Method, device, equipment, medium and product for adjusting collimation area

Abstract

The present disclosure relates to a method, apparatus, device, medium, and product for adjusting a collimation region of a medical imaging system. The method includes: obtaining a first function that characterizes a correspondence between collimation regions annotated based on a plurality of first images and corresponding automatically determined collimation regions, wherein the plurality of first images respectively include at least an object to be measured; performing a first operation, which includes: determining an adjustment parameter value corresponding to each readjustment for multiple readjustments of the plurality of collimation regions after the first adjustment, wherein the plurality of collimation regions after the first adjustment are obtained by processing the collimation regions automatically determined for the corresponding objects to be measured through the first function; in response to determining that a proportion of the adjustment parameter values ​​that are less than an adjustment threshold value among the multiple readjustments is greater than or equal to a preset proportion, continuing to perform the first operation; in response to determining that a proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is less than the preset proportion, updating the first function according to the adjustment parameter values ​​that are readjusted multiple times.

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical devices, and in particular to a method, device, electronic device, computer-readable storage medium, and computer program product for adjusting a collimation region of a medical imaging system. Background Art

[0002] During the operation of the medical imaging device, after the object to be measured is in place, the collimation area corresponding to the X-ray irradiation area is automatically determined, so that the X-ray covers the collimation area to form a medical image.

[0003] The approaches described in this section are not necessarily approaches that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any approach described in this section is prior art simply by virtue of its inclusion in this section. Similarly, unless otherwise indicated, the issues raised in this section should not be considered as having been recognized in any prior art. Summary of the Invention

[0004] According to one aspect of an embodiment of the present disclosure, a method for adjusting a collimation region of a medical imaging system is proposed, comprising: obtaining a first function for characterizing a correspondence between collimation regions annotated based on a plurality of first images and corresponding automatically determined collimation regions, wherein the plurality of first images each include at least an object to be measured; and performing a first operation. The first operation comprises: determining an adjustment parameter value corresponding to each readjustment for a plurality of collimation regions after the first adjustment, wherein the plurality of collimation regions after the first adjustment are obtained by processing the collimation regions automatically determined for the corresponding object to be measured through the first function; in response to determining that a proportion of the adjustment parameter values ​​of the plurality of readjustments that are less than an adjustment threshold is greater than or equal to a preset proportion, continuing to perform the first operation; and in response to determining that a proportion of the adjustment parameter values ​​of the plurality of readjustments that are less than the adjustment threshold is less than a preset proportion, updating the first function according to the adjustment parameter values ​​of the plurality of readjustments.

[0005] According to another aspect of an embodiment of the present disclosure, a device for adjusting a collimation region of a medical imaging system is proposed, comprising: a first unit for obtaining a first function for characterizing a correspondence between collimation regions annotated based on a plurality of first images and corresponding automatically determined collimation regions, wherein the plurality of first images respectively include at least an object to be measured; and a second unit for performing a first operation. The first operation comprises: determining an adjustment parameter value corresponding to each readjustment for a plurality of collimation regions after first adjustment, wherein the plurality of collimation regions after first adjustment are respectively obtained by processing the collimation regions automatically determined for the corresponding object to be measured through the first function; in response to determining that a proportion of the adjustment parameter values ​​of the plurality of readjustments that are less than an adjustment threshold is greater than or equal to a preset proportion, continuing to perform the first operation; in response to determining that a proportion of the adjustment parameter values ​​of the plurality of readjustments that are less than the adjustment threshold is less than a preset proportion, updating the first function according to the adjustment parameter values ​​of the plurality of readjustments.

[0006] According to another aspect of an embodiment of the present disclosure, an electronic device is proposed, which includes at least one processor and a memory communicatively connected to the at least one processor; the memory stores a computer program, and the computer program implements the method according to an embodiment of the present disclosure when executed by the at least one processor.

[0007] According to another aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing a computer program is provided, wherein the computer program implements any of the above methods when executed by a processor.

[0008] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the method according to any of the above aspects when executed by a processor.

[0009] According to one or more embodiments of the present disclosure, the determined first function can more accurately characterize the user's preference, thereby achieving automatic determination of the collimation area that is more in line with the user's habits.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings illustrate exemplary embodiments and constitute a part of the specification. Together with the description of the specification, they serve to explain exemplary implementation of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals designate similar, but not necessarily identical, elements.

[0012] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings so that those skilled in the art can better understand the above and other features and advantages of the present disclosure. In the accompanying drawings:

[0013] Figure 1 A schematic diagram showing adjustment of the automatically determined collimation area in the related art is shown;

[0014] Figure 2 A flow chart showing a method for adjusting a collimation region of a medical imaging system according to an embodiment of the present disclosure is shown;

[0015] Figure 3 A flowchart showing a method for adjusting a collimation area of ​​a medical imaging system according to other embodiments of the present disclosure is shown;

[0016] Figure 4 A block diagram showing an apparatus for adjusting a collimation region of a medical imaging system according to an embodiment of the present disclosure; and

[0017] Figure 5 An example configuration of an electronic device is shown that may be used to implement the methods described herein. DETAILED DESCRIPTION

[0018] In order to have a clearer understanding of the technical features, purposes and effects of the present disclosure, specific embodiments of the present disclosure are now described with reference to the accompanying drawings, in which the same reference numerals represent the same parts.

[0019] In this document, “illustrative” means “serving as an example, instance or illustration”, and any diagram or implementation described in this document as “illustrative” should not be interpreted as a more preferred or more advantageous technical solution.

[0020] To simplify the drawings, only the parts related to the present disclosure are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, to simplify the drawings and facilitate understanding, in some figures, only one of the components with the same structure or function is schematically depicted or labeled.

[0021] In this article, "one" not only means "only one" but also "more than one". In this article, "first", "second", etc. are only used to distinguish one from another, and do not indicate their importance or order, or the premise of each other.

[0022] Medical imaging systems, for example, use penetrating rays to image the interior of an object to be measured. An X-ray imaging system is a commonly used medical imaging system. X-ray imaging equipment has a collimator for limiting the emission range of X-rays, and X-ray imaging equipment is usually equipped with an illumination unit for projecting light onto the detector to indicate the projection range of X-rays on the detector when the X-ray tube is exposed. The X-ray imaging system may have an automatic collimation function, for example, based on a predetermined algorithm for automatically determining the collimation area, automatically determining the collimation area, that is, the projection range of X-rays on the detector during exposure. However, different regions and different users have different preferences for the size or position of the collimation area, and it is often necessary to adjust the collimation area automatically determined by the system.

[0023] Figure 1 A schematic diagram of adjusting the automatically determined collimation area in the related art is shown.

[0024] exist Figure 1 In the present invention, after the object to be measured is in place, the automatic collimation function of the medical imaging system is utilized, that is, the collimation area 100 is automatically determined by a predetermined algorithm stored in the medical imaging system. However, the collimation area desired by the user (such as a radiologist) varies from person to person. The user can adjust the collimation area 100 through the human-computer interaction device based on his or her own habits or experience. For example, the user inputs adjustment parameters such as the offset in the up or down direction, the offset in the left or right direction, the magnification and reduction coefficient, etc. through the human-computer interaction device to adjust the position, size, etc. of the collimation area 100 to obtain the adjusted collimation area 110 that conforms to the user's habits. The above process of adjusting the collimation area based on the user's habits on the basis of the automatic collimation result of the medical imaging system is not intuitive, and the operation is complicated and cumbersome. Users often find it difficult to understand the relationship between the adjustment parameters to be input and the final collimation area.

[0025] Figure 2 FIG. 2 is a flow chart showing a method 200 for adjusting a collimation region of a medical imaging system according to an embodiment of the present disclosure. Figure 2 As shown, method 200 includes step 210 and step 220 .

[0026] Step 210 : Obtain a first function, where the first function is used to characterize the correspondence between the collimation areas annotated based on a plurality of first images and the corresponding automatically determined collimation areas, wherein the plurality of first images respectively include at least the object to be measured.

[0027] In one or more examples, the object to be measured may be, for example, a chest, a palm, a knee joint, etc. of a human body.

[0028] In one or more examples, the first image is a three-dimensional image, such as an RGB-D image, that includes two-dimensional information and depth information. The depth information can be used to determine the distance between the X-ray tube and the detector. By obtaining this depth information, the scale of the X-ray projection range on the detector can be determined.

[0029] In one or more examples, the first function can be any suitable mathematical model or algorithm. The first function can be used to describe the similarity or difference between the alignment region manually annotated by the user and the automatically determined alignment region. For example, the first function can be a feature matching algorithm that can be used to compare the similarity between the automatically determined alignment region and the alignment region in the first image to determine the correspondence between the two. In another example, the first function can be a deformation model or transformation algorithm that can be used to transform the automatically determined alignment region into a desired alignment region based on the correspondence between the alignment region in the first image and the automatically determined alignment region. In another example, the first function can be a linear regression model that uses the user-annotated alignment region as the independent variable and the automatically determined alignment region as the dependent variable, and fits a linear function using training data. In specific implementations, methods such as least squares or gradient descent can be used to solve the problem. In another example, the first function can be a decision tree that uses the user-annotated alignment region as input features and the automatically determined alignment region as output labels, and learns the decision tree using training data. In specific implementations, algorithms such as ID3, C4.5, and CART can be used to generate the decision tree.

[0030] It should be noted that the specific algorithm selected for the first function should be determined according to the specific application scenario and data conditions. The mathematical model or algorithm for implementing the first function is not limited here.

[0031] In one or more examples, each object to be measured in the multiple first images can be from a human body of different body types, so as to expand the richness of the sample. Furthermore, each body type can also include body types of human bodies of different genders. This can help the algorithm of the first function better adapt to various body shapes and postures, thereby improving the accuracy and applicability of the algorithm. At the same time, using multiple human bodies of different body types (and optionally different genders) as the objects to be measured in the first image can also increase the robustness of the algorithm, enabling it to better handle a variety of different data input situations.

[0032] In one or more examples, the first function obtained in step 210 can be determined by the following steps: first, obtaining a plurality of automatically determined alignment regions and a plurality of labeled alignment regions corresponding to the plurality of first images. Then, determining the first function based on the plurality of automatically determined alignment regions and the corresponding plurality of labeled alignment regions. The "automatically determined alignment regions" are alignment regions automatically determined for a plurality of subjects of different body types (and optionally different genders) using the automatic alignment function of the medical imaging system, i.e., using a predetermined algorithm stored in the medical imaging system. For the same medical imaging system or model, this predetermined algorithm is typically fixed and unchanged. The "labeled alignment regions" are alignment regions manually labeled by a user on a plurality of first images of the plurality of subjects of different body types (and optionally different genders) captured using an image acquisition unit, such as a camera, and represent the alignment regions desired by the user. Due to differences in user habits and experience, the labeled alignment regions often differ from the alignment regions automatically determined by the system. In step 210 , a first function for characterizing the correspondence between the plurality of automatically determined collimation regions and the plurality of labeled collimation regions corresponding thereto is determined.

[0033] In one or more examples, the correspondence includes a ratio between a parameter value of the target parameter type of the marked collimation region and a parameter value of the target parameter type of the automatically determined collimation region.

[0034] The target parameter type may refer to parameters of the collimation area, such as a height parameter and a width parameter. For example, if the collimation area is a substantially rectangular collimation area frame, the parameters of the collimation area include at least one of the following: the length and / or height of the upper frame line, the length and / or height of the lower frame line, the length and / or height of the left frame line, the length and / or height of the right frame line, and the center point position coordinates of the collimation area frame. The height of the upper frame line and the lower frame line is, for example, the vertical distance from the center point, and the height of the left frame line and the right frame line is, for example, the vertical distance from the center point of each of the midpoints.

[0035] The ratio includes at least one of the following: the ratio of the upper frame line length of the marked collimation area to the upper frame line length of the automatically determined collimation area, the ratio of the upper frame line height of the marked collimation area to the upper frame line height of the automatically determined collimation area, the ratio of the lower frame line length of the marked collimation area to the lower frame line length of the automatically determined collimation area, the ratio of the lower frame line height of the marked collimation area to the lower frame line height of the automatically determined collimation area, the ratio of the left frame line length of the marked collimation area to the left frame line length of the automatically determined collimation area, the ratio of the left frame line height of the marked collimation area to the left frame line height of the automatically determined collimation area, the ratio of the right frame line length of the marked collimation area to the right frame line length of the automatically determined collimation area, the ratio of the right frame line height of the marked collimation area to the right frame line height of the automatically determined collimation area, and the ratio of the center point position coordinates of the marked collimation area to the center point position coordinates of the automatically determined collimation area.

[0036] In step 210, for different types of objects to be tested (such as different human organs), it is only necessary to replace multiple first images to adapt to different types of objects to be tested, for example, replacing multiple first images of chests with multiple first images of palms, so that the determination of the collimation area for different types of objects to be tested can be flexibly switched, thereby improving the applicability in various application scenarios.

[0037] Step 220 , performing a first operation. Step 220 further includes steps 221 to 223 .

[0038] Step 221 , determining an adjustment parameter value corresponding to each readjustment for multiple readjustments of a plurality of collimation areas after the first adjustment, wherein the plurality of collimation areas after the first adjustment are obtained by processing the collimation areas automatically determined for the corresponding object under test with the first function.

[0039] In one or more examples, determining the adjustment parameter value corresponding to each readjustment can include the following steps. Each time the object to be measured is positioned, a first adjustment region is first generated based on the collimation region automatically determined by the system and the first function obtained in step 210. This performs a preliminary, first adjustment based on the collimation region automatically determined by the system. Then, information about the first adjustment region is obtained, and the collimation region after the first adjustment is presented to the user, for example, via a cursor projected onto the detector. If the user is dissatisfied with the collimation region after the first adjustment, the user may readjust the collimation region after the first adjustment. Determining the adjustment parameter value corresponding to each readjustment can also include receiving user input regarding readjustment of the collimation region after the first adjustment to obtain the collimation region desired by the user. Finally, determining the adjustment parameter value based on the user input. For example, if the user input is a user dragging the collimation region after the first adjustment displayed on the display unit, the adjustment parameter value can be calculated based on the dragged region indicated by the dragging operation. For another example, if the user input is a user-entered parameter value, the user-entered parameter value is used as the adjustment parameter value.

[0040] Step 222 : In response to determining that the proportion of the adjustment parameter values ​​that are smaller than the adjustment threshold value among the multiple readjustments is greater than or equal to a preset proportion, continue to perform the first operation.

[0041] In an example, the preset ratio can be the ratio of the number of readjusted adjustment parameter values ​​that are less than the adjustment threshold to the total number of multiple readjustment of the adjustment parameter values. The adjustment threshold can be a criterion for determining whether the adjustment parameter value is too large. For example, the preset ratio is 0.8, and 100 readjusted adjustment parameter values ​​can be recorded. If the number of readjusted adjustment parameter values ​​that are less than the adjustment threshold is 90 times, then the proportion of the multiple readjusted adjustment parameter values ​​that are less than the adjustment threshold is 0.9. If it is greater than the preset ratio of 0.8, the first operation will continue to be performed, and the adjustment parameter value of each readjustment will continue to be recorded. In this way, the user's overall operating habits can be counted to exclude the user's one or only a few unconventional operations.

[0042] In one or more examples, adjusting the parameter value may include adjusting an absolute value or a relative value, for example, including at least one of the following: an offset of the upper and lower borders of the collimation area in the upward or downward direction, an offset of the left and right borders in the left or right direction, a magnification / reduction coefficient of the collimation area, and a ratio of any of the above offsets to the corresponding collimation area size after the first adjustment (i.e., an adjustment rate). During a predetermined number of readjustments, if each of the above adjustment parameters (e.g., the offset in the upward direction) is less than an adjustment threshold in a preset ratio of readjustments, then the first operation is continued.

[0043] In this way, if the proportion of the user's adjusted parameter values ​​for the collimation area after the first adjustment that is less than the adjustment threshold is greater than or equal to a preset proportion, the first function can be considered to be relatively consistent with the user's habits and no further adjustment of the first function is required. Therefore, a second batch of adjusted parameter values ​​can be collected to determine whether further updates to the first function are needed. In this way, by continuously collecting the user's adjusted parameter values ​​during actual operation and determining whether they meet the preset conditions, it can be determined whether the first function meets the user's habits and whether updates to the first function are necessary.

[0044] Step 223 : in response to determining that the proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is less than a preset proportion, update the first function according to the multiple readjustments of the adjustment parameter values.

[0045] In this step, if the proportion of adjusted parameter values ​​that are less than the adjustment threshold after multiple adjustments is less than a preset proportion, this indicates that the user has made excessive adjustments to the alignment area adjusted by the first function, resulting in a significant difference between the alignment area adjusted by the first function and the alignment area that meets the user's preferences. In this case, the first function is continuously updated until it meets the user's preferences. This allows the first function to be updated based on user preferences at different stages or when the user changes to a different scenario, thereby better adapting to different scenarios and user needs.

[0046] The initialized first function obtained by method 200 is derived based on the alignment regions annotated by the user in multiple first images. This makes the initialized first function relatively closer to the user's preferences. Using this initialized first function can reduce subsequent adjustments to the first function and improve the efficiency of determining the alignment region.

[0047] The initialized first function obtained by method 200 is then applied to the actual scenario of collimation region determination, i.e., the automatically determined collimation region is converted into the first adjusted collimation region using the first function. Based on the actual adjustment amount made by the user to the first adjusted collimation region, it is determined whether the first adjusted collimation region meets the user's preference, and whether the first function needs to be updated. The first function is updated until it meets the user's preference.

[0048] In summary, method 200 provides a collimation region adjustment method for a medical imaging system, so that the determined first function can more accurately characterize the user's preference, thereby achieving automatic determination of a collimation region that is more in line with the user's habits.

[0049] Figure 3 FIG. 3 is a flow chart showing a method 300 for adjusting a collimation region of a medical imaging system according to some other embodiments of the present disclosure. Figure 3 The method shown includes:

[0050] Step 310 : Obtain a first function for characterizing the correspondence between the collimation regions annotated based on the plurality of first images and the corresponding automatically determined collimation regions.

[0051] Step 321 : determining an adjustment parameter value corresponding to each readjustment for multiple readjustments of the multiple collimation regions after the first adjustment.

[0052] In response to the proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments being greater than or equal to the preset proportion, the process returns to step 321. In response to the proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments being greater than or equal to the preset proportion and less than the preset proportion, the process updates the first function according to the multiple readjustments of the adjustment parameter values.

[0053] Reference Figure 3 Method 300 may further include step 324, determining whether a proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is greater than or equal to a preset proportion. In response to determining that the proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is greater than or equal to the preset proportion, the method returns to step 321. In response to determining that the proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is less than the preset proportion, the method updates the first function according to the multiple readjustments of the adjustment parameter values.

[0054] In one or more examples, updating the first function according to the multiple readjusted adjustment parameter values ​​may include steps 3231 and 3232 .

[0055] Step 3231: Generate a second function based on the multiple readjusted adjustment parameter values ​​and the corresponding collimation regions after the first adjustment. The second function is used to characterize the correspondence between the desired collimation region and the corresponding automatically determined collimation region. The desired collimation region can be obtained based on the collimation region after the first adjustment and the corresponding adjustment parameter values.

[0056] In one or more examples, the second function may be any suitable mathematical model or algorithm. The specific method for implementing the second function may refer to the specific method for implementing the first function, which will not be described in detail here.

[0057] In one or more examples, generating the second function can be determined by the following steps: first, obtaining automatically determined collimation regions for each of the plurality of objects to be measured, a plurality of collimation regions after a first adjustment, and a plurality of adjusted adjustment parameter values. Then, based on the plurality of first adjusted collimation regions and the corresponding adjustment parameter values, generating a plurality of third adjusted collimation regions. Finally, determining the second function based on the automatically determined collimation regions and the plurality of third adjusted collimation regions.

[0058] In this way, if the user is not satisfied with the initial first function, a second function can be determined by collecting the user's adjustment parameter values ​​for the collimation area after the first adjustment, and the second function can be used as a recommendation that meets the user's habits.

[0059] Step 3232: Execute the second operation. Step 3232 further includes steps 3232-1 to 3232-3.

[0060] Step 3232-1: Add multiple second-adjusted collimation regions to the multiple first images for user viewing. The multiple second-adjusted collimation regions are each obtained by processing the automatically determined collimation regions of the corresponding first images using a second function. The second-adjusted collimation regions can be obtained by converting the automatically determined collimation regions using the second function.

[0061] In this way, multiple collimation areas after the second adjustment are respectively applied and displayed on multiple first images, that is, multiple first images in step 310. The second adjusted collimation areas can be displayed to the user more intuitively through the image, making it easier for the user to accept the accuracy and applicability of the second function.

[0062] Step 3232-2 receives input information indicating whether the user is satisfied with the plurality of collimation regions after the second adjustment. In step 3232-2, it is optionally determined whether the input information indicates satisfaction. The input information may be a preset operation for a preset object displayed on the terminal device. The preset object may be an operation icon or button. The preset operation may be a single-click, double-click, slide, or drag operation, etc.

[0063] Step 3232-3: in response to receiving the input information indicating satisfaction, using the second function as the current function for converting the automatically determined collimation area into the desired collimation area and updating the second function to the first function and then continuing to perform the first operation.

[0064] In this way, if user feedback is satisfactory, the second function can be considered to have met the user's preferences. The second function can then be set and used to present the collimation area converted by the second function to the user for actual work. The collimation area converted by the second function better meets the user's preferences, reducing or avoiding tedious user adjustments and improving work efficiency, thereby achieving automatic determination of a collimation area that better meets the user's preferences.

[0065] After the second function is updated to the first function, the user's adjusted parameter values ​​during actual work are continuously collected and judged to see if they meet the preset conditions. This allows the first function to be updated based on the user's habits. It can also be updated based on user habits at different stages or when the user's scenario changes, to better adapt to different scenarios and user needs.

[0066] In response to receiving input information indicating dissatisfaction, there may be the following two processing methods.

[0067] The first method, step 3232-4, generates a third function, updates the third function to the second function, and then performs the second operation. Specifically, the method returns to step 3232-1, adds the collimation regions adjusted based on the third function to the multiple first images for the user to review, and verifies whether the user is satisfied with the collimation regions adjusted based on the third function.

[0068] In an example, a third function is determined based on a plurality of automatically determined collimation regions and a plurality of respectively corresponding re-labeled collimation regions.

[0069] The re-marked multiple alignment regions can be derived from either of the following two methods.

[0070] In one approach, a user re-labels alignment regions on multiple first images. For example, if the user improves the labeling method or the previous labeling results are inaccurate, the user can use their experience and preferences to determine which alignment regions need to be re-labeled, which may result in different labeling results.

[0071] In another embodiment, a user re-marks the alignment region on multiple acquired second images. Each of the multiple second images includes at least one subject to be measured. At least a portion of the multiple second images differs from the multiple first images, for example, including subjects of different sizes. The user marks the alignment region on the multiple second images based on their experience or preferences.

[0072] In summary, you can change the annotation method or at least change part of the image for annotation. Users can choose the method that suits them according to their needs and experience.

[0073] The second method is to continue to perform the first operation based on the first function.

[0074] In this way, if the user's feedback is not satisfactory, it can be considered that the user has abandoned the operation and the process returns to step 321. At the same time, based on the first function, by continuously collecting the user's adjustment parameter values ​​during the actual operation and determining whether they meet the preset conditions, the first function can be updated according to the user's habits.

[0075] According to another aspect of an embodiment of the present disclosure, a device for adjusting a collimation area of ​​a medical imaging system is provided. Figure 4 FIG. 4 is a block diagram of an apparatus 400 for adjusting a collimation region of a medical imaging system according to an embodiment of the present disclosure. Figure 4 As shown, the apparatus 400 includes: a first unit 410 for obtaining a first function for characterizing the correspondence between alignment regions annotated based on a plurality of first images and corresponding automatically determined alignment regions, wherein each of the plurality of first images includes at least a subject to be measured. A second unit 420 for performing a first operation, the first operation comprising: determining an adjustment parameter value corresponding to each readjustment of a plurality of first-adjusted alignment regions, wherein the plurality of first-adjusted alignment regions are obtained by processing the first function with the alignment regions automatically determined for the corresponding subject to be measured; continuing the first operation in response to determining that a proportion of the adjustment parameter values ​​less than an adjustment threshold value among the plurality of readjustments is greater than or equal to a preset proportion; and updating the first function in response to determining that a proportion of the adjustment parameter values ​​less than the adjustment threshold value among the plurality of readjustments is less than a preset proportion, based on the plurality of readjustments. The operations of units 410 and 420 of the apparatus 400 are similar to the operations of steps S210 and S220 described above and are not further described herein.

[0076] According to another aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing a computer program is provided, wherein the computer program, when executed by a processor, implements the method 200 or 300 for adjusting a collimation region for a medical imaging system according to an embodiment of the present disclosure.

[0077] According to another aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the method 200 or 300 for adjusting a collimation region for a medical imaging system according to an embodiment of the present disclosure.

[0078] According to another aspect of the present disclosure, an electronic device is provided. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores a computer program that, when executed by the at least one processor, implements the method 200 or 300 for adjusting the collimation region of a medical imaging system according to an embodiment of the present disclosure. A medical imaging system according to an embodiment of the present disclosure may include the electronic device.

[0079] Figure 5An example configuration of an electronic device 500 that can be used to implement the methods described herein is shown. The electronic device 500 can be a variety of different types of devices, such as a server of a service provider, a device associated with a client (e.g., a client device), a system on a chip, and / or any other suitable computer device or computing system.

[0080] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system including at least one programmable processor 502, which can be a special purpose or general purpose programmable processor that can receive data and instructions from and transmit data and instructions to a storage system 504, at least one input device 510, and at least one output device 512.

[0081] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0082] In the context of the present disclosure, a computer-readable storage medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. More specific examples of extreme computer-readable storage media can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0083] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device 508 (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0084] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0085] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0086] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only limited by the claims after authorization and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. In addition, the steps may be performed in an order different from that described in this disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after this disclosure.

Claims

1. A method for adjusting a collimation region of a medical imaging system, comprising: Obtaining a first function for characterizing a correspondence between collimation areas annotated based on a plurality of first images and corresponding automatically determined collimation areas, wherein the plurality of first images respectively include at least the object to be measured; Performing a first operation, where the first operation includes: Determining an adjustment parameter value corresponding to each readjustment for multiple readjustments of a plurality of collimation regions after the first adjustment, wherein the plurality of collimation regions after the first adjustment are respectively obtained by processing the collimation regions automatically determined for the corresponding object under test through the first function; In response to determining that a proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is greater than or equal to a preset proportion, continuing to perform the first operation; In response to determining that a proportion of the adjustment parameter values ​​readjusted multiple times that are less than the adjustment threshold is less than the preset proportion, the first function is updated according to the adjustment parameter values ​​readjusted multiple times.

2. The method according to claim 1, wherein The updating of the first function according to the multiple readjusted adjustment parameter values ​​comprises: generating a second function based on the multiple readjusted adjustment parameter values ​​and the corresponding collimation regions after the first adjustment; Performing a second operation, the second operation including: adding a plurality of collimated areas after the second adjustment to the plurality of first images, respectively, wherein the plurality of collimated areas after the second adjustment are respectively obtained by processing the collimated areas automatically determined in the corresponding first images by the second function; receiving input information indicating whether the plurality of collimation regions after the second adjustment are satisfactory; In response to receiving input information indicating satisfaction, the second function is used as a current function for converting the automatically determined collimation area into a collimation area that meets an expectation, and the first operation is continued after the second function is updated to the first function.

3. The method according to claim 2, wherein: The second operation further includes: In response to receiving input information indicating dissatisfaction, generating a third function, and performing the second operation after updating the third function to the second function; or In response to receiving input information indicating dissatisfaction, continuing to perform the first operation based on the first function.

4. The method according to claim 1, wherein The first function obtained is determined by the following steps: Acquire a plurality of automatically determined collimation regions and a plurality of marked collimation regions respectively corresponding to the plurality of first images; The first function is determined based on the multiple automatically determined collimation areas and the corresponding multiple marked collimation areas.

5. The method according to claim 2, wherein Generating the second function includes: Acquiring collimation areas automatically determined for a plurality of objects to be measured, the plurality of collimation areas after the first adjustment, and the adjustment parameter values ​​of the plurality of readjustments; generating a plurality of third-adjusted collimation areas based on the plurality of first-adjusted collimation areas and the corresponding adjustment parameter values ​​of the plurality of readjustments; The second function is determined based on the automatically determined collimation area and the corresponding plurality of collimation areas after the third adjustment.

6. The method according to claim 3, wherein Generating the third function includes: Acquiring a plurality of automatically determined collimation areas and a plurality of re-labeled collimation areas respectively corresponding to the plurality of first images, or acquiring a plurality of automatically determined collimation areas and a plurality of re-labeled collimation areas respectively corresponding to a plurality of second images, wherein the plurality of second images respectively include at least the object to be measured, and at least a portion of the plurality of second images is different from the plurality of first images; The third function is determined based on the multiple automatically determined collimation areas and the corresponding re-marked collimation areas.

7. The method according to any one of claims 1 to 6, wherein The corresponding relationship includes a ratio between a parameter value of the target parameter type of the marked collimation area and a parameter value of the target parameter type of the automatically determined collimation area.

8. A device for adjusting a collimation region of a medical imaging system, comprising: A first unit is configured to obtain a first function for characterizing a correspondence between collimation areas annotated based on a plurality of first images and corresponding automatically determined collimation areas, wherein the plurality of first images respectively include at least an object to be measured; The second unit is configured to perform a first operation, where the first operation includes: Determining an adjustment parameter value corresponding to each readjustment for multiple readjustments of a plurality of collimation regions after the first adjustment, wherein the plurality of collimation regions after the first adjustment are respectively obtained by processing the collimation regions automatically determined for the corresponding object under test through the first function; In response to determining that a proportion of the adjustment parameter values ​​that are less than the adjustment threshold value among the multiple readjustments is greater than or equal to a preset proportion, continuing to perform the first operation; In response to determining that a proportion of the adjustment parameter values ​​readjusted multiple times that are less than the adjustment threshold is less than the preset proportion, the first function is updated according to the adjustment parameter values ​​readjusted multiple times.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program, which, when executed by the at least one processor, implements the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer program, wherein: The computer program implements the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product comprising a computer program, wherein The computer program implements the method according to any one of claims 1 to 7 when executed by a processor.

Images