Method and device for positioning region of interest, and CT (Computed Tomography) equipment

Abstract

The invention relates to the technical field of CT scanning, and discloses a method and device for positioning a region of interest and CT equipment. The method comprises the steps of obtaining a target positioning layer image; determining a first region of interest in the target positioning layer image based on a pre-constructed recognition model; determining target standard setting information corresponding to the first region of interest in pre-stored statistical information; wherein the statistical information comprises standard setting information corresponding to different types of regions of interest; and adjusting the first region of interest according to the target standard setting information, and determining a target region of interest in the target positioning layer image. According to the invention, the accuracy of positioning the region of interest during CT image scanning can be improved.

Description

Technical Field

[0001] The present application relates to the field of CT scanning technology, for example, to a method and device for locating a region of interest, and a CT device. Background Art

[0002] Currently, in a CT enhanced scanning process (eg, CT angiography scanning), after contrast agent injection, it is necessary to track changes in CT values ​​within a specified vascular region (ie, a region of interest) to determine whether a subsequent scanning process is triggered.

[0003] In the related art, the region of interest is usually determined on a positioning layer or a tracking layer, and the doctor needs to manually define the position and size of the region of interest on the positioning layer image.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] In the related art, the accuracy of the region of interest division depends on the doctor's medical scanning experience. If the doctor has little medical scanning experience, the region of interest tracked during CT image scanning will have a large error. Therefore, how to improve the accuracy of locating the region of interest during CT image scanning has become a technical problem that needs to be solved urgently.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a method and apparatus for locating a region of interest, and a CT device, which can improve the accuracy of locating a region of interest during CT image scanning.

[0009] In some embodiments, a method for locating a region of interest includes: acquiring a target positioning layer image; determining a first region of interest within the target positioning layer image based on a pre-built recognition model; determining target standard setting information corresponding to the first region of interest in pre-stored statistical information; wherein the statistical information includes standard setting information corresponding to different types of regions of interest; adjusting the first region of interest according to the target standard setting information to determine the target region of interest in the target positioning layer image.

[0010] Optionally, acquiring the target positioning layer image includes: receiving an image selection instruction input by a user; and determining the target positioning layer image from a plurality of positioning layer images according to the image selection instruction.

[0011] Optionally, based on a pre-constructed recognition model, determining a first region of interest in the target positioning layer image includes: using a recognition model to identify multiple regions of interest in the target positioning layer image; receiving a region determination instruction input by a user, and parsing region determination region information; wherein the region information includes region selection information or region demarcation information; when the region information is region selection information, using the region of interest corresponding to the region selection information as the first region of interest in the target positioning layer image; when the region information is region division information, using the region re-divided based on the region division information as the first region of interest in the target positioning layer image.

[0012] Optionally, determining target standard setting information corresponding to the first region of interest in pre-stored statistical information includes: identifying a region type to which the first region of interest belongs; and using standard setting information corresponding to a region of interest of the same region type in the statistical information as target standard setting information.

[0013] Optionally, after determining the target region of interest in the target positioning layer image, the method also includes: acquiring a current frame tracking layer image corresponding to the target positioning layer image; determining a second region of interest in the current frame tracking layer image based on a pre-built recognition model; comparing the target region of interest and the second region of interest to determine a deviation of the target region of interest; and adjusting the tracking area of ​​the tracking layer image according to the deviation of the target region of interest.

[0014] Optionally, the tracking area of ​​the tracking layer image is adjusted according to the deviation of the target region of interest, including: when the target region of interest does not deviate from the second region of interest, determining the target region of interest as the tracking area of ​​the tracking layer image; when the target region of interest deviates from the second region of interest, redetermining the target region of interest based on the second region of interest and statistical information, and using the redetermined target region of interest as the tracking area of ​​the tracking layer image.

[0015] Optionally, after redetermining the target region of interest based on the second region of interest and the statistical information, and using the redetermined target region of interest as the tracking area of ​​the tracking layer image, the method also includes: displaying switch options for the automatic trigger function and the manual trigger function so that the user can choose whether to turn off the automatic trigger function and turn on the manual trigger function instead.

[0016] Optionally, comparing the target region of interest and the second region of interest to determine the deviation of the target region of interest includes: identifying a first number of all pixels in the target region of interest; identifying a second number of pixels in the target region of interest in the second region of interest; when the ratio of the second number to the first number is greater than or equal to a set threshold, determining that the target region of interest has not deviated from the second region of interest; when the ratio of the second number to the first number is less than the set threshold, determining that the target region of interest has deviated from the second region of interest.

[0017] Optionally, the recognition model is constructed according to the following steps: obtaining a sample image in which the user has marked the area of ​​interest; wherein the marked area of ​​interest is a convex area; the sample image includes multiple human body parts, positioning layer images and / or tracking layer images under multiple imaging fields of view; based on the sample image, training a deep neural network model to obtain a recognition model.

[0018] In some embodiments, an apparatus for locating a region of interest includes a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for locating a region of interest when running the program instructions.

[0019] In some embodiments, a CT device includes: a device body; and a device for locating a region of interest as described above, which is installed on the device body.

[0020] The method and apparatus for locating a region of interest and the CT device provided in the embodiments of the present disclosure can achieve the following technical effects:

[0021] In the disclosed embodiment, the first region of interest in the target positioning layer image is identified by a pre-built recognition model, and the position and / or size of the first region of interest is adjusted according to the target standard setting information corresponding to the first region of interest in the pre-stored statistical information to determine the final target region of interest in the target positioning layer image. In this way, the user does not need to manually divide the position and size of the region of interest in the positioning layer image, which reduces the error in the region of interest division caused by the user's lack of scanning experience. Therefore, the disclosed embodiment can improve the accuracy of locating the region of interest during CT image scanning.

[0022] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0024] Figure 1 is a schematic diagram of a CT device provided by an embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram of a method for locating a region of interest provided by an embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram of a positioning layer image provided by an embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram of another positioning layer image provided by an embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of another method for locating a region of interest provided by an embodiment of the present disclosure;

[0029] Figure 6 is a schematic diagram of a tracking layer image in which a target region of interest does not deviate from a second region of interest provided by an embodiment of the present disclosure;

[0030] Figure 7 is a schematic diagram of a tracking layer image of a target region of interest deviating from a second region of interest provided by an embodiment of the present disclosure;

[0031] Figure 8 It is a schematic diagram of a device for locating a region of interest provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0033] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0034] Unless otherwise stated, the term "plurality" means two or more.

[0035] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0036] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0037] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0038] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0039] like Figure 1 As shown, the CT device 100 provided by the embodiment of the present disclosure includes a device body 110 and a device 800 for locating a region of interest.

[0040] Specifically, the device 800 for locating the region of interest is disposed on the device body 110 .

[0041] Optionally, the device 800 for locating a region of interest includes a processor. When performing a CT image scan, the processor can determine a first region of interest in a target positioning layer image based on a pre-built recognition model, and can adjust the position and / or size of the first region of interest according to target standard setting information corresponding to the first region of interest in pre-stored statistical information to determine the final target region of interest in the target positioning layer image.

[0042] In combination with the above-mentioned CT device, the embodiment of the present disclosure provides a method for locating a region of interest, such as Figure 2 As shown, the method includes:

[0043] S201, the processor obtains a target positioning layer image.

[0044] Specifically, the locator image is an image acquired using a lower radiation dose and a faster scanning speed before the formal CT scan. The target locator image is the locator image of the human body part that the user wants to scan, or the locator image selected by the user from multiple locator images of different human body parts.

[0045] S202: The processor determines a first region of interest in the target positioning layer image based on a pre-built recognition model.

[0046] Specifically, a region of interest (ROI) is a region that a user wants to track when performing a CT scan.

[0047] Specifically, the recognition model is a pre-built deep neural network model for identifying the region of interest in the positioning layer image or the tracking layer image.

[0048] Specifically, in the CT image scanning process, after contrast agent injection, it is necessary to track the change of CT value in the region of interest to determine whether the subsequent scanning process is triggered. If the region of interest is manually divided by users with less medical scanning experience, there is a problem of large division errors. Therefore, it is necessary to identify the first region of interest of the target positioning layer image based on a pre-built recognition model.

[0049] S203: The processor determines target standard setting information corresponding to the first region of interest in pre-stored statistical information.

[0050] The statistical information includes standard setting information corresponding to different types of regions of interest.

[0051] Specifically, in the disclosed embodiment, setting information of parameters such as positions and sizes of different types of regions of interest from users with rich experience in medical scanning is collected in advance, and this information is stored as statistical information as standard setting information corresponding to different types of regions of interest.

[0052] Specifically, after the first region of interest in the target positioning layer image is identified by the recognition model, the difference between the first region of interest and the region of interest divided by a user with rich medical scanning experience can be determined by determining the target standard setting information corresponding to the first region of interest in the statistical information. In this way, the first region of interest can be adjusted according to the target standard setting information.

[0053] Optionally, determining target standard setting information corresponding to the first region of interest in pre-stored statistical information includes: identifying a region type to which the first region of interest belongs; and using standard setting information corresponding to a region of interest of the same region type in the statistical information as target standard setting information.

[0054] Specifically, since one type of region of interest corresponds to one type of standard setting information, the target standard setting information for the first region of interest can be determined from the statistical information based on the region type to which the first region of interest belongs.

[0055] S204: The processor adjusts the first region of interest according to the target standard setting information to determine a target region of interest in the target positioning layer image.

[0056] Specifically, by adjusting the position and / or size of the first region of interest according to the target standard setting information, the region of interest finally determined can better meet the tracking requirements of the user.

[0057] Specifically, the target standard setting information includes information such as a reference size of the region of interest.

[0058] For example, the patient being scanned is an adult, the imaging field of view is 300 mm, and the tracking target is the coronary artery. The corresponding target positioning layer image is as follows: Figure 3 As shown, Figure 3 Region A in the middle is the coronary region, i.e., the first region of interest. The actual size of the first region of interest in the target positioning layer image is 42 pixels (diameter), while the reference size specified in the target standard setting information is 17 pixels (diameter). On this basis, the size of the first region of interest can be adjusted to 17 pixels according to the reference size, and the center position uses the center position of the original first region of interest, and the final target region of interest (such as Figure 3 The first region of interest may be adjusted with the center of the first region of interest as the center and then expand outward to the reference size of the target standard setting information. The first region of interest is generally elliptical or circular, and the center of the first region of interest may be obtained by identifying the outline of the first region of interest.

[0059] In the disclosed embodiment, the first region of interest in the target positioning layer image is identified by a pre-built recognition model, and the position and / or size of the first region of interest is adjusted according to the target standard setting information corresponding to the first region of interest in the pre-stored statistical information to determine the final target region of interest in the target positioning layer image. In this way, the user does not need to manually divide the position and size of the region of interest in the positioning layer image, which reduces the error in the region of interest division caused by the user's lack of scanning experience. Therefore, the disclosed embodiment can improve the accuracy of locating the region of interest during CT image scanning.

[0060] In some embodiments, acquiring the target positioning layer image includes: receiving an image selection instruction input by a user; and determining the target positioning layer image from a plurality of positioning layer images according to the image selection instruction.

[0061] Specifically, when there are multiple positioning layer images obtained by scanning, the user can determine the target positioning layer image from the multiple positioning layer images by inputting an image selection instruction.

[0062] In some embodiments, based on a pre-built recognition model, determining a first region of interest in a target positioning layer image includes: using a recognition model to identify multiple regions of interest in the target positioning layer image; receiving a region determination instruction input by a user, and parsing the region determination instruction to determine region information; wherein the region information includes region selection information or region demarcation information; when the region information is region selection information, the region of interest corresponding to the region selection information is used as the first region of interest in the target positioning layer image; when the region information is region division information, the region re-divided based on the region division information is used as the first region of interest in the target positioning layer image.

[0063] Specifically, when there are multiple regions of interest in the target positioning layer image identified by the recognition model, the user is required to input a region determination instruction to determine a target region of interest among the multiple regions of interest.

[0064] Specifically, the region information can be determined by parsing the region determination instruction, wherein the region information includes region selection information and region division information. Specifically, if the region information is region selection information, it indicates that there is a region that the user wants to track among the multiple identified regions of interest. Therefore, in this case, the region of interest corresponding to the region selection information can be used as the first region of interest in the target positioning layer image. If the region information is region division information, it indicates that there is no region that the user wants to track among the multiple identified regions of interest. Therefore, in this case, it is necessary to use the region re-divided based on the region division information as the first region of interest in the target positioning layer image.

[0065] For example, taking the identification of blood vessels in the target positioning layer image as the first region of interest as an example, the image identified is as follows: Figure 4 As shown. Figure 4 It can be seen that the identified regions of interest include the coronary artery region ( Figure 4 C region in the pulmonary artery area ( Figure 4 In this case, if it is determined that the coronary region needs to be selected according to the region determination instruction input by the user, the coronary region can be used as the first region of interest in the target positioning layer image.

[0066] It should be noted that when the recognition model identifies the region of interest in the target positioning layer image, there is a situation where only one region of interest is identified. In this case, the region of interest can be directly determined as the first region of interest in the target positioning layer image. The user can also be prompted to perform manual division.

[0067] In this embodiment, the recognition model can simultaneously recognize multiple regions of interest in the target positioning layer image. In this case, the user can determine the first region of interest among the multiple regions of interest by inputting a region determination instruction. In this way, a variety of selectable tracking regions are provided for the user, so that the user can select the tracking region according to the actual scanning requirements.

[0068] In addition, the region determination instruction based on receiving the user input also provides a screening basis for the subsequent adjustment of the region of interest based on the statistical information, that is, the information of which region of interest is extracted from the statistical information can be obtained through the determination instruction.

[0069] The present disclosure provides another method for locating a region of interest, such as Figure 5 As shown, the method includes:

[0070] S501, the processor obtains a target positioning layer image.

[0071] S502: The processor determines a first region of interest in the target positioning layer image based on a pre-built recognition model.

[0072] S503: The processor determines target standard setting information corresponding to the first region of interest in pre-stored statistical information.

[0073] The statistical information includes standard setting information corresponding to different types of regions of interest.

[0074] S504: The processor adjusts the first region of interest according to the target standard setting information to determine a target region of interest in the target positioning layer image.

[0075] S505: The processor obtains the current frame tracking layer image corresponding to the target positioning layer image.

[0076] Specifically, the tracking layer image (Tracker) is a cross-sectional image at the same position as the positioning layer image but at a different time.

[0077] S506: The processor determines a second region of interest in the tracking layer image of the current frame based on a pre-built recognition model.

[0078] Specifically, in the CT image scanning process, after contrast agent injection, it is necessary to track the change of CT value in the region of interest to determine whether the subsequent scanning process is triggered. Therefore, after acquiring the current frame tracking layer image corresponding to the target positioning layer image, it is necessary to identify the second region of interest in the current frame tracking layer image based on the recognition model to identify the change of CT value in the region of interest.

[0079] S507: The processor compares the target region of interest with the second region of interest to determine a deviation of the target region of interest.

[0080] Specifically, if the target region of interest of the target positioning layer image deviates from the second region of interest of the current frame tracking layer image, each subsequent frame tracking layer image acquired based on the target region of interest will be affected by this deviation, resulting in a continuous positioning error that increases frame by frame. The accumulation of this error may eventually lead to the failure of target tracking. Therefore, after identifying the second region of interest in the current frame tracking layer image, the target region of interest and the second region of interest are compared to determine the deviation of the target region of interest.

[0081] S508: The processor adjusts the tracking area of ​​the tracking layer image according to the deviation of the target area of ​​interest.

[0082] Specifically, if the target region of interest deviates, it indicates that continuing to acquire the next frame of tracking layer images based on the target region of interest may cause target tracking failure. Therefore, it is necessary to adjust the tracking region of the subsequent tracking layer images according to the deviation of the target region of interest.

[0083] Optionally, the tracking area of ​​the tracking layer image is adjusted according to the deviation of the target region of interest, including: when the target region of interest does not deviate from the second region of interest, determining the target region of interest as the tracking area of ​​the tracking layer image; when the target region of interest deviates from the second region of interest, redetermining the target region of interest based on the second region of interest and statistical information, and using the redetermined target region of interest as the tracking area of ​​the tracking layer image.

[0084] Specifically, if the target region of interest does not deviate from the second region of interest, it indicates that the target tracking is performed based on the target region of interest, and the current frame tracking layer image obtained does not have a positioning error. Therefore, in this case, the target region of interest can continue to be determined as the tracking region of the tracking layer image.

[0085] Specifically, if the target ROI deviates from the second ROI, it indicates that continuing to acquire the next frame of tracking layer image based on the target ROI may cause target tracking failure. Therefore, in this case, it is necessary to redefine the target ROI based on the second ROI and statistical information, and use the redetermined target ROI as the subsequent tracking area of ​​the tracking layer image.

[0086] In the embodiment of the present disclosure, after each acquisition of the current frame tracking layer image corresponding to the target positioning layer image, it is confirmed whether the target region of interest deviates from the second region of interest in the current frame tracking layer image, and the tracking region of the subsequent tracking layer image is adjusted according to the deviation of the region of interest. In this way, the tracking region can be adjusted in time to ensure that the tracking target is consistent with the preset target.

[0087] In some embodiments, after redetermining the target region of interest based on the second region of interest and the statistical information, and using the redetermined target region of interest as the tracking area of ​​the tracking layer image, the method also includes: displaying switch options for the automatic trigger function and the manual trigger function so that the user can choose whether to turn off the automatic trigger function and turn on the manual trigger function instead.

[0088] Specifically, automatic triggering means that during the tracking scanning process of the tracking layer image, if the CT value of the second region of interest in the tracking layer image reaches the CT threshold, the scanning process of the next frame of the tracking layer image is automatically triggered. Manual triggering means that the tracking layer image is scanned until the specified number of circles is reached, and during this period, the user can manually trigger the scanning of the next frame of the tracking layer image at any time.

[0089] In some embodiments, comparing the target region of interest with the second region of interest to determine the deviation of the target region of interest includes: identifying a first number of all pixels in the target region of interest; identifying a second number of pixels in the target region of interest in the second region of interest; determining that the target region of interest has not deviated from the second region of interest when the ratio of the second number to the first number is greater than or equal to a set threshold; and determining that the target region of interest has deviated from the second region of interest when the ratio of the second number to the first number is less than the set threshold.

[0090] Specifically, if the ratio of the second number of pixels in the target region of interest in the second region of interest to the first number of all pixels in the target region of interest is greater than or equal to the set threshold, it indicates that the second region of interest of the current frame tracking layer image basically includes all the contents in the target region of interest (the specific situation is as follows Figure 6 As shown, Figure 6 (The E region is the second region of interest, and the F region is the target region of interest). Therefore, in this case, it can be determined that the target region of interest does not deviate from the second region of interest.

[0091] Specifically, if the ratio of the second number of pixels in the target region of interest in the second region of interest to the first number of all pixels in the target region of interest is less than the set threshold, it indicates that some important content in the target region of interest is missing in the second region of interest of the current frame tracking layer image (the specific situation is as follows Figure 7 As shown, Figure 7 (The E region is the second region of interest, and the F region is the target region of interest). Therefore, in this case, it can be determined that the target region of interest deviates from the second region of interest.

[0092] Optionally, the threshold value is determined based on the scanned human body part, and different human body parts correspond to different threshold values. Taking scanning of the blood vessels of the lungs as an example, the threshold value is greater than or equal to 0.95.

[0093] In addition, in addition to the above-mentioned methods, the deviation of the target region of interest may also be confirmed by other methods, for example, by determining the relationship between the bounding rectangle corresponding to the target region of interest and the second region of interest.

[0094] In some embodiments, a recognition model is constructed according to the following steps: a sample image with an area of ​​interest marked by a user is obtained; wherein the marked area of ​​interest is a convex area; the sample image includes multiple human body parts, positioning layer images and / or tracking layer images under multiple imaging fields of view; based on the sample image, a deep neural network model is trained to obtain a recognition model.

[0095] Specifically, the sample images include multiple human body parts, positioning layer images and / or tracking layer images under multiple imaging fields, and the regions of interest therein are all marked by users with rich medical scanning experience (such as professional doctors or professional CT equipment operators). The marked content is to use the vascular areas corresponding to different human body parts as the regions of interest, and the marked regions of interest are convex regions.

[0096] Specifically, before training a deep neural network model based on sample images, the sample images can be processed by spline interpolation to improve image quality and increase the number of sample images.

[0097] Specifically, the network structure of the deep neural network model may be a UNet network structure, and the adopted loss function may be a Dice loss or a cross entropy loss.

[0098] In addition, the segmentation network structure can also be used as the network structure of the deep neural network model, or other traditional image processing algorithms (such as threshold segmentation, region growing and edge detection) can be used to construct the deep neural network model.

[0099] Combination Figure 8As shown, the embodiment of the present disclosure provides a device 800 for locating a region of interest, a processor 801 and a memory 802. Optionally, the device may also include a communication interface 803 and a bus 804. The processor 801, the communication interface 803, and the memory 802 may communicate with each other through the bus 804. The communication interface 803 may be used for information transmission. The processor 801 may call the logic instructions in the memory 802 to execute the method for locating a region of interest of the above embodiment.

[0100] In addition, the logic instructions in the memory 802 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0101] The memory 802 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 801 executes the function application and data processing by running the program instructions / modules stored in the memory 802, that is, the method for locating the region of interest in the above embodiment is implemented.

[0102] The memory 802 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 802 may include a high-speed random access memory and may also include a non-volatile memory.

[0103] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above method for locating a region of interest.

[0104] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0105] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0106] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0107] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0108] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0109] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for locating a region of interest, characterized in that: include: Acquire the target positioning layer image; Based on a pre-built recognition model, determining a first region of interest in the target positioning layer image; Determine target standard setting information corresponding to the first region of interest in pre-stored statistical information; wherein the statistical information includes standard setting information corresponding to different types of regions of interest; The first region of interest is adjusted according to the target standard setting information to determine the target region of interest in the target positioning layer image.

2. The method according to claim 1, characterized in that Get the target positioning layer image, including: Receive an image selection instruction input by a user; According to the image selection instruction, a target positioning layer image is determined from a plurality of positioning layer images.

3. The method according to claim 1, characterized in that: Based on the pre-built recognition model, determine the first region of interest in the target positioning layer image, including: A recognition model is used to identify multiple regions of interest in the target positioning layer image; Receiving a region determination instruction input by a user, and parsing the region determination instruction to determine region information; wherein the region information includes region selection information or region demarcation information; In the case where the region information is region selection information, the region of interest corresponding to the region selection information is used as the first region of interest in the target positioning layer image; In the case where the region information is region division information, the region re-divided based on the region division information is used as the first region of interest in the target positioning layer image.

4. The method according to claim 1, characterized in that: Determining target standard setting information corresponding to the first region of interest in pre-stored statistical information includes: Identify the region type to which the first region of interest belongs; The standard setting information corresponding to the region of interest having the same region type in the statistical information is used as the target standard setting information.

5. The method according to any one of claims 1 to 4, characterized in that After determining the target region of interest in the target positioning layer image, the method further includes: Obtain the current frame tracking layer image corresponding to the target positioning layer image; Based on the pre-built recognition model, determine a second region of interest in the tracking layer image of the current frame; Compare the target region of interest with the second region of interest to determine the deviation of the target region of interest; According to the deviation of the target region of interest, the tracking region of the tracking layer image is adjusted.

6. The method according to claim 5, characterized in that According to the deviation of the target area of ​​interest, adjust the tracking area of ​​the tracking layer image, including: In a case where the target region of interest does not deviate from the second region of interest, determining the target region of interest as the tracking region of the tracking layer image; In the case that the target region of interest deviates from the second region of interest, the target region of interest is re-determined according to the second region of interest and the statistical information, and the re-determined target region of interest is used as the tracking region of the tracking layer image.

7. The method according to claim 6, characterized in that After re-determining the target region of interest according to the second region of interest and the statistical information, and using the re-determined target region of interest as the tracking region of the tracking layer image, the method further includes: Display the switch options of the automatic trigger function and the manual trigger function so that the user can choose whether to turn off the automatic trigger function and turn on the manual trigger function.

8. The method according to claim 5, characterized in that Compare the target region of interest with the second region of interest to determine the deviation of the target region of interest, including: Identify a first number of all pixels in a target region of interest; Identify a second number of pixels in the target region of interest in a second region of interest; When the ratio of the second number to the first number is greater than or equal to a set threshold, determining that the target region of interest does not deviate from the second region of interest; When the ratio of the second number to the first number is less than a set threshold, it is determined that the target region of interest deviates from the second region of interest.

9. The method according to any one of claims 1 to 4, characterized in that Follow the steps below to build a recognition model: Obtain a sample image with an area of ​​interest marked by a user; wherein the marked area of ​​interest is a convex area; the sample image includes multiple human body parts, positioning layer images and / or tracking layer images under multiple imaging fields of view; According to the sample images, the deep neural network model is trained to obtain the recognition model.

10. A device for locating a region of interest, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for locating a region of interest according to any one of claims 1 to 9 when running the program instructions.

11. A CT device, characterized in that: include: Equipment body; The device for locating a region of interest as claimed in claim 10 is mounted on a device body.

Images