Image filtering enhancement method for heart magnetic resonance image

Abstract

The invention belongs to the technical field of image data processing, and particularly relates to an image filtering enhancement method for a cardiac magnetic resonance image, and the method comprises the steps: carrying out the filtering processing of a cardiac magnetic resonance original image, and obtaining a preprocessed image; a connected domain of the preprocessed image is extracted according to a K-means clustering algorithm, and an enhancement index of the connected domain is acquired; according to the enhancement indexes of the connected domains, combining two adjacent connected domains belonging to the same tissue organ to obtain a to-be-enhanced image region; acquiring an image enhancement coefficient of the to-be-enhanced image region; and performing regional image enhancement on the preprocessed image according to the image enhancement coefficient of the to-be-enhanced image region. According to the method, the enhancement coefficient of each region can be calculated in combination with the actual demand of image enhancement and the features of each region, and different regions of the image are enhanced by adopting different enhancement coefficients, so that key parts of the image are clearer and distinguishable, and doctors are better assisted in disease prevention and treatment.

Description

Technical Field

[0001] The present invention belongs to the technical field of image data processing, and in particular relates to an image filtering and enhancement method for cardiac magnetic resonance images. Background Art

[0002] Cardiovascular magnetic resonance imaging is a non-invasive medical imaging technology that evaluates the function and structure of the cardiovascular system. It uses the basic principles of magnetic resonance imaging to optimize the existing MRI (Magnetic Resonance Imaging) imaging technology to make it clinically valuable in view of the special difficulties in imaging the cardiovascular system. In the clinical diagnosis of cardiovascular diseases, CMR (Cardiac Magnetic Resonance) can play a great role.

[0003] However, under existing technical conditions, after medical images are acquired, a single enhancement coefficient is often used to perform a uniform linear enhancement transformation on the entire image area. This method lacks targeted enhancement processing for key organs and tissues, and is prone to enhancing interference information. It often enhances unnecessary organ tissues and other irrelevant pixels, and the effect is not ideal. Summary of the invention

[0004] In order to solve the above problems, the present disclosure provides an image filtering and enhancement method for cardiac magnetic resonance images, the method comprising:

[0005] Performing filtering on the original cardiac magnetic resonance image to obtain a preprocessed image;

[0006] Extracting the connected domain of the preprocessed image according to the K-means clustering algorithm, and obtaining an enhancement index of the connected domain;

[0007] According to the enhancement index of the connected domain, two adjacent connected domains belonging to the same tissue organ are merged to obtain an image region to be enhanced;

[0008] Acquire an image enhancement coefficient of the image area to be enhanced;

[0009] The pre-processed image is enhanced by region according to the image enhancement coefficient of the image region to be enhanced.

[0010] Optionally, the acquiring the enhancement index of the connected domain includes:

[0011] Obtaining a first average grayscale value of pixels in the connected domain, a region area of ​​the connected domain, and a variance of grayscale values ​​of all pixels in the connected domain;

[0012] Obtaining a second average grayscale value of an adjacent connected domain of the connected domain;

[0013] An enhancement index of the connected domain is obtained according to the first average gray value, the second average gray value, the region area, and the variance.

[0014] Optionally, acquiring the enhancement index of the connected domain according to the first average gray value, the second average gray value, the region area and the variance comprises the following formula:

[0015]

[0016] Among them, Z D is the enhancement index of the connected domain, is the first average grayscale, is the second average grayscale, a D is the area of ​​the connected domain, S D is the variance of the grayscale values ​​of all pixels in the connected domain, X is the number of the adjacent connected domain of D connected domain, and E is the total number of connected domains.

[0017] Optionally, merging two adjacent connected domains belonging to the same tissue organ according to the enhancement index of the connected domain to obtain the image region to be enhanced includes:

[0018] Obtaining a merging coefficient of the two adjacent connected domains that belong to the same tissue organ and need to be merged;

[0019] Normalizing the merging coefficient to obtain a merging probability;

[0020] According to the merging probability, the two adjacent connected domains belonging to the same tissue organ are merged to obtain the image region to be enhanced.

[0021] Optionally, the step of obtaining a merging coefficient of two adjacent connected domains that belong to the same tissue organ and need to be merged comprises the following formula:

[0022]

[0023] Among them, P 12 is the merging coefficient of two adjacent connected domains, is the absolute value of the grayscale difference between two adjacent connected domains, |Z1-Z2| is the absolute value of the enhancement index difference between two adjacent connected domains, a1 and a2 are the areas of two adjacent connected domains, d 12 is the distance between the two closest points in two adjacent connected domains.

[0024] Optionally, merging the two adjacent connected domains belonging to the same tissue organ according to the merging probability to obtain the image region to be enhanced includes:

[0025] When the merging probability is greater than a first threshold, determining that the two adjacent connected domains belong to the same tissue organ, and merging the two adjacent connected domains;

[0026] The merging process is repeatedly performed to obtain the image region to be enhanced.

[0027] Optionally, obtaining the image enhancement coefficient of the image area to be enhanced includes:

[0028] Acquire an enhancement index of the image area to be enhanced;

[0029] According to the enhancement index of the image area to be enhanced, an image enhancement coefficient of the image area to be enhanced is obtained.

[0030] Optionally, obtaining an enhancement index of the image area to be enhanced includes:

[0031] The average value of the enhancement indices of the two adjacent connected domains is used as the enhancement index of the image region to be enhanced.

[0032] Optionally, acquiring the image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced includes:

[0033] Acquiring an initial image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced;

[0034] The initial image enhancement coefficient is adjusted in a mapping interval to obtain the image enhancement coefficient of the image area to be enhanced.

[0035] Optionally, acquiring the initial image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced comprises the following formula:

[0036]

[0037] Among them, k H is the initial image enhancement coefficient, n is the upper boundary of the initial image enhancement coefficient mapping interval, Z H is the enhancement index of the image area to be enhanced, Z min is the minimum value of the enhancement index of the image area to be enhanced, Z max It is the maximum value of the enhancement index of the image area to be enhanced.

[0038] Optionally, the performing mapping interval adjustment on the initial image enhancement coefficient to obtain the image enhancement coefficient of the image area to be enhanced includes:

[0039] Acquire a first area of ​​the image region to be enhanced where the initial image enhancement coefficient is greater than 1;

[0040] Acquire a ratio of the first area to the total area of ​​the preprocessed image;

[0041] The upper boundary of the initial image enhancement coefficient mapping interval is adjusted so that the ratio is located between a second threshold and a third threshold, and the image enhancement coefficient of the image area to be enhanced is obtained, wherein the second threshold is less than the third threshold.

[0042] In summary, the disclosed embodiment provides an image filtering and enhancement method for cardiac magnetic resonance images, the method comprising: filtering the original cardiac magnetic resonance image to obtain a preprocessed image; extracting the connected domain of the preprocessed image according to the K-means clustering algorithm to obtain the enhancement index of the connected domain; merging two adjacent connected domains belonging to the same tissue organ according to the enhancement index of the connected domain to obtain the image region to be enhanced; obtaining the image enhancement coefficient of the image region to be enhanced; and performing regional image enhancement on the preprocessed image according to the image enhancement coefficient of the image region to be enhanced. The disclosed embodiment can extract the connected domain of the image according to the result obtained by the K-means clustering algorithm, and calculate the enhancement coefficient of each region in combination with the actual needs of image enhancement and the characteristics of each region, and use different enhancement coefficients to enhance different regions of the image, so that the key parts of the image are clearer and more distinguishable, and better assist doctors in the prevention and treatment of diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the implementation scheme of the present disclosure, the drawings required for use in the implementation scheme will be briefly introduced below. It should be understood that the drawings only show certain implementation schemes of the present disclosure and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on the drawings without paying creative work.

[0044] Figure 1 The figure is a flow chart showing a method for image filtering and enhancement of cardiac magnetic resonance images according to an exemplary embodiment.

[0045] Figure 2 It is a schematic diagram showing a connected domain of a pre-processed image extracted according to a K-means clustering algorithm according to an exemplary embodiment.

[0046] Figure 3 The figure is a schematic diagram of a cardiac magnetic resonance image after regional image enhancement according to an exemplary embodiment.

[0047] Figure 4The figure is a flow chart of an image filtering and enhancing method for cardiac magnetic resonance images according to a first exemplary embodiment.

[0048] Figure 5 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a second exemplary embodiment.

[0049] Figure 6 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a third exemplary embodiment.

[0050] Figure 7 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a fourth exemplary embodiment.

[0051] Figure 8 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a fifth exemplary embodiment.

[0052] Fig. 9 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a sixth exemplary embodiment.

[0053] Fig.10 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a seventh exemplary embodiment. DETAILED DESCRIPTION

[0054] In order to clearly illustrate the technical features of the present solution, the present disclosure is described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0055] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0056] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0057] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0058] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0059] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly indicated in the context, they should be understood as "one or more". In the description of the present disclosure, unless otherwise specified, "multiple" refers to two or more than two, and other quantifiers are similar; "at least one item", "one or more items" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one item a can represent any number of a; for another example, one or more items of a, b and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple; "and / or" is a kind of association relationship that describes the associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0060] Although operations or steps are described in a specific order in the drawings in the embodiments of the present disclosure, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or to perform all the operations or steps shown to obtain the desired results. In the embodiments of the present disclosure, these operations or steps can be performed in series; these operations or steps can also be performed in parallel; or some of these operations or steps can be performed.

[0061] At the same time, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws and regulations and relevant provisions. The present disclosure is described below in conjunction with specific embodiments.

[0062] First, the application scenario of the present disclosure is described. In the prior art, when performing linear enhancement on medical images, only a single enhancement coefficient can be used to enhance the entire image. In this way, when using traditional image linear enhancement methods, unnecessary tissues and organs and other irrelevant pixels are often enhanced together, and the image that needs to be focused on cannot be clearly presented, resulting in unsatisfactory image enhancement effects.

[0063] In response to the above problems, the embodiments of the present disclosure perform connected domain extraction and analysis on cardiac magnetic resonance images based on the K-means clustering algorithm. By calculating the grayscale distribution of the connected domain, the grayscale difference with the adjacent regions and the regional area elements, targeted enhancement indicators are obtained, the partitions are optimized according to the actual situation, and a reasonable indicator mapping range is calculated. The enhancement coefficients of each region in the image are adaptively obtained, and different enhancement coefficients are used to enhance different regions of the image, so that the key parts of the image are clearer and more distinguishable, which can better assist doctors in disease prevention and treatment.

[0064] Figure 1 FIG. 1 is a flow chart showing a method for image filtering and enhancement of cardiac magnetic resonance images according to an exemplary embodiment. Figure 1 As shown, the embodiment of the present disclosure provides an image filtering enhancement method for cardiac magnetic resonance images, and the method may include the following steps:

[0065] In step S10, filtering is performed on the original cardiac magnetic resonance image to obtain a preprocessed image.

[0066] In this step, the original cardiac magnetic resonance image is filtered to obtain a pre-processed image. Exemplarily, the cardiac region magnetic resonance image obtained from the magnetic resonance device can be grayed and filtered to remove noise to obtain the pre-processed image.

[0067] In step S20, a connected domain of the preprocessed image is extracted according to a K-means clustering algorithm to obtain an enhancement index of the connected domain.

[0068] In this step, the connected domain of the preprocessed image is extracted according to the K-means clustering algorithm to obtain the enhancement index of the connected domain. Figure 2 FIG. 1 is a schematic diagram showing a connected domain of a pre-processed image extracted according to a K-means clustering algorithm according to an exemplary embodiment. Figure 2As shown in the figure, in order to enhance the key connected areas of the image and improve the image contrast, the connected areas to be enhanced need to meet the following conditions: (1) there is a small grayscale difference between the area and the adjacent areas; (2) the area of ​​the area is small (when the area of ​​a certain area is too small, failure to enhance it may result in unclear key information); (3) the grayscale value distribution in the area is uniform (areas with uniform grayscale distribution can better express the detailed information in the area by giving them a larger enhancement coefficient).

[0069] Exemplarily, the first average grayscale value of the pixels in the connected domain, the area of ​​the connected domain, and the variance of the grayscale values ​​of all the pixels in the connected domain can be obtained, and then the second average grayscale value of the adjacent connected domain of the connected domain can be obtained, and then the enhancement index of the connected domain can be obtained based on the first average grayscale value, the second average grayscale value, the area and the variance.

[0070] In step S30, two adjacent connected domains belonging to the same tissue organ are merged according to the enhancement index of the connected domain to obtain an image region to be enhanced.

[0071] In this step, two adjacent connected domains belonging to the same tissue organ are merged according to the enhancement index of the connected domain to obtain the image region to be enhanced. Exemplarily, the merging coefficient of the two adjacent connected domains belonging to the same tissue organ and needing to be merged can be obtained, and then the merging coefficient can be normalized to obtain the merging probability, and then the two adjacent connected domains belonging to the same tissue organ are merged according to the merging probability to obtain the image region to be enhanced.

[0072] In step S40, an image enhancement coefficient of the image area to be enhanced is obtained.

[0073] In this step, the image enhancement coefficient of the image region to be enhanced is obtained. Exemplarily, the image enhancement coefficient of the image region to be enhanced can be obtained by obtaining an enhancement index of the image region to be enhanced, and then obtaining the image enhancement coefficient of the image region to be enhanced according to the enhancement index of the image region to be enhanced.

[0074] In step S50, the pre-processed image is enhanced by region according to the image enhancement coefficient of the image region to be enhanced.

[0075] In this step, the pre-processed image is enhanced by region according to the image enhancement coefficient of the image region to be enhanced. For example, by performing region enhancement with different enhancement coefficients on different regions of the pre-processed image, the key parts of the image can be made clearer and more distinguishable, so as to better assist doctors in the prevention and treatment of diseases. Figure 3FIG. 1 is a schematic diagram of a cardiac magnetic resonance image after regional image enhancement according to an exemplary embodiment. Figure 3 As shown, it can be seen that the clarity of the cardiac magnetic resonance image after regional image enhancement using different enhancement coefficients is significantly improved.

[0076] In summary, the disclosed embodiment provides an image filtering and enhancement method for cardiac magnetic resonance images, the method comprising: filtering the original cardiac magnetic resonance image to obtain a preprocessed image; extracting the connected domain of the preprocessed image according to the K-means clustering algorithm to obtain the enhancement index of the connected domain; merging two adjacent connected domains belonging to the same tissue organ according to the enhancement index of the connected domain to obtain the image region to be enhanced; obtaining the image enhancement coefficient of the image region to be enhanced; and performing regional image enhancement on the preprocessed image according to the image enhancement coefficient of the image region to be enhanced. The disclosed embodiment can extract the connected domain of the image according to the result obtained by the K-means clustering algorithm, and calculate the enhancement coefficient of each region in combination with the actual needs of image enhancement and the characteristics of each region, and use different enhancement coefficients to enhance different regions of the image, so that the key parts of the image are clearer and more distinguishable, which can better assist doctors in the prevention and treatment of diseases.

[0077] Figure 4 FIG. 1 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a first exemplary embodiment. Figure 4 As shown, the obtaining of the enhancement index of the connected domain may include the following steps:

[0078] In step S201, a first average grayscale value of pixels in the connected domain, a region area of ​​the connected domain, and a variance of grayscale values ​​of all pixels in the connected domain are obtained.

[0079] In this step, the first average gray value of the pixels in the D connected domain is obtained. The area of ​​the connected domain is a D And the variance S of the grayscale values ​​of all pixels in the connected domain D .

[0080] In step S202, a second average grayscale value of adjacent connected domains of the connected domain is obtained.

[0081] In this step, the second average gray value of the adjacent connected domain of the D connected domain is obtained.

[0082] In step S203, an enhancement index of the connected domain is obtained according to the first average gray value, the second average gray value, the region area and the variance.

[0083] In this step, according to the first average gray value The second average gray value Area D and variance S D , get the enhanced index Z of the connected domain of D D .

[0084] In some embodiments, according to the first average gray value The second average gray value The area a D and the variance S D , get the enhanced index Z of the connected domain of D D , which can include the following formula:

[0085]

[0086] Among them, Z D is the enhancement index of the connected domain, is the first average grayscale, is the second average grayscale, a D is the area of ​​the connected domain, S D is the variance of the grayscale values ​​of all pixels in the connected domain, X is the number of the adjacent connected domain of D connected domain, and E is the total number of connected domains.

[0087] In the above formula, It represents the minimum value of the grayscale difference between the connected domain D and other adjacent connected domains. When there are adjacent areas with small grayscale value differences, The minimum value of the gray value difference can be obtained, which is not affected by other areas with large gray value differences. The smaller the gray value difference, the better the enhancement index Z. D The larger the The increase of value enhances the index Z D The less affected; D The smaller the area, the smaller the area. The larger the value, the corresponding enhancement index Z D The larger the area, the stronger the index Z D The smaller the impact; grayscale variance S D The smaller it is, the more uniform the grayscale value distribution of pixels in the area is. D 2 +1) The larger the value, the corresponding enhancement index Z D The larger the S D The increase of the index Z D The greater the impact.

[0088] Figure 5FIG. 1 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a second exemplary embodiment. Figure 5 As shown, merging two adjacent connected domains belonging to the same tissue organ according to the enhancement index of the connected domain to obtain the image region to be enhanced may include the following steps:

[0089] In step S301, the merging coefficient of the two adjacent connected domains that belong to the same tissue organ and need to be merged is obtained.

[0090] In this step, the merging coefficient P of two adjacent connected domains that belong to the same tissue organ and need to be merged is obtained. 12 . For example, in order to ensure that the same organ region has the same enhancement coefficient on the basis of a small gray value difference, so that the enhanced image is clearer, it is necessary to further calculate the enhancement index of each connected domain obtained. The same organ region should meet the following conditions: (1) The connected domains belonging to the tissue organ are adjacent (two unconnected regions must not belong to the same organ); (2) There are differences in gray values ​​in different parts of the same organ in the magnetic resonance image. The difference must be a small difference. Two regions with too large a difference cannot belong to the same organ. Therefore, the gray values ​​in the two connected domains should be similar; (3) The indicators of the same organ region should all be small. Therefore, the enhancement indexes calculated for the two connected domains belonging to the same organ should be similar; (4) In the image, ordinary tissue regions usually appear as connected domains with larger areas. To ensure that the enhancement coefficient of ordinary tissue regions does not change during processing, the area of ​​the two connected domains should not be too large before merging.

[0091] In some embodiments, the step of obtaining the merging coefficient P of the two adjacent connected domains belonging to the same tissue organ and needing to be merged is as follows: 12 , which can include the following formula:

[0092]

[0093] Among them, P 12 is the merging coefficient of two adjacent connected domains, is the absolute value of the grayscale difference between two adjacent connected domains, |Z1-Z2| is the absolute value of the enhancement index difference between two adjacent connected domains, a1 and a2 are the areas of two adjacent connected domains, respectively, and d 12 is the distance between the two closest points in two adjacent connected domains.

[0094] In the above formula, Represents the gray value difference between two connected domains. The smaller the value, the closer the gray values ​​between the two regions are. The merging coefficient P of the two connected domains needs to be merged. 12 The larger the The value increases, the merging coefficient P12 The amplitude of the change is getting smaller and smaller; |Z1-Z2| represents the difference in the enhancement index between the two connected domains. The smaller the value, the closer the enhancement index between the two connected domains is, and the merging coefficient P of the two connected domains needs to be merged. 12 The larger the value of |Z1-Z2| is, the larger the merging coefficient P is. 12 The amplitude of the change becomes smaller and smaller; the larger the area of ​​the two connected domains, and The smaller the value, the more the merging coefficient P of the two connected domains needs to be merged. 12 The larger the value, the greater the 12 ≠0, that is, when the two connected domains have no connected parts, the merging coefficient P of the two connected domains needs to be merged 12 is 0.

[0095] In step S302, the merging coefficient is normalized to obtain a merging probability.

[0096] In this step, the merging coefficient P 12 Normalize it and map it to the interval [0,1] to get the merge probability P' 12 .

[0097] In step S303, the two adjacent connected domains belonging to the same tissue organ are merged according to the merging probability to obtain the image region to be enhanced.

[0098] In this step, according to the merging probability P' 12 , merge two adjacent connected domains belonging to the same tissue organ to obtain the image area to be enhanced.

[0099] Figure 6 FIG. 4 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a third exemplary embodiment. Figure 6 As shown, merging the two adjacent connected domains belonging to the same tissue organ according to the merging probability to obtain the image region to be enhanced may include the following steps:

[0100] In step S3031, when the merging probability is greater than the first threshold, it is determined that the two adjacent connected domains belong to the same tissue organ, and the two adjacent connected domains are merged.

[0101] In this step, the merge probability P' 12 When the value is greater than the first threshold, it is determined that the two adjacent connected domains belong to the same tissue organ, and the two adjacent connected domains are merged. For example, the first threshold may be 0.8.

[0102] In step S3032, the merging process is repeatedly performed to obtain the image area to be enhanced.

[0103] In this step, the above-mentioned merging process step S3031 is repeatedly performed until there is no mergeable region, and the image region to be enhanced can be obtained.

[0104] Figure 7 FIG. 4 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a fourth exemplary embodiment. Figure 7 As shown, the obtaining of the image enhancement coefficient of the image area to be enhanced may include the following steps:

[0105] In step S401, an enhancement index of the image area to be enhanced is obtained.

[0106] In this step, the enhancement index Z of the image area to be enhanced is obtained. H For example, the mean value of the enhancement indexes of the two adjacent connected domains can be used as the enhancement index Z of the image region to be enhanced. H .

[0107] In step S402, an image enhancement coefficient of the image region to be enhanced is obtained according to the enhancement index of the image region to be enhanced.

[0108] In this step, the image enhancement coefficient of the image region to be enhanced is obtained according to the enhancement index of the image region to be enhanced. H , obtain the initial image enhancement coefficient k of the image area to be enhanced H , and then the initial image enhancement coefficient k H A mapping interval adjustment is performed to obtain the image enhancement coefficient of the image area to be enhanced.

[0109] Figure 8 FIG. 4 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a fifth exemplary embodiment. Figure 8 As shown, the obtaining of the enhancement index of the image area to be enhanced may include the following steps:

[0110] In step S4011, the average value of the enhancement indices of the two adjacent connected domains is used as the enhancement index of the image region to be enhanced.

[0111] In this step, the average of the enhancement indexes of two adjacent connected domains is used as the enhancement index Z of the image area to be enhanced. H .

[0112] Fig. 9FIG. 4 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a sixth exemplary embodiment. Fig. 9 As shown, obtaining the image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced may include the following steps:

[0113] In step S4021, an initial image enhancement coefficient of the image region to be enhanced is obtained according to the enhancement index of the image region to be enhanced.

[0114] In this step, according to the enhancement index Z of the image area to be enhanced H , get the initial image enhancement coefficient k of the image area to be enhanced H .

[0115] In some embodiments, the enhancement index Z of the image area to be enhanced is H , obtain the initial image enhancement coefficient k of the image area to be enhanced H , which can include the following formula:

[0116]

[0117] Among them, k H is the initial image enhancement coefficient, n is the upper boundary of the initial image enhancement coefficient mapping interval, Z H is the enhancement index of the image area to be enhanced, Z min is the minimum value of the enhancement index of the image area to be enhanced, Z max It is the maximum value of the enhancement index of the image area to be enhanced.

[0118] In the above formula, the initial image enhancement coefficient k H The value range of is [0, n]. The upper boundary n of the initial image enhancement coefficient mapping interval is to be determined.

[0119] In step S4022, the mapping interval of the initial image enhancement coefficient is adjusted to obtain the image enhancement coefficient of the image area to be enhanced.

[0120] In this step, the initial image enhancement coefficient k H The mapping interval is adjusted to obtain the image enhancement coefficient of the image area to be enhanced. That is, a reasonable value of the upper boundary n of the initial image enhancement coefficient mapping interval is selected, so that the image enhancement coefficient of the image area to be enhanced can be obtained according to Formula 3.

[0121] Fig.10 FIG. 1 is a flow chart of an image filtering and enhancement method for cardiac magnetic resonance images according to a seventh exemplary embodiment. Fig.10As shown, the mapping interval adjustment of the initial image enhancement coefficient to obtain the image enhancement coefficient of the image area to be enhanced may include the following steps:

[0122] In step S40221, a first area of ​​the image region to be enhanced whose initial image enhancement coefficient is greater than 1 is obtained.

[0123] In this step, an initial n value is given, and then the first area A of the image region to be enhanced whose initial image enhancement coefficient is greater than 1 is obtained. LS .

[0124] In step S40222, the ratio of the first area to the total area of ​​the pre-processed image is obtained.

[0125] In this step, the first area A is obtained. LS The total area A of the preprocessed image T The ratio β.

[0126] In step S40223, the upper boundary of the initial image enhancement coefficient mapping interval is adjusted so that the ratio is located between a second threshold and a third threshold, and the image enhancement coefficient of the image area to be enhanced is obtained, wherein the second threshold is less than the third threshold.

[0127] In this step, a fixed step size may be used to adjust the upper boundary n of the initial image enhancement coefficient mapping interval. Exemplarily, the fixed step size may be 0.1, so that the ratio β is located between the second threshold and the third threshold. At this time, the value of n is determined, so that the image enhancement coefficient of the image area to be enhanced can be obtained by formula 3, wherein the second threshold is less than the third threshold. Exemplarily, the second threshold may be 0.3, and the third threshold may be 0.7.

[0128] For example, if the ratio β is less than 0.3, it can be considered that the image enhancement coefficient of the image region to be enhanced is generally too small, and the n value needs to be increased; if the ratio β is greater than 0.7, it can be considered that the image enhancement coefficient of the image region to be enhanced is generally too large, and the n value needs to be reduced. When the ratio β is in the interval [0.3, 0.7], it can be considered that the image enhancement coefficient of the image region to be enhanced is relatively appropriate.

[0129] In summary, the disclosed embodiment provides an image filtering and enhancement method for cardiac magnetic resonance images, the method comprising: filtering the original cardiac magnetic resonance image to obtain a preprocessed image; extracting the connected domain of the preprocessed image according to the K-means clustering algorithm to obtain the enhancement index of the connected domain; merging two adjacent connected domains belonging to the same tissue organ according to the enhancement index of the connected domain to obtain the image region to be enhanced; obtaining the image enhancement coefficient of the image region to be enhanced; and performing regional image enhancement on the preprocessed image according to the image enhancement coefficient of the image region to be enhanced. The disclosed embodiment can extract the connected domain of the image according to the result obtained by the K-means clustering algorithm, and calculate the enhancement coefficient of each region in combination with the actual needs of image enhancement and the characteristics of each region, and use different enhancement coefficients to enhance different regions of the image, so that the key parts of the image are clearer and more distinguishable, and better assist doctors in the prevention and treatment of diseases.

[0130] In another exemplary embodiment, the present disclosure further provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implements the steps of the image filtering and enhancement method for cardiac magnetic resonance images provided by the present disclosure.

[0131] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable electronic device, and the computer program has a code portion for executing the above-mentioned image filtering and enhancement method for cardiac magnetic resonance images when executed by the programmable electronic device.

[0132] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present disclosure. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. An image filtering and enhancement method for cardiac magnetic resonance images, characterized in that: The method comprises: Performing filtering on the original cardiac magnetic resonance image to obtain a preprocessed image; Extracting the connected domain of the preprocessed image according to the K-means clustering algorithm, and obtaining an enhancement index of the connected domain; According to the enhancement index of the connected domain, two adjacent connected domains belonging to the same tissue organ are merged to obtain an image region to be enhanced; Acquire an image enhancement coefficient of the image area to be enhanced; The pre-processed image is enhanced by region according to the image enhancement coefficient of the image region to be enhanced.

2. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 1, characterized in that: The obtaining of the enhancement index of the connected domain includes: Obtaining a first average grayscale value of pixels in the connected domain, a region area of ​​the connected domain, and a variance of grayscale values ​​of all pixels in the connected domain; Obtaining a second average grayscale value of an adjacent connected domain of the connected domain; An enhancement index of the connected domain is obtained according to the first average gray value, the second average gray value, the region area, and the variance.

3. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 2, characterized in that: The step of obtaining the enhancement index of the connected domain according to the first average gray value, the second average gray value, the region area, and the variance comprises the following formula: Among them, Z D is the enhancement index of the connected domain, is the first average grayscale, is the second average grayscale, a D is the area of ​​the connected domain, S D is the variance of the grayscale values ​​of all pixels in the connected domain, X is the number of the adjacent connected domain of D connected domain, and E is the total number of connected domains.

4. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 1, characterized in that: The step of merging two adjacent connected domains belonging to the same tissue organ according to the enhancement index of the connected domain to obtain the image region to be enhanced includes: Obtaining a merging coefficient of the two adjacent connected domains that belong to the same tissue organ and need to be merged; Normalizing the merging coefficient to obtain a merging probability; According to the merging probability, the two adjacent connected domains belonging to the same tissue organ are merged to obtain the image region to be enhanced.

5. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 4, characterized in that: The step of obtaining the merging coefficient of the two adjacent connected domains that belong to the same tissue organ and need to be merged includes the following formula: Among them, P 12 is the merging coefficient of two adjacent connected domains, is the absolute value of the grayscale difference between two adjacent connected domains, |Z1-Z2| is the absolute value of the enhancement index difference between two adjacent connected domains, a1 and a2 are the areas of two adjacent connected domains, d 12 is the distance between the two closest points in two adjacent connected domains.

6. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 4, characterized in that: The step of merging the two adjacent connected domains belonging to the same tissue organ according to the merging probability to obtain the image region to be enhanced includes: When the merging probability is greater than a first threshold, determining that the two adjacent connected domains belong to the same tissue organ, and merging the two adjacent connected domains; The merging process is repeatedly performed to obtain the image region to be enhanced.

7. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 1, characterized in that: The step of obtaining the image enhancement coefficient of the image area to be enhanced includes: Acquire an enhancement index of the image area to be enhanced; Acquiring an image enhancement coefficient of the image area to be enhanced according to an enhancement index of the image area to be enhanced; The average value of the enhancement indices of the two adjacent connected domains is used as the enhancement index of the image region to be enhanced.

8. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 7, characterized in that: The step of acquiring the image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced comprises: Acquiring an initial image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced; The initial image enhancement coefficient is adjusted in a mapping interval to obtain the image enhancement coefficient of the image area to be enhanced.

9. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 8, characterized in that: The step of obtaining the initial image enhancement coefficient of the image area to be enhanced according to the enhancement index of the image area to be enhanced comprises the following formula: Among them, k H is the initial image enhancement coefficient, n is the upper boundary of the initial image enhancement coefficient mapping interval, Z H is the enhancement index of the image area to be enhanced, Z min is the minimum value of the enhancement index of the image area to be enhanced, Z max It is the maximum value of the enhancement index of the image area to be enhanced.

10. The image filtering and enhancement method for cardiac magnetic resonance images according to claim 8, characterized in that: The step of adjusting the mapping interval of the initial image enhancement coefficient to obtain the image enhancement coefficient of the image area to be enhanced includes: Acquire a first area of ​​the image region to be enhanced where the initial image enhancement coefficient is greater than 1; Acquire a ratio of the first area to the total area of ​​the preprocessed image; The upper boundary of the initial image enhancement coefficient mapping interval is adjusted so that the ratio is located between a second threshold and a third threshold, and the image enhancement coefficient of the image area to be enhanced is obtained, wherein the second threshold is less than the third threshold.

Images