CN116958100A

CN116958100A - Method, device, equipment and medium for extracting DSA sequence key frames

Info

Publication number: CN116958100A
Application number: CN202310935513.0A
Authority: CN
Inventors: 高丰伟; 王季勇; 陈树湛
Original assignee: Shanghai Bodong Medical Technology Co ltd
Current assignee: Shanghai Bodong Medical Technology Co ltd
Priority date: 2023-07-27
Filing date: 2023-07-27
Publication date: 2023-10-27

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for extracting a DSA sequence key frame. The method comprises the following steps: acquiring a DSA sequence, and aiming at each DSA image in the DSA sequence, carrying out vascular stenosis identification on each DSA image to obtain a vascular stenosis identification result; and extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the vascular stenosis identification results respectively corresponding to the DSA images. According to the technical scheme provided by the embodiment of the invention, the key frames can be automatically extracted from the DSA sequence, so that the workload of doctors is reduced.

Description

Method, device, equipment and medium for extracting DSA sequence key frames

Technical Field

The embodiment of the invention relates to the technical field of image processing, in particular to a method, a device, equipment and a medium for extracting a DSA sequence key frame.

Background

In recent years, the incidence rate of coronary heart disease caused by coronary artery stenosis is high, and the trend of younger is aggravated year by year, so that the realization of accurate detection of coronary artery stenosis is of great importance.

Currently, fractional flow reserve (Fraction Flow Reservation, FFR) techniques for coronary arteries have been widely used in the detection of coronary artery stenosis. However, this technique requires the injection of adenosine into patients, and some patients are allergic to adenosine, which results in a problem that the applicable population is limited.

In order to solve the above problems, researchers have proposed a technique of extracting key frames from a digital subtraction angiography (Digital subtraction angiography, DSA) sequence and then detecting coronary artery stenosis (i.e., vascular stenosis) based on the key frames. It should be noted that, in this technology, key frames are extracted manually by a doctor, which obviously increases the workload of the doctor, and needs to be improved.

Disclosure of Invention

The embodiment of the invention provides a method, a device, equipment and a medium for extracting key frames of a DSA sequence, which are used for realizing automatic extraction of the key frames from the DSA sequence, thereby reducing the workload of doctors.

According to an aspect of the present invention, there is provided a method of extracting a DSA sequence key frame, which may include:

acquiring a DSA sequence, and aiming at each DSA image in the DSA sequence, carrying out vascular stenosis identification on each DSA image to obtain a vascular stenosis identification result;

And extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the vascular stenosis identification results respectively corresponding to the DSA images.

Optionally, according to the recognition result of the vessel stenosis corresponding to each DSA image, extracting one or more DSA images with no artifact and/or clear vessel boundary at the vessel stenosis from the DSA sequence as a key frame, including:

according to the blood vessel stenosis recognition result of the DSA image, determining the central line of the DSA image at the blood vessel stenosis, and obtaining the pixel value of each pixel point positioned in the vertical direction of the central line;

according to the pixel values of all the pixel points, obtaining characteristic information representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear;

and extracting one or more DSA images which are free of artifacts at the narrow part of the blood vessel and/or clear in the boundary of the blood vessel from the DSA sequence as key frames according to the characteristic information corresponding to each DSA image.

On the basis, optionally, according to the pixel values of each pixel point, obtaining characteristic information representing whether the DSA image has an artifact at a vascular stenosis and/or whether a vascular boundary is clear, including:

Calculating at least two pixel value gradients according to the pixel values of each pixel point, and obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear according to the at least two pixel value gradients;

or,

and analyzing the pixel values of each pixel point to obtain the peak value shape of the pixel value peak value corresponding to the pixel value of each pixel point, and obtaining the characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear or not according to the peak value shape.

On the basis, optionally, according to at least two pixel value gradients, obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear, including:

calculating gradient difference values between every two adjacent calculated pixel value gradients in at least two pixel value gradients, and obtaining characteristic information representing whether an artifact exists at a blood vessel stenosis position and/or whether a blood vessel boundary is clear or not according to each gradient difference value;

or,

and obtaining characteristic information representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear or not according to the gradient of at least two pixel values and a preset gradient threshold value.

On the basis, optionally, according to each gradient difference value, obtaining characteristic information representing whether the DSA image has artifact at the vascular stenosis and/or whether the vascular boundary is clear, including:

and when the absolute value of each gradient difference value is larger than the absolute value of the preset difference value threshold, determining that the DSA image has no artifact at the narrow position of the blood vessel and/or the blood vessel boundary is clear.

Alternatively, according to at least two pixel value gradients and a preset gradient threshold, obtaining feature information indicating whether an artifact exists in a DSA image at a vascular stenosis and/or whether a vascular boundary is clear, including:

when the pixel value gradients larger than the preset gradient threshold value exist in the at least two pixel value gradients, determining that the DSA image has no artifact at the narrow part of the blood vessel and/or the boundary of the blood vessel is clear.

Alternatively, and according to the peak shape, obtaining feature information that characterizes whether the DSA image has an artifact at a vascular stenosis and/or whether a vascular boundary is clear, including:

when the peak shape is columnar, then the DSA image is determined to be free of artifacts at the vessel stenosis and/or the vessel boundary is clear.

Alternatively, the method for extracting the key frames of the DSA sequence before determining the center line of the DSA image at the vascular stenosis according to the recognition result of the vascular stenosis of the DSA image further includes:

And performing vessel segmentation on the DSA image to obtain a vessel segmentation image.

On the basis, optionally, determining the center line of the DSA image at the vascular stenosis according to the vascular stenosis identification result of the DSA image comprises:

and extracting a region of interest from the vessel segmentation image corresponding to the DSA image according to the vessel stenosis recognition result of the DSA image, and taking the central line of the vessel contained in the region of interest as the central line of the DSA image at the vessel stenosis.

According to another aspect of the present invention, there is provided an apparatus for extracting a DSA sequence key frame, which may include:

the blood vessel stenosis recognition result obtaining module is used for obtaining a DSA sequence, and carrying out blood vessel stenosis recognition on each DSA image aiming at each DSA image in the DSA sequence to obtain a blood vessel stenosis recognition result;

and the key frame extraction module is used for extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the vascular stenosis identification results respectively corresponding to the DSA images.

According to another aspect of the present invention, there is provided an electronic device, which may include:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

The memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to implement the method of extracting a DSA sequence key frame provided by any embodiment of the present invention when executed.

According to another aspect of the invention, there is provided a computer readable storage medium having stored thereon computer instructions for causing a processor to perform the method of extracting a DSA sequence key frame provided by any embodiment of the invention when executed.

According to the technical scheme provided by the embodiment of the invention, through carrying out vascular stenosis recognition on each DSA image in the DSA sequence, one or more DSA images which are free of artifacts and/or clear in vascular boundaries at vascular stenosis positions can be extracted from the DSA sequence as key frames according to vascular stenosis recognition results respectively corresponding to each DSA image. According to the technical scheme, the key frames can be automatically extracted from the DSA sequence, so that the effect of reducing the workload of doctors is achieved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention, nor is it intended to be used to limit the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for extracting key frames of a DSA sequence according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of an embodiment of the present invention for extracting DSA sequences a flowchart of an example of vascular stenosis identification in a method of key frames;

FIG. 3 is a schematic diagram of a recognition result of a vascular stenosis in a method for extracting a key frame of a DSA sequence according to an embodiment of the present invention;

FIG. 4 is a flow chart of another method for extracting key frames of a DSA sequence provided in accordance with an embodiment of the present invention;

FIG. 5 is a flowchart of an example of vessel segmentation in another method of extracting a key frame of a DSA sequence provided in accordance with an embodiment of the present invention;

FIG. 6 is a flow chart of yet another method for extracting a DSA sequence key frame provided in accordance with an embodiment of the present invention;

FIG. 7 is a flow chart of yet another method for extracting key frames of a DSA sequence provided in accordance with an embodiment of the present invention;

FIG. 8 is a flow chart of an alternative example of a method for extracting key frames of a DSA sequence provided in accordance with an embodiment of the present invention;

FIG. 9 is a block diagram of an apparatus for extracting key frames of a DSA sequence according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of an electronic device implementing a method for extracting DSA sequence key frames in an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. The cases of "target", "original", etc. are similar and will not be described in detail herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a flowchart of a method for extracting a DSA sequence key frame according to an embodiment of the present invention. This embodiment may be applicable to the case of extracting key frames from DSA sequences that can be used to detect vascular stenosis. The method may be performed by an apparatus for extracting a DSA sequence key frame provided by an embodiment of the present invention, where the apparatus may be implemented by software and/or hardware, and the apparatus may be integrated on an electronic device, where the electronic device may be various user terminals or servers.

Referring to fig. 1, the method of the embodiment of the present invention specifically includes the following steps:

s110, acquiring a DSA sequence, and carrying out vascular stenosis recognition on each DSA image aiming at each DSA image in the DSA sequence to obtain a vascular stenosis recognition result.

Wherein, a DSA sequence is obtained, and the DSA sequence may include one or more DSA images, and in connection with an application scenario possibly related to an embodiment of the present invention, the DSA sequence may include a plurality of DSA images obtained continuously. It should be noted that, the DSA image may be an originally acquired DSA image; may be a DSA image (i.e. a vessel segmentation image or a vessel mask image) in which vessel segmentation has been completed; the DSA image can be obtained originally and can be directly used as a blood vessel segmentation image for application; etc., and are not particularly limited herein.

And respectively carrying out vascular stenosis recognition on each DSA image in the DSA sequence to obtain vascular stenosis recognition results respectively corresponding to each DSA image. In practical applications, the recognition of the vascular stenosis (i.e. detection of the vascular stenosis) may be optionally implemented by various methods, for example, a conventional target recognition method may be exemplified, for example, a method for recognizing the vascular stenosis by performing pattern recognition by using target features, where the target features may be, for example, a direction gradient histogram (histogram of oriented gradients, HOG) or Scale-invariant feature transform (Scale-invariant feature transform, SIFT), and the pattern recognition may be, for example, a support vector machine (Support Vector Machine, SVM) or a random forest; the target recognition method based on deep learning can be, for example, RCNN series, YOLO series or the like; of course, the remaining methods for identifying vascular stenosis may be implemented, and are not particularly limited herein.

For example, taking the example of packaging the method capable of realizing the recognition of the blood vessel stenosis as a blood vessel stenosis recognition module, in practical application, optionally, as shown in fig. 2, consecutive frames (i.e., consecutive multiple DSA images) in the DSA sequence are input into the blood vessel stenosis recognition module, so that the recognition of the blood vessel stenosis can be performed on these DSA images respectively by using the blood vessel stenosis recognition module; further, according to the output result of the blood vessel stenosis recognition module, blood vessel stenosis recognition results corresponding to the DSA images are obtained.

Still further exemplary, the vessel stenosis recognition result may be marked by a position frame, for example, a rectangular frame shown in fig. 3 is a position frame, and a region framed by the position frame is a vessel stenosis in the DSA image.

S120, extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the vascular stenosis recognition results respectively corresponding to the DSA images.

According to the related medical knowledge, it is known that the key frames for detecting the vascular stenosis need to meet the following key frame requirements: after the blood vessel stenosis recognition results corresponding to the DSA images are obtained, one or more DSA images meeting the key frame requirement can be extracted from the DSA sequence according to the blood vessel stenosis recognition results, and the extracted one or more DSA images are used as key frames.

Fig. 4 is a flow chart of another method for extracting a DSA sequence key frame provided in an embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, according to the recognition result of the vessel stenosis corresponding to each DSA image, extracting, from the DSA sequence, one or more DSA images with no artifact at the vessel stenosis and/or clear vessel boundary as key frames may include: according to the blood vessel stenosis recognition result of the DSA image, determining the central line of the DSA image at the blood vessel stenosis, and obtaining the pixel value of each pixel point positioned in the vertical direction of the central line; according to the pixel values of all the pixel points, obtaining characteristic information representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear; and extracting one or more DSA images which are free of artifacts at the narrow part of the blood vessel and/or clear in the boundary of the blood vessel from the DSA sequence as key frames according to the characteristic information corresponding to each DSA image. Wherein, the explanation of the same or corresponding terms as the above embodiments is not repeated herein.

Referring to fig. 4, the method of this embodiment may specifically include the following steps:

s210, acquiring a DSA sequence, and carrying out vascular stenosis recognition on each DSA image aiming at each DSA image in the DSA sequence to obtain a vascular stenosis recognition result.

S220, determining the central line of the DSA image at the blood vessel stenosis according to the blood vessel stenosis identification result of the DSA image, and obtaining the pixel value of each pixel point positioned in the vertical direction of the central line.

And obtaining the center line of the DSA image at the vascular stenosis according to the vascular stenosis identification result of the DSA image aiming at each DSA image in the DSA sequence. In practical applications, alternatively, the above-mentioned center line may be determined by various methods, for example, a blood vessel stenosis region may be extracted from the DSA image according to the recognition result of the blood vessel stenosis, and then the center line extracted from the blood vessel contained in the blood vessel stenosis region may be used as the center line of the DSA image at the blood vessel stenosis; for example, a central line can be extracted from the blood vessel contained in the DSA image, and then the extracted central line is intercepted according to the recognition result of the blood vessel stenosis to obtain the central line of the DSA image at the blood vessel stenosis; of course, the center line may be determined by other methods, and is not particularly limited herein. On this basis, the centerline may be extracted from the blood vessel by a manual calibration method, a topology refinement method, a distance transformation method, or an artificial intelligence (Artificial Intelligence, AI) training acquisition method, or the like, which is not particularly limited herein.

After obtaining the center line of the DSA image at the vascular stenosis, taking the direction perpendicular to the direction of the center line as the perpendicular direction, and obtaining the pixel value of each pixel point in the perpendicular direction in the DSA image. On this basis, in combination with the application scenario possibly related to the embodiment of the present invention, optionally, for the target point on the central line, a straight line including the target point and located in the vertical direction in the DSA image is taken as a vertical line, and each pixel point on the vertical line is taken as each pixel point located in the vertical direction in the DSA image. In practical application, the target point may be a pixel point on the central line that meets a preset condition, or may be a pixel point randomly selected from the central line, which is not specifically limited herein; the number of target points may be one, two or more, which may be set according to the actual situation, and is not specifically limited herein.

And S230, obtaining characteristic information representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear or not according to the pixel value of each pixel point.

The direction of the central line is the direction of the blood vessel, and then the vertical direction is perpendicular to the direction of the blood vessel. On the basis, the research finds that the pixel values of all the pixel points in the vertical direction in the DSA image can reflect whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear to a certain extent, so that the characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear is obtained according to the pixel values of all the pixel points.

S240, extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the characteristic information corresponding to each DSA image.

Because the characteristic information corresponding to each DSA image respectively can reflect whether the corresponding DSA image has an artifact at the vascular stenosis and/or whether the vascular boundary is clear, one or more DSA images without the artifact at the vascular stenosis and/or with the vascular boundary clear can be extracted from the DSA sequence as the key frame according to the characteristic information corresponding to each DSA image.

According to the technical scheme provided by the embodiment of the invention, the central line of the DSA image at the vascular stenosis is determined, and the characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear is obtained according to the pixel value of each pixel point in the DSA image, which is positioned in the vertical direction of the central line, so that the key frame can be extracted from the DSA sequence according to the characteristic information respectively corresponding to each DSA image. According to the technical scheme, the accuracy of key frame extraction is improved through pixel level processing.

An optional technical solution, before determining a centerline of the DSA image at the vascular stenosis according to the recognition result of the vascular stenosis of the DSA image, further includes:

In the case where the DSA image is an originally acquired DSA image that cannot be applied as a blood vessel segmentation image, the DSA image may be subjected to blood vessel segmentation to obtain a blood vessel segmentation image (i.e., a blood vessel mask image), so that the blood vessel segmentation image may be subjected to subsequent processing. It can be appreciated that the vessel segmentation process described above may improve the convenience and accuracy of subsequent processing, since the vessel segmentation image contains only vessels and no rest. On the basis, the blood vessel segmentation can be optionally performed by using a traditional segmentation algorithm, for example, maximum flow min-cut (Max-flow min-cut), level set or conditional random field; the segmentation algorithm based on deep learning can be utilized to segment blood vessels, for example, the segmentation algorithm can be a unet, a vnet or a nnunet; the existing segmentation software can also be used for carrying out blood vessel segmentation; etc., and are not particularly limited herein.

Illustratively, taking the case of packaging the method capable of implementing vessel segmentation as a vessel segmentation module, in practical application, optionally, as shown in fig. 5, consecutive frames (i.e., consecutive multiple DSA images) in the DSA sequence are input into the vessel segmentation module, so that vessel segmentation can be performed for these DSA images respectively by using the vessel segmentation module; and then, according to the output result of the blood vessel segmentation module, obtaining blood vessel segmentation images respectively corresponding to the DSA images.

According to the blood vessel stenosis recognition result of the DSA image, a region of interest (region of interest, ROI) can be extracted from the blood vessel segmentation image corresponding to the DSA image, namely, the region corresponding to the blood vessel stenosis recognition result in the blood vessel segmentation image is extracted as the ROI. It can be appreciated that the extracted ROI is a mask image of the DSA image at the stenosis of the blood vessel. Further, the centerline in the blood vessel included in the ROI is set as the centerline of the DSA image at the blood vessel stenosis.

According to the technical scheme, the blood vessel stenosis recognition result is matched with the blood vessel segmentation image to determine the central line, and the accuracy of the central line determination is improved by applying the blood vessel segmentation image only containing blood vessels.

Fig. 6 is a flow chart of yet another method of extracting a DSA sequence key frame provided in an embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, according to the pixel values of each pixel point, obtaining the feature information that characterizes whether the DSA image has an artifact at the vascular stenosis and/or whether the vascular boundary is clear may include: and calculating at least two pixel value gradients according to the pixel values of each pixel point, and obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear according to the at least two pixel value gradients. Wherein, the explanation of the same or corresponding terms as the above embodiments is not repeated herein.

Referring to fig. 6, the method of this embodiment may specifically include the following steps:

s310, acquiring a DSA sequence, and carrying out vascular stenosis recognition on each DSA image in the DSA sequence to obtain a vascular stenosis recognition result.

S320, determining the central line of the DSA image at the blood vessel stenosis according to the blood vessel stenosis identification result of the DSA image, and obtaining the pixel value of each pixel point positioned in the vertical direction of the central line.

In practical application, optionally, the pixel values of each pixel point located in the vertical direction of the center line can be obtained sequentially. For example, taking the above-mentioned target point example here as an example, the pixel values of the respective pixel points located on the vertical line may be sequentially obtained along the vertical direction from the target point. The pixel values of the pixel points obtained based on the above scheme can better reflect whether the DSA image has an artifact at a vascular stenosis and/or whether the vascular boundary is clear.

S330, calculating at least two pixel value gradients according to the pixel values of the pixel points.

The pixel value gradient can be calculated according to the pixel values of at least two pixel points in each pixel point, so that the at least two pixel value gradients are calculated according to the pixel values of each pixel point.

On this basis, in connection with an application scenario which may be involved in an embodiment of the present invention, a calculation example of a gradient of pixel values is provided herein. For example, the current value is selected from the pixel values of the respective pixel points, for example, a first pixel value in the pixel values of the respective pixel points may be used as the current value, and then a pixel value gradient between the current value and the reference value may be calculated using a pixel value after the current value in the pixel values of the respective pixel points as the reference value. Further, the reference value is updated to the current value, and the step of calculating a pixel value gradient between the current value and the reference value using, as the reference value, a pixel value obtained after the current value among the pixel values of the respective pixel points is repeatedly performed. Still further, in case a preset calculation end condition is satisfied, calculation of the pixel value gradients may be stopped, so as to obtain at least two pixel value gradients. It should be noted that the current value and the reference value may be obtained sequentially or at intervals, which is not specifically limited herein.

And S340, according to the gradient of at least two pixel values, obtaining characteristic information for representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear.

The at least two pixel value gradients can reflect the change information of the pixel value of each pixel point, for example, whether the pixel value of each pixel point has a sudden change in terms of the magnitude of the value, so that the characteristic information can be obtained according to the at least two pixel value gradients.

S350, extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the characteristic information corresponding to each DSA image.

According to the technical scheme provided by the embodiment of the invention, at least two pixel value gradients are calculated through the pixel values of each pixel point, and then whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear can be more accurately reflected according to the characteristic information obtained by the at least two pixel value gradients.

An optional technical solution, according to at least two pixel value gradients, obtains feature information that characterizes whether an artifact exists in a DSA image at a vascular stenosis and/or whether a vascular boundary is clear, including:

and calculating gradient difference values between every two adjacent calculated pixel value gradients in the at least two pixel value gradients, and obtaining characteristic information representing whether the DSA image has artifacts at the narrow position of the blood vessel and/or whether the boundary of the blood vessel is clear according to each gradient difference value.

Wherein, at least two pixel value gradients can be calculated in turn. For example, assuming that the pixel values of each pixel point sequentially obtained include A, B, C and D, a pixel value gradient 1 may be calculated according to a and B, a pixel value gradient 2 may be calculated according to B and C, and a pixel value gradient 3 may be calculated according to C and D. The gradient difference value is understood as the difference between a pixel value gradient calculated adjacently of a certain two of the at least two pixel value gradients. Continuing with the above example, by way of example, where pixel value gradient 1 and pixel value gradient 2 are calculated adjacently and pixel value gradient 2 and pixel value gradient 3 are calculated adjacently, the gradient difference values may be represented by the difference between pixel value gradient 1 and pixel value gradient 2 and the difference between pixel value gradient 2 and pixel value gradient 3, respectively. And calculating a gradient difference value between every two adjacent calculated pixel value gradients in the at least two pixel value gradients, thereby obtaining at least one gradient difference value.

Because the gradient difference value can reflect whether the two adjacent calculated pixel value gradients are relatively close, and when the DSA image has an artifact at a vascular stenosis position and/or a vascular boundary is clear, gradient abrupt changes exist in at least two pixel value gradients which are sequentially calculated, for example, the gradient difference value is directly transited from a larger pixel value gradient to a smaller pixel value gradient or is directly transited from a smaller pixel value gradient to a larger pixel value gradient, and the like, the characteristic information can be obtained according to the calculated gradient difference value.

According to the technical scheme, the characteristic information is obtained through the gradient difference values capable of reflecting the gradient change condition of the gradient of at least two pixel values, so that the accuracy of the characteristic information in the aspect of representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear is improved.

On the basis, optionally, according to the gradient difference values, obtaining characteristic information representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear, wherein the characteristic information comprises the following steps:

The preset difference threshold is understood to be a preset threshold value related to the gradient difference. In practice, since each gradient difference may have a positive or negative value, the absolute value of each of the gradient differences is calculated for uniform comparison. Further, when absolute values greater than a preset difference threshold exist in all calculated absolute values, which indicates that gradient abrupt change exists in gradients of at least two pixel values, it can be determined that the DSA image has no artifact and/or clear blood vessel boundaries at the blood vessel stenosis, otherwise, it is determined that the DSA image has artifact and/or blurred blood vessel boundaries at the blood vessel stenosis.

According to the technical scheme, whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear can be rapidly determined by comparing the numerical relation between the absolute value of each gradient difference value and the preset difference value threshold.

According to another alternative technical solution, according to at least two pixel value gradients, obtaining feature information representing whether an artifact exists in a DSA image at a vascular stenosis and/or whether a vascular boundary is clear, the method includes:

The preset gradient threshold value is understood to be a preset threshold value related to the gradient of the pixel value. Analysis shows that when the DSA image has an artifact at a vascular stenosis and/or a vascular boundary is clear, a target gradient generally exists in at least two pixel value gradients, one pixel point of two pixel points corresponding to two pixel values used for calculating the target gradient is located in a blood vessel, and the other pixel point is located out of the blood vessel, so that the two pixel values have a larger phase difference, and the target gradient is larger. Therefore, the characteristic information can be obtained according to at least two pixel value gradients and a preset gradient threshold value.

According to the technical scheme, whether the DSA image has an artifact at a blood vessel stenosis position and/or whether the blood vessel boundary is clear can be accurately determined by reflecting whether one of the two pixel points is located in the blood vessel and the other pixel value gradient is located outside the blood vessel and matching with the preset gradient threshold.

On the basis, optionally, according to the gradient of at least two pixel values and a preset gradient threshold value, obtaining characteristic information for representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear or not, including:

When a pixel value gradient larger than a preset gradient threshold exists in the at least two pixel value gradients, the target gradient exists in the at least two pixel value gradients, so that the DSA image can be determined to be free of artifacts at the vascular stenosis and/or clear in vascular boundaries, otherwise, the DSA image is determined to be artifacts at the vascular stenosis and/or blurred in vascular boundaries.

According to the technical scheme, whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear can be rapidly determined by comparing the numerical relation between the gradients of at least two pixel values and the preset gradient threshold.

Fig. 7 is a flow chart of yet another method for extracting key frames of DSA sequences provided in an embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, according to the pixel values of each pixel point, obtaining feature information that characterizes whether an artifact exists in a DSA image at a vascular stenosis and/or whether a vascular boundary is clear includes: and analyzing the pixel values of each pixel point to obtain the peak value shape of the pixel value peak value corresponding to the pixel value of each pixel point, and obtaining the characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear or not according to the peak value shape. The same or corresponding terms as those of the above embodiments are not repeated herein.

Referring to fig. 7, the method of this embodiment may specifically include the following steps:

s410, acquiring a DSA sequence, and carrying out vascular stenosis recognition on each DSA image aiming at each DSA image in the DSA sequence to obtain a vascular stenosis recognition result.

S420, determining the central line of the DSA image at the blood vessel stenosis according to the blood vessel stenosis identification result of the DSA image, and obtaining the pixel value of each pixel point positioned in the vertical direction of the central line.

S430, analyzing the pixel values of the pixel points to obtain the peak value shape of the pixel value peak value corresponding to the pixel value of each pixel point.

The pixel values of each pixel point are small, and to obtain the numerical variation of the pixel values, the pixel values may be analyzed, for example, the pixel values may be plotted in the order of obtaining the pixel values, so as to obtain the peak shape of the pixel value peak corresponding to the pixel value of each pixel point. The peak pixel value is understood as the pixel value (i.e., the maximum value) with the largest value among the pixel values of each pixel point. The number of the pixel value peaks may be one, two or more, and is not particularly limited herein. The peak shape may be used to describe the shape formed by the peaks of the pixel values, and may be, for example, a column, a rectangular wave, a trapezoid, or the like, which is not specifically limited herein, in connection with the application scenario that may be related to the embodiments of the present invention. It should be noted that, the peak shape may reflect the value change of the pixel values, and specifically may reflect how fast the pixel values change in terms of value, for example, from a minimum value to a maximum value.

And S440, obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear according to the peak shape.

According to the research, when the DSA image has artifacts at the narrow part of the blood vessel and/or the boundary of the blood vessel is clear, the pixel value of each pixel point changes rapidly, otherwise, the change is gentle, so that the characteristic information can be obtained according to the peak value shape capable of reflecting the numerical value change condition.

S450, extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the characteristic information corresponding to each DSA image.

According to the technical scheme provided by the embodiment of the invention, the pixel values of all the pixel points are analyzed to obtain the peak shapes of the pixel value peaks corresponding to the pixel values, so that the characteristic information is obtained according to the peak shapes capable of reflecting the numerical variation condition of the pixel values, and the accuracy of the characteristic information in the aspect of representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the blood vessel boundary is clear is improved.

An optional technical solution, according to the peak shape, obtains feature information that characterizes whether an artifact exists in a DSA image at a vascular stenosis and/or whether a vascular boundary is clear, including: when the peak shape is columnar, then the DSA image is determined to be free of artifacts at the vessel stenosis and/or the vessel boundary is clear.

When the peak shape is columnar, the pixel values of the pixel points are rapidly changed in numerical value, so that the DSA image is free of artifacts at the narrow part of the blood vessel and/or the boundary of the blood vessel is clear, otherwise, the DSA image is free of artifacts at the narrow part of the blood vessel and/or the boundary of the blood vessel is blurred.

According to the technical scheme, whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear can be rapidly determined by judging whether the peak shape is columnar or not.

In order to better understand the above-described respective technical solutions as a whole, an exemplary description thereof is given below in conjunction with specific examples. For example, referring to fig. 8, for each DSA image in the DSA sequence, an ROI is extracted from a vessel segmentation image corresponding to the DSA image according to a vessel stenosis recognition result of the DSA image. And obtaining a central line in a blood vessel contained in the ROI, calculating at least two pixel value gradients along the vertical direction of the central line, and determining whether a pixel value gradient X larger than a preset gradient threshold exists in the at least two pixel value gradients. After each DSA image is processed according to the above steps, one or more DSA images with pixel value gradient X may be extracted from the DSA sequence as key frames.

Fig. 9 is a block diagram of an apparatus for extracting a DSA sequence key frame according to an embodiment of the present invention, which is configured to perform the method for extracting a DSA sequence key frame according to any of the above embodiments. The device and the method for extracting the DSA sequence key frames in the above embodiments belong to the same inventive concept, and reference may be made to the above embodiments of the method for extracting the DSA sequence key frames for details which are not described in detail in the embodiments of the device for extracting the DSA sequence key frames. Referring to fig. 9, the apparatus may specifically include: a vascular stenosis recognition result obtaining module 510 and a key frame extracting module 520. Wherein,,

the vessel stenosis recognition result obtaining module 510 is configured to obtain a DSA sequence, and perform vessel stenosis recognition on each DSA image in the DSA sequence to obtain a vessel stenosis recognition result;

the key frame extraction module 520 is configured to extract, as a key frame, one or more DSA images from the DSA sequence, which are free from artifacts at the vascular stenosis and/or have clear boundaries of the blood vessels, according to the recognition results of the vascular stenosis corresponding to each DSA image.

Optionally, the key frame extraction module 520 includes:

the pixel value obtaining sub-module is used for determining the central line of the DSA image at the vascular stenosis according to the vascular stenosis identification result of the DSA image and obtaining the pixel value of each pixel point positioned in the vertical direction of the central line;

The characteristic information obtaining submodule is used for obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear according to the pixel value of each pixel point;

and the key frame extraction sub-module is used for extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the characteristic information corresponding to each DSA image.

On the basis, an optional feature information obtaining sub-module comprises:

the first obtaining unit of the characteristic information is used for calculating at least two pixel value gradients according to the pixel values of each pixel point, and obtaining characteristic information representing whether the DSA image has artifacts at the narrow position of the blood vessel and/or whether the boundary of the blood vessel is clear according to the at least two pixel value gradients;

or,

and the characteristic information second obtaining unit is used for analyzing the pixel values of all the pixel points to obtain the peak value shape of the pixel value peak value corresponding to the pixel values of all the pixel points, and obtaining characteristic information representing whether the DSA image has artifacts at the narrow position of the blood vessel and/or whether the boundary of the blood vessel is clear or not according to the peak value shape.

On the basis, an optional first obtaining unit of the characteristic information includes:

The first obtaining subunit of the characteristic information is used for calculating a gradient difference value between every two adjacent pixel value gradients in at least two pixel value gradients and obtaining characteristic information representing whether an artifact exists at a vascular stenosis position and/or whether a vascular boundary is clear or not according to each gradient difference value; or,

and the characteristic information second obtaining subunit is used for obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear according to the gradient of at least two pixel values and a preset gradient threshold value.

On this basis, an optional feature information first obtains the subunit, specifically:

Alternatively, the feature information second obtaining subunit is specifically configured to:

Alternatively, the feature information second obtaining unit includes:

And the third obtaining subunit of the characteristic information is used for determining that the DSA image has no artifact at the narrow part of the blood vessel and/or the boundary of the blood vessel is clear when the peak value is columnar.

Alternatively, the apparatus for extracting a DSA sequence key frame further includes:

the vessel segmentation image obtaining module is used for carrying out vessel segmentation on the DSA image before determining the central line of the DSA image at the vessel stenosis according to the vessel stenosis identification result of the DSA image so as to obtain a vessel segmentation image.

On the basis, optionally, the pixel value is obtained as a sub-module, which comprises:

and the central line determining unit is used for extracting a region of interest from the blood vessel segmentation image corresponding to the DSA image according to the blood vessel stenosis recognition result of the DSA image, and taking the central line in the blood vessel contained in the region of interest as the central line of the DSA image at the blood vessel stenosis.

According to the device for extracting the key frames of the DSA sequence, provided by the embodiment of the invention, the vascular stenosis recognition is carried out on each DSA image in the DSA sequence by the mutual cooperation of the vascular stenosis recognition result obtaining module and the key frame extracting module, and then one or more DSA images which are free of artifacts and/or clear in vascular boundaries at the vascular stenosis position can be extracted from the DSA sequence as the key frames according to the vascular stenosis recognition results respectively corresponding to each DSA image. The device can automatically extract the key frames from the DSA sequence, thereby achieving the effect of reducing the workload of doctors.

The device for extracting the DSA sequence key frames provided by the embodiment of the invention can be used for executing the method for extracting the DSA sequence key frames provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

It should be noted that, in the above embodiment of the apparatus for extracting a DSA sequence key frame, each unit and module included are only divided according to the functional logic, but not limited to the above division, so long as the corresponding function can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.

Fig. 10 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 10, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the method of extracting the DSA sequence key frames.

In some embodiments, the method of extracting the DSA sequence key frames may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method of extracting DSA sequence key frames described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of extracting the DSA sequence key frames in any other suitable way (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method for extracting a DSA sequence key frame, comprising:

acquiring a DSA sequence, and carrying out vascular stenosis recognition on each DSA image aiming at each DSA image in the DSA sequence to obtain a vascular stenosis recognition result;

2. The method according to claim 1, wherein the extracting one or more DSA images from the DSA sequence, which are free from artifacts at the vascular stenosis and/or have clear boundaries of the blood vessel, as key frames according to the respective recognition result of the vascular stenosis of each DSA image, comprises:

according to the pixel values of the pixel points, obtaining characteristic information representing whether the DSA image has artifacts at the narrow part of the blood vessel and/or whether the boundary of the blood vessel is clear;

and extracting one or more DSA images which are free of artifacts at the vascular stenosis and/or clear in vascular boundaries from the DSA sequence as key frames according to the characteristic information respectively corresponding to the DSA images.

3. The method according to claim 2, wherein the obtaining, based on the pixel values of the respective pixels, feature information indicating whether the DSA image has artifacts in a vascular stenosis and/or whether a vascular boundary is clear, includes:

calculating at least two pixel value gradients according to the pixel values of the pixel points, and obtaining characteristic information representing whether artifacts exist at a blood vessel stenosis position and/or whether a blood vessel boundary is clear or not according to the at least two pixel value gradients;

Or,

and analyzing the pixel values of the pixel points to obtain the peak shape of a pixel value peak corresponding to the pixel values of the pixel points, and obtaining characteristic information representing whether the DSA image has artifacts at a vascular stenosis position and/or whether the vascular boundary is clear according to the peak shape.

4. A method according to claim 3, wherein said deriving, from said at least two pixel value gradients, characteristic information characterizing whether or not the DSA image is subject to artifacts at vascular stenosis and/or whether or not vessel boundaries are clear, comprises:

calculating gradient difference values between every two adjacent calculated pixel value gradients in the at least two pixel value gradients, and obtaining characteristic information representing whether artifacts exist at a vascular stenosis position and/or whether a vascular boundary is clear or not according to each gradient difference value;

or,

and obtaining characteristic information representing whether the DSA image has artifacts at the vascular stenosis and/or whether the vascular boundary is clear according to the gradients of the at least two pixel values and a preset gradient threshold.

5. The method of claim 4, wherein the obtaining, from each of the gradient differences, feature information that characterizes whether the DSA image has artifacts at a vascular stenosis and/or whether a vascular boundary is clear, comprises:

And when the absolute value of each gradient difference value is larger than the absolute value of a preset difference value threshold, determining that the DSA image has no artifact at the narrow position of the blood vessel and/or the blood vessel boundary is clear.

6. The method according to claim 4, wherein the obtaining, from the at least two pixel value gradients and a preset gradient threshold, feature information characterizing whether the DSA image has artifacts at a vascular stenosis and/or whether a vascular boundary is clear, comprises:

and when the pixel value gradients larger than a preset gradient threshold exist in the at least two pixel value gradients, determining that the DSA image has no artifact at a vascular stenosis position and/or a vascular boundary is clear.

7. A method according to claim 3, wherein said deriving, from said peak shape, characteristic information characterizing whether or not said DSA image is present in a vessel stenosis and/or whether or not a vessel boundary is clear, comprises:

when the peak shape is columnar, then it is determined that the DSA image is free of artifacts at the vessel stenosis and/or vessel boundaries are clear.

8. The method of claim 2, wherein prior to the determining a centerline of the DSA image at a vessel stenosis from the DSA image's vessel stenosis identification result, further comprising:

And performing blood vessel segmentation on the DSA image to obtain a blood vessel segmentation image.

9. The method of claim 8, wherein the determining a centerline of the DSA image at a vascular stenosis from the DSA image recognition result comprises:

and extracting a region of interest from a blood vessel segmentation image corresponding to the DSA image according to a blood vessel stenosis recognition result of the DSA image, and taking a central line in a blood vessel contained in the region of interest as a central line of the DSA image at a blood vessel stenosis position.

10. An apparatus for extracting a DSA sequence key frame, comprising:

the blood vessel stenosis recognition result obtaining module is used for obtaining a DSA sequence, and carrying out blood vessel stenosis recognition on each DSA image in the DSA sequence to obtain a blood vessel stenosis recognition result;

11. An electronic device, comprising:

At least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores a computer program executable by the at least one processor to cause the at least one processor to perform the method of extracting DSA sequence key frames as claimed in any one of claims 1 to 9.

12. A computer readable storage medium storing computer instructions for causing a processor to perform the method of extracting DSA sequence key frames according to any of claims 1-9.