CN113516701A

CN113516701A - Image processing method, image processing device, related equipment and storage medium

Info

Publication number: CN113516701A
Application number: CN202110768702.4A
Authority: CN
Inventors: 徐韵成
Original assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Current assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Priority date: 2021-07-07
Filing date: 2021-07-07
Publication date: 2021-10-19

Abstract

The application discloses an image processing method, an image processing device, related equipment and a storage medium, wherein the method comprises the following steps: acquiring a medical scanning image, wherein the medical scanning image comprises a blood vessel segmentation result, and the blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image; generating a vessel medical image containing at least one vessel based on the vessel segmentation result; displaying a medical image related to a blood vessel, wherein the medical image related to the blood vessel includes a blood vessel medical image. By means of the method, the segmented blood vessel can be displayed, and therefore a user can quickly determine whether the segmentation of the blood vessel is accurate or not.

Description

Image processing method, image processing device, related equipment and storage medium

Technical Field

The present application relates to the field of medical image processing technologies, and in particular, to an image processing method and apparatus, and related devices and storage media.

Background

By imaging the blood vessel, the relevant vascular disease can be diagnosed by observing the morphology of the blood vessel. Currently, various vascular imaging techniques have been applied in clinical practice, such as Computed Tomography Angiography (CTA), Magnetic Resonance Angiography (MRA), and the like.

At present, the diagnosis of blood vessels requires post-processing reconstruction of original images obtained by scanning, for example, the diagnosis of plaque of blood vessels requires post-processing of original images to obtain curved surface reconstruction images. Generally, the generation of post-processing medical images such as curved surface reconstructed images requires the segmentation of blood vessels and the generation of corresponding medical images based on the results of the blood vessel segmentation, that is, the generation of post-processing medical images such as curved surface reconstructed images depends on the results of the blood vessel segmentation. Therefore, whether the vessel segmentation is accurate has a great influence on the formation of the post-processing medical image.

Disclosure of Invention

The application provides an image processing method and device, and related equipment and storage medium thereof.

In order to solve the technical problem, the application adopts a technical scheme that: there is provided an image processing method including: acquiring a medical scanning image, wherein the medical scanning image comprises a blood vessel segmentation result, and the blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image; generating a vessel medical image containing at least one vessel based on the vessel segmentation result; displaying a medical image related to a blood vessel, wherein the medical image related to the blood vessel includes a blood vessel medical image.

By using the blood vessel segmentation result of the medical scanning image, the automatic generation of the blood vessel medical image can be realized without manually segmenting the blood vessel by a user to obtain the blood vessel medical image, so that the blood vessel segmentation efficiency is improved, and the waiting time of the user is reduced; moreover, the segmented blood vessel can be displayed, so that a user can evaluate the segmentation condition of the blood vessel to quickly determine whether the segmentation of the blood vessel is accurate, and then the accuracy of the segmentation of the blood vessel can be ensured after the user confirms the segmentation of the blood vessel subsequently, and the accuracy of a medical image generated by using the blood vessel medical image can be improved.

The blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image in a first deep learning mode; and/or the blood vessel medical image is a three-dimensional image; and/or, the image processing method further comprises: in the displayed vascular medical image, the name of at least one blood vessel is displayed.

Therefore, the vessel segmentation can be automatically carried out based on the medical scanning image through the first deep learning mode, the efficiency and the accuracy of vessel segmentation are improved, the waiting time of a user is reduced, and the subsequent construction time of the post-processing medical image is shortened.

Wherein, before displaying the blood vessel medical image, the image processing method further comprises: determining a target vessel in a vessel medical image; based on the center line detection result of the target blood vessel, the center line of the target blood vessel is formed in the blood vessel medical image to update the blood vessel medical image.

Therefore, the central line on the target blood vessel can be automatically formed by using the detection result of the central line of the target blood vessel without manually determining the central line by a user, so that the forming efficiency of the central line is improved, and the waiting time of the user is reduced.

Wherein, after displaying the medical image related to the blood vessel, the image processing method further comprises: and responding to the adjustment operation of the user on the blood vessel medical image, adjusting the blood vessel medical image, and displaying the adjusted blood vessel medical image.

Therefore, the blood vessel medical image is adjusted to be more accurate, and the accuracy of the post-processing medical image generated based on the blood vessel medical image can be improved.

Wherein, responding to the adjustment operation of the user on the blood vessel medical image, the adjustment of the blood vessel medical image comprises the following steps: responding to the selection operation of a user on a tool item in a functional area of the display interface, and adjusting the blood vessel medical image to be matched with the selected tool item; and/or, adjusting the blood vessel medical image, including any one of the following: adjusting blood vessels in the blood vessel medical image; adding characters input by a user at a user-specified position in the blood vessel medical image; deleting the content added by the user in the user selection area of the blood vessel medical image; at least one of moving, scaling and rotating the vascular medical image; and taking the blood vessel selected by the user in the blood vessel medical image as the adjusted blood vessel medical image.

Therefore, by setting the display function area on the display interface, the user can conveniently adjust the blood vessel medical image through the tool items in the function area.

The method for adjusting the blood vessels in the blood vessel medical image comprises the following steps: adjusting the center line of the blood vessel in the blood vessel medical image; adjusting the position and/or length of the blood vessel in the blood vessel medical image; generating new blood vessels in a vascular medical image; and/or the medical image related to the blood vessel further comprises a curved surface reconstruction image of a target blood vessel in the at least one blood vessel, and after the blood vessel medical image is adjusted and the adjusted blood vessel medical image is displayed, the image processing method further comprises the following steps: responding to the confirmation operation of the user, updating the center line of the target blood vessel by using the adjustment content of the blood vessel, and generating a new curved surface reconstruction image based on the updated center line, or sending the adjustment content of the blood vessel to a server and receiving the new curved surface reconstruction image fed back by the server; and updating the displayed curved surface reconstruction image by using the new curved surface reconstruction image.

Therefore, a new curved surface reconstruction image is generated based on the adjusted blood vessel medical image and is updated and displayed, so that a user can check the updated medical image to confirm whether a place needing to be adjusted exists and improve the accuracy of the curved surface reconstruction image.

Wherein the vessel-related medical image further comprises at least one of: the method comprises the following steps of obtaining a curved surface reconstruction image of a target blood vessel in at least one blood vessel, a blood vessel section image corresponding to a specified position of the target blood vessel in the curved surface reconstruction image, a blood vessel straightening image of the curved surface reconstruction image, a maximum density projection reconstruction image of the target blood vessel, a medical scanning image containing the target blood vessel, and thumbnails of a plurality of medical scanning images obtained by scanning a target part, wherein at least one blood vessel belongs to the target part, and the plane of the blood vessel section image is vertical to the plane of the curved surface reconstruction image; the blood vessel image, the curved surface reconstruction image, the blood vessel section image, the blood vessel straightening image, the maximum density projection reconstruction image, the medical scanning image and the thumbnail are displayed on the same display interface or different display interfaces.

Therefore, by displaying the medical image related to the lesion diagnosis on the display interface, the user can be assisted in quickly diagnosing the lesion.

After the curved surface reconstructed image is displayed, the image processing method further comprises the following steps: responding to a first preset operation of a user, determining a display angle matched with the first preset operation, and displaying a curved surface reconstruction image matched with the display angle again; displaying a medical scan image, comprising: and displaying the medical scanning image, and highlighting the target blood vessel in the medical scanning image.

Therefore, the angle adjustment operation is carried out on the curved surface reconstructed image, so that the curved surface reconstructed image matched with the display angle is displayed on the display interface again, and the diagnosis of the focus of a user is assisted.

And two or more of the blood vessel image, the curved surface reconstruction image, the blood vessel section image, the blood vessel straightening image and the maximum density projection reconstruction image are generated based on a preset slide reading rule in response to the same operation of a user.

Therefore, two or more medical images which accord with the preset film reading rule can be directly generated through the same operation, repeated or mechanical screenshot and other operations are avoided, and the medical image generation efficiency is improved.

The display method of the blood vessel further comprises the following steps: displaying at least one lesion information on the blood vessel; and/or generating and displaying diagnosis auxiliary information based on the detection information of the blood vessel and the lesion information, and copying or modifying the diagnosis auxiliary information in response to a second preset operation of the user.

Therefore, by displaying at least one type of lesion information of the blood vessel, information about the lesion can be presented to the user, thereby assisting the user in diagnosing the lesion and avoiding misdiagnosis or missed diagnosis

In order to solve the above technical problem, another technical solution adopted by the present application is: an image processing device is provided, which includes an acquisition module for acquiring a medical scanning image, wherein the medical scanning image includes a blood vessel segmentation result obtained by performing blood vessel segmentation on the medical scanning image; a generation module, configured to generate a vascular medical image including at least one blood vessel based on a blood vessel segmentation result; a display module for displaying a medical image related to a blood vessel, wherein the medical image related to a blood vessel comprises a blood vessel medical image.

In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided an image processing apparatus comprising a processor and a memory, the memory storing program instructions, the processor being configured to execute the program instructions to implement the image processing method described above.

In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a computer-readable storage medium storing program instructions that can be executed to implement the image processing method described above.

According to the scheme, the blood vessel medical image can be automatically generated by utilizing the blood vessel segmentation result of the medical scanning image, a user does not need to manually segment the blood vessel to obtain the blood vessel medical image, the blood vessel segmentation efficiency is improved, and the waiting time of the user is reduced; moreover, the segmented blood vessel can be displayed, so that a user can evaluate the segmentation condition of the blood vessel to quickly determine whether the segmentation of the blood vessel is accurate, and then the accuracy of the segmentation of the blood vessel can be ensured after the user confirms the segmentation of the blood vessel subsequently, and the accuracy of a medical image generated by using the blood vessel medical image can be improved.

Drawings

FIG. 1 is a schematic flowchart of an embodiment of an image processing method provided in the present application;

FIG. 2 is a schematic diagram of an embodiment of a vascular medical image provided by the present application;

FIG. 3 is a schematic view of an embodiment of a medical scan image provided herein;

FIG. 4 is a schematic diagram of one embodiment of a thumbnail provided herein;

FIG. 5 is a schematic diagram of an embodiment of a surface reconstructed image provided herein;

FIG. 6 is a schematic diagram of an embodiment of a vessel alignment map of a curved reconstructed image provided by the present application;

FIG. 7 is a schematic diagram of one embodiment of a display interface provided herein;

FIG. 8 is a schematic flow chart diagram illustrating an image processing method according to another embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram of an embodiment of an image processing apparatus provided in the present application;

FIG. 10 is a schematic structural diagram of an embodiment of an image processing apparatus provided in the present application;

FIG. 11 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided in the present application.

Detailed Description

In order to make the purpose, technical solution and effect of the present application clearer and clearer, the present application is further described in detail below with reference to the accompanying drawings and examples.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

The device for executing the image processing method of the present application is, for example, an electronic device including a display screen, such as a computer, a tablet, a mobile phone, or a device with a specific function (e.g., a device for medical information processing), and is not limited in particular herein.

Referring to fig. 1-7, fig. 1 is a schematic flowchart of an embodiment of an image processing method provided by the present application, fig. 2 is a schematic diagram of an embodiment of a vascular medical image provided by the present application, fig. 3 is a schematic diagram of an embodiment of a medical scanned image provided by the present application, fig. 4 is a schematic diagram of an embodiment of a thumbnail provided by the present application, fig. 5 is a schematic diagram of an embodiment of a curved reconstructed image provided by the present application, fig. 6 is a schematic diagram of an embodiment of a vessel straightening graph of a curved reconstructed image provided by the present application, and fig. 7 is a schematic diagram of an embodiment of a display interface provided by the present application. It should be noted that, if the result is substantially the same, the flow sequence shown in fig. 1 is not limited in this embodiment. As shown in fig. 1, the present embodiment includes:

step S11: and acquiring a blood vessel segmentation result of the medical scanning image.

The method of the embodiment is used for processing and displaying medical images related to blood vessels, such as a curved surface reconstructed image, a blood vessel straightening map of the curved surface reconstructed image, and the like, and the medical images of the curved surface reconstructed image, the blood vessel straightening map of the curved surface reconstructed image, and the like are post-processed medical images obtained by performing post-processing on the basis of medical scanning images. The medical scanning image is an image obtained by imaging a blood vessel through an imaging technology in the medical technology field, some diseases related to the blood vessel can be checked based on the blood vessel medical image, and when the blood vessel of the head and the neck needs to be diagnosed, the blood vessel medical image is obtained by scanning the head and the neck. In one embodiment, the medical scan image may be an angiographic image, which may also be referred to as a CTA image, obtained by Computed Tomography (CT) techniques; of course, the medical scan image may also be an angiographic image obtained by Magnetic Resonance Angiography (MRA) technique. It is understood that in other embodiments, the angiographic image may be obtained by other vessel imaging techniques, and is not limited in any way.

Because the blood vessels of each part in the human body are connected or wound, the blood vessels of the neck of the human body need to be diagnosed, and a medical scanning image of the blood vessels of the brain, the neck and the like of the human body needs to be actually acquired so as to ensure the integrity of the acquired blood vessels of the neck, and in the actual diagnosis process, the blood vessels of other parts may influence the diagnosis of a user, so that the blood vessels on the medical scanning image need to be segmented firstly, and the influence of the existence of the blood vessels of other parts on the diagnosis is avoided. That is, the blood vessel segmentation is actually to segment a blood vessel of a region to be diagnosed from a blood vessel of another region, or to segment one or more blood vessels to be diagnosed from another blood vessel, so as to diagnose the blood vessel to be diagnosed, thereby improving the diagnosis efficiency. In view of this, in the present embodiment, when a medical scan image of a blood vessel is acquired, the blood vessel segmentation is automatically performed on the medical scan image, and thus, the blood vessel can be intelligently segmented, and a blood vessel segmentation result of the medical scan image can be acquired. Compared with a mode of manually segmenting blood vessels, the embodiment automatically segments the blood vessels when the medical scanning images of the blood vessels are acquired, so that the blood vessel segmentation efficiency is improved, and the waiting time of a user is reduced, thereby shortening the time of generating the post-processing medical images based on the blood vessel segmentation results, for example, reducing the time required for constructing the curved surface reconstruction images.

In an embodiment, the blood vessel segmentation result may be obtained by processing the medical scanning image by using a first deep learning mode. In the conventional blood vessel segmentation, the image before the blood vessel enhancement is subtracted from the image after the blood vessel enhancement to obtain the blood vessel segmentation result, so that the patient needs to receive scanning radiation twice. Compared with the traditional blood vessel segmentation, the method can directly adopt the first deep learning mode to automatically process to obtain the result of the blood vessel segmentation based on the medical scanning image, such as a CTA (computed tomography angiography) image after the blood vessel enhancement, that is to say, the method can be used for obtaining the result of the blood vessel segmentation, and the patient can reduce the radiation once. Moreover, the blood vessel segmentation result obtained through the first deep learning mode is more accurate, and the accuracy of constructing the post-processing medical image is improved. In addition, due to the accuracy of the blood vessel segmentation, the user basically does not need to modify the blood vessel segmentation result or the modification amount is less, so that the time for manually segmenting the blood vessel by the user is shortened, and the workload of the user is lightened. The algorithm or the network model related to the first deep learning manner is not specifically limited herein, and may be specifically set according to actual use requirements.

Since the result of vessel segmentation affects the detection of the subsequent centerline, in order to avoid the inaccuracy of the result of vessel segmentation obtained by the first deep learning method, in an embodiment, the user may adjust the result of vessel segmentation by an adjustment operation, where the specific adjustment method is determined according to the problem of the result of vessel segmentation. For example, if a certain blood vessel is missing after the blood vessel segmentation, the missing blood vessel can be generated by using the region growing tool.

In an embodiment, the server may perform blood vessel segmentation on the acquired medical scanning image to obtain a blood vessel segmentation result, and obtain the blood vessel segmentation result of the medical scanning image by receiving feedback of the server on the blood vessel segmentation result. It is to be understood that, in other embodiments, the device itself may perform vessel segmentation on the medical scanning image to obtain a vessel segmentation result, which is not specifically limited herein. The server or the device can perform blood vessel segmentation processing on the acquired medical scanning image in a preset deep learning mode to obtain a blood vessel segmentation result.

Step S12: based on the vessel segmentation result, a vessel medical image containing at least one vessel is generated.

In the present embodiment, a blood vessel medical image including at least one blood vessel is generated based on the blood vessel segmentation result. That is, after the blood vessels that are not needed in the actual diagnosis are separated from the blood vessels that are needed in the diagnosis, the blood vessel medical image is generated based on the blood vessels that are needed in the diagnosis, so that the blood vessels at other parts or the blood vessels that are not needed in the diagnosis are prevented from affecting the blood vessel medical image that is needed in the diagnosis. Wherein, the vessel medical image can only comprise one vessel or a plurality of vessels needing diagnosis. For example, as shown in fig. 2, the vessels required for diagnosis are Left Internal-Carotid-Artery (L-ICA), Right Internal-Carotid-Artery (R-ICA), Left vertebral Artery (L-VA), and Right vertebral Artery (R-VA), and in order to avoid the presence of other vessels affecting the diagnosis, only these four vessels to be diagnosed are included in the vascular medical image.

In another embodiment, in order to reduce the calculation amount in the actual blood vessel segmentation process, the blood vessel medical image may include all blood vessels of the target region including the blood vessel to be diagnosed, for example, when the blood vessel to be diagnosed is the left internal carotid artery of the head and neck, in order to reduce the calculation amount in the actual blood vessel segmentation process, all blood vessels of the head and neck region including the left internal carotid artery are included in the blood vessel medical image after the blood vessel segmentation.

In one embodiment, the blood vessel medical image is a three-dimensional image, and the blood vessel is in a three-dimensional form, so that a user can observe the condition of the blood vessel from multiple angles and multiple levels, for example, the condition of a focus in the blood vessel, and more information related to the blood vessel can be obtained compared with the blood vessel two-dimensional image, so that the user can make an accurate diagnosis and avoid misdiagnosis. It is understood that in other embodiments, the vessel medical image may also be a two-dimensional image, and is not limited in particular.

Step S13: a medical image relating to the blood vessel is displayed.

In this embodiment, a medical image relating to a blood vessel may be displayed on the display interface. The medical image related to the blood vessel includes a blood vessel medical image, that is, a blood vessel three-dimensional image generated based on a blood vessel segmentation result is displayed on a display interface, that is, a three-dimensional form of the blood vessel to be diagnosed is displayed on the display interface, so that a user can evaluate the blood vessel medical image generated automatically based on the blood vessel segmentation result, and the user can quickly determine whether the segmentation of the blood vessel is accurate or whether other problems such as lack of regions exist in the blood vessel segmentation result, so that the time for processing the medical image after the generation of the subsequent blood vessel medical image is shortened, and the waiting time of the user is further reduced. The display interface may be a display screen of the device, or other interfaces capable of displaying content, and may be specifically set according to actual use, which is not specifically limited herein.

In order to facilitate a user to more clearly and intuitively observe the condition of the blood vessel, for example, the segmentation condition of the blood vessel, in one embodiment, the blood vessel is displayed in a volume rendering manner as shown in fig. 2. It will be appreciated that in other embodiments, the vascular medical image may be displayed in other manners that are easily viewable by the user.

Further, in order to facilitate the user to determine the blood vessels on the blood vessel medical image, in an embodiment, the name of at least one blood vessel is displayed on the blood vessel medical image, and the blood vessel name is correspondingly displayed on the blood vessels in the blood vessel medical image, so that the user can quickly and directly know the positions of the blood vessels and the specific blood vessel of each blood vessel from the displayed blood vessel medical image, the film reading speed of the user is increased, and the diagnosis efficiency of the user is improved. The method comprises the steps of classifying blood vessels in a preset deep learning mode, determining the blood vessel names of the blood vessels based on the classification, and marking the blood vessel names corresponding to the blood vessels on a blood vessel medical image. In a specific embodiment, as shown in fig. 2, the vascular medical image includes four blood vessels, the four blood vessels are determined to be L-ICA, R-ICA, L-VA and R-VA respectively through a preset deep learning manner, and the blood vessel names 21 are labeled at the corresponding blood vessels in the vascular medical image, so that a user can distinguish the blood vessels on the vascular medical image, thereby assisting the user in diagnosing the lesion of the blood vessel.

In one embodiment, when there are one or more blood vessels in the blood vessel medical image, the blood vessel names of the blood vessels are directly and simultaneously displayed on the corresponding blood vessels in the blood vessel medical image without an operation instruction of a user. In other embodiments, the vessel name of each vessel may be displayed on the vessel medical image based on a selection operation of the user. For example, as shown in fig. 2, taking the blood vessel name 21 of a certain blood vessel as an example of single display on the blood vessel medical image, the left display area of the blood vessel medical image displays a list 22 of blood vessel names, and the user can display the blood vessel name 21 on the corresponding blood vessel in the blood vessel medical image in response to the user's selection operation by selecting a name in the list 22 of blood vessel names or selecting a certain blood vessel on the blood vessel medical image. The blood vessel names 21 mentioned above can be identified and named through a preset deep learning mode, and an algorithm or a network model related to the preset deep learning mode can be specifically set according to the use requirement, which is not specifically limited herein.

In other embodiments, the medical images related to the blood vessel may further include a medical scanned image including the blood vessel as shown in fig. 3, thumbnails 41 of a plurality of medical scanned images obtained by scanning the target region as shown in fig. 4, a curved reconstructed image 51 of at least one blood vessel as shown in fig. 5, a blood vessel tangent plane map 52 corresponding to a specified position of the blood vessel in the curved reconstructed image as shown in fig. 5, a blood vessel straightening map 61 or a maximum density projection reconstructed image of the curved reconstructed image as shown in fig. 6, and the like, which are not particularly limited herein. It should be noted that the curved surface reconstructed image is obtained by performing curved surface reconstruction on one or more blood vessels in the medical scanning image, that is, the curved surface reconstructed image may be obtained by performing curved surface reconstruction on one blood vessel in the medical scanning image, and at this time, the curved surface reconstructed image only includes the blood vessel; the curved surface reconstructed image may also be a curved surface reconstruction of a plurality of blood vessels in the medical scanning image, and the curved surface reconstructed image includes the plurality of blood vessels. The blood vessel straightening graph of the curved surface reconstruction image is an image obtained by straightening a certain blood vessel on the curved surface reconstruction image, and the blood vessel straightening graph of the curved surface reconstruction image is beneficial to diagnosing and analyzing the stenosis degree of the plaque. The above-mentioned blood vessel related medical image may be a medical image corresponding to a target blood vessel in at least one blood vessel, and is based on a center line on the blood vessel medical image and the medical scanning image when specifically constructing the curved reconstructed image of the target blood vessel, so that the target blood vessel is highlighted when the medical scanning image is displayed, and the curved reconstructed image of the target blood vessel can be constructed more accurately.

Wherein, for the medical scanning image containing blood vessels or the thumbnails of a plurality of medical scanning images obtained by scanning the target part, at least one blood vessel needing to be diagnosed belongs to the target part; for the blood vessel tangent plane map corresponding to the specified position of the target blood vessel in the curved reconstructed image, the plane of the blood vessel tangent plane map is perpendicular to the plane of the curved reconstructed image, specifically, the blood vessel tangent plane map is shown as a region 52 in fig. 5, wherein in the region 52, the sub-region including the white outer frame is the blood vessel tangent plane corresponding to the specified position of the target blood vessel, i.e., the position corresponding to the white pointer in the region 51, the sub-region located at the upper part of the sub-region including the white outer frame is the blood vessel tangent plane corresponding to the upper part of the specified position of the target blood vessel in the region 51, and the sub-region located at the lower part of the sub-region including the white outer frame is the blood vessel tangent plane corresponding to the lower part of the specified position of the target blood vessel in the region 51.

In one embodiment, the medical images related to the blood vessel may be displayed on the same display interface at the same time or on different display interfaces. For example, as shown in fig. 7, medical images related to blood vessels are simultaneously displayed on the same display interface, and the medical images related to blood vessels include a medical scanning image, a curved reconstructed image, a blood vessel tangent plane image corresponding to a specified position of a target blood vessel in the curved reconstructed image, a blood vessel medical image, and thumbnails of several medical scanning images obtained by scanning a target part. The first area 71 of the display interface displays medical scanning images, the second area 72 displays curved surface reconstruction images, the third area 73 displays a blood vessel tangent plane image corresponding to the designated position of a target blood vessel in the blood curved surface reconstruction images, the fourth area 74 displays blood vessel medical images, and the fifth area 75 displays thumbnails of a plurality of medical scanning images obtained by scanning the target part. The medical images related to the blood vessels are displayed on the same interface, so that a user can observe the medical images related to the blood vessels simultaneously, the user can visually compare the medical images, the aim of assisting a doctor in diagnosing is fulfilled, and the diagnosis efficiency and accuracy are improved; moreover, each medical image is displayed on the same interface in different areas, the display interface is clear, and the display content is prevented from being mixed. In addition, medical images displayed in different areas on the same interface can be exchanged according to the reading habits of users.

More than two of the blood vessel image, the curved surface reconstruction image, the blood vessel section image, the blood vessel straightening image and the maximum density projection reconstruction image are generated based on a preset slide reading rule in response to the same operation of a user, that is, the user can generate two or more medical images which accord with the preset slide reading rule through the same operation. For example, taking the curved reconstructed image and the blood vessel straightening map as an example, the preset interpretation rule is to generate the medical image at the first angle, and the user can directly generate the curved reconstructed image and the blood vessel straightening map at the first angle through the same operation, so that the two medical images are simultaneously displayed on the display interface at the first angle.

In the embodiment of the present application, the medical image related to the blood vessel is displayed so that a user can visually observe a plurality of medical images related to the blood vessel, so that the user can judge whether a lesion exists in the blood vessel from a plurality of angles, and the diagnosis efficiency and accuracy of the user are improved. Further, in order to assist the user in viewing the medical image, that is, assist the user in diagnosing a lesion in a blood vessel, in one embodiment, the device or the server may acquire information about at least one lesion of a blood vessel in the medical image, and may display the information about the at least one lesion of the blood vessel on the display interface, so that the user may obtain information related to the lesion while viewing the lesion in the medical image, for example, morphological parameters of the lesion, a type of the lesion, and the like, thereby assisting the user in diagnosing the lesion and improving the diagnosis efficiency and accuracy of the user; in addition, the information of the focus displayed to the user can be diversified, rich diagnosis information can be provided, and the time for the user to make a focus treatment scheme is shortened. It is to be understood that, in other embodiments, information of at least one type of lesion in the medical image may also be prompted by voice broadcast or other methods, and may be specifically set according to actual use needs, which is not specifically limited herein.

The server or the device can detect the medical scanning image in a preset deep learning mode to obtain information of at least one focus. Compared with the method that a user directly judges whether a focus exists in a blood vessel through naked eyes based on a medical scanning image, the method and the device can automatically detect the focus when the medical image of the blood vessel is obtained, so that the speed and the accuracy of focus detection are improved, and misdiagnosis or missed diagnosis is avoided; in addition, the relevant information of the focus can be automatically acquired while the focus is detected, so that the risk of the focus can be evaluated by a user, and the user can be assisted to make a relevant treatment scheme.

In some embodiments, in displaying the information of the lesion, the information of the lesion may be displayed together with the medical image. In other embodiments, the information of the lesion may be displayed alone, that is, the information of the lesion is not displayed together with the medical image. How to display the information of the focus can be specifically set according to actual use needs, and is not specifically limited herein.

In some embodiments, the information of the lesion may be displayed together with the medical scanning image or a post-processing medical image generated based on the medical scanning image, wherein the post-processing medical image may be a three-dimensional image of a blood vessel, a curved surface reconstruction image, a blood vessel straightening map of a curved surface reconstruction image, or a maximum density projection reconstruction image, and the like, and is not limited in particular. In some embodiments, information of the lesion may be displayed together with a medical image corresponding to the lesion, so that a user may quickly diagnose the lesion based on the lesion information of the corresponding medical image. For example, since an aneurysm is detected based on a medical scan image, a plaque is detected based on a curved surface reconstructed image, that is, a medical image corresponding to the aneurysm is a medical scan image, and a medical image corresponding to the plaque is a curved surface reconstructed image, information on the aneurysm and information on the plaque can be displayed together with the medical scan image and the curved surface reconstructed image. Note that, the information on the lesion may not be displayed together with the medical image corresponding to the lesion, and for example, when a plurality of lesions are included, the information on the plurality of lesions may be displayed together with a certain medical image. Specifically, if the lesion includes plaque and aneurysm, information on the plaque and aneurysm is displayed together with the medical scan image.

It can be understood that, in the above embodiment, when the information of the lesion and the medical image are displayed on the display interface together, the information of the lesion and the medical image may be displayed in different regions on the same display interface, so that the display interface is clear and intuitive, and the user can diagnose the lesion conveniently. In other embodiments, the information of the lesion may also be displayed in the same region as the medical image, that is, the information of the lesion is displayed on the medical image, for example, the information of the lesion may be displayed at a position on a blood vessel of the medical image corresponding to the lesion, specifically, the region of the lesion may be highlighted, and/or the display of the relevant lesion may be displayed in text, and how to display the information may not be limited.

In one embodiment, after the user confirms that the displayed medical image and the focus information are correct, the method can also automatically generate and display diagnosis auxiliary information according to the detection information of the blood vessel and the information of the focus by using a preset deep learning mode, namely, automatically generate structured text content capable of assisting the diagnosis of the user, so that a doctor is assisted to finish the writing of a diagnosis report, the time consumed by the writing of the diagnosis report is reduced, the time for the patient to wait for the diagnosis report is further reduced, and styles and habits of different users in writing the report can be standardized.

Wherein, the structured text content can also be copied or modified. Specifically, the diagnosis assistance information is automatically copied or modified in response to a second preset operation by the user. The structured report content can assist the diagnosis of doctors, so that the diagnosis efficiency and accuracy of the doctors can be improved. In addition, the user can send the medical image and the related information which are confirmed to be correct to the medical image system for other users to check, or can print the content of the display interface through the function of film on the interface.

Referring to fig. 8, fig. 8 is a schematic flowchart illustrating an image processing method according to another embodiment of the present application. It should be noted that, if the result is substantially the same, the flow sequence shown in fig. 8 is not limited in this embodiment. As shown in fig. 8, the present embodiment includes:

s80: and acquiring a blood vessel segmentation result of the medical scanning image.

Step S80 is similar to step S11 in the above embodiment, and is not repeated here.

S81: based on the vessel segmentation result, a vessel medical image containing at least one vessel is generated.

Step S81 is similar to step S12 in the above embodiment, and is not repeated here.

S82: a target vessel in a vascular medical image is determined.

In the present embodiment, the blood vessel medical image is generated based on the result of blood vessel segmentation, that is, the blood vessel medical image includes only a blood vessel to be diagnosed, and the blood vessel to be diagnosed may be a certain blood vessel of a certain part. If only one blood vessel is included in the blood vessel medical image, the blood vessel is determined as a target blood vessel; if the vascular medical image includes a plurality of blood vessels, one of the blood vessels can be determined as a target blood vessel, and when the plurality of blood vessels need to be diagnosed, the plurality of blood vessels in the vascular medical image can be the target blood vessel.

The target blood vessel can be determined by a user or determined by the device or the server. And is not particularly limited herein. For example, taking the target blood vessel determined by the user as an example, as shown in fig. 2, the user may determine the target blood vessel by clicking the blood vessel on the blood vessel medical image through a pointer, wherein each blood vessel on the blood vessel medical image may be identified and named in a preset deep learning manner when the blood vessel medical image is generated, and a blood vessel name 21 is marked at a position on the blood vessel medical image corresponding to the blood vessel, so that the user can conveniently select and determine the target blood vessel; or, a list 22 containing the blood vessel names is generated in an adjacent area of the blood vessel medical image through a preset deep learning mode, and the user can perform selection operation on the list 22 of the blood vessel names through a pointer to determine the target blood vessel, for example, the user selects a blood vessel "L-ICA" in the list 22 of the blood vessel names, and at the moment, the blood vessel "L-ICA" in the blood vessel medical image can be highlighted, so that the user can determine whether the target blood vessel selection is wrong or not based on the displayed blood vessel; alternatively, the blood vessel name 21 may be marked at the position of the blood vessel corresponding to the blood vessel medical image, and the list 22 including the blood vessel name may be generated in the adjacent region of the blood vessel medical image, and the two may be combined together to determine the target blood vessel.

S83: based on the center line detection result of the target blood vessel, the center line of the target blood vessel is formed in the blood vessel medical image to update the blood vessel medical image.

In the embodiment, based on the center line detection result of the target blood vessel, the center line can be automatically formed on the target blood vessel in the blood vessel medical image to update the blood vessel medical image, so that the blood vessel medical image including the center line is obtained, the user does not need to manually determine the center line, the efficiency of center line formation is improved, the time for generating post-processing medical images such as curved surface reconstruction images is shortened, and the waiting time of the user is further reduced. That is, as shown in fig. 2, the updated blood vessel medical image differs from the original blood vessel medical image only in whether or not the center line 23 is formed on the target blood vessel. Since the updated blood vessel medical image is displayed in a volume rendering manner, in order to ensure that the user can observe the detection condition of the central line 23 from the updated blood vessel medical image, the formed central line 23 can be clearly displayed on the target blood vessel by adjusting the brightness, contrast and the like of the central line 23 relative to the target blood vessel.

In one embodiment, the centerline detection result of the target blood vessel is obtained by performing centerline detection on the target blood vessel of the blood vessel medical image. For example, if the internal carotid artery and the vertebral artery need to be diagnosed, the internal carotid artery and the vertebral artery are determined to be the target blood vessels, then the starting point and the end point of the internal carotid artery and the vertebral artery are found on the blood vessel medical image, the central line of the internal carotid artery is extracted and obtained based on the starting point and the end point of the internal carotid artery, and the central line of the vertebral artery is extracted and obtained based on the starting point and the end point of the vertebral artery, so that the central line detection results of the internal carotid artery and the vertebral artery are obtained.

And the detection result of the central line is obtained by processing the blood vessel medical image by using a second deep learning mode. Traditional central line testing process all is that the user goes on with semi-automatic mode in the workstation, compares in traditional central line testing mode, and this application can directly utilize the second degree of depth learning mode to detect based on blood vessel medical image is automatic and obtain the central line, has improved the precision and the efficiency that the central line detected. The algorithm or the network model related to the second deep learning manner is not specifically limited herein, and may be specifically set according to actual use requirements.

Whether the above-mentioned detection result of the center line accurately affects the generation of the medical image related to the target blood vessel. For example, assuming that the target blood vessel is regarded as a special pipeline, the surface of the pipeline is formed by rolling and enveloping the spherical center along a certain curve (central axis), that is, the central axis of the pipeline directly affects the formed surface of the pipeline, and the central line of the blood vessel can be regarded as the central axis, so the detection result of the central line directly affects the construction of the curved surface reconstruction image or other medical images which need to be generated based on the central line. Based on this, in order to avoid the situation that the detection result of the center line obtained by the deep learning method is inaccurate, in an embodiment, the user may adjust the detection result of the center line of the target blood vessel through an adjustment operation, so that the accuracy of the center line is ensured, and the accuracy of the medical image generated by using the center line can be further improved.

S84: a medical image relating to the blood vessel is displayed.

Step S84 is similar to step S13 in the above embodiment, and is not repeated here.

S85: and responding to the adjustment operation of the user on the blood vessel medical image, and adjusting the blood vessel medical image.

In one embodiment, after the user views the vessel medical image on the display interface, the user determines whether the vessel medical image needs to be adjusted based on the displayed content. For example, the user may confirm whether the vessel segmentation is correct through the vessel medical image, and may also confirm whether the center line position on the target vessel is accurate or whether there is a lack or the like through the vessel medical image, thereby determining whether to adjust the vessel medical image.

The adjustment operation for the blood vessel medical image may be determined according to a specific problem existing in the blood vessel medical image. In a specific embodiment, the adjusting operation on the blood vessel medical image may include any one of the following: performing a vessel adjustment on the vessel medical image, for example, adjusting a region of a vessel or adjusting a center line of the vessel; characters input by a user are added at a user-specified position in the blood vessel medical image, and then labeling information and the like can be added on the blood vessel medical image; deleting the content added by the user in the user selection area of the blood vessel medical image, for example, deleting characters added by the user or line segments modified from the central line; at least one of moving, scaling and rotating the vascular medical image; the blood vessel selected by the user in the blood vessel medical image is used as the adjusted blood vessel medical image, that is, the blood vessel medical image is adjusted to only display the selected blood vessel, that is, the selected blood vessel is displayed on the display interface in a full page manner, so that the blood vessel medical image only displays the selected blood vessel on the display interface, and the blood vessel medical image is not modified.

In an embodiment, the vessel adjustment of the vessel medical image may be an adjustment of a centerline of the vessel. For example, it may be that a user-selected centerline in the vascular medical image is highlighted, that is, the selected centerline is highlighted, for example, in a highlighted form, to enable the user to more clearly and intuitively observe the centerline, so that the user can evaluate the automatically formed centerline; or the center line selected by the user in the blood vessel medical image is moved; or connecting the central line in the blood vessel medical image with a line segment added by the user for the central line to form a new central line; or the center line in the blood vessel medical image and/or the line segment added by the user to the center line can be subjected to angle adjustment so as to enable the center line to be more consistent with the morphological constitution of the blood vessel.

In other embodiments, the vessel adjustment performed on the vessel medical image may also be an adjustment of a vessel region, that is, an adjustment of a result of vessel segmentation. For example, it is known from the blood vessel segmentation result that the blood vessel segmentation is not accurate enough, and if a certain blood vessel is too long or too short, the length of the blood vessel in the blood vessel medical image needs to be adjusted; if the blood vessel segmentation result shows that a certain blood vessel is missing, a new blood vessel needs to be generated in the blood vessel medical image; alternatively, the position of the blood vessel on the blood vessel medical image may be adjusted by moving, zooming, rotating, or the like.

In order to facilitate the adjustment of the blood vessel medical image by the user, in one embodiment, as shown in fig. 2, a functional area 24 is displayed on the display interface, and the tool items on the functional area 24 can be used for adjusting the blood vessel medical image. Specifically, a functional area 24 is included in the area located on the left side of the blood vessel medical image, a plurality of tool items are included in the functional area 24, and the currently displayed tool items are basic tool items in the device. Wherein, the tool items are from left to right, and from top to bottom: the method comprises the following steps of displaying a display layout tool of an interface, globally displaying a selected blood vessel, adjusting the brightness or contrast of a central line or the blood vessel and the like, translating a selected target, amplifying the selected target, writing the selected target, measuring an angle of the selected target, and refreshing a page. In other embodiments, a delete tool, a reset tool, etc. may also be included, and are not specifically limited herein. Further, there are differences in the tool items involved in the adjustment of the blood vessel center line and the adjustment of the blood vessel region, and in one embodiment, the tool item corresponding to the adjustment of the blood vessel center line and the tool item corresponding to the adjustment of the blood vessel region may be displayed separately and simultaneously, or may be displayed in the functional region 24 when a corresponding adjustment is required.

In a specific embodiment, a user can select a tool item in a functional area of a display interface, and in response to the selection operation of the user, the vessel medical image is adjusted in a manner of being matched with the selected tool item, so that the vessel medical image is automatically adjusted.

S86: and displaying the adjusted blood vessel medical image.

In this embodiment, after the user adjusts the blood vessel medical image, the display interface displays the adjusted blood vessel medical image, so that the user can confirm whether there are other places to be adjusted in the adjusted blood vessel medical image through the display interface.

S87: and in response to the confirmation operation of the user, updating the center line of the target blood vessel by using the content of the blood vessel adjustment, and generating a new curved surface reconstruction image based on the updated center line, or sending the content of the blood vessel adjustment to a server and receiving the new curved surface reconstruction image fed back by the server.

In particular, since diagnosis of a lesion such as a plaque of a blood vessel requires other medical images such as a curved surface reconstructed image, it is necessary to acquire other medical images such as a curved surface reconstructed image generated based on a blood vessel medical image when detecting a plaque of a blood vessel.

In the present embodiment, in response to the confirmation operation of the user, that is, after the user confirms that the adjusted blood vessel medical image has no problem, the center line of the target blood vessel is updated using the content of the adjusted blood vessel, and a new curved surface reconstructed image is automatically generated based on the updated center line. In other embodiments, for the calculation of the curved reconstructed image by the server, after the user confirms the operation, the contents of the blood vessel adjustment are sent to the server, the server generates a new curved reconstructed image based on the updated center line, and at the moment, the generated new curved reconstructed image is sent to the device, so that the device acquires a new curved reconstructed image generated based on the adjusted blood vessel medical image.

For example, as shown in fig. 2, taking the server computing to generate the curved reconstructed image as an example, the user may send the adjusted blood vessel medical image to the server through the "sending" port, so that the server can generate a new curved reconstructed image based on the adjusted blood vessel medical image; and the vessel medical image and other medical images displayed on the display interface are correct, the adjustment steps in the embodiment are not required to be executed, and at this time, the vessel medical image and other medical images can be sent to the medical image system through the sending port, so that other users can view the vessel medical images and other medical images, and meanwhile, the contents of the display interface can be printed through the film port.

S88: and updating the displayed curved surface reconstruction image by using the new curved surface reconstruction image.

In this embodiment, the obtained new curved surface reconstructed image is displayed on the display interface to display the new curved surface reconstructed image to the user, so that the curved surface reconstructed image on the display interface is updated.

Further, in order to facilitate the user to diagnose the lesion faster and more accurately based on the curved surface reconstructed image or other medical images, in an embodiment, the curved surface reconstructed image may be further adjusted based on a preset radiographing rule, that is, a radiographing rule of the user, so that the curved surface reconstructed image is displayed on the display interface in a form conforming to the preset rule. For example, the preset slide reading rule may be to display the curved reconstructed image at a preset angle on the display interface, or may also be to display a blood vessel straightening graph of the curved reconstructed image at a preset angle on the display interface, and the like, which is not limited herein. In other embodiments, the curved surface reconstruction image can be directly generated based on the preset film reading rule, and subsequent further adjustment is avoided, so that the medical image conforming to the film reading habit of the user can be generated at one time. In addition, the user may further perform operations such as filtering, deleting, or transmitting the displayed medical image.

S89: and responding to a first preset operation of a user, determining a display angle matched with the first preset operation, and displaying the curved surface reconstruction image matched with the display angle again.

In this embodiment, even if the curved surface reconstructed image can be displayed on the display interface based on the preset rule, the preset rule may be unfavorable for the diagnosis of the current lesion, so that the user may change the display angle of the curved surface reconstructed image by performing the first preset operation on the curved surface reconstructed image. Specifically, a user may perform a first preset operation on the curved surface reconstructed image displayed on the display interface, where the first preset operation may be an angle adjustment for displaying the curved surface reconstructed image, so that when the user performs the first preset operation, the device may automatically determine a display angle matched with the first preset operation, and redisplay the curved surface reconstructed image matched with the display angle on the display interface. The user may adjust the display angle of the curved reconstructed image by using 30 ° as an adjustment amount, that is, the adjustment amount of the display angle of the curved reconstructed image is 30 ° each time. In an embodiment, the adjustment amount of the curved surface reconstructed image may be 20 °, 35 ° or other degrees, and is not particularly limited herein.

In other embodiments, if the user confirms that the curved surface reconstructed image meets the predetermined rule and has no influence on the determination of the lesion, i.e., no adjustment is required, step S89 may not be performed.

Referring to fig. 9, fig. 9 is a schematic structural diagram of an embodiment of an image processing apparatus according to the present application. In this embodiment, the image processing apparatus 90 includes an acquisition module 91, a generation module 92, and a display module 93. The acquiring module 91 is configured to acquire a medical scanning image, where the medical scanning image includes a blood vessel segmentation result, and the blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image. The generation module 92 is configured to generate a vascular medical image including at least one blood vessel based on the blood vessel segmentation result. The display module 93 is configured to display a medical image related to a blood vessel, wherein the medical image related to a blood vessel includes a blood vessel medical image.

The blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image in a first deep learning mode; and/or the blood vessel medical image is a three-dimensional image; the display module 93 specifically further includes: in the displayed vascular medical image, the name of at least one blood vessel is displayed.

Before displaying the blood vessel medical image, the generating module 92 specifically further includes: determining a target vessel in a vessel medical image; based on the center line detection result of the target blood vessel, the center line of the target blood vessel is formed in the blood vessel medical image to update the blood vessel medical image.

After displaying the medical image related to the blood vessel, the generating module 92 specifically further includes: and responding to the adjustment operation of the user on the blood vessel medical image, adjusting the blood vessel medical image, and displaying the adjusted blood vessel medical image.

The generating module 92 adjusts the blood vessel medical image in response to the adjustment operation of the user on the blood vessel medical image, and includes: responding to the selection operation of a user on a tool item in a functional area of the display interface, and adjusting the blood vessel medical image to be matched with the selected tool item; and/or, the adjusting the blood vessel medical image comprises any one of the following steps: adjusting blood vessels in the blood vessel medical image; adding characters input by a user at a user-specified position in the blood vessel medical image; deleting the content added by the user in the user selection area of the blood vessel medical image; at least one of moving, scaling and rotating the vascular medical image; and taking the blood vessel selected by the user in the blood vessel medical image as the adjusted blood vessel medical image.

Wherein, the adjusting the blood vessel in the blood vessel medical image comprises any one of the following steps: adjusting the center line of the blood vessel in the blood vessel medical image; adjusting the position and/or length of the blood vessel in the blood vessel medical image; generating new blood vessels in a vascular medical image; and/or, the medical image related to the blood vessel further includes a curved surface reconstructed image of a target blood vessel in the at least one blood vessel, and the generating module 92 further specifically includes, after adjusting the blood vessel medical image and displaying the adjusted blood vessel medical image: responding to the confirmation operation of the user, updating the center line of the target blood vessel by using the adjustment content of the blood vessel, and generating a new curved surface reconstruction image based on the updated center line, or sending the adjustment content of the blood vessel to a server and receiving the new curved surface reconstruction image fed back by the server; and updating the displayed curved surface reconstruction image by using the new curved surface reconstruction image.

Wherein the medical image related to the blood vessel further comprises at least one of: the method comprises the following steps of obtaining a curved surface reconstruction image of at least one blood vessel, a blood vessel section image corresponding to the appointed position of the blood vessel in the curved surface reconstruction image, a blood vessel straightening image of the curved surface reconstruction image, a maximum density projection reconstruction image of the blood vessel, a medical scanning image containing the blood vessel, and thumbnails of a plurality of medical scanning images obtained by scanning a target part, wherein the at least one blood vessel belongs to the target part, and the plane of the blood vessel section image is vertical to the plane of the curved surface reconstruction image; the blood vessel image, the curved surface reconstruction image, the blood vessel section image, the blood vessel straightening image, the maximum density projection reconstruction image, the medical scanning image and the thumbnail are displayed on the same display interface or different display interfaces.

After the display module 93 displays the curved surface reconstructed image, the method specifically includes: responding to a first preset operation of a user, determining a display angle matched with the first preset operation, and displaying a curved surface reconstruction image matched with the display angle again; displaying a medical scan image, comprising: and displaying the medical scanning image, and highlighting the target blood vessel in the medical scanning image.

Wherein, the display module 93 displays at least one kind of lesion information about the blood vessel; and/or generating and displaying diagnosis auxiliary information based on the detection information of the blood vessel and the lesion information, and copying or modifying the diagnosis auxiliary information in response to a second preset operation of the user.

Referring to fig. 10, fig. 10 is a schematic structural diagram of an embodiment of an image processing apparatus provided in the present application. In this embodiment, the image processing apparatus 100 includes a processor 101 and a memory 103.

Processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having signal processing capabilities. The processor 101 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor 101 may be any conventional processor 101 or the like.

The memory 103 in the image processing apparatus 100 stores program instructions necessary for the processor 101 to run.

The processor 101 is configured to execute program instructions to implement the methods provided by any of the embodiments of the image processing method of the present application and any non-conflicting combinations thereof.

Referring to fig. 11, fig. 11 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided in the present application. The computer readable storage medium 110 of the embodiments of the present application stores program instructions 111, and the program instructions 111, when executed, implement the methods provided by any of the embodiments of the image processing method of the present application and any non-conflicting combinations. The program instructions 111 may form a program file stored in the computer-readable storage medium 110 in the form of a software product, so as to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods according to the embodiments of the present application. And the aforementioned computer-readable storage medium 110 includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.

The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims

1. An image processing method, characterized in that the method comprises:

acquiring a medical scanning image, wherein the medical scanning image comprises a blood vessel segmentation result obtained by performing blood vessel segmentation on the medical scanning image;

generating a vessel medical image containing at least one vessel based on the vessel segmentation result;

displaying a medical image related to the blood vessel, wherein the medical image related to the blood vessel includes the blood vessel medical image.

2. The method of claim 1,

the blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image in a first deep learning mode;

and/or the blood vessel medical image is a three-dimensional image;

and/or, the method further comprises: displaying a name of the at least one blood vessel in the displayed blood vessel medical image.

3. The method according to claim 1, wherein prior to said displaying the vascular medical image, the method further comprises:

determining a target vessel in the vascular medical image;

forming a center line of the target blood vessel in the vascular medical image based on the center line detection result of the target blood vessel to update the vascular medical image.

4. The method according to claim 1, wherein after said displaying the medical image related to the blood vessel, the method further comprises:

responding to the adjustment operation of the user on the blood vessel medical image, adjusting the blood vessel medical image, and displaying the adjusted blood vessel medical image.

5. The method of claim 4, wherein the adjusting the vascular medical image in response to a user adjustment operation on the vascular medical image comprises:

responding to the selection operation of a user on a tool item in a functional area of a display interface, and adjusting the blood vessel medical image to be matched with the selected tool item;

and/or, the adjusting the blood vessel medical image comprises any one of the following steps:

adjusting the blood vessel in the blood vessel medical image;

adding characters input by a user at a user-specified position in the blood vessel medical image;

deleting the content added by the user in the user selection area of the blood vessel medical image;

at least one of moving, scaling and rotating the vascular medical image;

and taking the blood vessel selected by the user in the blood vessel medical image as the adjusted blood vessel medical image.

6. The method according to claim 5, wherein the adjusting the vessel in the vessel medical image comprises any one of the following steps:

adjusting a centerline of the vessel in the vessel medical image;

adjusting the position and/or length of the blood vessel in the blood vessel medical image;

generating new blood vessels in the vascular medical image;

and/or the medical image related to the blood vessel further comprises a curved surface reconstruction image of a target blood vessel in the at least one blood vessel, and after the adjusting the blood vessel medical image and displaying the adjusted blood vessel medical image, the method further comprises:

in response to the confirmation operation of the user, updating the center line of the target blood vessel by using the adjustment content of the blood vessel, and generating a new curved surface reconstruction image based on the updated center line, or sending the adjustment content of the blood vessel to a server and receiving the new curved surface reconstruction image fed back by the server;

and updating the displayed curved surface reconstruction image by using the new curved surface reconstruction image.

7. The method according to claim 1, wherein the medical image relating to the blood vessel further comprises at least one of: a curved surface reconstructed image of a target blood vessel in the at least one blood vessel, a blood vessel section image corresponding to a specified position of the target blood vessel in the curved surface reconstructed image, a blood vessel straightening image of the curved surface reconstructed image, a maximum density projection reconstructed image of the target blood vessel, a medical scanning image containing the target blood vessel, and thumbnails of a plurality of medical scanning images obtained by scanning a target part, wherein the at least one blood vessel belongs to the target part, and a plane where the blood vessel section image is located is perpendicular to a plane where the curved surface reconstructed image is located;

the blood vessel image, the curved surface reconstruction image, the blood vessel section image, the blood vessel straightening image, the maximum density projection reconstruction image, the medical scanning image and the thumbnail are displayed on the same display interface or different display interfaces.

8. The method of claim 7, wherein after displaying the curved reconstructed image, the method further comprises:

responding to a first preset operation of a user, determining a display angle matched with the first preset operation, and displaying the curved surface reconstruction image matched with the display angle again;

the displaying the medical scan image comprises:

and displaying the medical scanning image, and highlighting the target blood vessel in the medical scanning image.

9. The method of claim 7, wherein two or more of the vessel image, the curved surface reconstructed image, the vessel section image, the vessel straightening image and the maximum density projection reconstructed image are generated based on a preset scoring rule in response to a same operation of a user.

10. The method of claim 1, further comprising:

displaying at least one lesion information about the blood vessel; and/or the presence of a gas in the gas,

and generating and displaying diagnosis auxiliary information based on the detection information and the focus information of the blood vessel, and copying or modifying the diagnosis auxiliary information in response to a second preset operation of a user.

11. An image processing apparatus is characterized in that,

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a medical scanning image, the medical scanning image comprises a blood vessel segmentation result, and the blood vessel segmentation result is obtained by performing blood vessel segmentation on the medical scanning image;

a generation module, configured to generate a vascular medical image including at least one blood vessel based on the blood vessel segmentation result;

a display module for displaying a medical image related to the blood vessel, wherein the medical image related to the blood vessel comprises the blood vessel medical image.

12. An image processing apparatus, characterized in that the image processing apparatus comprises a processor and a memory, the memory storing program instructions for execution by the processor to implement the method of any one of claims 1-10.

13. A computer-readable storage medium, characterized in that the computer-readable storage medium stores program instructions that are executable to implement the method of any one of claims 1-10.