Medical imaging method and device

Abstract

The embodiment of the invention provides a medical imaging method which comprises the steps that a target image of a target space where medical imaging equipment is located is obtained through computer vision equipment, and the medical imaging equipment at least comprises first scanning equipment and second scanning equipment; the target image at least comprises a scanning bed of the medical imaging equipment, first scanning equipment and second scanning equipment; based on the target image, collision detection is carried out on a target object in the target space, a collision detection result is determined, and the target object at least comprises a scanning bed, a first scanning device and / or a second scanning device; determining a moving scheme of the scanning bed, the first scanning device and / or the second scanning device in the target space based on the collision detection result; and based on the moving scheme, controlling the scanning bed, the first scanning device and / or the second scanning device to move, and controlling the medical imaging device to perform medical imaging.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of medical imaging, and in particular to a medical imaging method and apparatus. BACKGROUND

[0002] With the increasing demand for multi-department combined surgery and the requirement for surgical precision, in order to cope with complex and variable patient scanning medical scenarios, the combined application of medical imaging equipment has gradually become an important development field of medical imaging. Digital subtraction angiography (DSA) equipment can obtain clear blood vessel images, and its clinical demand for cooperation with CT-on-rails (CTOR) equipment is increasing in the treatment of heart, nerve, tumor and other fields. In the joint application scenario of the two, medical staff often need to manually adjust the position of the involved equipment (for example, a scanning bed, a C-arm of a DSA, and a gantry of a CTOR) to avoid collision, which consumes a lot of time and effort, is low in efficiency, and is prone to collision due to the negligence of medical staff, and is low in safety.

[0003] Therefore, it is necessary to provide a medical imaging method and apparatus to realize efficient and safe image scanning. SUMMARY

[0004] One or more embodiments of the present specification provide a medical imaging method. The method comprises: acquiring a target image of a target space by a computer vision device, the target space being a space where a medical imaging device is located, the medical imaging device comprising at least a first scanning device and a second scanning device, the target image comprising at least a scanning bed of the medical imaging device, the first scanning device and the second scanning device; performing collision detection on a target object in the target space based on the target image to determine a collision detection result, the target object comprising at least one of the scanning bed, the first scanning device and the second scanning device; determining a movement scheme of the scanning bed, the first scanning device and / or the second scanning device in the target space based on the collision detection result; and controlling the scanning bed, the first scanning device and / or the second scanning device to move based on the movement scheme, and controlling the medical imaging device to perform medical imaging.

[0005] In some embodiments, the computer vision device is installed on top of the target space.

[0006] In some embodiments, the first scanning device is a digital subtraction angiography (DSA) device, and the second scanning device is a CT-on-rails (CTOR) device.

[0007] In some embodiments, the determining the movement scheme of the scan bed, the first scan device and / or the second scan device in the target space comprises: obtaining a current working phase of the medical imaging device; and in response to the current working phase being a working phase of the second scan device, determining that the movement scheme comprises an avoidance path of a gantry of the first scan device.

[0008] In some embodiments, the movement scheme further comprises a rotation scheme of the scan bed, and the determining the rotation scheme comprises: obtaining a scan position of a current scan object; determining whether the scan bed needs to be rotated based on the target image, the scan position and the collision detection result; in response to the scan bed needing to be rotated, determining rotation information of the rotation; and determining the rotation scheme based on the rotation information.

[0009] In some embodiments, the movement scheme further comprises a translation scheme and / or a lifting scheme of the scan bed, and the determining the translation scheme comprises: determining whether the scan bed needs to be translated and / or lifted based on the target image and the scan position; in response to the scan bed needing to be translated and / or lifted, determining translation information of the translation and / or lifting information of the lifting; and determining the translation scheme and / or the lifting scheme based on the translation information and / or the lifting information.

[0010] In some embodiments, the determining the movement scheme of the scan bed, the first scan device and / or the second scan device in the target space further comprises: in response to the current working phase being a working phase of the first scan device or a non-working phase of the medical imaging device, determining that the movement scheme comprises returning the scan bed, the first scan device and / or the second scan device to a preset position.

[0011] In some embodiments, the obtaining the target image of the target space by the computer vision device comprises: obtaining a current use state of the computer vision device; in response to the current use state being a normal use state, controlling the computer vision device to obtain the target image; in response to the current use state being an abnormal use state, sending prompt information and / or a recommended movement scheme to a user, and controlling the medical imaging device to perform the movement and the medical imaging by the user.

[0012] In some embodiments, in response to the collision detection result comprising a collision between the target object and a non-target object, the determining the movement scheme comprises a movement path of the non-target object.

[0013] The one or more embodiments of the specification provide a medical imaging device, comprising a processor configured to perform the medical imaging method according to the embodiments of the specification. BRIEF DESCRIPTION OF DRAWINGS

[0014] The specification will be further illustrated in the way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers refer to the same structures, wherein:

[0015] Figure 1 is a schematic diagram of an application scenario of an exemplary medical imaging system according to some embodiments of the specification;

[0016] Figure 2 is a block diagram of an exemplary medical imaging system according to some embodiments of the specification;

[0017] Figure 3 is a flowchart of an exemplary medical imaging method according to some embodiments of the specification;

[0018] Figure 4 is a schematic diagram of an exemplary determination of a movement scheme according to some embodiments of the specification;

[0019] Figure 5 is a schematic diagram of an exemplary determination of a movement scheme according to some other embodiments of the specification. DETAILED DESCRIPTION

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the specification, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some examples or embodiments of the specification, and for those skilled in the art, the specification can be applied to other similar scenarios without creative labor on the basis of these drawings. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

[0021] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0022] As shown in the specification and claims, unless the context clearly indicates otherwise, the words "comprise", "comprising", "consist of" and / or "consisting of" do not preclude the inclusion of unknown elements. Generally, the terms "comprising" and "including" are used only to indicate the inclusion of the specified steps and elements, and these steps and elements do not constitute an exhaustive or exhaustive list of steps or elements.

[0023] Flowcharts are used in the specification to illustrate the operation of systems in accordance with embodiments of the specification. It should be understood that the operations in the front or back do not necessarily have to be performed in the order shown. Instead, various steps can be handled in reverse order, or simultaneously. Other operations can also be added to these processes, or one or more steps can be removed from these processes.

[0024] DSA devices can be widely used in the fields of heart, nerve, tumor and peripheral blood vessels. With the improvement of surgical precision requirements and the surge in demand for multi-department combined surgery, there are more and more clinical needs for DSA devices to be used with sliding rail CT devices. In the joint application scenario, doctors usually need to collect CT images of patients during surgery, and then fuse the images with the intraoperative DSA images, and then perform puncture under the perspective guidance of the fused images. The above scenario has high requirements for the cooperation accuracy of the two devices, which involves the adjustment of the target position of the patient and the horizontal position, height position, etc. controlled by the sliding rail CT device, to ensure the accuracy of the target position shooting; At the same time, it also needs to consider the collision risk in the movement of the sliding rail CT device and the DSA device to ensure the safety of the collection. At present, the process is usually realized by manual control of medical staff, which is low in efficiency and low in safety.

[0025] The present specification provides a medical imaging method and device. The method comprises obtaining a target image of a target space by a computer vision device. The target space is a space where a medical imaging device is located, and the medical imaging device comprises at least a first scanning device (e.g., a DSA device) and a second scanning device (e.g., a sliding CT device). The target image comprises at least a scanning bed of the medical imaging device, the first scanning device, and the second scanning device. The method comprises performing collision detection on a target object in the target space based on the target image, and determining a collision detection result. The target object comprises at least one of the scanning bed, the first scanning device, and the second scanning device. The method comprises determining a movement scheme of the scanning bed, the first scanning device, and / or the second scanning device in the target space based on the collision detection result. In the movement scheme, the scanning bed, the first scanning device, and / or the second scanning device move in the target space without collision. The method further comprises controlling the scanning bed, the first scanning device, and / or the second scanning device to move based on the movement scheme, and controlling the medical imaging device to perform medical imaging.

[0026] According to embodiments of the present application, the medical imaging scanning process is automatically performed collision detection based on computer vision to ensure that each device (e.g., the scanning bed, the first scanning device, and the second scanning device) in the medical imaging scanning process does not collide with other devices, thereby improving the efficiency and safety of medical imaging scanning, and making the process of using the DSA device and the sliding CT device together more intelligent and automated.

[0027] Figure 1 FIG. 1 is a schematic diagram of an example application scenario 100 of a medical imaging system according to some embodiments of the present specification. As shown in FIG. 1, the medical imaging system 100 can comprise a storage device 110, a processing device 120, a terminal 130, a network 140, a medical imaging device 150, and a computer vision device 160. Figure 1

[0028] The medical imaging device 150 refers to a device that uses different media to reproduce the structure inside the human body as an image in a medical manner. In some embodiments, the medical imaging device 150 can comprise a scanning bed 150-1, a first scanning device 150-2, and a second scanning device 150-3.

[0029] The scanning bed 150-1 refers to a device that carries a scanning object during medical imaging scanning. In some embodiments, the scanning bed 150-1 can be shared by the first scanning device 150-2 and the second scanning device 150-3, and can move between the two. In some embodiments, the scanning bed 150-1 can rotate, translate, and lift.

[0030] ​The first scanning device 150-2 and the second scanning device 150-3 refer to different devices for acquiring medical images by scanning. For example, the first scanning device 150-2 can be an angiography device, the second scanning device 150-3 can be a CT device, etc. In some embodiments, the first scanning device 150-2 can be a Digital Subtraction Angiography (DSA) device, and the second scanning device 150-3 can be a CT-on-rails (CTOR) device. In some embodiments, the first scanning device 150-2 can include a gantry. For example, a C-arm of a DSA device, etc. By setting the first scanning device 150-2 as a DSA device and the second scanning device 150-3 as a CTOR device, the combined application of the DSA device and the CTOR device can be achieved to acquire accurate DSA images and CT images based on treatment needs.

[0031] The medical imaging device 150 is in a target space 150-4. For example, the target space 150-4 can be an examination room in which the medical imaging device 150 is located. The target space 150-4 can be used to accommodate the medical imaging device 150, a current scanning object, the computer vision device 160, a user (e.g., an operator), etc.

[0032] The computer vision technology refers to a technology that uses computers and mathematical algorithms to simulate the human visual system to recognize, understand, analyze, and process images and videos. For example, the computer vision device 160 refers to a device that applies computer vision technology to acquire images, such as a camera, a video camera, etc. In some embodiments, the computer vision device 160 can be configured to take images (i.e., target images) of the target space 150-4. In some embodiments, the computer vision device 160 can be of various types, various specifications, etc.

[0033] In some embodiments, the computer vision device 160 can be installed in the target space 150-4, such as the top of the target space 150-4, the side wall of the target space 150-4, etc. For example only, the computer vision device 160 can be installed at the top of the target space 150-4. The top of the target space 150-4 refers to the upper part of the target space 150-4 in the vertical direction. For example, on the ceiling of the target space 150-4, on a part of the wall close to the ceiling of the target space 150-4, etc. It can be understood that when the computer vision device 160 is located at the top of the target space 150-4, the largest possible image taking field of view can be obtained, and interference from obstacles in the target space 150-4 (e.g., blocked by the medical imaging device 150, etc.) can be avoided, improving the shooting effect.

[0034] In some embodiments, the computer vision device 160 can have different installation numbers. It can be understood that the computer vision device 160 needs to obtain image information of the entire target space 150-4 for subsequent collision detection, etc., and the field of view of a single computer vision device 160 is relatively limited, so multiple computer vision devices 160 can be configured to obtain the image of the entire field of view of the target space 150-4. In some embodiments, the computer vision device 160 can have different installation angles. For example, 0 degrees-360 degrees, etc. The installation number and installation angle of the computer vision device 160 can be set based on experience or demand. In some embodiments, the installation number and installation angle of the computer vision device 160 can be related to the information of the target space 150-4. The information of the target space 150-4 refers to the relevant information of the target space 150-4. For example, the area of the target space 150-4, the object position information in the target space 150-4, the object size information, the object spacing information, etc. For example, the larger the area of the target space 150-4, the more computer vision devices 160 can be installed. The installation angle of a certain computer vision device 160 can be b degrees towards a certain object position in the target space 150-4, etc.

[0035] The processing device 120 can process data and / or information obtained from other devices or system components, perform the image processing method shown in some embodiments of the present specification based on the data, information and / or processing results, and complete one or more functions described in some embodiments of the present specification. For example, the processing device 120 can perform collision detection on the target object in the target space 150-4 based on the target image, and determine the collision detection result. For another example, the processing device 120 can determine the movement scheme of the scanning bed 150-1, the first scanning device 150-2 and / or the second scanning device 150-3 in the target space 150-4 based on the collision detection result. In some embodiments, the processing device 120 can obtain pre-stored data and / or information from the storage device 110, such as the target image of the target space 150-4, the target object in the target space 150-4, etc., to execute the medical imaging method shown in some embodiments of the present specification.

[0036] In some embodiments, the processing device 120 can include one or more sub-processing devices (e.g., single-core processing devices or multi-core multi-core processing devices). For example only, the processing device 120 can include a central processing unit (CPU), a graphics processing unit (GPU), a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof.

[0037] The storage device 110 can store data or information. In some embodiments, the storage device 110 can store data and / or information related to the medical imaging system 100, for example, target images of the target space 150-4 where the medical imaging device 150 is located obtained by the computer vision device 160. In some embodiments, the storage device 110 can store data and / or information processed by the processing device 120, for example, collision detection results, movement schemes, etc. The storage device 110 can include one or more storage components, each of which can be a standalone device or a part of other devices. The storage device can be local or implemented through the cloud.

[0038] The terminal 130 can interact with a user. The user can issue operation instructions to the processing device 120 through the terminal 130 to make the processing device 120 complete a specified operation, for example, control the medical imaging device 150 to perform medical imaging, etc. In some embodiments, the terminal 130 can receive collision detection results from the processing device 120, and the user can move a non-target object according to the collision detection results, etc. In some embodiments, the terminal 130 can be one or any combination of a mobile device, a tablet computer, a laptop computer, a desktop computer, and other devices with input and / or output functions.

[0039] The network 140 can connect components of the system and / or connect the system with external resource parts. The network 140 enables communication between components and / or between the system and other parts outside the system, facilitating exchange of data and / or information. In some embodiments, one or more components in the medical imaging system 100 (for example, the storage device 110, the processing device 120, the terminal 130, the medical imaging device 150, etc.) can send data and / or information to other components through the network 140. In some embodiments, the network 140 can be any one or more of a wired network or a wireless network.

[0040] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of the present specification. Various changes and modifications can be made by those of ordinary skill in the art under the guidance of the present specification. The features, structures, methods, and other characteristics of the exemplary embodiments described in the present specification can be combined in various ways. For example, the processing device 120 can be based on a cloud computing platform, for example, a public cloud, a private cloud, a community cloud, and a hybrid cloud, etc. However, these changes and modifications will not depart from the scope of the present specification.

[0041] Figure 2is a block diagram of an exemplary medical imaging system according to some embodiments of the present specification. In some embodiments, the medical imaging system 200 can include an image acquisition module 210, a collision detection module 220, a movement scheme determination module 230, and a medical imaging module 240. In some embodiments, each module in the medical imaging system 200 can be implemented by the processing device 120.

[0042] In some embodiments, the image acquisition module 210 can be configured to acquire a target image of a target space by a computer vision device. The target space is a space where the medical imaging device is located, and the medical imaging device includes at least a first scanning device and a second scanning device. The target image includes at least a scanning bed, the first scanning device, and the second scanning device of the medical imaging device. For more information about how to acquire the target image of the target space, see the description of step 310.

[0043] In some embodiments, the collision detection module 220 can be configured to perform collision detection on a target object in the target space based on the target image, and determine a collision detection result. The target object includes at least one of the scanning bed, the first scanning device, and the second scanning device. For more information about how to determine the collision detection result, see the description of step 320.

[0044] In some embodiments, the movement scheme determination module 230 can be configured to determine a movement scheme of the scanning bed, the first scanning device, and / or the second scanning device in the target space based on the collision detection result. In the movement scheme, the scanning bed, the first scanning device, and / or the second scanning device move in the target space without collision. For more information about how to acquire the movement scheme, see the description of step 330.

[0045] In some embodiments, the medical imaging module 240 can be configured to control the scanning bed, the first scanning device, and / or the second scanning device to move based on the movement scheme, and control the medical imaging device to perform medical imaging. For more information about how to control the medical imaging device to perform medical imaging, see the description of step 340.

[0046] In some embodiments, two or more modules in the medical imaging system 200 can be combined into one module, which can implement the functions of the two or more modules. For example, the collision detection module 220 and the movement scheme determination module 230 can be combined into one module, which can be configured to determine the collision detection result and determine the movement scheme. In some embodiments, one or more modules in the medical imaging system 200 can be deleted, or one or more modules can be added to the medical imaging system 200.

[0047] Figure 3 is a flowchart of an exemplary medical imaging method according to some embodiments of the present specification. As shown inFigure 3 As shown, the flow 300 includes the following steps. In some embodiments, the flow 300 can be performed by the processing device 120.

[0048] At step 310, a target image of a target space is acquired by a computer vision device (e.g., the computer vision device 160). The target space is a space (e.g., the target space 150-4) where the medical imaging device (e.g., the medical imaging device 150) is located. In some embodiments, the step 310 can be performed by the image acquisition module 210. More about the target space, the computer vision device can be found in the description of the target space, the computer vision device. Figure 1

[0049] The target image refers to an image of the space where the medical imaging device is located. For example, a full view image of the target space. In some embodiments, the medical imaging device at least includes a first scanning device and a second scanning device, and the target image can at least include a scanning bed, the first scanning device and the second scanning device of the medical imaging device. More about the medical imaging device, the scanning bed, the first scanning device and the second scanning device can be found in the description of the medical imaging device, the scanning bed, the first scanning device and the second scanning device. Figure 1

[0050] In some embodiments, the target image can include a color image and a depth image. The color image refers to an image presented by combining light rays of different colors. For example, an RGB image, etc. The depth image refers to an image containing three-dimensional feature information of an object. In some embodiments, the depth image can not only record two-dimensional image information of the target image, but also include distance information of each pixel point in the two-dimensional image information to the computer vision device. In some embodiments of the present specification, by setting the target image to include a color image and a depth image, the image type of the target image can be expanded, and more comprehensive image information can be obtained from the target image.

[0051] In some embodiments, the processing device 120 can acquire the target image of the target space by the computer vision device in various ways. For example, the processing device 120 can continuously or intermittently capture the target image of the target space by the computer vision device. For another example, the processing device 120 can control the computer vision device to rotate and capture the target image of the target space at different angles.

[0052] ​​In some embodiments, the processing device 120 can acquire a current use state of the computer vision device. The current use state refers to information reflecting the use of the device at the current time. In some embodiments, the current use state can include a normal use state and an abnormal use state. The normal use state refers to a state in which the computer vision device can normally work. The abnormal use state refers to a state in which the computer vision device cannot normally work. For example, malfunction, unable to start, etc. In some embodiments, the processing device 120 can directly acquire the current use state of the computer vision device through the medical imaging system 200.

[0053] In response to the current use state being a normal use state, the processing device 120 can control the computer vision device to acquire the target image and proceed to the subsequent steps. The specific acquisition manner can be referred to the foregoing related description. In response to the current use state being an abnormal use state, the processing device 120 can send prompt information and / or a recommended movement scheme to the user, and manually control the medical imaging device to move and perform medical imaging by the user. For example, the processing device 120 can determine the prompt information and / or the recommended movement scheme by acquiring preset information (for example, querying a preset table, querying historical data, acquiring user input information, etc.), a preset algorithm, etc., and send to the user. The prompt information refers to abnormal reminding information of the computer vision device, etc. The recommended movement scheme refers to a candidate movement scheme of the scanning bed, the first scanning device and / or the second scanning device. The user refers to a control person of the medical imaging system, for example, a medical staff. More content about the movement scheme can be referred to the related description of step 340.

[0054] In some embodiments of the present specification, by acquiring the current use state of the computer vision device; in response to the current use state being a normal use state, controlling the computer vision device to acquire the target image; in response to the current use state being an abnormal use state, sending prompt information and / or a recommended movement scheme to the user, and controlling the medical imaging device to move and perform medical imaging by the user, it can be confirmed whether the computer vision device is normally enabled, abnormal information is found in time and reminded, and manual control by the user is facilitated, avoiding the influence of device abnormality on the operation process and the delay of treatment opportunity.

[0055] In step 320, the target object in the target space is subjected to collision detection based on the target image, and a collision detection result is determined. In some embodiments, step 320 can be performed by the collision detection module 220.

[0056] The target object refers to a subject object that needs to be moved. In some embodiments, the target object can include at least one of the scanning bed, the first scanning device, and the second scanning device. In some embodiments, the processing device 120 can determine the target object in multiple ways. For example, the processing device 120 can take all parts or all objects in the target space as the target object. For another example, the processing device 120 can determine the target object by obtaining user input information.

[0057] It can be understood that when there are multiple objects in the space and a certain object needs to be moved, the object can collide with other objects. Collision detection refers to a process of determining whether two or more objects come into contact or collide during movement. The principle of collision detection is to abstract objects as geometric figures, and when objects collide, there will be a tangent / intersection point at the boundary of the geometric figure. By identifying the contact between the geometric figures corresponding to multiple objects, it can be determined whether a collision occurs and other collision-related information.

[0058] The collision detection result refers to the result after the object collision detection. For example, whether the objects collide, the position of the object collision, etc. In some embodiments, the processing device 120 can determine the collision detection result by performing collision detection on the target object in the target space based on the target image through a preset algorithm. An exemplary preset algorithm includes the following steps:

[0059] First step, collision detection preprocessing: processing the target image through image recognition algorithms, image recognition models, etc. to determine the relevant information of all objects in the target image (e.g., position information, size information, contour graphics, etc. of all objects in the target image);

[0060] Second step, rough collision detection: performing measurement and calculation on the target object and non-target objects through bounding box algorithms, bounding sphere algorithms, etc. to roughly judge whether the target object and the non-target object are likely to collide. The non-target object refers to other objects in the target space other than the target object. For example, when the target object is the first scanning device, the non-target object can be the second scanning device, the user, the current scanning object, other medical devices, etc.

[0061] Third step, detailed collision detection: when the rough collision detection result is that a collision is likely to occur, more accurate collision calculation is performed through the separation axis theorem, vector-based collision detection algorithms, etc. to determine the collision detection result.

[0062] In some embodiments, the processing device 120 can determine the collision detection result by performing collision detection on the target object in the target space based on the target image, through a machine learning model, etc. For example, the processing device 120 can process the target image through a collision detection model to determine the collision detection result. In some embodiments, the collision detection model can be a neural network (NN) model, a deep neural network (DNN) model, a convolutional neural network (CNN) model, etc., or any combination thereof. The input of the collision detection model can be the target image, and the output can be the collision detection result.

[0063] The collision detection model can be obtained through training. The processing device 120 can train an initial collision detection model based on training samples to determine the collision detection model. The processing device 120 can input the training samples to the initial collision detection model, establish a loss function based on the label and the output result of the initial collision detection model, update the parameters of the initial collision detection model, and when the loss function of the initial collision detection model meets a preset condition, the model training is completed, and the collision detection model is determined. The preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc. The training samples can be sample target images, which can be obtained through historical data; the label can be the actual collision detection result corresponding to the sample target image, which can be obtained through multiple collision tests and manual annotation.

[0064] In some embodiments, collision detection can be performed through a combination of acoustic wave technology, laser radar technology, etc., and the aforementioned computer vision technology.

[0065] At step 330, a movement scheme of the scanning bed, the first scanning device, and / or the second scanning device in the target space is determined based on the collision detection result. In some embodiments, step 330 can be performed by the movement scheme determination module 230.

[0066] In the movement scheme, the scanning bed, the first scanning device, and / or the second scanning device move in the target space without collision. The movement scheme refers to the specific movement information of the devices in the target space. For example, the movement determination result (i.e., whether to move), the movement path, the movement distance, etc. In some embodiments, the movement scheme can include a rotation scheme, a translation scheme, and / or a lifting scheme of the scanning bed, an avoidance path of the gantry of the first scanning device, a movement endpoint of the second scanning device, etc. For more information about the rotation scheme, the translation scheme, the lifting scheme, and the avoidance path, please refer to Figures 4-5 and the related description.

[0067] In some embodiments, the processing device 120 can determine a movement scheme of the scanning bed, the first scanning device and / or the second scanning device in the target space based on the collision detection result by a preset algorithm, a machine learning model, etc. The preset algorithm can include a safety corridor algorithm, a shortest path algorithm, a depth-first search algorithm, a breadth-first search algorithm, etc. The machine learning model can be a NN model, an RNN model, a Graph Neural Network (GNN) model, etc. Different collision detection results can correspond to different preset algorithms, machine learning models, etc. In some embodiments, the processing device 120 can construct a preset table based on historical collision detection results and corresponding preset algorithms, machine learning models, and determine a preset algorithm, a machine learning model based on the current collision detection result by querying the preset table, and then calculate and determine the movement scheme.

[0068] In some embodiments, the processing device 120 can determine the movement scheme to include a movement path of the non-target object in response to the collision detection result including the collision between the target object and the non-target object.

[0069] The movement path refers to specific movement route information. In some embodiments, the processing device 120 can determine the movement path of the non-target object based on the target image to obtain related information of the non-target object, and based on the related information of the non-target object by a preset algorithm, a machine learning model, etc. in response to the collision detection result including the collision between the target object and the non-target object. The related information of the non-target object can include size information, position information, etc. of the non-target object, and can be obtained by obtaining user input information, image recognition algorithm, etc. The preset algorithm can include a safety corridor algorithm, a shortest path algorithm, a depth-first search algorithm, a breadth-first search algorithm, etc. The machine learning model can be a NN model, an RNN model, a GNN model, etc.

[0070] In some embodiments of the present specification, in response to the collision detection result including the collision between the target object and the non-target object, the determination of the movement scheme to include the movement path of the non-target object can obtain accurate movement route of the non-target object when the collision between the target object and the non-target object is predicted, so as to facilitate timely movement of the non-target object and avoid movement of the target object and image scanning.

[0071] In some embodiments, the processing device 120 can determine the movement scheme to include an avoidance path of the gantry of the first scanning device in response to the collision detection result including the target object obtaining a current working phase of the medical imaging device; and in response to the current working phase being the working phase of the second scanning device. More details about determining the avoidance path can be referred to in Figure 4 and related descriptions thereof.

[0072] In some embodiments, the movement scheme can include a rotation scheme of the scanning bed, the processing device 120 can acquire a scanning position of a current scanning object; determine whether the scanning bed needs to be rotated based on the target image, the scanning position and the collision detection result; in response to the scanning bed needing to be rotated, determine rotation information of the rotation, the rotation information at least including a rotation direction and a rotation angle; and determine the rotation scheme based on the rotation information. For more details about determining the rotation scheme, please refer to Figure 5 and the related description.

[0073] At step 340, based on the movement scheme, control the scanning bed, the first scanning device and / or the second scanning device to move, and control the medical imaging device to perform medical imaging. In some embodiments, step 340 can be performed by the medical imaging module 240.

[0074] In some embodiments, the processing device 120 can automatically control the scanning bed, the first scanning device and / or the second scanning device to move based on the movement scheme. For example, the processing device 120 can control the scanning bed to rotate based on the rotation scheme of the scanning bed in the movement scheme. For another example, the processing device 120 can control the second scanning device to move from the starting position to the end position based on the movement end point of the second scanning device.

[0075] In some embodiments, the processing device 120 can receive a control instruction of a user through the terminal, and control the medical imaging device to perform medical imaging based on the control instruction. For example, the processing device 120 can receive a control instruction of a doctor through the terminal to control the second scanning device to scan at a scanning position, and control the second scanning device to move to the scanning position to perform medical imaging.

[0076] In some embodiments of the present specification, the target image of the target space is acquired by the computer vision device, the target object in the target space is subjected to collision detection based on the target image, a collision detection result is determined, a movement scheme of the scanning bed, the first scanning device and / or the second scanning device in the target space is determined based on the collision detection result, in the movement scheme, the scanning bed, the first scanning device and / or the second scanning device move in the target space without collision; and based on the movement scheme, the scanning bed, the first scanning device and / or the second scanning device are controlled to move, and the medical imaging device is controlled to perform medical imaging, which can make the first scanning device and the second scanning device jointly used, be suitable for complex medical imaging scenarios, determine an accurate, safe and reliable movement scheme of the medical imaging device, so as to make the joint imaging process efficient, intelligent and automatic, save the operation time of the doctor and improve the operation efficiency.

[0077] Figure 4 is a schematic diagram of an example of determining a movement scheme according to some embodiments of the present specification.

[0078] As shown in Figure 4 The processing device 120 can acquire a current working phase 410 of the medical imaging device. For example only, the medical imaging device can include a first scanning device 450 and a second scanning device 460. The current working phase 410 of the medical imaging device includes a working phase 411 of the second scanning device 460, a working phase 412 of the first scanning device 450, and a non-working phase 413 of the medical imaging device. The working phase 411 of the second scanning device 460 refers to a phase in which the second scanning device 460 is running. For example, a phase in which the second scanning device 460 is performing medical imaging, etc. The working phase 412 of the first scanning device 450 refers to a phase in which the first scanning device 450 is running. For example, a phase in which the first scanning device 450 is performing medical imaging, etc. The non-working phase 413 of the medical imaging device refers to a phase in which the medical imaging device stops running. For example, a shutdown phase of the medical imaging device, etc.

[0079] In response to the current working phase 410 being the working phase 411 of the second scanning device 460, the processing device 120 can determine that the movement scheme 420 includes an avoidance path 430 of a gantry (e.g., a C-arm) of the first scanning device 450. It can be understood that when the imaging of the second scanning device 460 is performed, the first scanning device 450 needs to be moved away to avoid interference with the imaging of the second scanning device 460. The avoidance path 430 of the gantry of the first scanning device 450 refers to a movement path of the gantry of the first scanning device 450 that does not collide with other objects in the target space. In some embodiments, the avoidance path 430 of the gantry of the first scanning device 450 can include a movement route and an end position of the gantry of the first scanning device 450.

[0080] In some embodiments, in response to the current working phase 410 being the working phase 411 of the second scanning device 460, the processing device 120 can determine a collision detection result for the first scanning device 450 as a target object, process the collision detection result based on collision information between the target object and a non-target object included in the collision detection result by a preset algorithm, a machine learning model, etc., and determine the avoidance path 430 of the gantry of the first scanning device 450 so that the gantry of the first scanning device 450 does not collide with the non-target object. The specific preset algorithm and machine learning model can refer to the related description of the foregoing step 330.

[0081] In some embodiments of the present disclosure, by acquiring the current working stage 410 of the medical imaging device, in response to the current working stage 410 being the working stage 411 of the second scanning device 460, determining the moving scheme 420 including the avoidance path 430 of the gantry of the first scanning device 450, the path of the first scanning device 450 can be planned when the second scanning device 460 is used, avoiding the first scanning device 450 interfering with the normal operation of the second scanning device 460 and affecting the surgical treatment.

[0082] In some embodiments, in response to the current working stage 410 being the working stage 412 of the first scanning device 450 or the non-working stage 413 of the medical imaging device, the processing device 120 can determine the moving scheme 420 including restoring the scanning bed 440, the first scanning device 450 and / or the second scanning device 460 to the preset position 470. The preset position 470 can be preset based on experience or demand. In some embodiments, the preset position 470 can be the initial position, i.e., the position of the scanning bed 440, the first scanning device 450 and / or the second scanning device 460 before starting operation. Specifically, the moving scheme 420 can include a restoration route for restoring the scanning bed 440, the first scanning device 450 and / or the second scanning device 460 to the preset position 470, which can be determined by reversing the path of the scanning bed 440, the first scanning device 450 and / or the second scanning device 460 moving from the preset position 470 to the current position.

[0083] In some embodiments of the present disclosure, in response to the current working stage 410 being the working stage 412 of the first scanning device 450 or the non-working stage 413 of the medical imaging device, by determining the moving scheme 420 including restoring the scanning bed 440, the first scanning device 450 and / or the second scanning device 460 to the preset position 470, the aforementioned medical imaging device can be restored to the original position after use, avoiding the adverse effects on the next use caused by random movement after placement.

[0084] Figure 5 is a schematic diagram of an example of determining a moving scheme according to some other embodiments of the present disclosure.

[0085] As shown in Figure 5 , the moving scheme 580 can include a rotation scheme 581 of the scanning bed. The processing device 120 can acquire the scanning position 530 of the current scanning object 520. Based on the target image 540, the scanning position 530 and the collision detection result 510, the processing device 120 can determine whether the scanning bed needs to be rotated. In response to the scanning bed needing to be rotated, the processing device 120 can determine the rotation information 550 of the rotation and determine the rotation scheme 581 based on the rotation information 550.

[0086] The current scan object 520 refers to the object being scanned for medical images at the current moment. For example, the current scan object 520 could be a patient undergoing surgery. The scan location 530 refers to the location where the medical image scan needs to be performed. For example, the region of interest of the current scan object 520. In some embodiments, the user can use a selection window on the terminal to select the scan location 530 of the current scan object 520 and upload it to the processing device 120.

[0087] Understandably, the scanning device has a limited range of movement. If the scanning position 530 of the current object 520 exceeds the range of movement of the scanning device, the scanning bed can be rotated to bring the scanning position 530 of the current object 520 closer to the scanning device and within the range of movement of the scanning device, so as to ensure the successful scanning of medical images.

[0088] In some embodiments, the processing device 120 may determine whether the scanning bed needs to be rotated based on the target image 540, the scanning position 530, and the collision detection result 510, according to a first preset rule. More information about the target image 540 and the collision detection result 510 can be found in [link to relevant documentation]. Figure 3 And related descriptions. The first preset rule can be set based on experience or requirements. For example, the first preset rule can be to determine the position of the slide rail and the position of the scanning bed of the second scanning device based on the target image 540. If the position of the slide rail of the second scanning device is not parallel to the position of the scanning bed, it is determined that the scanning bed needs to be rotated until the position of the slide rail of the second scanning device is parallel to the position of the scanning bed. As another example, the first preset rule can be to determine the farthest moving position of the second scanning device based on the target image 540. If the farthest moving position cannot reach the scanning position 530, and the collision detection result 510 includes that the scanning bed does not collide with non-target objects when rotated 180 degrees, it is determined that the scanning bed needs to be rotated 180 degrees.

[0089] In some embodiments, the processing device 120 can also process the target image 540, the scanning position 530 and the collision detection result 510 through preset algorithms, machine learning models and the like to determine whether the scanning bed needs to be rotated.

[0090] Rotation information 550 refers to rotation-related information. For example, rotation direction 551 (clockwise, counterclockwise, etc.), rotation angle 552 (0 to 360 degrees), etc.

[0091] In some embodiments, in response to the need for the scanning bed to rotate, the processing device 120 can determine the rotation information 550 in various ways. For example, the processing device 120 can determine the rotation information 550 by acquiring user input. Alternatively, the processing device 120 can determine the rotation information 550 by processing the target image 540, the scanning position 530, and the collision detection result 510 using a preset algorithm or machine learning model.

[0092] Rotation scheme 581 refers to a specific execution scheme of rotation. For example, rotation scheme 581 could be rotating the scanning bed 180 degrees clockwise. In some embodiments, the processing device 120 can synthesize the rotation information 550 to determine rotation scheme 581. For example, if the rotation information 550 includes a rotation direction 551 of clockwise and a rotation angle 552 of 180 degrees, then determining rotation scheme 581 could be rotating the scanning bed 180 degrees clockwise.

[0093] like Figure 5 As shown, the movement scheme may include a translation scheme 582 and / or a lifting scheme 583 for the scanning bed. The processing device 120 can determine whether the scanning bed needs to be translated and / or lifted based on the target image 540 and the scanning position 530. In response to the need for translation and / or lifting of the scanning bed, the processing device 120 can determine translation information 560 for translation and / or lifting information 570 for lifting. The translation information 560 includes at least a translation direction 561 and a translation distance 562, and the lifting information 570 includes at least a lifting direction 571 and a lifting distance 572. Based on the translation information 560 and / or the lifting information 570, the processing device 120 can determine a translation scheme 582 and / or a lifting scheme 583.

[0094] Understandably, the scanning device has a limited range of motion, and the scanning bed must pass through the scanning ring of the second scanning device to perform medical image scanning. Therefore, the horizontal position and / or vertical height of the object to be scanned needs to be adjusted so that the scanning bed can pass smoothly through the scanning ring of the second scanning device to ensure successful scanning of medical images.

[0095] In some embodiments, the processing device 120 may determine whether the scanning bed needs to be translated and / or raised / lowered based on the target image 540 and the scanning position 530, according to a second preset rule. The second preset rule may be set based on experience or requirements. For example, the second preset rule may be to determine the furthest moving position of the second scanning device based on the target image 540. If the furthest moving position cannot reach the scanning position 530, and the collision detection result 510 includes a collision with a non-target object when the scanning bed rotates 180 degrees, then it is determined that the scanning bed needs to be translated to the furthest moving position to reach the scanning position 530. As another example, the second preset rule may be to determine, based on the target image 540, that the highest position of the body in the vertical direction when the scanned object is lying flat is higher than the highest position of the inner diameter of the scanning ring of the second scanning device. If this is determined, it is determined that the scanned object cannot pass through the scanning ring, and therefore the scanning bed needs to be lowered so that the scanned object can pass through the scanning ring.

[0096] In some embodiments, the processing device 120 can also determine whether the scan bed needs to be translated and / or lifted by processing the target image 540 and the scan position 530 through a preset algorithm, a machine learning model, etc.

[0097] The translation information 560 refers to information related to translation. For example, a translation direction 561 (a direction of a slide rail of the second scanning device, etc.), a translation distance 562, etc. The lifting information 570 refers to information related to lifting. For example, a lifting direction 571 (vertically upward, vertically downward, etc.), a lifting distance 572, etc.

[0098] In some embodiments, in response to the scan bed needing to be translated and / or lifted, the processing device 120 can determine the translation information 560 and / or the lifting information 570 in various manners. For example, the processing device 120 can determine the translation information 560 and / or the lifting information 570 by obtaining user input. For another example, the processing device 120 can determine the translation information 560 and / or the lifting information 570 by processing the target image 540 and the scan position 530 through a preset algorithm, a machine learning model, etc.

[0099] The translation scheme 582 refers to a specific execution scheme of translation. For example, the translation scheme 582 can be moving the scan bed by 30 cm in the opposite direction of the slide rail of the second scanning device. The lifting scheme 583 refers to a specific execution scheme of lifting. For example, the lifting scheme 583 can be moving the scan bed vertically upward by 10 cm.

[0100] In some embodiments, the processing device 120 can integrate the translation information 560 and / or the lifting information 570 to determine the translation scheme 582 and / or the lifting scheme 583. The specific integration manner can refer to the foregoing related content of the rotation scheme, which will not be described herein again.

[0101] In some embodiments, the processing device 120 can select a scheme with the minimum displacement distance of the scan bed as the movement scheme 580. The displacement distance refers to a vector distance of the geometric center of the scan bed in the target space, which can be determined by calculating the Euclidean distance, etc. For example, the movement scheme A of the scan bed is moving the scan bed by d cm in the opposite direction of the slide rail of the second scanning device and moving the scan bed vertically upward by e cm, which corresponds to a scan bed displacement distance f; the movement scheme B of the scan bed is moving the scan bed by d cm in the opposite direction of the slide rail of the second scanning device and rotating the scan bed counterclockwise by g degrees, which corresponds to a scan bed displacement distance h, and h is less than f. Therefore, the movement scheme A is selected as the movement scheme 580 of the scan bed.

[0102] In some embodiments of the present specification, by setting the moving scheme 580 to include the rotating scheme 581 and / or the translating scheme 582 and / or the lifting scheme 583, the processing device 120 can acquire the scanning position 530 of the current scanning object 520; determine whether the scanning bed needs to rotate and / or translate and / or lift based on the target image 540, the scanning position 530, and the collision detection result 510; in response to the scanning bed needing to rotate and / or translate and / or lift, determine the rotating information 550 and / or the translating information 560 and / or the lifting information 570 of the rotation; and based on the rotating information 550 and / or the translating information 560 and / or the lifting information 570, determine the rotating scheme 581 and / or the translating scheme 582 and / or the lifting scheme 583, which can enable the scanning bed to efficiently and accurately move to a reasonable position, so that the medical imaging can be smoothly performed, the time cost consumption and errors of manual movement are avoided, and the moving efficiency of the scanning bed is improved. In addition, by selecting the scheme with the smallest displacement distance of the scanning bed as the moving scheme 580, the moving position of the patient can be as small as possible, and the normal use of other medical devices (for example, a catheter inserted in the patient's body, etc.) is avoided.

[0103] One or more embodiments of the present specification also provide a medical imaging device, including a processor configured to perform the method of any one of the embodiments of the present specification.

[0104] The above has described the basic concepts, and it is obvious that the above detailed disclosure is only taken as an example, and does not constitute a limitation on the present specification. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and corrections to the present specification. Such modifications, improvements and corrections are suggested in the present specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present specification.

[0105] Meanwhile, specific words are used in the present specification to describe the embodiments of the present specification. As "one embodiment", "an embodiment", and / or "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of the present specification. Therefore, it should be emphasized and noted that the "an embodiment" or "one embodiment" or "one alternative embodiment" mentioned in different positions in the present specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present specification can be properly combined.

[0106] Furthermore, the order of the processing elements and sequences described in this specification are not intended to be construed as a limitation, unless specifically stated, but are included to provide a complete description of one or more embodiments of the present specification. Regardless of the particular sequence of processing elements and sequences, however, the description herein of a process should be understood to include any and all combinations of one or more elements, and sequences that can be perceived as either open-ended or specific.

[0107] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting, unless specifically stated as such. It should be noted that, as used in the specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It should also be noted that, as used in the specification and the appended claims, the term "or" is generally intended to mean "and / or" unless the context clearly dictates otherwise. Furthermore, the words "comprise," "comprising," "include," "including," and the like are generally intended to be synonymous, unless the context clearly dictates otherwise. Unless specifically stated otherwise, and as can be apparent from the disclosure, use of terms such as "processing," "computing," "calculating," "determining," "displaying," or the like, refer to actions or processes of a machine that manipulates or transforms data represented as physical electronic or magnetic quantities within memories, registers, or other information storage devices. Note, too, that while embodiments can be implemented by software, the software can be written in any of numerous languages or combinations of languages, and can be executed in a machine or on a machine.

[0108] Some embodiments use numerals to describe components, quantities of attributes, it should be understood that such numerals used in the description of the embodiments are, in some examples, modified by the adjectives "about," "approximately," or "substantially." Unless otherwise indicated, "about," "approximately," or "substantially" mean that the described numerical value allows for ±20% variation. Accordingly, numerical parameters in the specification and claims are approximations, and can vary depending upon the desired properties sought to be obtained by the particular embodiments. In some embodiments, numerical parameters are determined by the use of standard techniques. Although the numerical ranges and parameters setting forth the broad scope of the embodiments of the specification are approximations, unless otherwise indicated, these numerical values are to be understood as being modified in all instances by a term selected from the group consisting of about, approximately, substantially, and like terms as used herein to indicate the approximations. In some embodiments, numerical parameters are determined by the use of standard techniques.

[0109] Each patent, patent application, publication, and other material cited in this specification is incorporated herein by reference in its entirety. In the event of inconsistencies between the disclosure of this specification and the materials incorporated by reference, the disclosure of this specification is intended to prevail. Nothing in this specification is to be construed as an admission that the application is not entitled to antedate such material by virtue of prior application. In the event of inconsistencies between the disclosure of this specification and any document incorporated by reference, the disclosure of this specification is intended to prevail. It should be noted that, if the description, definitions, and / or terminology used in the materials incorporated by reference differ from the description, definitions, and / or terminology used in the present specification, the description, definitions, and / or terminology used in the present specification shall control.

[0110] Finally, it should be understood that the embodiments described herein are only given by way of example and that other modifications can occur to persons skilled in the art. Therefore, the scope of the present description is not intended to be limited to the embodiments described herein but is only limited by the claims that follow.

Claims

1. A medical imaging method, characterized in that, The method includes: A target image is acquired by a computer vision device, wherein the target space is the space where the medical imaging device is located, and the medical imaging device includes at least a first scanning device and a second scanning device, and the target image includes at least the scanning bed of the medical imaging device, the first scanning device and the second scanning device; Based on the target image, collision detection is performed on the target object in the target space, and the collision detection result is determined. The target object includes at least one of the scanning bed, the first scanning device, and the second scanning device. Based on the collision detection results, a movement scheme for the scanning bed, the first scanning device, and / or the second scanning device in the target space is determined; and Based on the aforementioned movement scheme, the scanning bed, the first scanning device, and / or the second scanning device are controlled to move, and the medical imaging device is controlled to perform medical imaging.

2. The method according to claim 1, characterized in that, The computer vision device is installed on top of the target space.

3. The method according to claim 1, characterized in that, The first scanning device is a digital subtraction angiography device, and the second scanning device is a sliding rail CT device.

4. The method according to claim 3, characterized in that, The determination of the movement scheme of the scanning bed, the first scanning device, and / or the second scanning device in the target space includes: Obtain the current operating stage of the medical imaging device; and In response to the current working phase being the working phase of the second scanning device, the movement scheme is determined to include an avoidance path for the rack of the first scanning device.

5. The method according to claim 4, characterized in that, The movement scheme further includes a rotation scheme for the scanning bed, wherein determining the rotation scheme includes: Get the scan position of the currently scanned object; Based on the target image, the scanning position, and the collision detection result, determine whether the scanning bed needs to be rotated; In response to the need for the scanning bed to rotate, rotation information for the rotation is determined; and Based on the rotation information, the rotation scheme is determined.

6. The method according to claim 5, characterized in that, The movement scheme further includes a translation scheme and / or a lifting scheme for the scanning bed, wherein determining the translation scheme includes: Based on the target image and the scanning position, determine whether the scanning bed needs to be translated and / or raised / lowered; In response to the scanning bed requiring translation and / or lifting, determine translation information for the translation and / or lifting information for the lifting; and Based on the translation information and / or the elevation information, the translation scheme and / or elevation scheme are determined.

7. The method according to claim 4, characterized in that, The method for determining the movement scheme of the scanning bed, the first scanning device, and / or the second scanning device in the target space further includes: In response to the current working phase being either the working phase of the first scanning device or the non-working phase of the medical imaging device, the determined movement scheme includes restoring the scanning bed, the first scanning device, and / or the second scanning device to a preset position.

8. The method according to claim 1, characterized in that, The acquisition of the target image in the target space via computer vision equipment includes: Obtain the current usage status of the computer vision device; In response to the current usage state being normal usage state, the computer vision device is controlled to acquire the target image; In response to the current usage state being an abnormal usage state, a prompt message and / or suggested relocation plan are sent to the user, who then controls the medical imaging device to perform the relocation and the medical imaging.

9. The method according to claim 1, characterized in that, In response to the collision detection result including a collision between the target object and a non-target object, the movement scheme is determined to include the movement path of the non-target object.

10. A medical imaging apparatus, comprising a processor for performing the method of any one of claims 1 to 9.

Images