WO2021259390A2

WO2021259390A2 - Coronary artery calcified plaque detection method and apparatus

Info

Publication number: WO2021259390A2
Application number: PCT/CN2021/122142
Authority: WO
Inventors: 梁隆恺; 吴振洲; 刘盼
Original assignee: 北京安德医智科技有限公司
Priority date: 2021-04-16
Filing date: 2021-09-30
Publication date: 2021-12-30
Also published as: CN113034491A; WO2021259390A3; CN113034491B

Abstract

The present disclosure relates to a coronary artery calcified plaque detection method and apparatus. The method comprises: segmenting an image to be processed, and determining a plurality of target regions of a first organ in said image; for any target region, determining a first grayscale threshold value and a second grayscale threshold value of the target region according to grayscale information of the target region; respectively determining a suspected lesion region and a pseudo lesion region in the target region according to the first grayscale threshold value and the second grayscale threshold value of the target region; and determining a lesion region of the first organ according to the suspected lesion regions and pseudo lesion regions of the target regions. According to the embodiments of the present disclosure, not only can the omission of calcified plaque at small branch blood vessels of a coronary artery blood vessel in an image to be processed be effectively reduced, but the recall rate of calcified plaque is also improved, and the accuracy of the identification of calcified plaque can be significantly improved.

Description

Method and device for detecting coronary artery calcified plaque

Technical field

The present disclosure relates to the technical field of computer vision, and in particular to a method and device for detecting coronary calcified plaques.

Background technique

Cardiovascular disease is a disease that seriously endangers human health. Most cardiovascular diseases are caused by atherosclerotic plaques. Calcified plaque in the coronary arteries is a sign of the degree of atherosclerosis, which can predict the possibility of coronary artery disease in patients.

In clinical practice, coronary angiography images can be obtained by injecting contrast agents. However, due to the thickness of blood vessels, the distribution of contrast dose in the blood vessels is different, resulting in different gray values of calcified plaques.

Summary of the invention

In view of this, the present disclosure proposes a method and device for detecting coronary calcified plaque.

According to one aspect of the present disclosure, there is provided a lesion detection method, the method includes: segmenting an image to be processed, and determining multiple target regions of a first organ in the image to be processed; for any target region, according to The gray information of the target area determines the first gray threshold and the second gray threshold of the target area, the first gray threshold is greater than the second gray threshold; according to the first gray threshold of the target area A gray-level threshold and a second gray-level threshold respectively determine the suspected lesion area and the pseudo-lesion area in the target area; determine the lesion of the first organ according to the suspected lesion area and the pseudo-lesion area of each of the target areas area.

In a possible implementation manner, performing segmentation processing on the image to be processed and determining multiple target regions of the first organ in the image to be processed includes: segmenting the image to be processed and determining that the image is The organ area of the organ area includes a second organ and a first organ, and the size of the second organ is larger than the size of the first organ; classifying the organ area to obtain multiple classification areas; The first area of each first organ and the second area of the second organ are determined from the plurality of classification areas; according to the first area and the second area, the majority of the image to be processed is determined Target areas.

In a possible implementation, determining the first area of each first organ and the second area of the second organ from the multiple classification areas includes: calculating the number of pixels in the multiple classification areas The most classified area is determined as the second area; among the plurality of classified areas, the classified areas other than the second area are determined as the first area; wherein, according to the first area, A region and the second region, determining multiple target regions in the image to be processed, including: performing an expansion operation on the first region to obtain an expanded third region; from the third region , Removing the area overlapping with the second area to obtain a cropped area; performing crop processing on the image to be processed according to the cropped area to obtain the multiple target areas.

In a possible implementation manner, determining the first gray threshold value and the second gray threshold value of the target area according to the gray information of the target area includes: determining the gray value of pixels in the target area Sort, determine the gray value of the median as the second gray threshold; add the second gray threshold and a preset offset threshold to obtain the first gray threshold.

In a possible implementation manner, respectively determining the suspected lesion area and the pseudo lesion area in the target area according to the first gray threshold value and the second gray threshold value of the target area includes: according to the target area The first gray-scale threshold value of the target area is determined as the suspected lesion area; the area where the pixel in the target area has a gray value greater than the first gray-scale threshold value is determined as the suspected lesion area; according to the second gray-scale threshold value of the target area , Determining the area where the pixel in the target area has a gray value greater than the second gray threshold value as a fourth area, the fourth area includes a plurality of connected areas; the number of pixels in each connected area is greater than The connected area with the preset threshold is determined as the pseudo-focus area.

In a possible implementation manner, determining the lesion area of the first organ according to the suspected lesion area and the pseudo lesion area of each of the target areas includes: removing and The area where the pseudo lesion area overlaps is the lesion area of the first organ.

In a possible implementation, the image to be processed includes a cardiac medical image, the first organ includes coronary blood vessels, the second organ includes aortic blood vessels, and the target area includes a coronary blood vessel segment. Area, the lesion area includes a calcified plaque area.

According to one aspect of the present disclosure, there is provided a lesion detection device, which includes: a segmentation module for performing segmentation processing on an image to be processed, and determining multiple target regions of a first organ in the image to be processed; and a threshold module for For any target area, determine a first gray level threshold and a second gray level threshold of the target area according to gray level information of the target area, where the first gray level threshold is greater than the second gray level threshold; The suspected lesion and pseudo-lesion determination module is used to determine the suspected lesion area and the pseudo-lesion area in the target area according to the first gray threshold and the second gray threshold of the target area; the lesion determining module is used for Determine the lesion area of the first organ according to the suspected lesion area and the pseudo lesion area of each of the target areas.

In a possible implementation, the segmentation module includes: a segmentation sub-module: used to segment the image to be processed and determine the organ region in the image to be processed, the organ region including the second organ and the second organ An organ, the size of the second organ is greater than the size of the first organ; classification sub-module: used to classify the organ region to obtain multiple classification regions; the first region and the second region determination sub-module: It is used to determine the first area of each first organ and the second area of the second organ from the multiple classification areas; the target area determination sub-module: is used to determine the first area and the second area according to the first area and the second area. Area, to determine multiple target areas in the image to be processed.

In a possible implementation manner, the first region and the second region determining sub-module are configured to: determine the classification region with the largest number of pixels in the plurality of classification regions as the second region; Among the plurality of classification areas, the classification area except for the second area is determined as the first area; wherein, the target area determination sub-module is used to: perform an expansion operation on the first area to obtain the expansion After the third area; from the third area, remove the area that overlaps the second area to obtain a cropped area; perform cropping processing on the image to be processed according to the cropped area to obtain the Describe multiple target areas.

In a possible implementation manner, the threshold determination module is used to: sort the gray values of pixels in the target area, determine the gray value of the median as the second gray threshold; The second gray-scale threshold is added to the preset offset threshold to obtain the first gray-scale threshold.

In a possible implementation manner, the suspected lesion and pseudo-lesion determining module includes: a suspected lesion determining submodule, configured to determine the gray value of pixels in the target area greater than the first gray threshold value of the target area The area where the pixel of the first gray-scale threshold is located is determined as the suspected lesion area; the pseudo-lesion determination sub-module is configured to determine the gray-scale of the pixel in the target area according to the second gray-scale threshold of the target area. The area where the pixel with the value greater than the second gray-scale threshold is determined to be the fourth area, and the fourth area includes a plurality of connected areas; the connected area with the number of pixels greater than the preset threshold in each connected area is determined as the Pseudo lesion area.

In a possible implementation manner, the lesion determination module is configured to remove the area overlapping with the pseudo-lesion area from the suspected lesion area of each target area to obtain the lesion area of the first organ.

According to another aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to call the instructions stored in the memory to execute The above method.

According to another aspect of the present disclosure, there is provided a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions implement the above method when executed by a processor.

In the embodiment of the present disclosure, multiple target areas can be determined from the image to be processed, and for each target area, the first grayscale threshold and the second grayscale threshold of each target area can be determined respectively, and then according to the first grayscale threshold of each target area The first gray-scale threshold and the second gray-scale threshold respectively determine the suspected lesion area and the pseudo-lesion area in each target area, and finally the suspected lesion area and the pseudo-lesion area in each target area are used to determine the lesion area of the image to be processed ( Such as calcified plaque area). This method can identify calcified plaques by setting different thresholds at different positions of the first organ (such as coronary vessels) in the image to be processed. Omissions increase the recall rate of calcified plaques, and can significantly improve the accuracy of calcified plaque recognition.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, rather than limiting the present disclosure. According to the following detailed description of exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present disclosure will become clear.

Description of the drawings

The drawings included in the specification and constituting a part of the specification together with the specification illustrate exemplary embodiments, features, and aspects of the present disclosure, and are used to explain the principle of the present disclosure.

Fig. 1 shows a flowchart of a lesion detection method according to an embodiment of the present disclosure.

Fig. 2 shows a schematic diagram of a segmentation process of a to-be-processed image according to an embodiment of the present disclosure.

Fig. 3 shows a schematic diagram of a clipping region according to an embodiment of the present disclosure.

Fig. 4 shows a schematic diagram of grayscale distribution of a target area according to an embodiment of the present disclosure.

Fig. 5 shows a schematic diagram of a suspected lesion area and a pseudo-lesion area according to an embodiment of the present disclosure.

Fig. 6 shows a schematic diagram of a lesion area according to an embodiment of the present disclosure.

Fig. 7 shows a block diagram of a lesion detection device according to an embodiment of the present disclosure.

FIG. 8 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

FIG. 9 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

detailed description

Hereinafter, various exemplary embodiments, features, and aspects of the present disclosure will be described in detail with reference to the drawings. The same reference numerals in the drawings indicate elements with the same or similar functions. Although various aspects of the embodiments are shown in the drawings, unless otherwise noted, the drawings are not necessarily drawn to scale.

The dedicated word "exemplary" here means "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" need not be construed as being superior or better than other embodiments.

The term "and/or" in this article is only an association relationship that describes the associated objects, which means that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, exist alone B these three situations. In addition, the term "at least one" in this document means any one of a plurality of or any combination of at least two of the plurality, for example, including at least one of A, B, and C, and may mean including A, Any one or more elements selected in the set formed by B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. Those skilled in the art should understand that the present disclosure can also be implemented without certain specific details. In some instances, the methods, means, elements, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the gist of the present disclosure.

Fig. 1 shows a flow chart of a focus detection method according to an embodiment of the present disclosure. As shown in Fig. 1, the focus detection method includes: in step S1, a segmentation process is performed on an image to be processed, and the image to be processed is determined Multiple target areas of an organ.

In step S2, for any target area, the first gray threshold and the second gray threshold of the target area are determined according to the gray information of the target area, and the first gray threshold is greater than the first gray threshold. Two gray scale threshold.

In step S3, the suspected lesion area and the pseudo lesion area in the target area are respectively determined according to the first gray threshold value and the second gray threshold value of the target area.

In step S4, the lesion area of the first organ is determined according to the suspected lesion area and the pseudo lesion area of each of the target areas.

In a possible implementation, the lesion detection method can be executed by electronic equipment such as a terminal device or a server, and the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, etc., other processing equipment It can be a server or a cloud server, etc. In some possible implementations, the lesion detection method can be implemented by a processor invoking a computer-readable instruction stored in a memory. Alternatively, the method can be executed by the server.

In a possible implementation, the image to be processed may be a medical image, which may be an image taken by various types of medical equipment, or an image used for medical diagnosis, for example, a computer tomography (Computed Tomography). , CT) images or MRI (Magnetic Resonance Imaging, MRI) images, etc. The image to be processed may be a two-dimensional medical image or a three-dimensional medical image. The present disclosure does not limit the type of image to be processed and the specific acquisition method.

In a possible implementation, the image to be processed includes an organ and a lesion on the organ. For example, the image to be processed is a cardiac medical image, and the organ in the image to be processed may be a blood vessel in the heart, including the aorta. Blood vessels and coronary vessels, lesions on organs can be calcified plaques on coronary vessels. The present disclosure does not limit the specific organ types and the types of lesions on the organs. Among them, there may be one or more lesions on the organ, and the present disclosure does not limit the number of lesions on the organ.

In a possible implementation manner, in step S1, the image to be processed may be segmented to determine multiple target regions of the first organ in the image to be processed. The image to be processed includes, for example, a cardiac medical image, the first organ in the image to be processed includes, for example, coronary blood vessels, and the target area in the image to be processed includes, for example, the area where the coronary blood vessel segments are located.

In a possible implementation manner, a segmentation network may be preset to perform segmentation processing on the image to be processed and determine multiple target regions of the first organ in the image to be processed. The segmentation network can be a deep convolutional neural network, including multiple convolutional layers, multiple deconvolutional layers, fully connected layers, etc. The specific segmentation networks that can be used include but are not limited to U-Network (U-NET) , V-Network (V-NET) and other network structures, the present disclosure does not limit the specific network structure of the segmented network.

Among them, you can set a random number as the initial value of the network parameters, train the parameters of the network through the sample images of the training set, and then detect the segmentation error of the network from the verification set, adjust the parameters of the network, and repeat the above process until the network The error is the smallest on the verification set, and a trained segmentation network is obtained. Among them, the gradient descent method can be used to adjust the network parameters of the segmentation network to optimize the network parameters and improve the accuracy of the segmentation network.

Among them, the training data can be annotated with medical image data (for example, artificially annotated coronary vascular data) by professionals with medical background under the review of senior doctors, and establish a sample image database according to a preset ratio (for example, 9:1 ) Divide each sample image into a training set and a verification set. The present disclosure does not limit the value of the preset ratio.

In a possible implementation manner, in step S2, the first gray-scale threshold and the second gray-scale threshold of each target area can be determined according to the gray-scale information of each target area, and the first gray-scale threshold is greater than the second gray-scale threshold. Degree threshold.

The first gray threshold can be used to determine the suspected lesion area in the target area, and the second gray threshold can be used to determine the pseudo lesion area in the target area. Since the gray information of each target area may be different, the first gray threshold and the second gray threshold of each target area may also be different.

In a possible implementation manner, in step S3, each target area may be segmented by the first threshold according to the first gray threshold value of each target area to determine the suspected lesion area in each target area; according to each target area The second gray-scale threshold of the region, the second threshold segmentation is performed on each target region, and the pseudo-lesion region in each target region is determined.

In a possible implementation manner, in step S4, according to the suspected lesion area and the pseudo-lesion area of each of the target areas, the area of the suspected lesion area that does not contain the pseudo-lesion area is determined as the lesion area of the first organ . Wherein, the lesion area includes, for example, a calcified plaque area of a coronary artery.

According to the embodiments of the present disclosure, multiple target areas can be determined from the image to be processed, and for each target area, the first grayscale threshold and the second grayscale threshold of each target area can be determined respectively, and then according to the first grayscale threshold of each target area The first gray-scale threshold and the second gray-scale threshold determine the lesion area of the image to be processed, and different thresholds can be set for different positions of the first organ (such as coronary blood vessels) in the image to be processed to identify calcified plaques. Not only can it effectively reduce the omission of calcified plaques at the small branch vessels of the coronary blood vessels in the image to be processed, and improve the recall rate of calcified plaques, but also can significantly improve the accuracy of calcified plaque recognition.

The following is an expanded description of the lesion detection method according to the embodiment of the present disclosure.

In a possible implementation, step S1 may include: step S11, segmenting the image to be processed, and determining an organ region in the image to be processed, the organ region including a second organ and a first organ , The size of the second organ is larger than the size of the first organ.

Step S12: Classify the organ regions to obtain multiple classification regions.

Step S13: Determine the first area of each first organ and the second area of the second organ from the multiple classification areas.

Step S14: Determine multiple target areas in the image to be processed according to the first area and the second area.

Fig. 2 shows a schematic diagram of a segmentation process of a to-be-processed image according to an embodiment of the present disclosure. As shown in FIG. 2, the image 21 to be processed is a Computed Tomography Angiography (CTA) image, and the image 21 to be processed is segmented to obtain a segmentation result 22, which determines the organ region in the image 21 to be processed, that is, the heart The area of blood vessels in an angiographic image. The segmentation result 22 may be a binary label, marking the blood vessel area in the cardioangiography image as 1, and marking the background area outside the blood vessel area as 0.

As shown in the segmentation result 22, the organ area is a blood vessel area, including the second organ and the first organ. Among them, the second organ includes aortic vessels, that is, the organ area within the dashed frame in the segmentation result 22; the first organ is a coronary vessel segment, that is, the organ area outside the dashed frame in the segmentation result 22.

As shown in the segmentation result 22, the coronary vessels originate from the roots of the aortic vessels, and the size of the aortic vessels is larger than the size of the coronary vessels. Compared with the aortic vessels, the coronary vessels are relatively small. The same lesion (calcified plaque) may not affect the blood circulation in the aortic vessels, but may block the coronary vessels. Moreover, affected by the dose distribution of the contrast agent and the thickness of the blood vessel, the brightness distribution of each branch blood vessel segment in the image to be processed is uneven. Therefore, after the organ area is obtained, it can be classified according to the size of each part on the organ.

In a possible implementation manner, in step S12, the organ regions are classified to obtain multiple classification regions.

For example, assuming that the organ region is a blood vessel region, the organ region is classified, that is, the blood vessel region is separated, and multiple blood vessel segments are obtained, and each blood vessel segment is a classification area.

It should be understood that the present disclosure does not limit the specific classification method. The neural network algorithm can be used to input the organ region into a pre-trained classification network to obtain multiple classification regions; or, the organ region can be circumscribed by a rectangle. Cutting is performed to obtain a plurality of classification regions; among them, the plurality of classification regions obtained by the cutting can be respectively input into a preset first organ registration model for registration prediction, and the positional relationship between the classification regions is obtained.

In a possible implementation manner, step S13 may include: determining the classification area with the largest number of pixels in the plurality of classification areas as the second area; dividing the plurality of classification areas by The classification area outside the second area is determined to be the first area.

For example, suppose that the organ area includes N classification areas, that is, classification area 1 to classification area N. Calculate the number of pixels in each of the N classification areas, determine the classification area with the largest number of pixels as the second area, and determine the remaining N-1 classification areas as the first area.

For example, the organ area is the blood vessel area of the segmentation result 22 in FIG. Area), the first area is the branch blood vessel segment area outside the dashed box in the segmentation result 22 (ie, the coronary blood vessel area), including multiple branch blood vessel segment areas.

Therefore, by dividing the multiple classification areas into the first area of each first organ and the second area of the second organ, it is beneficial to more accurately determine the subsequent target area, reduce the amount of calculation, and improve the calculation efficiency.

In a possible implementation manner, step S14 may include: performing an expansion operation on the first region to obtain a third region after expansion; from the third region, removing the region overlapping with the second region , Obtain a cropped area; perform crop processing on the image to be processed according to the cropped area to obtain the multiple target areas.

Fig. 3 shows a schematic diagram of a clipping region according to an embodiment of the present disclosure. As shown in Figure 3, V _other represents the first area (the solid rectangular area in Figure 3), which is the coronary vascular area, and V _main represents the second area (the cylinder area in Figure 3), which is the aortic vascular area .

The expansion operation is performed on the first area V _other to obtain the expanded third area V _other-big (the area in the dashed frame in FIG. 3 ). Among them, the present disclosure does not limit the specific expansion operation method, and the morphological expansion operation can be performed _{on the first region V other} _{; and the first region V other} can also be regionally expanded by a preset expansion coefficient.

From the third area V _other-big , the area overlapping with the second area V _main (the striped area in FIG. 3) is _{removed to obtain the cropped area V 1} (the gray area in FIG. 3).

It should be understood that the first region V _other in FIG. 3 uses one coronary artery segment as an illustration, and the first region V _other is multiple coronary artery segment regions. Correspondingly, the shearing region V ₁ is different from the second region V _main. Intersection of multiple expanded coronary vascular segment regions.

According to the cropping area V ₁ , the image to be processed is cropped to obtain multiple target areas. For example, a cropped image of the same size as the image to be processed can be determined according to the cropped area V _1. _{In the cropped image, the gray value of the pixels contained in the cropped area V 1} is marked as 1, and the cropped area V The gray value of the pixels contained in the background outside _{1 is marked as 0.} Multiply the cropped image and the image to be processed to obtain the target area of the image to be processed.

Therefore, by performing the expansion operation on the first area in the organ area, it can be ensured that the calcified plaque part can be extracted together with the first area, and the recall rate and accuracy of the calcified plaque can be improved; by removing the area overlapping with the second area , It can reduce the amount of calculation and improve the efficiency of identifying calcified plaques.

Through steps S11 to S14, multiple target regions of the first organ (for example, coronary blood vessels) can be determined from the image to be processed, which is beneficial to subsequently setting appropriate thresholds according to the target regions of each part of the first organ, which can reduce the The size of each part of the first organ is different, and the contrast dose is unevenly distributed on the first organ, which results in the influence of the different gray values of the calcified plaques on each part of the first organ, and it can also reduce the size of the first organ. Omission of calcified plaque at the site.

After obtaining multiple target areas in step S1, the gray level threshold of each target area can be determined according to the gray information of each target area.

In a possible implementation manner, step S2 may include: sorting the gray values of pixels in the target area, determining the gray value of the median as the second gray threshold; The second gray-scale threshold is added to the preset offset threshold to obtain the first gray-scale threshold.

FIG. 4 shows a schematic diagram of the grayscale distribution of a target area according to an embodiment of the present disclosure. As shown in FIG. 4, the pixels in any target area can be sorted according to the size of the gray value, and the abscissa in the figure represents the target area The gray value of the middle pixel is A to B, and the vertical axis represents the number of pixels corresponding to the gray value.

It should be understood that the gray value range A to B of the pixel in the target area can be determined according to the image type of the image to be processed. For example, assuming that the image to be processed is a CT image, the gray value of the pixel in the target area (that is, the CT value ) The range is -1000HU～1000HU, and HU is the Heinz unit of the CT value. The present disclosure does not limit the value range of the gray value.

As shown in Figure 4, the median gray value T ₀ can be determined as the second gray threshold, and the second gray threshold T _{0 is added} to the preset offset threshold T _{1 to} obtain the first gray Degree threshold T _fin . Wherein, the result of the addition of the second gray-scale threshold T ₀ and the preset offset threshold T ₁ needs to be less than the maximum gray-scale value of the pixel in the target area. The preset offset threshold T ₁ can be determined based on clinical experience. The specific value of the offset threshold T _{1 is not limited.}

It should be understood that multiple target areas may be included in the image to be processed, and the gray information of each target area is different. The corresponding first gray threshold T _fin and second gray level can be determined according to the gray information of each target area. Degree threshold T ₀ .

In this way, different thresholds can be set for different positions of the first organ (for example, coronary blood vessels), reduce the influence of the inconsistency of brightness at different positions in the first organ, and improve the accuracy of calcified plaque recognition.

After the first gray-scale threshold and the second gray-scale threshold of each target area are determined in step S2, the suspected lesion area and the pseudo-lesion area of each target area can be determined through step S3.

In a possible implementation manner, step S3 may include: according to the first gray-scale threshold of the target area, determining the area where the pixel in the target area has a gray-scale value greater than the first gray-scale threshold, Determined as the suspected lesion area.

According to the second gray-scale threshold of the target area, determine the area where the pixel in the target area has a gray-scale value greater than the second gray-scale threshold as a fourth area, and the fourth area includes a plurality of Connected areas: Connected areas where the number of pixels in each connected area is greater than a preset threshold are determined as the pseudo-focus area.

Fig. 5 shows a schematic diagram of a suspected lesion area and a pseudo-lesion area according to an embodiment of the present disclosure. As shown in Figure 5, the cylindrical shape represents a target area. According to the first gray threshold of the target area, perform the first threshold segmentation process on the target area, and the gray value of the pixels in the target area is greater than the first gray scale. The area where the threshold pixel is located is determined as the suspected lesion area 51 (the black solid line area in FIG. 5).

Perform a second threshold segmentation process on the target area according to the second grayscale threshold of the target area, and determine the area where the pixels in the target area have a grayscale value greater than the second grayscale threshold as the fourth area 52 (the dotted area in FIG. 5, the dotted area identified in the figure includes area 51).

The fourth area 52 may include a plurality of connected areas, and a connected area with a pixel number greater than a preset threshold in each connected area is determined as a pseudo-focus area. For example, the fourth area in Figure 5 includes 3 connected domains, the number of pixels in the two gray dotted areas is less than the preset threshold, and the number of pixels in the black dotted area is greater than the preset threshold. The black dotted area can be determined as Pseudo lesion area.

Among them, the preset threshold can be determined based on clinical experience. For example, the lesion is a calcified plaque on a coronary artery, which can be set to the maximum value of calcified plaque statistics based on clinical experience. The present disclosure does not limit the specific value of the preset threshold. .

It should be understood that, for multiple target areas, the process of determining the suspected lesion area and the pseudo-lesion area from one target area can be referred to in FIG. 5, and the suspected lesion area and the pseudo-lesion area of each target area can be determined respectively.

In this way, the suspected lesion area determined according to the second gray-scale threshold can increase the recall rate of calcified plaques, and the pseudo-lesion area determined according to the first gray-scale threshold (for example, the small branch blood vessels on the coronary vessels are high). The bright part) can reduce the false positive rate of calcified plaques. Therefore, by determining the suspected lesion area and the pseudo-lesion area, it is helpful to improve the accuracy of subsequent calcified plaque determination.

In step S3, the suspected lesion area and the pseudo-lesion area of each target area are determined, and the lesion area of the first organ (for example, the calcified plaque area of coronary blood vessels) can be determined through step S4.

In a possible implementation manner, step S4 may include: removing the area overlapping with the pseudo-lesion area from the suspected lesion area of each of the target areas to obtain the lesion area of the first organ (for example, coronary artery). Calcified plaque areas of blood vessels).

Fig. 6 shows a schematic diagram of a lesion area according to an embodiment of the present disclosure. As shown in FIG. 6, the cylindrical shape represents a target area, the solid line area represents the suspected lesion area 51, and the dotted line area represents the pseudo lesion area 61 (including the gray area 51). In the suspected lesion area 51, the area (gray area) overlapping with the pseudo lesion area 61 is removed to obtain the lesion area (black area).

It should be understood that for multiple target areas, refer to the process of determining the lesion area from one target area with reference to FIG. 6, and determine the lesion area of each target area from the suspected lesion area of each target area, and the lesion area of each target area. Collection, that is, the lesion area of the first organ.

In this way, determining the lesion area (such as the calcified plaque area) based on the suspected lesion area and the pseudo-lesion area is beneficial to increase the recall rate of calcified plaques, reduce the false positive rate of calcified plaques, and thus improve the recognition of calcified plaques Accuracy.

Therefore, according to the lesion detection method of the embodiment of the present disclosure, multiple target regions can be determined from the image to be processed, and for each target region, the first grayscale threshold and the second grayscale threshold of each target region can be determined respectively, and then according to The first gray-scale threshold and the second gray-scale threshold of each target area respectively determine the suspected lesion area and the pseudo-lesion area in each target area. Finally, the suspected lesion area and the pseudo-lesion area in each target area can be used to determine the target area. Process the image of the lesion area, such as the calcified plaque area. The method is simple and easy to implement, not only can effectively reduce the omission of calcified plaques at the small branch vessels of the coronary blood vessels in the image to be processed, and improve the recall rate of calcified plaques, but also can significantly improve the accuracy of calcified plaque recognition.

It can be understood that, without violating the principle logic, the various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment, which is limited in length and will not be repeated in this disclosure. Those skilled in the art can understand that, in the above method of the specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

In addition, the present disclosure also provides lesion detection devices, electronic equipment, computer-readable storage media, and programs, all of which can be used to implement any of the lesion detection methods provided in the present disclosure. For the corresponding technical solutions and descriptions, refer to the corresponding records in the method section. ,No longer.

FIG. 7 shows a block diagram of a lesion detection device according to an embodiment of the present disclosure. As shown in FIG. 7, the device includes: a segmentation module 71, configured to perform segmentation processing on an image to be processed, and determine the first organ in the image to be processed Multiple target areas.

The threshold determination module 72 is configured to determine the first gray threshold and the second gray threshold of the target area according to the gray information of the target area for any target area, and the first gray threshold is greater than the gray level information. The second gray-scale threshold.

The suspected lesion and pseudo-lesion determining module 73 is configured to respectively determine the suspected lesion area and the pseudo-lesion area in the target area according to the first gray threshold value and the second gray threshold value of the target area.

The lesion determination module 74 is configured to determine the lesion area of the first organ according to the suspected lesion area and the pseudo lesion area of each of the target areas.

In a possible implementation, the segmentation module 71 includes: a segmentation sub-module: used to segment the image to be processed and determine an organ region in the image to be processed, and the organ region includes a second organ and The size of the first organ, the second organ is larger than the size of the first organ.

Classification sub-module: used to classify the organ regions to obtain multiple classification regions.

The first area and second area determining sub-module: used to determine the first area of each first organ and the second area of the second organ from the multiple classification areas.

Target area determination sub-module: used to determine multiple target areas in the image to be processed according to the first area and the second area.

In a possible implementation manner, the first region and the second region determining sub-module are configured to: determine the classification region with the largest number of pixels in the plurality of classification regions as the second region; Among the plurality of classification areas, classification areas other than the second area are determined as the first area.

Wherein, the target area determining submodule is used to: perform an expansion operation on the first area to obtain a third area after expansion; from the third area, remove the area overlapping with the second area to obtain Cropping area; performing cropping processing on the image to be processed according to the cropping area to obtain the multiple target areas.

In a possible implementation manner, the threshold determination module 72 is used to: sort the gray values of pixels in the target area, determine the gray value of the median as the second gray threshold; The second gray-scale threshold is added to the preset offset threshold to obtain the first gray-scale threshold.

In a possible implementation manner, the suspected lesion and pseudo-lesion determining module 73 includes: a suspected lesion determining sub-module, configured to calculate the gray value of pixels in the target area according to the first gray level threshold of the target area The area where the pixel is larger than the first gray-scale threshold is determined as the suspected lesion area.

The pseudo-lesion determination sub-module is configured to determine, according to the second gray-scale threshold of the target area, the area where the pixel in the target area has a gray-scale value greater than the second gray-scale threshold as the fourth area, The fourth area includes a plurality of connected areas; a connected area whose number of pixels in each connected area is greater than a preset threshold is determined as the pseudo-focus area.

In a possible implementation manner, the lesion determination module 74 is configured to remove the area overlapping with the pseudo-lesion area from the suspected lesion area of each of the target areas to obtain the lesion area of the first organ.

In some embodiments, the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. For specific implementation, refer to the description of the above method embodiments. For brevity, here No longer.

The embodiments of the present disclosure also provide a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above-mentioned method when executed by a processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

An embodiment of the present disclosure also proposes an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above method.

The electronic device can be provided as a terminal, server or other form of device.

FIG. 8 shows a block diagram of an electronic device 800 according to an embodiment of the present disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and other terminals.

8, the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , And communication component 816.

The processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.

The power supply component 806 provides power for various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor can not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module. The above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

The sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation. For example, the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components. For example, the component is the display and the keypad of the electronic device 800. The sensor component 814 can also detect the electronic device 800 or the electronic device 800. The position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact. The sensor component 814 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on communication standards, such as wireless network (WiFi), second-generation mobile communication technology (2G), third-generation mobile communication technology (3G), fourth-generation mobile communication technology (4G) or The fifth-generation mobile communication technology (5G), or a combination of them. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field-available A programmable gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium, such as the memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to implement the above method.

FIG. 9 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server. 9, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above-mentioned method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to the network, and an input output (I/O) interface 1958 . The electronic device 1900 can operate based on the operating system stored in the memory 1932, such as the Microsoft Server Operating System (Windows ServerTM), the graphical user interface operating system (Mac OS XTM) launched by Apple, and the multi-user and multi-process computer operating system (UnixTM) ), free and open source Unix-like operating system (LinuxTM), open source Unix-like operating system (FreeBSDTM) or similar.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to complete the foregoing method.

The present disclosure may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.

The computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon The protruding structure in the hole card or the groove, and any suitable combination of the above. The computer-readable storage medium used here is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.

The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .

The computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or in one or more programming languages. Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages. Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server implement. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the user’s computer) connect). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be personalized by using the status information of the computer-readable program instructions. The computer-readable program instructions are executed to realize various aspects of the present disclosure.

Here, various aspects of the present disclosure are described with reference to flowcharts and/or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine that makes these instructions when executed by the processor of the computer or other programmable data processing device , A device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner, so that the computer-readable medium storing the instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

It is also possible to load computer-readable program instructions onto a computer, other programmable data processing device, or other equipment, so that a series of operation steps are executed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , So that the instructions executed on the computer, other programmable data processing apparatus, or other equipment realize the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

The flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions, and operations of the system, method, and computer program product according to multiple embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more components for realizing the specified logical function. Executable instructions. In some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

The computer program product can be specifically implemented by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc. Wait.

The various embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Without departing from the scope and spirit of the described embodiments, many modifications and changes are obvious to those of ordinary skill in the art. The choice of terms used herein is intended to best explain the principles, practical applications, or improvements to the technology in the market for each embodiment, or to enable other ordinary skilled in the art to understand the various embodiments disclosed herein.

Claims

A method for detecting lesions, characterized in that the method includes:

Performing segmentation processing on the image to be processed, and determining multiple target regions of the first organ in the image to be processed;

For any target area, determine a first gray level threshold and a second gray level threshold of the target area according to gray level information of the target area, where the first gray level threshold is greater than the second gray level threshold;

Respectively determining a suspected lesion area and a pseudo lesion area in the target area according to the first gray threshold value and the second gray threshold value of the target area;

Determine the lesion area of the first organ according to the suspected lesion area and the pseudo lesion area of each of the target areas.
The method according to claim 1, wherein performing segmentation processing on the image to be processed and determining multiple target regions of the first organ in the image to be processed comprises:

Segmenting the image to be processed to determine an organ region in the image to be processed, the organ region includes a second organ and a first organ, and the size of the second organ is larger than the size of the first organ;

Classify the organ regions to obtain multiple classification regions;

Determine the first area of each first organ and the second area of the second organ from the multiple classification areas;

According to the first area and the second area, multiple target areas in the image to be processed are determined.
The method according to claim 2, wherein determining the first area of each first organ and the second area of the second organ from the plurality of classification areas comprises:

Determining the classification area with the largest number of pixels in the plurality of classification areas as the second area;

Determining, among the plurality of classification areas, classification areas other than the second area as the first area;

Wherein, the determining multiple target areas in the image to be processed according to the first area and the second area includes:

Performing an expansion operation on the first area to obtain an expanded third area;

From the third area, remove the area overlapping with the second area to obtain a cropped area;

According to the cropping area, performing cropping processing on the image to be processed to obtain the multiple target areas.
The method according to claim 1, wherein the determining the first gray level threshold and the second gray level threshold of the target area according to the gray level information of the target area comprises:

Sorting the gray values of pixels in the target area, and determining the gray value of the median as the second gray value threshold;

The second gray-scale threshold value and the preset offset threshold value are added to obtain the first gray-scale threshold value.
The method according to claim 1, wherein the respectively determining the suspected lesion area and the pseudo lesion area in the target area according to the first gray threshold value and the second gray threshold value of the target area comprises:

Determining, according to the first gray-scale threshold value of the target area, an area where a pixel in the target area has a gray-scale value greater than the first gray-scale threshold value as the suspected lesion area;

According to the second gray-scale threshold of the target area, determine the area where the pixel in the target area has a gray-scale value greater than the second gray-scale threshold as a fourth area, and the fourth area includes a plurality of Connected area

A connected area with a pixel number greater than a preset threshold in each connected area is determined as the pseudo-focus area.
The method according to claim 1, wherein determining the lesion area of the first organ according to the suspected lesion area and the pseudo lesion area of each of the target areas comprises:

From the suspected lesion areas of each of the target regions, the area overlapping with the pseudo-lesion area is removed to obtain the lesion area of the first organ.
The method according to claim 2, wherein the image to be processed comprises a cardiac medical image, the first organ comprises coronary blood vessels, the second organ comprises aortic blood vessels, and the target area comprises coronary arteries The area where the blood vessel segment is located, and the lesion area includes a calcified plaque area.
A lesion detection device, which is characterized in that it comprises:

A segmentation module, configured to perform segmentation processing on the image to be processed, and determine multiple target regions of the first organ in the image to be processed;

Threshold determination module for determining a first gray threshold and a second gray threshold of the target area according to gray information of the target area for any target area, where the first gray threshold is greater than the gray level information of the target area. The second gray threshold;

The suspected lesion and pseudo-lesion determination module is configured to determine the suspected lesion area and the pseudo-lesion area in the target area according to the first gray threshold value and the second gray threshold value of the target area;

The lesion determination module is configured to determine the lesion area of the first organ according to the suspected lesion area and the pseudo lesion area of each of the target areas.
An electronic device, characterized in that it comprises:

processor;

A memory for storing processor executable instructions;

Wherein, the processor is configured to call instructions stored in the memory to execute the method according to any one of claims 1 to 7.
A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the method according to any one of claims 1 to 7 when the computer program instructions are executed by a processor.