Ultrasound graph-based intrauterine adhesion analysis system
By combining black and white ultrasound and Doppler ultrasound technology, the brightness and contrast of ultrasound images are automatically adjusted, and the accuracy and efficiency of uterine cavity adhesion judgment in the prior art are solved, achieving higher diagnostic accuracy and efficiency.
Patent Information
- Application Number
- CN202411534580.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When judging uterine cavity adhesions, the prior art relies on artificial adjustment of the position of the ultrasonic probe and the brightness of the image, and the contrast is not high and time-consuming, making it difficult to accurately analyze focal and extensive adhesions.
Combining the black and white ultrasound module and the Doppler ultrasound module, a comprehensive image is generated through high-frequency ultrasound and blood flow velocity direction analysis, an automatic adjustment of image brightness and contrast, optimize image quality, and judge uterine cavity adhesion.
It improves the diagnostic accuracy and efficiency of uterine adhesions, reduces artificial subjective judgments, enhances the visibility of focal and extensive adhesion areas, and provides quantitative and qualitative evaluation.
Smart Images

Figure CN119033411A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of medical analysis, and in particular to an intrauterine adhesion analysis system based on ultrasound images. Background Art
[0002] Ultrasound is a high-frequency sound wave. The vaginal ultrasound method is relatively non-invasive for evaluating the female reproductive system and can provide high-resolution images, allowing doctors to observe the endometrium and its adjacent structures more accurately. Based on the ultrasound images, doctors can determine whether there is intrauterine adhesion by secondary analysis and comparison of normal endometrial structure and changes that may cause adhesions.
[0003] Intrauterine adhesions may form several adhesion structures, which will have an adverse effect on the echo effect of ultrasound contrast imaging: Focal adhesions refer to adhesions formed in local areas of the endometrium due to inflammation or other pathological changes. When ultrasound encounters this area, a strong bright spot will be produced, which may cover or confuse the ultrasound echo of the surrounding normal tissue. Extensive adhesions refer to intrauterine adhesions in a larger range, which may have a significant impact on the distribution of ultrasound contrast imaging, resulting in abnormal dark areas with weakened echo signals in certain areas of the image.
[0004] In the existing technology, doctors usually manually judge focal adhesions and extensive adhesions by changing the position and angle of the ultrasound probe multiple times, obtaining images of different sections, and then adjusting the image brightness and contrast in the ultrasound image. This method has a low judgment accuracy and is time-consuming. Therefore, it is necessary to design an accurate analysis system for intrauterine adhesions based on ultrasound images. Summary of the invention
[0005] The purpose of the present invention is to provide an intrauterine adhesion analysis system based on ultrasound images to solve the problems raised in the above background technology.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intrauterine adhesion analysis system based on ultrasound images, the adhesion analysis system comprising a black and white ultrasound module, a Doppler ultrasound module, a data analysis module, and an image processing module. The black and white ultrasound module uses high-frequency ultrasound to generate images through reflection and scattering of tissues in the body. The Doppler ultrasound module uses ultrasound combined with the Doppler principle to measure the changes in sound wave frequency caused by the movement of red blood cells in the blood, and evaluates the blood flow speed and direction. The data analysis module combines the processed black and white ultrasound image with the blood flow analysis results to form a comprehensive analysis result of the inside of the uterus. The image processing module is used to adjust the brightness and contrast technical parameters of the ultrasound image in real time according to the blood flow analysis results to optimize the image quality.
[0007] According to the above technical solution, the black and white ultrasound module includes an ultrasound transmitter, an ultrasound receiver, and an ultrasound image generation module, and the ultrasound receiver is electrically connected to the ultrasound image generation module; The ultrasonic transmitter is used to transmit high-frequency ultrasonic signals to penetrate the endometrial tissue, the ultrasonic receiver is used to receive the reflected ultrasonic signals and convert them into electrical signals, and the ultrasonic image generation module processes and converts the received electrical signals to generate black and white ultrasonic images; The Doppler ultrasound module includes a Doppler signal receiver, a Doppler signal processing unit, and a flow pattern diagram generating module. The Doppler signal receiver is installed on the ultrasound receiver, and the Doppler signal receiver is electrically connected to the Doppler signal processing unit, and the Doppler signal processing unit is electrically connected to the flow pattern diagram generating module. The Doppler signal receiver uses the Doppler effect to obtain the frequency change of the reflected wave, the Doppler signal processing unit is used to analyze the Doppler frequency shift in the received ultrasonic signal, thereby calculating the blood flow velocity and direction, generating the blood flow direction and data, and the flow pattern diagram generation module is used to convert the Doppler data into a Doppler flow pattern diagram to display the blood flow velocity and direction; The data analysis module includes an image registration module, a state analysis module, and a regional assessment module. The image registration module is electrically connected to the ultrasound image generation module and the flow pattern map generation module. The state analysis module is electrically connected to the image registration module. The regional assessment module is electrically connected to the state analysis module. The image registration module places the black-and-white ultrasound image and the Doppler flow pattern map in the same coordinate system for registration, and uses a geometric transformation algorithm to ensure that the two images are accurately overlapped in the same coordinate system. The state analysis module analyzes the blood flow direction and data, compares the abnormal blood flow data with the normal blood flow data, and determines whether there are focal adhesions and extensive adhesions. The regional assessment module is used to correspond the area where the abnormal blood flow data exists with the area in the black-and-white ultrasound image, so as to assess the health status of each area of the endometrium and whether the black-and-white ultrasound image needs to be adjusted. The image processing module includes a real-time image adjustment module and a data storage module, wherein the data storage module is electrically connected to the ultrasound image generation module and the flow pattern map generation module, and the real-time image adjustment module is electrically connected to the state analysis module and the region assessment module; The real-time image adjustment module reads the judgment results of focal adhesion and extensive adhesion, automatically adjusts the technical parameters of the black-and-white ultrasound image, and changes the contrast and brightness of each area in the black-and-white ultrasound image. The data storage module is used to record the black-and-white ultrasound image, Doppler flow pattern diagram and blood flow direction and data, and stores them in a database for subsequent analysis and comparison.
[0008] According to the above technical solution, the generation process of the Doppler flow pattern diagram is specifically as follows: S2-1, dividing the detection area of the Doppler signal receiver into a dot matrix of detection points, wherein the dot matrix has multiple detection points, and when the Doppler signal receiver moves with the ultrasonic transmitter, recording the coordinates of each detection point of the Doppler signal receiver in real time; S2-2. When ultrasound waves encounter moving red blood cells, part of the wave will be reflected back to the Doppler signal receiver. The Doppler signal receiver is used to obtain the frequency change of the reflected wave and calculate the blood flow speed and direction. The frequency of the ultrasound wave emitted by the ultrasound transmitter is , the frequency of the reflected wave received at a certain detection point is , then the frequency shift is , blood flow velocity ,in is the blood flow velocity conversion factor, is the propagation speed of ultrasound in blood; S2-3, make the detection area have detection points, and the blood flow velocity at each detection point is , as blood flows toward the ultrasound probe Increased, blood flows away from the probe The blood flow direction at each detection point is determined by reducing the blood flow velocity and direction data, and a Doppler flow pattern diagram is generated based on the blood flow velocity and direction data.
[0009] According to the above technical solution, the registration of the black and white ultrasound image and the Doppler flow pattern map is achieved through the image registration module, and the specific method is as follows: S2-4, extracting feature points from the Doppler flow pattern map and the black-and-white ultrasound image, respectively, performing preliminary registration based on the extracted feature points, using an affine transformation model to estimate the spatial relationship, and further refining the registration based on the estimated spatial relationship through an iterative closest point optimization algorithm to reduce the overlap error between the two images; S2-5. Resample the Doppler flow pattern image to ensure that it is aligned with the pixels of the black-and-white ultrasound image, and superimpose the aligned Doppler flow pattern image on the black-and-white ultrasound image to generate a final composite image.
[0010] According to the above technical scheme, the specific method for judging whether there is focal adhesion or extensive adhesion in the uterine cavity is: S3-1. Select multiple samples from healthy volunteers, use Doppler signal receivers to detect blood vessels in the endometrial region of the volunteers, obtain blood flow velocity and direction data, and obtain normal blood flow data at each position by averaging; S3-2. When the blood flow velocity of the detection points around a certain area is different from the normal blood flow data When the blood flow direction increases and deflects around this area, and the blood flow direction at the detection points inside the area is random, this area is defined as a potential focal adhesion area. The echo intensity of this area is re-detected by the ultrasonic receiver. If it meets the strong echo reflection, this area is judged to be a focal adhesion area. S3-3. When the overall blood flow velocity in a certain area Compared with normal blood flow data, the detection points in this area are The distribution of is uneven, that is Greater than the variance setting value , then this area is defined as potential extensive adhesion, and the echo intensity of this area is re-detected by the ultrasonic receiver. If it meets the weak echo reflection, this area is judged to be extensive adhesion.
[0011] According to the above technical solution, the specific method for automatically adjusting the contrast and brightness of each area of the black and white ultrasound image is: S4-1. Find the area corresponding to the focal adhesion area in the Doppler flow pattern image in the black and white ultrasound image and enhance the image contrast of this area The magnitude of the enhancement is related to the overall blood flow velocity in this detection area of the patient. and normal blood flow velocity The ratio is positively correlated, specifically ,in is the default contrast; S4-2. Find the area corresponding to the extensive adhesion in the Doppler flow pattern in the black and white ultrasound image and increase the brightness of this area The magnitude of the increase is related to the overall blood flow velocity in this detection area of the patient. and normal blood flow velocity The ratio is negatively correlated, specifically ,in It is the default brightness, in cd / m².
[0012] According to the above technical solution, the specific method of verifying and optimizing the adjustment parameters of contrast and brightness is as follows: S5-1. When checking the brightness, if the medical staff determines that the brightness of this area needs to be adjusted, manually adjust the brightness to , record it The value is the adjustment ratio. In subsequent adjustments, you can choose to increase or decrease the adjustment ratio to continuously optimize. To manually adjust the brightness of the confirmation; S5-2. When checking the contrast, if the medical staff determines that the display effect of this area is not good, first reduce the brightness If the display effect is normal, there is no need to adjust the contrast. If the display effect is still not achieved, manually adjust the contrast at different brightness reduction levels. , until the appropriate and , and then optimize the automatic adjustment results according to this adjustment ratio. Confirm the contrast for manual adjustment.
[0013] The intrauterine adhesion analysis method using the above analysis system comprises the following steps: S1. The patient is examined in the supine position. The ultrasound transmitter is activated to emit high-frequency ultrasound waves, which penetrate the endometrial tissue. The ultrasound receiver receives the reflected waves, processes the received electrical signals, and generates a black-and-white ultrasound image. S2, while the ultrasonic receiver receives the reflected wave, the Doppler signal receiver is used to obtain the frequency change of the reflected wave, calculate the blood flow velocity and direction, and generate a corresponding Doppler flow pattern map, and align the black and white ultrasonic image with the Doppler flow pattern map to ensure that they accurately overlap in the same coordinate system; S3. Compare the abnormal blood flow data with the normal blood flow data to determine whether there is focal adhesion or extensive adhesion in the endometrium, and evaluate the health status of each area of the endometrium based on the abnormal blood flow data and the black-and-white ultrasound image information; S4, automatically adjusting the contrast and brightness of each area of the black-and-white ultrasound image according to the judgment results of focal adhesion and extensive adhesion, and storing the processed black-and-white ultrasound image, Doppler flow pattern diagram, blood flow direction and related data in a database; S5. Medical personnel review the synthesized images and analysis results, conduct quality assessment of the black-and-white ultrasound images, and verify and optimize the adjustment parameters of the contrast and brightness of the black-and-white ultrasound images.
[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention observes blood flow changes by combining Doppler ultrasound technology, provides information on blood flow velocity and blood flow direction, and can indirectly evaluate the health of the endometrium based on the characteristics of the blood flow. When taking ultrasound images, Doppler ultrasound and traditional black-and-white ultrasound are used in combination to determine the blood flow conditions in the endometrium. Abnormal blood flow patterns indicate the presence of extensive adhesions or focal adhesions. The observed flow patterns and contrast imaging status produce quantitative and qualitative evaluations of the adhesion structure, and automatically adjust ultrasound technical parameters, contrast and image brightness gain, which can enhance the contrast between focal adhesions and surrounding normal tissues, as well as enhance the visibility of extensive adhesion areas. The process can be automatically adjusted without subjective human judgment, thereby improving the accuracy of ultrasound images. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic diagram of the overall module structure of the present invention; Figure 2 It is a traditional black and white ultrasound image without processing; Figure 3 It is a black and white ultrasound image processed by the algorithm of the present invention; Figure 4 It is a Doppler flow pattern diagram of the present invention. DETAILED DESCRIPTION
[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0017] See also Figure 1 The present invention provides a technical solution: a uterine adhesion analysis system based on ultrasound images, the adhesion analysis system includes a black-and-white ultrasound module, a Doppler ultrasound module, a data analysis module, and an image processing module. The black-and-white ultrasound module uses high-frequency ultrasound to generate images through reflection and scattering of tissues in the body. The Doppler ultrasound module uses ultrasound combined with the Doppler principle to measure the frequency changes of sound waves caused by the movement of red blood cells in the blood and evaluate the blood flow speed and direction. The data analysis module combines the processed black-and-white ultrasound image with the blood flow analysis result to form a comprehensive analysis result of the inside of the uterus. The image processing module is used to adjust the brightness and contrast technical parameters of the ultrasound image in real time according to the blood flow analysis result to optimize the image quality. The black and white ultrasound module includes an ultrasound transmitter, an ultrasound receiver, and an ultrasound image generation module, and the ultrasound receiver is electrically connected to the ultrasound image generation module; The ultrasonic transmitter is used to transmit high-frequency ultrasonic signals to penetrate the endometrial tissue, the ultrasonic receiver is used to receive the reflected ultrasonic signals and convert them into electrical signals, and the ultrasonic image generation module processes and converts the received electrical signals to generate black and white ultrasonic images; The Doppler ultrasound module includes a Doppler signal receiver, a Doppler signal processing unit, and a flow pattern diagram generating module. The Doppler signal receiver is installed on the ultrasound receiver, and the Doppler signal receiver is electrically connected to the Doppler signal processing unit, and the Doppler signal processing unit is electrically connected to the flow pattern diagram generating module. The Doppler signal receiver uses the Doppler effect to obtain the frequency change of the reflected wave. The Doppler signal processing unit is used to analyze the Doppler frequency shift in the received ultrasonic signal, thereby calculating the blood flow velocity and direction, generating the blood flow direction and data. The flow pattern diagram generation module is used to convert the Doppler data into a Doppler flow pattern diagram to display the blood flow velocity and direction. The data analysis module includes an image registration module, a state analysis module, and a regional assessment module. The image registration module is electrically connected to the ultrasound image generation module and the flow pattern map generation module. The state analysis module is electrically connected to the image registration module. The regional assessment module is electrically connected to the state analysis module. The image registration module places the black-and-white ultrasound image and the Doppler flow pattern map in the same coordinate system for registration, and uses a geometric transformation algorithm to ensure that the two images overlap accurately in the same coordinate system. The state analysis module analyzes the blood flow direction and data, compares the abnormal blood flow data with the normal blood flow data, and determines whether there are focal adhesions and extensive adhesions. The regional assessment module is used to match the area where the abnormal blood flow data exists with the area in the black-and-white ultrasound image, so as to assess the health status of each area of the endometrium and whether the black-and-white ultrasound image needs to be adjusted. The image processing module includes a real-time image adjustment module and a data storage module, the data storage module is electrically connected to the ultrasound image generation module and the flow pattern map generation module, and the real-time image adjustment module is electrically connected to the state analysis module and the region assessment module; The real-time image adjustment module reads the judgment results of focal adhesion and extensive adhesion, automatically adjusts the technical parameters of the black-and-white ultrasound image, and changes the contrast and brightness of each area in the black-and-white ultrasound image. The data storage module is used to record the black-and-white ultrasound image, Doppler flow pattern diagram, blood flow direction and data, and stores them in the database for subsequent analysis and comparison.
[0018] The intrauterine adhesion analysis method using the above analysis system comprises the following steps: S1. The patient is examined in the supine position. The ultrasound transmitter is activated to emit high-frequency ultrasound waves, which penetrate the endometrial tissue. The ultrasound receiver receives the reflected waves, processes the received electrical signals, and generates a black-and-white ultrasound image. S2, while the ultrasonic receiver receives the reflected wave, the Doppler signal receiver is used to obtain the frequency change of the reflected wave, calculate the blood flow velocity and direction, and generate a corresponding Doppler flow pattern map, and align the black and white ultrasonic image with the Doppler flow pattern map to ensure that they accurately overlap in the same coordinate system; S3. Compare the abnormal blood flow data with the normal blood flow data to determine whether there is focal adhesion or extensive adhesion in the endometrium, and evaluate the health status of each area of the endometrium based on the abnormal blood flow data and the black-and-white ultrasound image information; S4, automatically adjusting the contrast and brightness of each area of the black-and-white ultrasound image according to the judgment results of focal adhesion and extensive adhesion, and storing the processed black-and-white ultrasound image, Doppler flow pattern diagram, blood flow direction and related data in a database; S5. The medical staff reviews the synthesized images and analysis results, conducts quality assessment of the black-and-white ultrasound images, and verifies and optimizes the adjustment parameters of the contrast and brightness of the black-and-white ultrasound images; Through the above process, the patient's ultrasound examination can more accurately assess the health of the endometrium. The combination of high-frequency ultrasound and Doppler signals ensures the precise registration of images and blood flow data, which can effectively identify focal adhesions or extensive adhesions. In addition, automatic adjustment of image contrast and brightness improves the visualization of the image, making it easier for medical staff to make more accurate quality assessments and diagnoses, ultimately improving the accuracy and efficiency of diagnosis.
[0019] In S2, the process of calculating the blood flow velocity and direction and generating the corresponding Doppler flow pattern diagram is as follows: S2-1, dividing the detection area of the Doppler signal receiver into a dot matrix of detection points, wherein the dot matrix has multiple detection points, and when the Doppler signal receiver moves with the ultrasonic transmitter, recording the coordinates of each detection point of the Doppler signal receiver in real time; S2-2. When ultrasound waves encounter moving red blood cells, part of the wave will be reflected back to the Doppler signal receiver. The Doppler signal receiver is used to obtain the frequency change of the reflected wave and calculate the blood flow speed and direction. The frequency of the ultrasound wave emitted by the ultrasound transmitter is , the frequency of the reflected wave received at a certain detection point is , then the frequency shift is , blood flow velocity ,in is the blood flow velocity conversion factor, is the propagation speed of ultrasound in blood; S2-3, make the detection area have detection points, and the blood flow velocity at each detection point is , as blood flows toward the ultrasound probe Increased, blood flows away from the probe Reduce, so as to determine the blood flow direction of each detection point, and generate a Doppler flow pattern diagram based on the blood flow velocity and direction data; In S2, the registration of the black-and-white ultrasound image and the Doppler flow pattern map is achieved through the image registration module, and the specific method is as follows: S2-4, extracting feature points from the Doppler flow pattern map and the black-and-white ultrasound image, respectively, performing preliminary registration based on the extracted feature points, using an affine transformation model to estimate the spatial relationship, and further refining the registration based on the estimated spatial relationship through an iterative closest point optimization algorithm to reduce the overlap error between the two images; S2-5, resampling the Doppler flow pattern image to ensure that it is aligned with the pixels of the black-and-white ultrasound image, and superimposing the aligned Doppler flow pattern image on the black-and-white ultrasound image to generate a final composite image; In S3, the specific method for judging whether there is focal adhesion or extensive adhesion in the uterine cavity is: S3-1. Select multiple samples from healthy volunteers, use Doppler signal receivers to detect blood vessels in the endometrial region of the volunteers, obtain blood flow velocity and direction data, and obtain normal blood flow data at each position by averaging; S3-2. When the blood flow velocity of the detection points around a certain area is different from the normal blood flow data When the blood flow direction increases and deflects around this area, and the blood flow direction at the detection points inside the area is random, this area is defined as a potential focal adhesion area. The echo intensity of this area is re-detected by the ultrasonic receiver. If it meets the strong echo reflection, this area is judged to be a focal adhesion area. S3-3. When the overall blood flow velocity in a certain area Compared with normal blood flow data, the detection points in this area are The distribution of is uneven, that is Greater than the variance setting value , then this area is defined as potential extensive adhesion, and the echo intensity of this area is re-detected by the ultrasonic receiver. If it meets the weak echo reflection, this area is judged to be extensive adhesion; In S4, the automatic adjustment of the contrast and brightness of each area of the black-and-white ultrasound image is achieved by a real-time image adjustment module, and the specific method is as follows: S4-1. Find the area corresponding to the focal adhesion area in the Doppler flow pattern image in the black and white ultrasound image and enhance the image contrast of this area The magnitude of the enhancement is related to the overall blood flow velocity in this detection area of the patient. and normal blood flow velocity The ratio is positively correlated, specifically ,in is the default contrast; S4-2. Find the area corresponding to the extensive adhesion in the Doppler flow pattern in the black and white ultrasound image and increase the brightness of this area The magnitude of the increase is related to the overall blood flow velocity in this detection area of the patient. and normal blood flow velocity The ratio is negatively correlated, specifically ,in is the default brightness, in cd / m²; In S5, the contrast and brightness adjustment parameters are checked and optimized by the real-time image adjustment module, and the specific method is as follows: S5-1. When checking the brightness, if the medical staff determines that the brightness of this area needs to be adjusted, manually adjust the brightness to , record it The value is the adjustment ratio. In subsequent adjustments, you can choose to increase or decrease the adjustment ratio to continuously optimize. To manually adjust the brightness of the confirmation; S5-2. When checking the contrast, if the medical staff determines that the display effect of this area is not good, first reduce the brightness If the display effect is normal, there is no need to adjust the contrast. If the display effect is still not achieved, manually adjust the contrast at different brightness reduction levels. , until the appropriate and , and then optimize the automatic adjustment results according to this adjustment ratio. Confirm the contrast for manual adjustment.
[0020] By verifying and optimizing the brightness and contrast adjustment parameters, medical staff can accurately improve the visualization of ultrasound images. The manual adjustment of brightness and contrast ensures that each area is displayed optimally, thereby improving the recognition of lesions and the accuracy of diagnosis. This dynamic adjustment mechanism not only improves image quality, but also provides a reliable reference standard for subsequent automatic adjustments, significantly improving the overall efficiency and effectiveness of ultrasound examinations.
[0021] Comparative experiment: To evaluate the accuracy of the black-and-white ultrasound images processed by the algorithm of the present invention in showing intrauterine adhesions compared with the traditional black-and-white ultrasound images: Ten patients diagnosed with intrauterine adhesions by hysteroscopic surgery were selected as the intrauterine adhesion group, and 30 patients with negative intrauterine adhesions by hysteroscopy during the same period were selected as the non-intrauterine adhesion group. All subjects received traditional black-and-white ultrasound and Doppler ultrasound examination combined with the algorithm of the present invention. The traditional black-and-white ultrasound was the control group, and the Doppler ultrasound examination combined with the algorithm of the present invention was the study group. The ultrasound examinations were performed by the same experienced ultrasound physician, and the operation process followed the standardized process. Both ultrasound examinations collected cross-sectional and longitudinal images of the endometrium.
[0022] Two experienced radiologists independently performed blind evaluation on all ultrasound images, including: uterine cavity morphology: normal / abnormal; adhesion site: none / uterine fundus / uterine wall / cervix; adhesion degree: mild / moderate / severe; when the two physicians disagreed on the evaluation results, they reached a consensus through consultation. The accuracy, positive predictive value, and negative predictive value indicators were used to evaluate the performance of the two ultrasound examination methods in diagnosing intrauterine adhesions. The traditional black-and-white ultrasound images were used as reference. Figure 2 , black and white ultrasound image after algorithm processing Figure 3 , the Doppler flow pattern diagram involved in the experiment is referenced Figure 4 . Sensitivity (true positive rate): the percentage of patients who are actually sick but are correctly judged as sick according to the test standard. The higher the sensitivity, the better, and the ideal sensitivity is 100%. Specificity (true negative rate): the percentage of patients who are actually not sick but are correctly judged as not sick according to the test standard. The higher the specificity, the better, and the ideal specificity is 100%. The experimental results are as follows: in the analysis results of the black-and-white ultrasound images processed by the algorithm of the present invention, all 10 patients in the intrauterine adhesion group were found to have intrauterine adhesions, with a sensitivity of 100%, and 28 of the 30 patients in the non-intrauterine adhesion group were found to have no intrauterine adhesions, with a specificity of 93.3%; in the analysis results of the traditional black-and-white ultrasound images, 8 of the 10 patients in the intrauterine adhesion group were found to have intrauterine adhesions, with a sensitivity of 80%, and 27 of the 30 patients in the non-intrauterine adhesion group were found to have no intrauterine adhesions, with a specificity of 90%.
[0023] Conclusion: Compared with traditional black-and-white ultrasound images, the black-and-white ultrasound images processed by the algorithm of the present invention are clearer and more accurate in showing intrauterine adhesions, which can provide a more reliable basis for clinical diagnosis and treatment.
[0024] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0025] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A system for analyzing intrauterine adhesions based on ultrasound, characterized in that: It includes a black-and-white ultrasound module, a Doppler ultrasound module, a data analysis module, and an image processing module. The black-and-white ultrasound module uses high-frequency ultrasound to generate images through reflection and scattering of tissues in the body. The Doppler ultrasound module uses ultrasound combined with the Doppler principle to measure the changes in sound wave frequency caused by the movement of red blood cells in the blood and evaluate the blood flow speed and direction. The data analysis module combines the processed black-and-white ultrasound image with the blood flow analysis result to form a comprehensive analysis result of the inside of the uterus. The image processing module is used to adjust the brightness and contrast technical parameters of the ultrasound image in real time according to the blood flow analysis result to optimize the image quality.
2. The ultrasound-based intrauterine adhesion analysis system according to claim 1, characterized in that: The black and white ultrasound module includes an ultrasound transmitter, an ultrasound receiver, and an ultrasound image generation module, and the ultrasound receiver is electrically connected to the ultrasound image generation module; The ultrasonic transmitter is used to transmit high-frequency ultrasonic signals to penetrate the endometrial tissue, the ultrasonic receiver is used to receive the reflected ultrasonic signals and convert them into electrical signals, and the ultrasonic image generation module processes and converts the received electrical signals to generate black and white ultrasonic images; The Doppler ultrasound module includes a Doppler signal receiver, a Doppler signal processing unit, and a flow pattern diagram generating module. The Doppler signal receiver is installed on the ultrasound receiver, and the Doppler signal receiver is electrically connected to the Doppler signal processing unit, and the Doppler signal processing unit is electrically connected to the flow pattern diagram generating module. The Doppler signal receiver uses the Doppler effect to obtain the frequency change of the reflected wave, the Doppler signal processing unit is used to analyze the Doppler frequency shift in the received ultrasonic signal, thereby calculating the blood flow velocity and direction, generating the blood flow direction and data, and the flow pattern diagram generation module is used to convert the Doppler data into a Doppler flow pattern diagram to display the blood flow velocity and direction; The data analysis module includes an image registration module, a state analysis module, and a regional assessment module. The image registration module is electrically connected to the ultrasound image generation module and the flow pattern map generation module. The state analysis module is electrically connected to the image registration module. The regional assessment module is electrically connected to the state analysis module. The image registration module places the black-and-white ultrasound image and the Doppler flow pattern map in the same coordinate system for registration, and uses a geometric transformation algorithm to ensure that the two images are accurately overlapped in the same coordinate system. The state analysis module analyzes the blood flow direction and data, compares the abnormal blood flow data with the normal blood flow data, and determines whether there are focal adhesions and extensive adhesions. The regional assessment module is used to correspond the area where the abnormal blood flow data exists with the area in the black-and-white ultrasound image, so as to assess the health status of each area of the endometrium and whether the black-and-white ultrasound image needs to be adjusted. The image processing module includes a real-time image adjustment module and a data storage module, wherein the data storage module is electrically connected to the ultrasound image generation module and the flow pattern map generation module, and the real-time image adjustment module is electrically connected to the state analysis module and the region assessment module; The real-time image adjustment module reads the judgment results of focal adhesion and extensive adhesion, automatically adjusts the technical parameters of the black-and-white ultrasound image, and changes the contrast and brightness of each area in the black-and-white ultrasound image. The data storage module is used to record the black-and-white ultrasound image, Doppler flow pattern diagram and blood flow direction and data, and stores them in a database for subsequent analysis and comparison.
3. The ultrasound-based intrauterine adhesion analysis system according to claim 2, characterized in that: The generation process of the Doppler flow pattern diagram is specifically as follows: S2-1, dividing the detection area of the Doppler signal receiver into a dot matrix of detection points, wherein the dot matrix has multiple detection points, and when the Doppler signal receiver moves with the ultrasonic transmitter, recording the coordinates of each detection point of the Doppler signal receiver in real time; S2-2. When ultrasound waves encounter moving red blood cells, part of the wave will be reflected back to the Doppler signal receiver. The Doppler signal receiver is used to obtain the frequency change of the reflected wave and calculate the blood flow speed and direction. The frequency of the ultrasound wave emitted by the ultrasound transmitter is , the frequency of the reflected wave received at a certain detection point is , then the frequency shift is , blood flow velocity ,in is the blood flow velocity conversion factor, is the propagation speed of ultrasound in blood; S2-3, make the detection area have detection points, and the blood flow velocity at each detection point is , as blood flows toward the ultrasound probe Increased, blood flows away from the probe The blood flow direction at each detection point is determined by reducing the blood flow velocity and direction data, and a Doppler flow pattern diagram is generated based on the blood flow velocity and direction data.
4. The ultrasound-based intrauterine adhesion analysis system according to claim 3, characterized in that: The working method of the image registration module is: S2-4, extracting feature points from the Doppler flow pattern map and the black-and-white ultrasound image, respectively, performing preliminary registration based on the extracted feature points, using an affine transformation model to estimate the spatial relationship, and further refining the registration based on the estimated spatial relationship through an iterative closest point optimization algorithm to reduce the overlap error between the two images; S2-5. Resample the Doppler flow pattern image to ensure that it is aligned with the pixels of the black-and-white ultrasound image, and superimpose the aligned Doppler flow pattern image on the black-and-white ultrasound image to generate a final composite image.
5. The ultrasound-based intrauterine adhesion analysis system according to claim 4, characterized in that: The specific method for judging whether there is focal adhesion and extensive adhesion is: S3-1. Select multiple samples from healthy volunteers, use Doppler signal receivers to detect blood vessels in the endometrial region of the volunteers, obtain blood flow velocity and direction data, and obtain normal blood flow data at each position by averaging; S3-2. When the blood flow velocity of the detection points around a certain area is different from the normal blood flow data When the blood flow direction increases and deflects around this area, and the blood flow direction at the detection points inside the area is random, this area is defined as a potential focal adhesion area. The echo intensity of this area is re-detected by the ultrasonic receiver. If it meets the strong echo reflection, this area is judged to be a focal adhesion area. S3-3. When the overall blood flow velocity in a certain area Compared with normal blood flow data, the detection points in this area are The distribution of is uneven, that is Greater than the variance setting value , then this area is defined as potential extensive adhesion, and the echo intensity of this area is re-detected by the ultrasonic receiver. If it meets the weak echo reflection, this area is judged to be extensive adhesion.
6. The ultrasound-based intrauterine adhesion analysis system according to claim 5, characterized in that: The working method of the real-time image adjustment module is: S4-1. Find the area corresponding to the focal adhesion area in the Doppler flow pattern image in the black and white ultrasound image and enhance the image contrast of this area The magnitude of the enhancement is related to the overall blood flow velocity in this detection area of the patient. and normal blood flow velocity The ratio is positively correlated, specifically ,in is the default contrast; S4-2. Find the area corresponding to the extensive adhesion in the Doppler flow pattern in the black and white ultrasound image and increase the brightness of this area The magnitude of the increase is related to the overall blood flow velocity in this detection area of the patient. and normal blood flow velocity The ratio is negatively correlated, specifically ,in It is the default brightness, in cd / m².
7. The ultrasound-based intrauterine adhesion analysis system according to claim 6, characterized in that: The working method of the real-time image adjustment module also includes: S5-1. When checking the brightness, if the medical staff determines that the brightness of this area needs to be adjusted, manually adjust the brightness to , record it The value is the adjustment ratio. In subsequent adjustments, you can choose to increase or decrease the adjustment ratio to continuously optimize. To manually adjust the brightness of the confirmation; S5-2. When checking the contrast, if the medical staff determines that the display effect of this area is not good, first reduce the brightness If the display effect is normal, there is no need to adjust the contrast. If the display effect is still not achieved, manually adjust the contrast at different brightness reduction levels. , until the appropriate and , and then optimize the automatic adjustment results according to this adjustment ratio. Confirm the contrast for manual adjustment.
8. A method for analyzing intrauterine adhesions based on ultrasound, characterized in that: The method works according to the system of claim 2, comprising the following steps: S1. The patient is examined in the supine position. The ultrasound transmitter is activated to emit high-frequency ultrasound waves, which penetrate the endometrial tissue. The ultrasound receiver receives the reflected waves, processes the received electrical signals, and generates a black-and-white ultrasound image. S2, while the ultrasonic receiver receives the reflected wave, the Doppler signal receiver is used to obtain the frequency change of the reflected wave, calculate the blood flow velocity and direction, and generate a corresponding Doppler flow pattern map, and align the black and white ultrasonic image with the Doppler flow pattern map to ensure that they accurately overlap in the same coordinate system; S3. Compare the abnormal blood flow data with the normal blood flow data to determine whether there is focal adhesion or extensive adhesion in the endometrium, and evaluate the health status of each area of the endometrium based on the abnormal blood flow data and the black-and-white ultrasound image information; S4, automatically adjusting the contrast and brightness of each area of the black-and-white ultrasound image according to the judgment results of focal adhesion and extensive adhesion, and storing the processed black-and-white ultrasound image, Doppler flow pattern diagram, blood flow direction and related data in a database; S5. Medical personnel review the synthesized images and analysis results, conduct quality assessment of the black-and-white ultrasound images, and verify and optimize the adjustment parameters of the contrast and brightness of the black-and-white ultrasound images.
Citation Information
Patent Citations
Ultrasonic diagnosing device
CN102131465A
Ultrasonic image adjusting method, terminal equipment and readable storage medium
CN113256502A
Method and system for providing ultrasound image
CN113558658A
Ultrasonic-based blood flow measurement method and ultrasonic imaging system
CN115670512A
Blood flow extraction image forming apparatus, blood flow extraction image forming method, and non-transitory storage medium
CN117297660A
Cited By
Ultrasound imaging system and method for identifying connected regions
CN115251989A
Abnormal blood flow distribution characterization method, device and equipment based on ultrasonic image
CN119887657A
Hysteroscope image auxiliary diagnosis and treatment evaluation system fused with traditional Chinese and western medicine multi-modal representation
CN121964154A
An hysteroscope image assisted diagnosis and treatment evaluation system fusing multi-modal representations of traditional Chinese and western medicine
CN121964154B
