth layer of calm exhalation fascia arranged in sequence according to the pixel values ​​of the first preprocessed image, the abdominal muscle between the first layer of calm exhalation fascia and the second layer of calm exhalation fascia is the first external abdominal oblique muscle, the abdominal muscle between the second layer of calm exhalation fascia and the third layer of calm exhalation fascia is the first internal abdominal oblique muscle, and the abdominal muscle between the third layer of calm exhalation fascia and the fourth layer of calm exhalation fascia is the first transverse abdominal muscle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images