Visual obstetrical image examination processing method

Abstract

The invention discloses a visual obstetrical image examination processing method, which belongs to the technical field of obstetrical image examination processing, and comprises an image acquisition module, an image processing module, a cyclic influence evaluation module and an output and diagnosis module, the image acquisition module is utilized to acquire and preliminarily process a current obstetrical image, and the current obstetrical image is transmitted to the image processing module; an image processing module is utilized to sequentially calculate and output an image quality evaluation index V, a processing effect enhancement index CZ and a cyclic influence evaluation index CF, and based on the result of the cyclic influence evaluation index CF, the cyclic influence evaluation module is utilized to trigger adjustment of an image processing strategy according to the result of the processing effect enhancement index CZ. According to the method, the image quality and the diagnosis accuracy are improved by comprehensively and quantitatively evaluating the image quality, adjusting the processing method in a personalized manner and introducing a cyclic influence mechanism, so that richer diagnosis information and more accurate decision support are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of obstetric imaging examination and processing, and particularly relates to a visualization method for obstetric imaging examination and processing. Background Art

[0002] With the continuous progress of medical technology, obstetric imaging examination plays a crucial role in prenatal diagnosis. However, traditional imaging examination methods are often limited by the volatility of image quality and the singularity of processing methods, making it difficult to meet the accurate diagnosis needs of clinicians. To overcome these limitations, a visualization method for obstetric imaging examination and processing has emerged.

[0003] Regarding the above and existing related technologies, the inventor believes that the following defects often exist: existing image quality assessment methods often rely on a single index and are difficult to comprehensively reflect multiple dimensions of images, which leads to the fact that in practical applications, doctors cannot accurately judge the overall quality and processing effect of images, and existing image processing methods lack personalized adjustment for different image characteristics, which also results in unsatisfactory processing effects in some cases and even introduces new noise and blurring. In addition, existing image processing methods often ignore the cyclic influence during the processing, and thus there are cumulative errors and instability factors during the processing. Summary of the Invention

[0004] The technical problem to be solved by the present invention is: there are limitations in image quality assessment, singularity of processing methods, and lack of cyclic influence mechanism in the prior art. For this reason, we propose a visualization method for obstetric imaging examination and processing.

[0005] The technical solution mainly is: a visualization method for obstetric imaging examination and processing, including an image acquisition module, an image processing module, a cyclic influence assessment module, and an output and diagnosis module, characterized in that: the image processing module includes an image quality measurement unit, an enhanced effect unit after image processing, and a cyclic influence trigger unit;

[0006] The specific processing steps are as follows:

[0007] Step 1: Use the image acquisition module to collect and preliminarily process the current obstetric image, and transmit it to the image processing module;

[0008] Step 2: Use the image processing module to calculate and output the image quality assessment index V, the processing effect enhancement index CZ, and the cyclic influence assessment index CF in sequence;

[0009] Step 3: Based on the result of the cyclic influence assessment index CF, and use the cyclic influence assessment module to trigger the adjustment of the image processing strategy according to the result of the processing effect enhancement index CZ;

[0010] Step 4: The output and diagnosis module outputs the adjusted image processing strategy and the adjusted current obstetric image.

[0011] Preferably, the image processing module stores and summarizes the processing effect enhancement index CZ and the cyclic influence assessment index CF, and classifies and stores the final values of the processing effect enhancement index CZ and the cyclic influence assessment index CF for different pregnancy periods of the completed obstetric image examinations to form a cyclic influence reference interval {CF l -CF h} and a processing effect enhancement interval {CZ l -CZ h};

[0012] Among them, CF l is the lowest cyclic influence assessment index, CF h is the highest cyclic influence assessment index, CZ l is the lowest processing effect enhancement index, and CZ h is the highest processing effect enhancement index.

[0013] Preferably, the calculation formula for the unit measuring the image quality is as follows:

[0014]

[0015] Where:

[0016] V is the image quality assessment index;

[0017] Q is the image clarity, and Q is used to measure the contrast between different tissues in the current obstetric image;

[0018] YM is the image area, and YM reflects the proportion of the fetal area in the total area of the current obstetric image;

[0019] ZS is the noise level value, and ZS reflects the background noise intensity in the current obstetric image;

[0020] YD is the motion blur value, and YD reflects the degree of blur in the current obstetric image caused by the movement of the fetus and the mother;

[0021] T is the feature loss value, and T reflects the degree of loss of key anatomical features in the current obstetric image;

[0022] XJ is the detail retention value, and XJ reflects the degree of retention of detail information in the current obstetric image;

[0023] Multiplying the image clarity Q by the square root of the image area YM aims to emphasize the importance of clarity in image quality;

[0024] The calculation of the feature loss value T is combined with the square root of the detail retention value XJ, aiming to reflect the role of detail retention in compensating for feature loss.

[0025] Preferably, the calculation formulas for the noise level value ZS, the motion blur value YD, the feature loss value T, and the detail retention value XJ are as follows:

[0026]

[0027] XJ = (XJ det[il - XJ smooth ) 2 ;

[0028] Where:

[0029] N is the total number of pixels, and N reflects the total number of pixels in the current obstetric image;

[0030] Z i is the noise value of the i-th pixel, and Z i represents the noise value of each pixel in the current obstetric image;

[0031] Z avg is the average pixel noise, and Z avg represents the average degree of noise of all pixels in the current obstetric image;

[0032] calculates the variance of the noise in the current obstetric image. The larger the variance, the higher the noise level;

[0033] D is the current frame image;

[0034] D ref is the reference frame image, and D ref represents the obstetric image one frame before and one frame after the current obstetric image;

[0035] calculates the difference between the current frame image D and the reference frame image D ref . The larger the difference, the higher the degree of motion blur;

[0036] T lost is the amount of lost features, and T lost reflects the number of key anatomical features lost in the current obstetric image;

[0037] T total is the total amount of features, and T total reflects the total number of key anatomical features that should be included in the current obstetric image;

[0038] calculates the percentage of key anatomical features lost in the current obstetric image;

[0039] XJ detail is the image after detail enhancement processing;

[0040] XJ smooth is the image after smoothing processing;

[0041] XJ = (XJ det[il - XJ smooth ) 2 calculates the retention degree of detail information in the current obstetric image after detail enhancement processing.

[0042] Preferably, the calculation formula of the image processing enhancement effect unit is as follows:

[0043]

[0044] Where:

[0045] CZ is the processing effect enhancement index;

[0046] represents the direct influence of the image quality and clarity on the processing effect;

[0047] represents the negative influence of feature loss on the processing effect;

[0048]

[0049] Preferably, the calculation formula of the loop influence trigger unit is as follows:

[0050]

[0051] Where:

[0052] CF is the loop influence evaluation index;

[0053] represents the adjusted value of the processing effect enhancement index CZ after considering the influence of feature loss on the image quality evaluation index V;

[0054] represents the comprehensive negative influence degree of noise level and motion blur relative to detail retention; Considers the relative influence of image clarity Q in the proportional relationship between processing effect and image area YM.

[0055] Preferably, based on the results of the loop influence evaluation index CF and the processing effect enhancement index CZ, the adjustment processing of the noise level value ZS, the motion blur value YD, the feature loss value T, and the detail retention value XJ is as follows:

[0056] If the cycle influence evaluation index CF is within the cycle influence reference interval {CF l -CF h}, then the adjustment of the image processing strategy will not be triggered;

[0057] If the cycle influence evaluation index CF is lower than the minimum cycle influence evaluation index CF l , then the adjustment of the image processing strategy will be triggered. The specific adjustments of the image processing strategy include:

[0058] When the motion blur value YD is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, increase the intensity of the motion deblurring process to reduce the value of the motion blur value YD in order to restore the clear fetal structure;

[0059] When the feature loss value T is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, enhance the contrast and brightness of the current obstetric image to reduce the value of the feature loss value T in order to highlight and easily identify the key anatomical features of the fetus;

[0060] When neither the motion blur value YD nor the feature loss value T is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, increase the intensity of the detail enhancement process to increase the detail retention value XJ, and at the same time reduce the intensity of the noise filtering to reduce the noise level value ZS.

[0061] Preferably, the devices used in the image acquisition module include ultrasonic devices and MRI devices;

[0062] The devices used in the image processing module and the cycle influence evaluation module include an image processing workstation and image processing software;

[0063] The devices used in the output and diagnosis module include a display device.

[0064] Technical effects and advantages of the present invention:

[0065] In the present invention, through the image quality measurement unit, a comprehensive quantitative evaluation of the image quality is achieved. By integrating multiple key parameters, the overall quality and processing effect of the image can be more accurately reflected, thereby providing richer diagnostic information.

[0066] In the present invention, according to the calculation results of the enhancement effect unit and the cyclic influence trigger unit after image processing, personalized adjustment can be performed for different image characteristics. Among them, there are different adjustment strategies when the motion blur value YD and the feature loss value T are respectively the main contributing factors in the current obstetric image, and when neither the motion blur value YD nor the feature loss value T is the main contributing factor in the current obstetric image. This personalized adjustment strategy can ensure the optimization of the processing effect and reduce unnecessary noise and blur.

[0067] In the present invention, through iterative calculation and the cyclic influence mechanism, the changes in the image processing process can be dynamically reflected, which helps to detect and handle potential problems in a timely manner, thereby ensuring the stability and accuracy of the processing process. At the same time, this mechanism can also provide more accurate decision-making support, thereby improving the accuracy and reliability of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a method flow chart of the visualization obstetric image examination and processing method;

[0069] Figure 2 is a schematic diagram of the overall structure of the visualization obstetric image examination and processing method;

[0070] Figure 3 is a schematic diagram of the structure of the image processing module in the present invention;

[0071] Figure 4 is a schematic diagram of the trigger adjustment of the cyclic influence evaluation index CF in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0072] Now, the present invention will be further described in detail with reference to the accompanying drawings and preferred embodiments.

[0073] Refer to Figures 1-4 As shown, the present invention provides a technical solution: a visualization obstetric image examination and processing method, including an image acquisition module, an image processing module, a cyclic influence evaluation module, and an output and diagnosis module, characterized in that: the image processing module includes an image quality measurement unit, an enhancement effect unit after image processing, and a cyclic influence trigger unit;

[0074] The specific processing steps are as follows:

[0075] Step 1: Use the image acquisition module to collect and preliminarily process the current obstetric image, and transmit it to the image processing module;

[0076] Step 2: Use the image processing module to sequentially calculate and output the image quality evaluation index V, the processing effect enhancement index CZ, and the cyclic influence evaluation index CF;

[0077] Step 3: Based on the results of the cyclic influence evaluation index CF and using the cyclic influence evaluation module, trigger the adjustment of the imaging processing strategy according to the results of the processing effect enhancement index CZ;

[0078] Step 4: The output and diagnosis module outputs the adjusted imaging processing strategy and the adjusted current obstetric image;

[0079] The devices used in the image acquisition module include ultrasonic devices and MRI devices;

[0080] The devices used in the image processing module and the cyclic influence evaluation module include an image processing workstation and image processing software;

[0081] The devices used in the output and diagnosis module include a display device.

[0082] The method steps, modules, units, and devices used in the visualization obstetric image examination and processing method of this embodiment constitute a complete system, which can realize high-quality acquisition, processing, evaluation, and diagnosis of obstetric images. By continuously optimizing and adjusting the imaging processing method, the image quality and diagnosis accuracy can be further improved. More importantly, the result value of the cyclic influence trigger unit, the cyclic influence evaluation index CF, can cyclically influence the calculation process of the image quality evaluation index V in the image quality measurement unit, forming a closed-loop feedback system. This cyclic influence mechanism can more accurately reflect the dynamic changes in the actual application of the obstetric image examination and processing method, thereby providing more accurate decision-making support. And by continuously optimizing and adjusting the processing strategy, it can ensure that the image quality always remains in the best state, thereby improving the accuracy and reliability of prenatal diagnosis.

[0083] Refer to Figures 1-4 As shown, in this implementation scheme: The calculation formula of the image quality measurement unit is as follows:

[0084]

[0085] Among them:

[0086] V is the image quality evaluation index;

[0087] Q is the image clarity, and Q is used to measure the contrast between different tissues in the current obstetric image;

[0088] YM is the image area, and YM reflects the proportion of the fetal area in the total area in the current obstetric image;

[0089] ZS is the noise level value, and ZS reflects the background noise intensity in the current obstetric image;

[0090] YD is the motion blur value, and YD reflects the degree of blur in the current obstetric image caused by the movement of the fetus and the mother;

[0091] Let T be the feature loss value, which reflects the degree of loss of key anatomical features in the current obstetric image;

[0092] Let XJ be the detail retention value, which reflects the degree of detail information retention in the current obstetric image;

[0093] The image clarity Q is multiplied by the square root of the image area YM to emphasize the importance of clarity in image quality;

[0094] The combination of the feature loss value T and the calculation of the square root of the detail retention value XJ is aimed at reflecting the role of detail retention in compensating for feature loss;

[0095] The calculation formulas for the noise level value ZS, the motion blur value YD, the feature loss value T, and the detail retention value XJ are as follows:

[0096]

[0097] XJ = (XJ det[il - XJ smooth ) 2 ;

[0098] Where:

[0099] Let N be the total number of pixels, which reflects the total number of pixels in the current obstetric image;

[0100] Z i is the noise value of the i-th pixel, and Z i represents the noise value of each pixel in the current obstetric image;

[0101] Z avg is the average pixel noise value, and Z avg represents the average degree of noise of all pixels in the current obstetric image;

[0102] calculates the variance of the noise in the current obstetric image. The larger the variance, the higher the noise level;

[0103] Let D be the current frame image;

[0104] D ref is the reference frame image, and D ref represents the obstetric image one frame before and one frame after the current obstetric image;

[0105] calculates the difference between the current frame image D and the reference frame image D ref . The larger the difference, the higher the degree of motion blur;

[0106] T lost is the lost feature quantity, T lost reflects the number of key anatomical features lost in the current obstetric image;

[0107] T total is the total feature quantity, T total reflects the total number of key anatomical features that should be included in the current obstetric image;

[0108] What is calculated is the percentage of key anatomical feature loss in the current obstetric image;

[0109] XJ detail is the image after detail enhancement processing;

[0110] XJ smooth is the image after smoothing processing;

[0111] XJ = (XJ det[il - XJ smooth ) 2 What is calculated is the retention degree of detail information in the current obstetric image after detail enhancement processing.

[0112] In the algorithm of this embodiment, the image clarity Q measures the contrast between different tissues in the current obstetric image and is the basis for image quality assessment. In the formula, The multiplication of is aimed at emphasizing the importance of clarity in image quality and combining it with the area ratio to consider the overall performance of the image. The image area YM reflects the proportion of the fetal area in the total area of the image, which helps to evaluate the focusing degree of the image and the effectiveness of the information. In the formula, The multiplication of reflects the direct impact of the area ratio on image quality. The noise level value ZS and the motion blur value YD are both negative factors in image quality assessment, and after adding the noise level value ZS and the motion blur value YD as the denominator of aims at emphasizing their negative impact on image quality, and at the same time, by dividing by the product of clarity and area ratio, further highlighting their adverse effects;

[0113] The feature loss value T reflects the degree of loss of key anatomical features in the image, while is aimed at quantifying the relative impact of feature loss on image quality, and at the same time considering the compensation effect of detail retention on feature loss, while the detail retention value XJ measures the retention degree of detail information in the current obstetric image;

[0114] The image quality measurement unit in this embodiment can comprehensively consider multiple dimensions of image clarity, area ratio, noise level, motion blur, feature loss, and detail retention, thereby realizing a comprehensive quantitative evaluation of image quality. This helps to more accurately understand the overall quality of the image and provides a reliable basis for subsequent image processing.

[0115] Based on the level of the image quality evaluation index V, this algorithm unit can judge the quality performance of the image in different aspects, and then guide the formulation of image processing strategies. Among them, when the value of the image quality evaluation index V is low, it can adjust the key factors affecting quality, including increasing the intensity of clarity enhancement processing and reducing the intensity of noise filtering, etc.

[0116] By optimizing image quality, the image quality measurement unit helps to improve the accuracy in prenatal diagnosis. And clearer images, less noise and blur, and more complete retention of anatomical features will all contribute to more accurately judging the health status of the fetus during obstetric examinations.

[0117] Refer to Figures 1-4 As shown, in this implementation: the calculation formula of the enhanced effect unit after image processing is as follows:

[0118]

[0119] Where:

[0120] CZ is the enhanced index of the processing effect;

[0121] represents the direct impact of the image quality and clarity on the processing effect;

[0122] represents the negative impact of feature loss on the processing effect;

[0123] considers both the relative impact of the noise level on the processing effect and introduces the comprehensive effect of detail retention and motion blur.

[0124] In the algorithm of this embodiment, the image quality evaluation index V serves as the basis for the enhanced effect unit after image processing. The image quality evaluation index V reflects the original quality of the image. The image quality evaluation index V is multiplied by the square root of the image clarity Q to emphasize the importance of clarity in the processing effect. The feature loss value T is similar to the image quality measurement unit. The feature loss value T also represents the degree of loss of key anatomical features in the enhanced effect unit after image processing. The feature loss value T is divided by aims to quantify the relative impact of feature loss on the processing effect and consider the compensation effect of the image quality evaluation index V and the area ratio on feature loss;

[0125] The noise level value ZS in the image processing post-enhancement effect unit. When processing the noise level value ZS, the comprehensive effects of the detail retention value XJ and the motion blur value YD are considered. The noise level value ZS is divided by It aims to evaluate the relative impact of the noise level on the processing effect, and consider the compensation effect of detail retention on the noise level and the negative impact of motion blur on the noise level;

[0126] The processing effect enhancement index CZ value of this embodiment can intuitively reflect the improvement degree of the processing strategy on the image quality. By comparing the processing effect enhancement index CZ values under different processing strategies, it is possible to evaluate which strategy is more effective, thereby optimizing the processing flow. Specifically, when the processing effect enhancement index CZ value is low, it indicates that the current processing strategy has limited improvement effect on the image quality. At this time, according to the change trend of the processing effect enhancement index CZ value, the parameters and methods of the processing strategy can be adjusted to improve the processing effect, including if the processing effect enhancement index CZ value is mainly affected by the noise level, the intensity of noise filtering can be considered to be increased, and if it is mainly affected by feature loss, the intensity of detail enhancement processing can be considered to be increased;

[0127] This algorithm evaluates the processing effect, making the image processing post-enhancement effect unit contribute to a more reasonable allocation of medical resources. For images with higher quality, unnecessary processing steps and resource consumption can be reduced, and for images with lower quality, they can be preferentially processed and optimized.

[0128] Refer to Figures 1-4 As shown, in this implementation scheme: The calculation formula of the loop impact trigger unit is as follows:

[0129]

[0130] Where:

[0131] CF is the loop impact evaluation index;

[0132] Represents the adjusted value of the processing effect enhancement index CZ after considering the impact of feature loss on the image quality evaluation index V;

[0133] Represents the comprehensive negative impact degree of the noise level and motion blur relative to detail retention; Consider the relative impact of the image sharpness Q in the proportional relationship between the processing effect and the image area YM.

[0134] In the algorithm of this embodiment, the processing effect enhancement index CZ serves as the basis of the loop impact trigger unit. The processing effect enhancement index CZ reflects the enhancement effect of the image processing method. The processing effect enhancement index CZ and Calculate the partial product, aiming to emphasize the adjusted value of the processing effect after considering the influence of feature loss. Among them, the noise level value ZS and the motion blur value YD are in the cyclic influence trigger unit. Perform the division calculation of the square root, aiming to evaluate the comprehensive negative impact of noise level and motion blur on detail retention. Finally, divide the image sharpness Q by Calculate the part, aiming to consider the relative influence of sharpness in the relationship between processing effect and image area ratio;

[0135] The cyclic influence evaluation index CF value of this embodiment can cyclically influence the calculation process of the image quality evaluation index V, forming a continuous feedback mechanism. This helps to timely discover problems in the processing strategy and make adjustments, and ensures that the processing effect always remains in the best state. By iteratively calculating the cyclic influence evaluation index CF value, it is possible to more accurately understand the long-term influence of the processing strategy on image quality, which helps to formulate a more reasonable processing strategy and avoid the negative impact of short-term optimization measures on long-term effects;

[0136] The cyclic influence mechanism of this embodiment can enhance the stability of the entire evaluation system. Even if some unforeseen problems and changes occur during the processing, the system can maintain the stability and optimization of the overall performance through iterative calculation and adjustment.

[0137] Refer to Figures 1-4 As shown, in this implementation: The image processing module stores and summarizes the processing effect enhancement index CZ and the cyclic influence evaluation index CF, and classifies and stores the final values of the processing effect enhancement index CZ and the cyclic influence evaluation index CF of different pregnancy periods for which obstetric image examinations have been completed, forming a cyclic influence reference interval {C feature loss value T - CF h} and a processing effect enhancement interval {CZ l - CZ h};

[0138] Among them, CF l is the lowest cyclic influence evaluation index, CF h is the highest cyclic influence evaluation index, CZ l is the lowest processing effect enhancement index, and CZ h is the highest processing effect enhancement index;

[0139] Based on the results of the cyclic influence evaluation index CF and the processing effect enhancement index CZ, the adjustment processing of the noise level value ZS, the motion blur value YD, the feature loss value T, and the detail retention value XJ is as follows:

[0140] If the cyclic influence evaluation index CF is within the cyclic influence reference interval {CF l - CF h}, the adjustment of the image processing strategy will not be triggered;

[0141] If the cycle impact evaluation index CF is lower than the minimum cycle impact evaluation index CF l , the adjustment of the image processing strategy will be triggered. The specific adjustments to the image processing strategy include:

[0142] When the motion blur value YD is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, increase the intensity of the motion deblurring process to reduce the value of the motion blur value YD and restore the clear fetal structure;

[0143] When the feature loss value T is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, increase the contrast and brightness of the current obstetric image to reduce the value of the feature loss value T and highlight and make it easier to identify the key anatomical features of the fetus;

[0144] When neither the motion blur value YD nor the feature loss value T is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, increase the intensity of the detail enhancement process to increase the detail retention value XJ, and at the same time reduce the intensity of the noise filtering to reduce the noise level value ZS.

[0145] In this embodiment, by iteratively calculating the value of the cycle impact evaluation index CF and feeding it back into the calculation process of the image quality evaluation index V, the cycle impact trigger unit can continuously optimize the evaluation result of the image quality. This helps to more accurately understand the quality performance of the image at different processing stages and provides a more reliable basis for formulating subsequent processing strategies. Since the value of the cycle impact evaluation index CF can reflect the long-term impact of the processing strategy on the image quality, the cycle impact trigger unit can help formulate more adaptable processing strategies. These strategies can be adjusted and optimized according to the changes in the image quality at different stages to ensure that the processing effect always meets the clinical requirements. By introducing the cycle impact mechanism, the cycle impact trigger unit can enhance the overall performance of the entire obstetric image examination and processing method;

[0146] In addition, by classifying and storing the final values of the processing effect enhancement index CZ and the cycle impact evaluation index CF for different pregnancy periods of the completed obstetric image examinations, a cycle impact reference interval {CF l -CF h} and a processing effect enhancement interval {CZ l -CZ hThrough continuous adjustment and optimization, the obstetric images can be made clearer, with richer details, lower noise, and less motion blur, thereby improving the diagnostic value of the images. High-quality images help to more accurately identify the structures and abnormalities of the fetus, thus reducing the risks of misdiagnosis and missed diagnosis. Clear images and accurate diagnostic results can enhance patients' satisfaction and trust in medical services. Through continuous iteration and optimization of the feedback loop, it can promote the development and innovation of obstetric image processing technology and provide better support and services for clinical practice;

[0147] In summary, the final values of the processing effect enhancement index CZ and the cyclic influence assessment index CF for different gestational periods of completed obstetric image examinations have been classified and stored, forming the cyclic influence reference interval {CF l -CF h} and the processing effect enhancement interval {CZ l -CZ h}, as well as the feedback loop formed by adjusting the examination processing method, which not only improves the image quality, reduces the risks of misdiagnosis and missed diagnosis, but also enhances patients' satisfaction and promotes the development of technology.

[0148] It should be noted that any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall also fall within the protection scope of the present invention.

Claims

1. A visual obstetric image examination processing method, comprising an image acquisition module, an image processing module, a circulatory impact assessment module and an output and diagnosis module, characterized in that: The image processing module includes an image quality measurement unit, an image processing enhancement effect unit, and a cyclic impact trigger unit; The specific processing steps are as follows: Step 1: using the image acquisition module to collect and preliminarily process the current obstetric image, and transmit it to the image processing module; Step 2: using the image processing module, sequentially calculating the output image quality evaluation index V, the processing effect enhancement index CZ and the circulation impact evaluation index CF; Step 3: Based on the result of the cyclic impact evaluation index CF, and using the cyclic impact evaluation module, trigger the adjustment of the image processing strategy according to the result of the processing effect enhancement index CZ; Step 4: The output and diagnosis module outputs the adjusted image processing strategy and the adjusted current obstetric image.

2. A visual obstetric image examination processing method according to claim 1, characterized in that: The image processing module stores and summarizes the treatment effect enhancement index CZ and the circulatory impact assessment index CF, and classifies and stores the final values ​​of the treatment effect enhancement index CZ and the circulatory impact assessment index CF of different gestational periods that have completed obstetric imaging examinations to form a circulatory impact reference interval {CF l -CF h } and the processing effect enhancement interval {CZ l -CZ h }; Among them, CF l The minimum index for the circular impact assessment, CF h The highest index for circular impact assessment, CZ l The lowest index for enhancing the treatment effect, CZ h Enhances the highest index for processing effect.

3. A visual obstetric image examination processing method according to claim 2, characterized in that: The calculation formula for measuring the image quality unit is as follows: in: V is the image quality assessment index; Q is image clarity, which is used to measure the contrast between different tissues in current obstetric images; YM is the image area, which reflects the proportion of the fetal area to the total area in the current obstetric image; ZS is the noise level value, which reflects the background noise intensity in the current obstetric image; YD is the motion blur value, which reflects the blur degree in the current obstetric image caused by the movement of the fetus and the mother; T is the feature loss value, which reflects the degree of loss of key anatomical features in current obstetric images; XJ is the detail retention value, which reflects the degree of detail information retention in the current obstetric image; The image clarity Q is multiplied by the image area YM under the square root, which is intended to emphasize the importance of clarity in image quality; The feature loss value T is combined with the calculation of the detail retention value XJ under the square root, aiming to reflect the role of detail retention in compensating for feature loss.

4. A method for visualizing obstetric imaging examination and processing according to claim 3, characterized in that: The calculation formulas of the noise level value ZS, motion blur value YD, feature loss value T and detail retention value XJ are as follows: XJ=(XJ det[il -XJ smooth ) 2 ; in: N is the total number of pixels, and N reflects the total number of pixels in the current obstetric image; Z i is the noise value of the ith pixel, Z i Represents the noise value of each pixel in the current obstetric image; Z avg is the average pixel noise, Z avg It indicates the average degree of all pixel noise in the current obstetric image; The variance of the noise in the current obstetric image is calculated. The larger the variance, the higher the noise level; D is the current frame image; D ref is the reference frame image, D ref Indicates obstetric images one frame before and one frame after the current obstetric image; The calculation is the current frame image D and the reference frame image D ref The difference between them, the larger the difference, the higher the degree of motion blur; T lost is the missing feature quantity, T lost Reflects the number of key anatomical features missing in current obstetric imaging; T total is the total feature quantity, T total Reflect the total number of key anatomical features that should be included in current obstetric imaging; The percentage of key anatomical features missing in current obstetric imaging was calculated; XJ detail This is the image after detail enhancement processing; XJ smooth is the image after smoothing; XJ=(XJ det[il -XJ smooth ) 2 What is calculated is the degree of retention of detail information in the current obstetric image after detail enhancement processing.

5. The method for visualizing obstetric imaging examination according to claim 3, characterized in that: The calculation formula of the image processing enhancement effect unit is as follows: in: CZ is the treatment effect enhancement index; Indicates the direct impact of image quality and clarity on processing results; Indicates the negative impact of feature loss on the processing effect; It not only considers the relative influence of noise level in the processing effect, but also introduces the combined effect of detail preservation and motion blur.

6. A method for visualizing obstetric imaging examination and processing according to claim 5, characterized in that: The calculation formula of the cycle impact trigger unit is as follows: in: CF is the cycle impact assessment index; It represents the adjusted value of the processing effect enhancement index CZ after considering the influence of feature loss on the image quality evaluation index V; Indicates the combined negative impact of noise level and motion blur on detail preservation; Consider the relative influence of image clarity Q in the proportional relationship between processing effect and image area YM.

7. A method for visualizing obstetric imaging examination and processing according to claim 6, characterized in that: Based on the results of the cycle impact evaluation index CF and the processing effect enhancement index CZ, the adjustment process of the noise level value ZS, the motion blur value YD, the feature loss value T and the detail retention value XJ is as follows: If the circulatory impact assessment index CF is within the circulatory impact reference interval {CF l -CF h }, the adjustment of the image processing strategy will not be triggered; If the CF is lower than the minimum CF l , then the trigger process adjusts the image processing strategy. The specific image processing strategy adjustments include: When the motion blur value YD is a major contributing factor in the current obstetric images and the value of the processing effect enhancement index CZ is low, the intensity of the motion deblurring process is increased to reduce the value of the motion blur value YD so as to restore a clear fetal structure; When the feature loss value T is a major contributing factor in the current obstetric image and the value of the processing effect enhancement index CZ is low, the contrast and brightness of the current obstetric image are enhanced to reduce the value of the feature loss value T, so as to highlight and easily identify key anatomical features of the fetus; When the motion blur value YD and the feature loss value T are not the main contributing factors in the current obstetric images, and the value of the processing effect enhancement index CZ is low, the intensity of the detail enhancement processing is increased to improve the detail retention value XJ, and the intensity of the noise filtering is reduced to reduce the noise level value ZS.

8. The method for visualizing obstetric imaging examination and processing according to claim 1, characterized in that: The equipment used in the image acquisition module includes ultrasound equipment and MRI equipment; The equipment used by the image processing module and the circulation impact assessment module includes an image processing workstation and image processing software; The devices used by the output and diagnosis module include a display device.

Images