CN115908413B - Contrast image segmentation method, electronic device, processing system and storage medium - Google Patents
Contrast image segmentation method, electronic device, processing system and storage medium Download PDFInfo
- Publication number
- CN115908413B CN115908413B CN202310016740.3A CN202310016740A CN115908413B CN 115908413 B CN115908413 B CN 115908413B CN 202310016740 A CN202310016740 A CN 202310016740A CN 115908413 B CN115908413 B CN 115908413B
- Authority
- CN
- China
- Prior art keywords
- image
- segmentation
- contrast
- segmented
- contrast image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The embodiment of the invention provides a contrast image segmentation method, electronic equipment, a processing system and a storage medium, wherein an initial contrast image is firstly acquired; then inputting the image into a segmentation model to obtain a segmentation result of the contrast image; then binarizing the segmentation result according to the first confidence coefficient threshold value and the second confidence coefficient threshold value to obtain a first segmentation image and a second segmentation image; wherein the first confidence threshold is less than the second confidence threshold; and finally, determining a final segmented image according to the first segmented image and the second segmented image. The contrast image is segmented according to the traditional method, and then a first segmented image with better segmentation details and a large amount of noise is obtained through different confidence thresholds, and a second segmented image with slightly worse vascular segmentation details and less noise is obtained, so that the advantages of the two segmented images can be combined, a final segmented image with good segmentation details and less noise is obtained, and the segmentation accuracy of the contrast image is effectively improved.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method for segmenting a contrast image, an electronic device, a processing system, and a storage medium.
Background
A contrast image is a medical image of wide application. The method for acquiring the angiocarpy contrast image comprises the steps of inserting a catheter through femoral artery of thigh or other peripheral arteries, sending the catheter to ascending aorta, searching for left or right coronary artery for insertion, injecting contrast agent, and enabling coronary artery to be developed under X-ray, so that the contrast image is obtained. Since other tissues such as bones of a human body are also imaged by X-rays, a large amount of noise is often present in a contrast image, and the contrast image is easily blurred, so that the contrast image needs to be processed.
Vessel segmentation techniques are the basis for contrast image processing. In the prior art, a contrast image is usually segmented through a machine learning model, and binarization processing is carried out according to a confidence coefficient of 0.5 after the segmentation processing, but the contrast image binarized by the traditional method has a large amount of noise or pixel deletion due to the fact that the contrast image is complex, and the segmentation accuracy of the contrast image is low.
Disclosure of Invention
In view of the above, the present invention provides a contrast image segmentation method, an electronic device, a processing system and a storage medium, which aim to solve the problem of low accuracy of contrast image segmentation in the prior art.
A first aspect of an embodiment of the present invention provides a method for segmenting a contrast image, including:
acquiring an initial contrast image;
inputting the initial contrast image into a pre-established segmentation model to obtain a segmentation result of the contrast image;
performing binarization processing on the segmentation result according to the first confidence threshold value to obtain a first segmentation image, and performing binarization processing on the segmentation result according to the second confidence threshold value to obtain a second segmentation image; wherein the first confidence threshold is less than the second confidence threshold;
a final segmented image of the contrast image is determined from the first segmented image and the second segmented image.
A second aspect of an embodiment of the present invention provides a contrast image segmentation apparatus, including:
the acquisition module is used for acquiring an initial contrast image;
the segmentation module is used for inputting the initial contrast image into a pre-established segmentation model to obtain a segmentation result of the contrast image;
the processing module is used for carrying out binarization processing on the segmentation result according to the first confidence threshold value to obtain a first segmentation image, and carrying out binarization processing on the segmentation result according to the second confidence threshold value to obtain a second segmentation image; wherein the first confidence threshold is less than the second confidence threshold;
and the determining module is used for determining a final segmentation image of the contrast image according to the first segmentation image and the second segmentation image.
A third aspect of an embodiment of the present invention provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the contrast image segmentation method of the first aspect as above when the computer program is executed.
A fourth aspect of an embodiment of the present invention provides a contrast image processing system comprising a medical X-ray examination apparatus and an electronic apparatus as in the above third aspect.
A fifth aspect of an embodiment of the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the contrast image segmentation method of the first aspect above.
The embodiment of the invention provides a contrast image segmentation method, electronic equipment, a processing system and a storage medium, wherein an initial contrast image is firstly acquired; then inputting the initial contrast image into a pre-established segmentation model to obtain a segmentation result of the contrast image; then carrying out binarization processing on the segmentation result according to a first confidence coefficient threshold value to obtain a first segmentation image, and carrying out binarization processing on the segmentation result according to a second confidence coefficient threshold value to obtain a second segmentation image; wherein the first confidence threshold is less than the second confidence threshold; and finally, determining a final segmentation image of the contrast image according to the first segmentation image and the second segmentation image. The contrast image is segmented according to the traditional method, and then a first segmented image with better segmentation details and a large amount of noise is obtained through two different confidence thresholds, and a second segmented image with slightly worse vascular segmentation details and less noise is obtained, so that the advantages of the first segmented image and the second segmented image can be combined, a final segmented image with good segmentation details and less noise is obtained, and the segmentation accuracy of the contrast image is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an application scene diagram of a contrast image segmentation method provided by an embodiment of the present invention;
FIG. 2 is a flowchart of an implementation of a contrast image segmentation method provided by an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a contrast image segmentation apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
Fig. 1 is an application scene diagram of a contrast image segmentation method according to an embodiment of the present invention. As shown in fig. 1, in some embodiments, the method for segmenting a contrast image provided in the embodiments of the present invention may be applied to, but is not limited to, the application scenario. The system may include: a medical X-ray examination apparatus 11 and an electronic apparatus 12.
Firstly, the catheter needs to be inserted through femoral artery or other peripheral artery of thigh of patient, and sent to ascending aorta, then left or right coronary artery mouth is searched for insertion, then contrast medium is injected into coronary artery, at this time, the medical X-ray examination device 11 shoots developed contrast image, and sends it to electronic device 12, and electronic device 12 segments and processes the contrast image to obtain clear cardiovascular segmentation map.
The electronic device 12 may be a terminal or a server, the terminal may be an examination terminal provided on the medical X-ray examination device 11, an office terminal of a doctor, or the like, and the server may be a management server of a hospital information management system of a hospital, or may be a cloud server, which is not limited herein.
Fig. 2 is a flowchart of an implementation of a contrast image segmentation method according to an embodiment of the present invention. As shown in fig. 2, a contrast image segmentation method, applied to the electronic device 12 shown in fig. 1, may include:
s210, acquiring an initial contrast image.
In the embodiment of the present invention, the initial contrast image may be taken in real time by the medical X-ray examination apparatus 11 in fig. 1, or may be acquired from an information management system of a hospital, which is not limited herein.
S220, inputting the initial contrast image into a pre-established segmentation model to obtain a segmentation result of the contrast image.
In the embodiment of the present invention, the segmentation model may be a supervised learning model, a migration learning model, or the like, which is not limited herein. When the segmentation model is trained, the contrast images in the training set are required to be sampled, different areas in the contrast images can be classified during sampling, for example, the contrast images can be divided into a simple foreground area, a difficult foreground area, a simple background area, a complex background area and the like, the sampling proportion of the difficult foreground area and the complex background area is adjusted by adjusting the proportion of the images sampled in the different areas, and the sampling sum of the foreground and the background is balanced, so that the segmentation model can effectively segment the foreground area and the background area, and the recognition effect of the difficult foreground and the complex background is improved.
S230, carrying out binarization processing on the segmentation result according to a first confidence threshold value to obtain a first segmentation image, and carrying out binarization processing on the segmentation result according to a second confidence threshold value to obtain a second segmentation image; wherein the first confidence threshold is less than the second confidence threshold.
S240, determining a final segmentation image of the contrast image according to the first segmentation image and the second segmentation image.
In the embodiment of the invention, the output of the segmentation model is an image marked with a confidence, each pixel point in the image is provided with a confidence, and binarization is usually performed by taking 0.5 as a threshold, namely, pixels larger than 0.5 are treated as blood vessels, and blood vessels smaller than 0.5 are treated as the background. However, the detail of the image in the image obtained by the recognition is poor, noise exists, and the recognition effect is poor.
Therefore, the conventional binarization processing can be improved. The confidence threshold may be lowered, for example from 0.5 to 0.1, and it may be found that the details of the image after binarization are greatly improved, but this way the noise is further increased.
In the embodiment of the invention, the contrast image is segmented according to the traditional method, and then the first segmented image with better segmentation details and a large amount of noise is obtained through two different confidence thresholds, and the second segmented image with slightly worse vascular segmentation details and less noise is obtained, so that the advantages of the first segmented image and the second segmented image can be combined, the final segmented image with good segmentation details and less noise is obtained, and the segmentation accuracy of the contrast image is effectively improved.
In addition, due to factors such as blood vessel blocking, noise interference, unclear shooting and the like, a breakpoint of a blood vessel exists in the processed image, so that an isolated blood vessel exists outside a main blood vessel in the segmented image, and in the binarization process, the isolated blood vessel is easily identified as background noise by a higher confidence threshold value, so that the segmentation effect of the blood vessel is poor, therefore, the main blood vessel and the isolated blood vessel are reserved through a first segmentation image, the low noise characteristic of the image is reserved through a second segmentation image, and a better segmentation image is obtained through combination.
In some embodiments, S240 may include: firstly, blood vessels of a first communication area in a first segmented image are segmented separately, and then the segmented blood vessels of a main communication area are directly covered in the first communication area of a second segmented image, so that a final segmented image of a contrast image is obtained. The first communication area is 2 communication areas with the largest area.
In the embodiment of the invention, the segmentation details of the first segmentation image on the blood vessel are better, so that the main blood vessel, namely the communication region with the largest area, can be reserved. In addition, there may be a single communication region (i.e., isolated blood vessel) formed by a part of blood vessels caused by a blood vessel breakpoint, and this part of blood vessels will not be in communication with the main communication region, and when the area is small, this part of blood vessels can be ignored, but when the area is large, this communication region needs to be collected, and the 2 communication regions with the largest area, i.e., the first communication region, are formed with the largest communication region.
The background noise of the second segmented image is less, but the details of blood vessels are poor, so that the blood vessels segmented by the first communication area in the first segmented image are directly covered into the second segmented image, and the segmentation details of the first segmented image and the low-noise characteristic of the second segmented image can be combined, so that the processing effect of the contrast image is effectively improved.
In some embodiments, the pixels in the first segmented image are divided into first vessel pixels and first background pixels; the pixel points in the second divided image are divided into a second blood vessel pixel point and a second background pixel point. Accordingly, S240 may include: overlapping each pixel point in the first divided image and each pixel point in the second divided image in a one-to-one correspondence manner to obtain an overlapped image; wherein the overlapping image includes a first overlapping region and a second overlapping region; the pixel points in the first overlapping area are obtained by overlapping the first background pixel points and the second background pixel points; the second overlapping region overlaps a region of the image other than the first overlapping region; when the second overlapping area meets the preset condition, setting the second overlapping area as a blood vessel area; when the second overlapping area does not meet the preset condition, setting the second overlapping area as a background area; and according to the first overlapping area, the background area and the blood vessel area, the final segmentation image of the contrast image is obtained by stitching.
In the embodiment of the invention, after the first segmentation image and the second segmentation image are overlapped, three pixel points exist, namely, a pixel point A obtained by overlapping a first background pixel point and a second background pixel point, a pixel point B obtained by overlapping a first blood vessel pixel point and a second background pixel point, and a pixel point C obtained by overlapping a first blood vessel pixel point and a second blood vessel pixel point.
After the above-described overlapping is completed, the 3 types of pixel points may be set to different colors, for example, pixel point a is set to gray, pixel point B is set to black, and pixel point C is set to white. The gray regions are the first overlapping regions described above, and each of the second overlapping regions is formed by doping black and white. It is thus possible to determine whether each second overlapping region is more likely to be a blood vessel or a background by the ratio of black and white. If the white occupancy in the second overlapping region is relatively large, the second overlapping region is considered to be more likely to be a background, and the whole second overlapping region is filled with black; if the black color is relatively large, it is considered that the blood vessel is more likely to be present, and the entire second overlapping region is filled with white.
In some embodiments, the preset condition is that an area of the second overlapping area is greater than a preset area, and a ratio of a pixel point obtained by overlapping the first blood vessel pixel point and the second blood vessel pixel point in the second overlapping area in all pixel points of the second overlapping area is greater than a preset proportion.
In the embodiment of the present invention, in addition to the above-mentioned determination of the black-and-white ratio (i.e., the pixel point ratio is greater than the preset ratio), the determination may be performed by the area of each second overlapping region. For a small overlapping area, the possibility of background noise is higher, and even if the area is a blood vessel, the area is very small, the effect of identifying the whole blood vessel is not greatly influenced, so that the area is small and the area is filled as the background, thereby effectively weakening the influence of the background noise.
In some embodiments, the first confidence threshold is within a first range and the second confidence threshold is within a second range. Correspondingly, the training process of the segmentation model comprises the following steps: acquiring a contrast training image and a label image corresponding to the contrast training image; forming a training set by the contrast training image and the label image corresponding to the contrast training image, and training the segmentation model; traversing the values of the first confidence coefficient threshold values in the first range and traversing the values of the second confidence coefficient threshold values in the second range, and processing the segmentation result according to the first confidence coefficient threshold value under each value and the second confidence coefficient threshold value under each value to obtain a plurality of final segmentation images of the contrast training image; evaluating the plurality of final segmented images according to the label image to obtain an evaluation value; taking the value of the first confidence threshold corresponding to the final segmentation image with the highest evaluation value as the final value of the first confidence threshold; and taking the value of the second confidence threshold corresponding to the final segmentation image with the highest evaluation value as the final value of the second confidence threshold.
In the embodiment of the present invention, in addition to the above sample acquisition and model training, the training process of the segmentation model needs to select the most suitable first confidence threshold and second confidence threshold. For example, the first confidence threshold has a value of 0.1 and 0.3, and the second confidence threshold has a value of 0.5 and 0.6, and the combination may include: and (3) performing binarization processing on segmentation results obtained during training of the training set according to the combinations, and then evaluating the final segmentation image, wherein the combination with the highest evaluation value is selected as a first confidence threshold and a second confidence threshold.
In the embodiment of the present invention, the evaluation value may include at least one of: sensitivity, specificity, accuracy, area under receiver operating characteristics, DICE coefficient, and IOU overlap.
In some embodiments, the first range is [0.1,0.3]; the second range is [0.5,0.6].
In some embodiments, prior to S240, the method may further comprise: performing binarization processing on the segmentation result according to a third confidence threshold value to obtain a third segmentation image; wherein the third confidence threshold is less than the first confidence threshold; accordingly, S240 may include: a final segmented image of the contrast image is determined from the third segmented image, the first segmented image and the second segmented image.
In the embodiment of the invention, the third confidence threshold value may be 0.1, and since the third confidence threshold value is very small, the obtained third segmentation image has a stronger segmentation effect on the blood vessels, and more tiny blood vessels are attached to the segmented main blood vessels, namely, the area of the largest connected region is larger, so that after the first segmentation image and the second segmentation image are overlapped in the above manner, an image with better details and very little noise is obtained, and then the main blood vessels, namely, the connected region with the largest area, in the third segmentation image are covered in the image after the above overlapping process, so that in the final segmentation result, more tiny blood vessels are attached to the main blood vessels, the details are better, and because only the main blood vessels are covered, the isolated blood vessels of the background region and the breakpoint are still along the image in the above overlapping process, the identification of the isolated blood vessels and the low noise characteristic of the image can be ensured.
In some embodiments, S220 may include: dividing the initial contrast image according to a matched filtering algorithm to obtain a fourth divided image; and inputting the initial contrast image and the fourth segmentation image into a pre-established segmentation model to obtain a segmentation result of the contrast image.
In the embodiment of the invention, the original contrast image is segmented according to the traditional matched filtering algorithm, and then the third segmented image and the original image are input into the segmentation model for comparison, so that noise generated in the segmentation process is removed, break points caused by pixel missing are complemented, and the accuracy of contrast image segmentation is effectively improved.
In summary, the beneficial effects of the invention are as follows:
the contrast image is segmented according to the traditional method, and then a first segmented image with better segmentation details and a large amount of noise is obtained through two different confidence thresholds, and a second segmented image with slightly worse vascular segmentation details and less noise is obtained, so that the advantages of the first segmented image and the second segmented image can be combined, a final segmented image with good segmentation details and less noise is obtained, and the segmentation accuracy of the contrast image is effectively improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a contrast image segmentation apparatus according to an embodiment of the present invention. As shown in fig. 3, in some embodiments, the contrast image segmentation apparatus 3 includes:
an acquisition module 310, configured to acquire an initial contrast image;
the segmentation module 320 is configured to input an initial contrast image into a pre-established segmentation model, so as to obtain a segmentation result of the contrast image;
the processing module 330 is configured to perform binarization processing on the segmentation result according to a first confidence threshold to obtain a first segmented image, and perform binarization processing on the segmentation result according to a second confidence threshold to obtain a second segmented image; wherein the first confidence threshold is less than the second confidence threshold;
a determining module 340 is configured to determine a final segmented image of the contrast image based on the first segmented image and the second segmented image.
Optionally, the pixel points in the first segmented image are divided into a first vascular pixel point and a first background pixel point; the pixel points in the second divided image are divided into a second blood vessel pixel point and a second background pixel point. Correspondingly, the determining module 340 is specifically configured to overlap each pixel point in the first divided image with each pixel point in the second divided image in a one-to-one correspondence manner, so as to obtain an overlapped image; wherein the overlapping image includes a first overlapping region and a second overlapping region; the pixel points in the first overlapping area are obtained by overlapping the first background pixel points and the second background pixel points; the second overlapping region overlaps a region of the image other than the first overlapping region; when the second overlapping area meets the preset condition, setting the second overlapping area as a blood vessel area; when the second overlapping area does not meet the preset condition, setting the second overlapping area as a background area; and according to the first overlapping area, the background area and the blood vessel area, the final segmentation image of the contrast image is obtained by stitching.
Optionally, the preset condition is that the area of the second overlapping area is larger than the preset area, and the ratio of the pixel points obtained by overlapping the first blood vessel pixel point and the second blood vessel pixel point in the second overlapping area in all the pixel points in the second overlapping area is larger than the preset proportion.
Optionally, the first confidence threshold is within a first range and the second confidence threshold is within a second range; correspondingly, the contrast image segmentation device 3 further comprises a training module, which is used for acquiring a contrast training image and a label image corresponding to the contrast training image; forming a training set by the contrast training image and the label image corresponding to the contrast training image, and training the segmentation model; traversing the values of the first confidence coefficient threshold values in the first range and traversing the values of the second confidence coefficient threshold values in the second range, and processing the segmentation result according to the first confidence coefficient threshold value under each value and the second confidence coefficient threshold value under each value to obtain a plurality of final segmentation images of the contrast training image; evaluating the plurality of final segmented images according to the label image to obtain an evaluation value; taking the value of the first confidence threshold corresponding to the final segmentation image with the highest evaluation value as the final value of the first confidence threshold; and taking the value of the second confidence threshold corresponding to the final segmentation image with the highest evaluation value as the final value of the second confidence threshold.
Optionally, the first range is [0.1,0.3]; the second range is [0.5,0.6].
Optionally, the shadow image processing device 3 further includes a third segmentation module, configured to perform binarization processing on the segmentation result according to a third confidence threshold value to obtain a third segmented image; wherein the third confidence threshold is less than the first confidence threshold; accordingly, the determining module 340 is configured to determine a final segmented image of the contrast image according to the third segmented image, the first segmented image and the second segmented image.
Optionally, the segmentation module 320 is specifically configured to segment the initial contrast image according to a matched filtering algorithm to obtain a fourth segmented image; and inputting the initial contrast image and the fourth segmentation image into a pre-established segmentation model to obtain a segmentation result of the contrast image.
The contrast image segmentation apparatus provided in this embodiment may be used to execute the above method embodiments, and its implementation principle and technical effects are similar, and this embodiment will not be described herein.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 4, an electronic device 4 according to an embodiment of the present invention is provided, the electronic device 4 of the embodiment including: a processor 40, a memory 41 and a computer program 42 stored in the memory 41 and executable on the processor 40. The steps of the various contrast image segmentation method embodiments described above, such as steps 210 through 240 shown in fig. 2, are implemented when the processor 40 executes the computer program 42. Alternatively, the processor 40, when executing the computer program 42, performs the functions of the modules/units of the system embodiments described above, such as the functions of the modules 310-340 shown in fig. 3.
By way of example, the computer program 42 may be partitioned into one or more modules/units, which are stored in the memory 41 and executed by the processor 40 to complete the present invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions for describing the execution of the computer program 42 in the electronic device 4.
The electronic device 4 may be a terminal or a server, the terminal may be a mobile phone, an MCU, an ECU, etc., the server may be a physical server or a cloud server, and the electronic device 4 may include, but is not limited to, a processor 40, a memory 41. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not meant to be limiting of the electronic device 4, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input-output device, a network access device, a bus, etc.
The processor 40 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store computer programs and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
An embodiment of the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above-described embodiment of a contrast image segmentation method.
The computer readable storage medium stores a computer program 42, the computer program 42 comprising program instructions which, when executed by the processor 40, implement all or part of the processes of the above described embodiments, or may be implemented by means of hardware associated with the instructions of the computer program 42, the computer program 42 being stored in a computer readable storage medium, the computer program 42, when executed by the processor 40, implementing the steps of the above described embodiments of the method. The computer program 42 comprises computer program code, which may be in the form of source code, object code, executable files, or in some intermediate form, among others. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The computer readable storage medium may be an internal storage unit of the electronic device of any of the foregoing embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the computer-readable storage medium may also include both internal storage units and external storage devices of the electronic device. The computer-readable storage medium is used to store a computer program and other programs and data required for the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (8)
1. A contrast image segmentation method, comprising:
acquiring an initial contrast image;
inputting the initial contrast image into a pre-established segmentation model to obtain a segmentation result of the contrast image;
performing binarization processing on the segmentation result according to a first confidence threshold value to obtain a first segmentation image, and performing binarization processing on the segmentation result according to a second confidence threshold value to obtain a second segmentation image; wherein the first confidence threshold is less than the second confidence threshold;
determining a final segmented image of the contrast image from the first segmented image and the second segmented image;
the pixel points in the first segmented image are divided into a first blood vessel pixel point and a first background pixel point; the pixel points in the second divided image are divided into a second blood vessel pixel point and a second background pixel point;
said determining a final segmented image of the contrast image from said first segmented image and said second segmented image, comprising:
overlapping each pixel point in the first divided image and each pixel point in the second divided image in a one-to-one correspondence manner to obtain an overlapped image; wherein the overlapping image includes a first overlapping region and a second overlapping region; the pixel points in the first overlapping area are overlapped by the first background pixel points and the second background pixel points; the second overlapping region is a region of the overlapping image other than the first overlapping region;
when the second overlapping area meets a preset condition, setting the second overlapping area as a blood vessel area;
when the second overlapping area does not meet the preset condition, setting the second overlapping area as a background area;
splicing according to the first overlapping area, the background area and the blood vessel area to obtain a final segmentation image of the contrast image;
the preset condition is that the area of the second overlapping area is larger than a preset area, and the proportion of the pixels obtained by overlapping the first blood vessel pixels and the second blood vessel pixels in the second overlapping area in all the pixels in the second overlapping area is larger than a preset proportion.
2. The contrast image segmentation method according to claim 1, wherein the first confidence threshold is within a first range and the second confidence threshold is within a second range;
the training process of the segmentation model comprises the following steps:
acquiring a contrast training image and a label image corresponding to the contrast training image;
forming a training set by the contrast training image and the label image corresponding to the contrast training image, and training the segmentation model;
traversing the value of a first confidence coefficient threshold value in the first range and traversing the value of a second confidence coefficient threshold value in the second range, and processing the segmentation result according to the first confidence coefficient threshold value under each value and the second confidence coefficient threshold value under each value to obtain a plurality of final segmentation images of the contrast training image;
evaluating the plurality of final segmented images according to the tag image to obtain an evaluation value;
taking the value of a first confidence coefficient threshold corresponding to the final segmentation image with the highest evaluation value as the final value of the first confidence coefficient threshold; and taking the value of a second confidence threshold corresponding to the final segmentation image with the highest evaluation value as the final value of the second confidence threshold.
3. The contrast image segmentation method as set forth in claim 2, wherein the first range is [0.1,0.3]; the second range is [0.5,0.6].
4. The contrast image segmentation method as set forth in claim 1, further comprising, prior to determining a final segmented image of a contrast image from the first segmented image and the second segmented image:
performing binarization processing on the segmentation result according to a third confidence threshold value to obtain a third segmentation image; wherein the third confidence threshold is less than the first confidence threshold;
said determining a final segmented image of the contrast image from said first segmented image and said second segmented image, comprising:
and determining a final segmentation image of the contrast image according to the third segmentation image, the first segmentation image and the second segmentation image.
5. The method of any one of claims 1-4, wherein inputting the initial contrast image into a pre-established segmentation model to obtain a segmentation result of the contrast image comprises:
dividing the initial contrast image according to a matched filtering algorithm to obtain a fourth divided image;
and inputting the initial contrast image and the fourth segmentation image into a pre-established segmentation model to obtain a segmentation result of the contrast image.
6. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the contrast image segmentation method according to any one of the preceding claims 1-5 when the computer program is executed.
7. A contrast image processing system comprising a medical X-ray examination apparatus and an electronic device as claimed in claim 6.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of the contrast image segmentation method according to any one of the preceding claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310016740.3A CN115908413B (en) | 2023-01-06 | 2023-01-06 | Contrast image segmentation method, electronic device, processing system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310016740.3A CN115908413B (en) | 2023-01-06 | 2023-01-06 | Contrast image segmentation method, electronic device, processing system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115908413A CN115908413A (en) | 2023-04-04 |
| CN115908413B true CN115908413B (en) | 2023-05-26 |
Family
ID=85771803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310016740.3A Active CN115908413B (en) | 2023-01-06 | 2023-01-06 | Contrast image segmentation method, electronic device, processing system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115908413B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230346B (en) * | 2017-03-30 | 2020-09-11 | 北京市商汤科技开发有限公司 | Method and device for segmenting semantic features of image and electronic equipment |
| CN111507455B (en) * | 2019-01-31 | 2021-07-13 | 数坤(北京)网络科技股份有限公司 | Neural network system generation method and device, image processing method and electronic equipment |
| CN112258380A (en) * | 2019-07-02 | 2021-01-22 | 北京小米移动软件有限公司 | Image processing method, device, equipment and storage medium |
| CN113705807B (en) * | 2021-08-26 | 2022-06-10 | 上海睿刀医疗科技有限公司 | Neural network training device and method, ablation needle arrangement planning device and method |
| CN113807448A (en) * | 2021-09-23 | 2021-12-17 | 广州极飞科技股份有限公司 | Point cloud data segmentation model training method and device, storage medium and electronic equipment |
| CN114708282B (en) * | 2022-04-20 | 2022-12-20 | 推想医疗科技股份有限公司 | Image segmentation method and device, electronic device and computer-readable storage medium |
-
2023
- 2023-01-06 CN CN202310016740.3A patent/CN115908413B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115908413A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107665486B (en) | Automatic splicing method and device applied to X-ray images and terminal equipment | |
| CN108010021B (en) | Medical image processing system and method | |
| CN109410221B (en) | Cerebral perfusion image segmentation method, device, server and storage medium | |
| CN111862044B (en) | Ultrasonic image processing method, ultrasonic image processing device, computer equipment and storage medium | |
| CN107622501B (en) | Boundary detection method for medical image | |
| JPH09508814A (en) | Automatic method and system for segmenting medical images | |
| US11967181B2 (en) | Method and device for retinal image recognition, electronic equipment, and storage medium | |
| US11379989B2 (en) | Method and device of extracting label in medical image | |
| CN110610498A (en) | Mammary gland molybdenum target image processing method, system, storage medium and equipment | |
| CN111462115B (en) | Medical image display method and device and computer equipment | |
| CN109583364A (en) | Image-recognizing method and equipment | |
| CN109712134B (en) | Iris image quality evaluation method and device and electronic equipment | |
| CN111462139A (en) | Medical image display method, medical image display device, computer equipment and readable storage medium | |
| CN116309676A (en) | Coronary vessel image segmentation method and device, electronic equipment and storage medium | |
| US8160336B2 (en) | Reducing false positives for automatic computerized detection of objects | |
| CN113876345A (en) | Method and device for identifying ischemic penumbra, electronic device and storage medium | |
| CN115908413B (en) | Contrast image segmentation method, electronic device, processing system and storage medium | |
| CN110443792B (en) | Bone scanning image processing method and system based on parallel deep neural network | |
| CN116030042B (en) | Diagnostic device, method, equipment and storage medium for doctor's diagnosis | |
| CN114445445B (en) | Artery segmentation method and device for CT image, electronic device and storage medium | |
| CN113920100A (en) | Knowledge distillation-based weak supervision bone scanning image hot spot segmentation method and system | |
| CN116128914A (en) | Two-stage segmentation method for contrast image, electronic device, processing system and storage medium | |
| CN112734701A (en) | Fundus focus detection method, fundus focus detection device and terminal equipment | |
| CN112529002A (en) | Tongue picture classification method and device, computer equipment and storage medium | |
| CN114612373A (en) | Image identification method and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |