Scanning preparation method, device and system for medical imaging system
Through 3D cameras and human body information models, the automation of patient positioning and registration in medical imaging systems is achieved, and the problems of inaccurate positioning and registration errors in the prior art are solved, and the efficiency and accuracy of scanning preparation are improved.
Patent Information
- Application Number
- CN202010320652.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-04-22
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2040-04-22
AI Technical Summary
The patient positioning and registration process in the existing medical imaging system is cumbersome and relies on manual operations, lack of automation, resulting in inaccurate positioning and registration errors, affecting the scanning quality.
The 3D camera is used to collect two-dimensional color and depth images of the patient, and the human body feature points and candidate scanning area position information are obtained through the pre-trained human body information model. The hospital bed is automatically controlled to move the scanning area to the scanning center, and the human body information model is used. Register patient information.
It improves the degree of automation of patient positioning and information registration, reduces manual operation errors, and improves the efficiency and accuracy of scanning preparation.
Smart Images

Figure CN113538707B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the medical field, and in particular to a scanning preparation method, device and system based on a three-dimensional camera in a medical imaging system. Background Art
[0002] In medical imaging systems such as magnetic resonance imaging (MR) systems or computed tomography (CT) systems, some preparation work needs to be done before starting the actual scan.
[0003] For example, in one example, taking the MR system as an example, the work of preparing for scanning may include the following steps: 1) the patient lies on the bed; 2) the patient is positioned, including: determining the location of the target scanning area to be scanned by the patient, and then moving it to the scanning center of the medical imaging system, such as the center of the magnet. 3) The patient is registered, that is, the patient information is entered into the working interface of the application software system of the MR system, including name, ID card, height, weight, and patient posture information. 4) The corresponding scanning parameters such as the protocol set are selected and the scanning is started. Of course, in other examples, the above steps 3) and 4) can also be performed before steps 1) and 2). Summary of the invention
[0004] In view of this, embodiments of the present invention provide, on the one hand, a scanning preparation method in a medical imaging system, and on the other hand, provide a scanning preparation system in a medical imaging system, so as to improve the automation level of scanning preparation.
[0005] The scanning preparation method in the medical imaging system proposed in the embodiment of the present invention includes: when the bed in the medical imaging system is at the origin position or the near-origin position, triggering a 3D camera installed above the bed to collect two-dimensional color and depth images of the current patient; receiving the two-dimensional color and depth images collected by the 3D camera, and inputting the two-dimensional color and depth images into a pre-trained first human body information model to obtain the position information of multiple human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system; the first human body information model uses multiple groups of pre-acquired two-dimensional color and depth images as input parameter sets, and uses the pre-acquired position information of multiple human body feature points corresponding to each group of two-dimensional color and depth images in the camera coordinate system or the bed coordinate system as the output parameter set to be trained ; when the position information is the position information in the camera coordinate system, the position information of the multiple human feature points in the camera coordinate system is converted into the position information in the bed coordinate system according to the conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration; the position information of the multiple candidate scanning areas in the bed coordinate system is calculated according to the position information of the multiple human feature points in the bed coordinate system; the position information of the multiple candidate scanning areas in the bed coordinate system is provided to the medical imaging application device, so that the medical imaging application device determines the position information of the current scanning area in the bed coordinate system, and controls the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device.
[0006] In one embodiment, when the coil covers the patient's body area, further obtaining the body area information covered by the coil output by the first human body information model; the method further comprises:
[0007] The body area information covered by the coil is provided to the medical imaging application device, so that the medical imaging application device determines the candidate scanning areas supported by the medical imaging system according to the body area information covered by the coil, and then selects the current scanning area from the candidate scanning areas supported by the medical imaging system.
[0008] In one embodiment, it further includes: inputting the two-dimensional color and depth images into a pre-trained second human body information model to obtain the patient's height, weight and posture information output by the second human body information model; the second human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as an input parameter set, and using the pre-acquired height, weight and posture information corresponding to each group of two-dimensional color and depth images as an output parameter set; providing the patient's height, weight and posture information to the medical imaging application device, so that the medical imaging application device uses the height, weight and posture information to register the patient's information.
[0009] In one embodiment, the medical imaging application device uses the height, weight and posture information to register the patient's information, including: during the patient registration stage, the medical imaging application device pre-fills the height, weight and posture information in a corresponding information box and presents it to the user.
[0010] In one embodiment, the medical imaging application device uses the height, weight and posture information to register the patient's information, including: when receiving a user-triggered scan start instruction, the medical imaging application device compares the height, weight and posture information with the height, weight and posture information pre-registered by the user, and when the deviation information of the height and weight exceeds a set threshold or the posture information is inconsistent, a warning message box pops up, and according to the user's choice, determines the height, weight and posture information used for the current scan.
[0011] The acquisition control and image analysis device proposed in the embodiment of the present invention includes: an acquisition control module, which is used to trigger a 3D camera installed above the bed to acquire two-dimensional color and depth images of the current patient when the bed in the medical imaging system is at the origin position or near the origin position; and an image analysis module, which is used to receive the two-dimensional color and depth images acquired by the 3D camera, and input the two-dimensional color and depth images into a pre-trained first human body information model to obtain the position information of multiple human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system; when the position information is the position information in the camera coordinate system, the position information of the multiple human body feature points in the camera coordinate system is further converted into the position information in the bed coordinate system according to the conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration. information; according to the position information of the multiple human body feature points in the bed coordinate system, calculate the position information of the multiple candidate scanning areas in the bed coordinate system; provide the position information of the multiple candidate scanning areas in the bed coordinate system to the medical imaging application device, so that the medical imaging application device determines the position information of the current scanning area in the bed coordinate system, and according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device, moves the current scanning area to the scanning center; wherein, the first human body information model uses a plurality of groups of two-dimensional color and depth images acquired in advance as an input parameter set, and uses the position information of a plurality of human body feature points in advance corresponding to each group of two-dimensional color and depth images in the camera coordinate system or the bed coordinate system as an output parameter set for training.
[0012] In one embodiment, when the coil covers the patient's body area, the image analysis module further obtains the body area information covered by the coil output by the first human body information model, and further provides the body area information covered by the coil to the medical imaging application device, so that the medical imaging application device determines the candidate scanning areas supported by the medical imaging system according to the body area information covered by the coil, and then selects the current scanning area from the candidate scanning areas supported by the medical imaging system.
[0013] In one embodiment, the image analysis module further inputs the two-dimensional color and depth image into a pre-trained second human body information model to obtain the patient's height, weight and posture information output by the second human body information model; the patient's height, weight and posture information is provided to the medical imaging application device, so that the medical imaging application device uses the height, weight and posture information to register the patient's information; wherein the second human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as an input parameter set, and using the pre-acquired height, weight and posture information corresponding to each group of two-dimensional color and depth images as an output parameter set.
[0014] The image acquisition and analysis system proposed in an embodiment of the present invention includes: at least one memory and at least one processor, wherein: the at least one memory is used to store a computer program; the at least one processor is used to call the computer program stored in the at least one memory to execute the scanning preparation method in the medical imaging system as described in any of the above embodiments.
[0015] The image acquisition and analysis system proposed in the embodiment of the present invention includes: a 3D camera, which is installed at a set position above the medical imaging system; and the acquisition control and image analysis device as described in any of the above embodiments.
[0016] A scanning preparation system in a medical imaging system proposed in an embodiment of the present invention comprises: the image acquisition and analysis system as described above; and a medical imaging application device, which is used to determine the position information of the current scanning area in the bed coordinate system according to the position information of multiple candidate scanning areas in the bed coordinate system provided by the image acquisition and analysis system, and control the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device.
[0017] In one embodiment, the medical imaging application device is further used to register the patient's information based on the patient's height, weight and posture information provided by the image acquisition and analysis system.
[0018] Another scanning preparation system in a medical imaging system proposed in an embodiment of the present invention includes: a first device and a second device; wherein the first device includes a first memory and a first processor, wherein: the first memory is used to store computer programs; the first processor is used to call the computer program stored in the first memory to perform the following operations: when the bed in the medical imaging system is at the origin position or near the origin position, trigger the three-dimensional camera installed above the bed to collect two-dimensional color and depth images of the current patient; the second device includes a second memory and a second processor, wherein: the second memory is used to store computer programs; the second processor is used to call the computer program stored in the second memory to perform the following operations: receive the two-dimensional color and depth images collected by the three-dimensional camera, and input the two-dimensional color and depth images into a pre-trained first human body information model to obtain the position information of multiple human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system; the first The human body information model is trained by using a plurality of groups of pre-acquired two-dimensional color and depth images as an input parameter set, and using the pre-acquired position information of a plurality of human body feature points corresponding to each group of two-dimensional color and depth images in a camera coordinate system or a bed coordinate system as an output parameter set; when the position information is the position information in the camera coordinate system, the position information of the plurality of human body feature points in the camera coordinate system is converted into the position information in the bed coordinate system according to the conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration; the position information of a plurality of candidate scanning areas in the bed coordinate system is calculated according to the position information of the plurality of human body feature points in the bed coordinate system; the position information of the current scanning area in the bed coordinate system is determined according to the position information of the plurality of candidate scanning areas in the bed coordinate system, and according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device, the bed is controlled to move the current scanning area to the scanning center.
[0019] The computer-readable storage medium proposed in the embodiment of the present invention stores a computer program thereon; the computer program can be executed by a processor and implement the scanning preparation method in the medical imaging system as described in any of the above embodiments.
[0020] It can be seen from the above scheme that, in the embodiment of the present invention, a 3D camera is used to collect two-dimensional color and depth images of the current patient, and the image acquired by the 3D camera is input into a pre-trained first human body information model, so that the position information of the human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system can be obtained, and then the position information of multiple candidate scanning areas in the bed coordinate system can be calculated, and the information is provided to the medical imaging application device of the medical imaging system. The medical imaging application device determines the position information of the selected current scanning area in the bed coordinate system, and controls the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device, thereby improving the degree of automation of patient positioning during the scanning preparation process.
[0021] In addition, by further inputting the image acquired by the 3D camera into a pre-trained second human body information model, and obtaining the patient's height, weight and posture information output by the second human body information model; the patient's height, weight and posture information is provided to the medical imaging application device, so that the medical imaging application device uses the height, weight and posture information to register the patient's information, thereby improving the degree of automation of patient registration during the scanning preparation process.
[0022] Furthermore, by training the first human body information model, information of the body area covered by the coil is further output, and the information of the body area covered by the coil is provided to the medical imaging application device, so that the medical imaging application device uses the information of the body area covered by the coil to determine or narrow the scanning area currently supported by the medical imaging system. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the above and other features and advantages of the present invention will be more apparent to those skilled in the art. In the accompanying drawings:
[0024] Figure 1 It is a schematic diagram of the structure of an implementation environment involved in various embodiments of the present invention.
[0025] Figure 2 This is an exemplary flow chart of a method for acquiring human body information based on a three-dimensional camera for scanning preparation in a medical imaging system in an embodiment of the present invention.
[0026] Figure 3 The present invention is an exemplary flowchart of a scan preparation method in a medical imaging system according to an example of the present invention.
[0027] Figure 4The present invention is a flowchart of a scan preparation method in a medical imaging system according to another example of the present invention.
[0028] Figure 5 1 is an exemplary structural diagram of an acquisition control and image analysis device in an embodiment of the present invention.
[0029] Figure 6 Schematic diagram of the structure of another acquisition control and image analysis device in an embodiment of the present invention.
[0030] Figure 7 is an exemplary structural diagram of an image acquisition and analysis system in an embodiment of the present invention.
[0031] Figure 8 This is an exemplary structural diagram of a scan preparation system in a medical imaging system according to an embodiment of the present invention.
[0032] Fig. 9 This is an exemplary structural diagram of a scan preparation system in yet another medical imaging system according to an embodiment of the present invention.
[0033] The reference numerals are as follows:
[0034]
[0035] DETAILED DESCRIPTION
[0036] In the embodiment of the present invention, considering that for the patient positioning steps in most common use cases, the operator manually performs the following steps: a) quickly and roughly move the patient's target scanning area into the magnet hole through a control panel or device. b) Turn on the laser light mark, and the mark will be displayed on the patient. c) Slowly move the diagnostic bed and determine the exact position of the patient's target scanning area under the guidance of the laser light mark; d) Move the patient's target scanning area to the scanning center, such as the magnet center, through a control panel or device. It can be seen that the above manual positioning process is complicated and time-consuming, and the accuracy of patient positioning depends on the operator's knowledge and experience of human anatomy, and the results lack standardization and repeatability.
[0037] To this end, an embodiment of the present invention considers providing a patient positioning solution based on a three-dimensional (3D) camera in a medical imaging system, wherein the accurate position of the patient target scanning area used for positioning is obtained by using images captured by the 3D camera and a pre-trained first human body information model.
[0038] In addition, considering the patient registration steps in most common use cases, the patient's height and weight information can be measured by a height gauge and a scale / weighing instrument, and these measurements take a certain amount of time, and the measured values need to be filled in manually. But in some emergency situations, it is unlikely to measure patients lying in bed or unable to move, such as stroke patients or comatose patients. Therefore, in some cases, for convenience or to save time, the patient data comes from the operator's estimation or the patient's self-estimation, but the estimated data is usually not accurate enough, which will directly affect the scan, such as SAR (Specific Absorption Rate) calculation. The patient's posture information includes head first / feet first, prone, supine or side-lying, etc., which is manually filled in by the operator observing the patient's posture. Sometimes, the operator may inadvertently enter the wrong patient posture, resulting in incorrect orientation information in the medical image, which may cause misdiagnosis, and the consequences are very serious at this time.
[0039] To this end, an embodiment of the present invention considers providing a patient registration solution based on a 3D camera in a medical imaging system, wherein the height, weight and posture information used for registration are obtained by using images collected by 3D camera and a pre-trained second human body information model.
[0040] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail with reference to the following embodiments.
[0041] For the sake of brevity and intuitiveness in description, the scheme of the present invention is explained below by describing several representative implementations. A large number of details in the implementations are only used to help understand the scheme of the present invention. However, it is obvious that the technical scheme of the present invention may not be limited to these details when implemented. In order to avoid unnecessarily obscuring the scheme of the present invention, some implementations are not described in detail, but only a framework is given. Hereinafter, "including" means "including but not limited to", and "according to..." means "at least according to..., but not limited to only according to...". Due to the language habits of Chinese, when the number of a component is not specifically specified below, it means that the component can be one or more, or can be understood as at least one.
[0042] Figure 1 FIG. 1 is a schematic diagram of a structure of an implementation environment involved in each embodiment of the present invention. Figure 1 As shown, the implementation environment includes: an image acquisition and analysis system 110 and a medical imaging system 120. The image acquisition and analysis system 110 includes: a 3D camera 111 and an acquisition control and image analysis device ( Figure 1 The medical imaging system 120 includes: a medical imaging device 121, a hospital bed (or a patient operating table) 122, and a medical imaging application device ( Figure 1 The acquisition control and image analysis device may be provided in the computer of the medical imaging application device, or may be provided in a separate computer, such as a dedicated computer 112. When the acquisition control and image analysis device is provided in a separate computer, it may communicate with the medical imaging application device through a network.
[0043] The 3D camera 111 is used to continuously capture two-dimensional color (RGB) and depth images of the patient lying on the bed. When the 3D camera 111 is installed at a proper height of the ceiling (or bracket) 140 through the mounting system 130, the field of view can cover the entire or most of the bed 122, and the full view of the patient 150 can be obtained at one time.
[0044] The acquisition control and image analysis device may include an acquisition control module and an image analysis module. The acquisition control module is used to trigger the 3D camera 111 to acquire images. The image analysis module is used to analyze the images acquired by the 3D camera and provide the corresponding results to the medical imaging application device.
[0045] The medical imaging device 121 may be a magnetic resonance imaging (MRI) device or a computer tomography (CT) machine, and is used to perform imaging scanning on a patient target scanning area placed at a scanning center based on determined scanning parameters. A touch screen or control panel 1211 may be provided on the medical imaging device 121 .
[0046] The bed 122 is used to carry the patient and move the target scanning area of the patient to the scanning center of the medical scanning device 121 .
[0047] The medical imaging application device is used to perform patient positioning and patient registration based on the image analysis results provided by the image analysis system.
[0048] Figure 2 1 is an exemplary flow chart of a method for obtaining human body information for scanning preparation based on a 3D camera in a medical imaging system according to an embodiment of the present invention. The method is mainly implemented by the acquisition control and image analysis device in the 3D image acquisition and analysis system 110. Figure 2 As shown, the method may include the following steps:
[0049] Step S21 , when the bed is moved to the original position or near the original position, the 3D camera 111 is triggered to collect the two-dimensional color and depth images of the patient.
[0050] In this embodiment, the medical imaging application device can know the state and position of the bed, so when the bed moves to the original position or near the original position, it can notify the acquisition control module in the acquisition control and image analysis device to trigger the 3D camera to acquire the patient's two-dimensional color and depth images, and hand over the acquired images to the image analysis module to start image analysis. When the bed leaves the original position or near the original position, the medical imaging application device can notify the acquisition control and image analysis device to stop image acquisition and analysis.
[0051] Generally, when the bed is moved to the original position or near the original position, it can be ensured that the patient is completely located in the field of view of the 3D camera. Therefore, in this step, when the bed is moved to the original position or near the original position, the 3D camera can be triggered to collect images.
[0052] Step S22, input the two-dimensional color and depth image into a pre-trained first human body information model, and obtain the position information of multiple human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system. The human body feature points include anatomical parts that are easy to identify in the image, such as the top of the head, the tip of the nose, the chin, the eyes, the ears, the wrist joints, the elbow joints, the knee joints, the ankle joints, etc. In this embodiment, 37 feature points can be identified.
[0053] In this step, the first human body information model can be trained using multiple groups of pre-acquired two-dimensional color and depth images as input parameter sets, and using the pre-acquired position information of multiple human body feature points corresponding to each group of two-dimensional color and depth images in the camera coordinate system or the bed coordinate system as the output parameter set.
[0054] Among them, when the position information is the position information in the camera coordinate system, in this embodiment, the position information of the multiple human body feature points in the camera coordinate system can be further converted into position information in the bed coordinate system according to the conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration.
[0055] In addition, in this step, the two-dimensional color and depth images can also be input into a pre-trained second human body information model to obtain the patient's height, weight and posture information output by the second human body information model. The second human body information model can be trained using multiple sets of pre-acquired two-dimensional color and depth images as input parameter sets, and using the pre-acquired height, weight and posture information corresponding to each set of two-dimensional color and depth images as output parameter sets.
[0056] In specific implementation, the first human body information model and the second human body information model can be two separate models or the same model. When they are the same model, the output parameter set includes: the pre-acquired position information of multiple human body feature points corresponding to each set of two-dimensional color and depth images in the camera coordinate system or the bed coordinate system, and the information of the height, weight and posture of the human body.
[0057] Step S23, calculating and obtaining position information of multiple candidate scanning areas in the bed coordinate system according to the position information of the multiple human body feature points in the bed coordinate system.
[0058] In this step, because the characteristic points of the human body and the center points of the corresponding candidate scanning areas satisfy a certain anatomical proportional relationship, after each characteristic point is determined, the center point of the candidate scanning area can be calculated based on the depth (thickness) information of the human body in the depth image. At the same time, based on the position of the human body characteristic points and the anatomical proportional relationship, the three-dimensional range of different candidate scanning areas of different patients can be calculated, and each candidate scanning area can be determined.
[0059] Step S24, providing the position and range information of the multiple candidate scanning areas in the bed coordinate system to the medical imaging application device. In the case where the patient's height, weight and posture information are also obtained in step S22, the patient's height, weight and posture information can be further provided to the medical imaging application device in this step.
[0060] After receiving the position information of the above-mentioned multiple candidate scanning areas in the bed coordinate system, the medical imaging application device can determine the position information of the current scanning area in the bed coordinate system, and move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center.
[0061] After receiving the above-mentioned information of height, weight and posture, the medical imaging application device can use the information of height, weight and posture to register the information of the patient.
[0062] The above steps S22 to S24 can be implemented by an image analysis module in the acquisition control and image analysis device.
[0063] The above steps S21 to S24 are repeatedly performed at a fixed frame rate to continuously monitor the patient. In this way, the relevant information in the medical imaging application device will be updated in real time.
[0064] In addition, when the coil covers the patient's body area, the first human body information model in step S22 can further obtain and output information about the body area covered by the coil. Accordingly, the input parameter set required for training the first human body information model includes two-dimensional color and depth images when the coil covers the patient's body area, and the output parameter set also includes information about the body area covered by the coil. Afterwards, in step S24, the information about the body area covered by the coil can be further provided to the medical imaging application device, so that the medical imaging application device determines the candidate scanning area currently supported by the system according to the body area covered by the coil.
[0065] The following uses the magnetic resonance imaging system as an example. Figure 2 The entire scan preparation method of the method is described in detail.
[0066] Figure 3 FIG. 1 is an exemplary flow chart of a scan preparation method in a medical imaging system in an example of the present invention. In this example, a scenario of performing patient registration after patient positioning is taken as an example. Figure 3 As shown, the method may include the following steps:
[0067] Step S31, the patient is placed on the bed.
[0068] Step S32, move the bed to the original position or near the original position, and the medical imaging application device triggers the acquisition control and image analysis device to execute the steps S21 to S24.
[0069] Step S33: the medical imaging application device presents the candidate scanning areas supported by the medical imaging system.
[0070] In this step, the candidate scanning areas supported by the medical imaging system and basic information such as the patient's name can be displayed on the touch screen or display screen of the magnet, or can also be displayed on a computer display screen outside the scanning room.
[0071] The candidate scanning areas supported by the medical imaging system may be determined based on the candidate scanning areas supported by the 3D image acquisition and analysis system 110 and / or the scanning areas supported by the predetermined coils.
[0072] In addition, in this embodiment, if the coil further covers the patient's body area, the body area covered by the coil is further obtained according to the two-dimensional color and depth images of the patient collected in real time by the 3D camera. Then the candidate scanning area supported by the system in step S33 can be further determined or narrowed according to the body area covered by the coil identified based on the 3D image. That is, the candidate scanning area supported by the medical imaging system can be determined according to any one or any combination of the candidate scanning area supported by the 3D image acquisition and analysis system 110, the scanning area supported by the predetermined coil, and the body area covered by the coil identified based on the 3D image. If it is determined according to at least two of the candidate scanning area supported by the 3D image acquisition and analysis system 110, the scanning area supported by the predetermined coil, and the body area covered by the coil identified based on the 3D image, then the intersection of the at least two can be taken.
[0073] In step S34, the medical imaging application device determines a current scanning area from the candidate scanning areas according to the user's selection, and filters the protocol set or workflow according to the current scanning area.
[0074] Step S35, after the user triggers the operation of moving the scanning area to the center of the magnet, the medical imaging application device moves the current scanning area to the center of the magnet according to the position information of the current scanning area in the bed coordinate system provided by the acquisition control and image analysis device and the position of the bed relative to the center of the magnet.
[0075] Step S36, when the user leaves the scanning room and enters the operating room to start patient registration and opens the patient registration dialog interface, the medical imaging application device pre-fills the patient's height, weight and posture information provided by the acquisition control and image analysis device in the corresponding information box in the patient registration dialog interface and presents it to the user.
[0076] Step S37: According to the user's selection, the medical imaging application device determines the current protocol set or workflow from the protocol sets or workflows filtered out in step S34. Scan preparation ends here, and scanning can be started later.
[0077] Step S38, starting scanning according to the user's trigger.
[0078] Figure 4 FIG. 1 is an exemplary flow chart of a scan preparation method in a medical imaging system in another example of the present invention. In this example, a scenario of performing patient registration before patient positioning is taken as an example. Figure 4 As shown, the method may include the following steps:
[0079] In this example, patient registration begins after the patient is positioned and sent to the scanning center. At this time, the 3D image acquisition and analysis system integrated into the medical imaging system works in the following steps:
[0080] Step S41, the medical imaging application device receives patient information registered by a user, wherein the patient information includes the patient's height, weight and posture information.
[0081] Step S42: the medical imaging application device determines the current protocol set or workflow.
[0082] In this step, the current protocol set may be determined according to the user's selection, or the protocol set used in the last scan may be determined as the current protocol set for this scan.
[0083] Step S43: After the user leaves the operating room and comes to the scanning room, the user places the patient on the bed.
[0084] Steps S44-S45 are the same as the aforementioned steps S32 and S33.
[0085] Step S46: The medical imaging application device determines a current scanning area from the candidate scanning areas according to the patient information registered in step S41.
[0086] Step S47 is the same as the aforementioned step S35.
[0087] Step S48: After the user arrives at the operating room, receiving a scan start instruction triggered by the user.
[0088] In step S49, the medical image application device compares the height, weight and posture information of the patient provided by the acquisition control and image analysis device with the height, weight and posture information registered in step S41. When the deviation information of the height and weight exceeds the set threshold or the posture information is inconsistent, a warning message box may pop up to highlight the deviation, and step S50 is executed. Otherwise, step S51 is executed, and no message may be prompted.
[0089] Step S50, determining the height, weight and posture information used for the current scan according to the user's selection.
[0090] Step S51, scanning starts.
[0091] It can be seen that in this embodiment, after the user clicks to start scanning in step S48, step S49 will be triggered to check the patient information. Only when the check is passed will the actual scanning in step S51 begin.
[0092] The scanning preparation method in the medical imaging system in the embodiment of the present invention is described in detail above. The scanning preparation system in the medical imaging system in the embodiment of the present invention is described in detail below. The scanning preparation system in the medical imaging system in the embodiment of the present invention can be used to implement the scanning preparation method in the medical imaging system in the embodiment of the present invention. For details not disclosed in detail in the embodiment of the system of the present invention, please refer to the corresponding description in the embodiment of the method of the present invention, and will not be repeated here one by one.
[0093] Figure 5 FIG. 1 is an exemplary structural diagram of the acquisition control and image analysis device in an embodiment of the present invention. Figure 5 As shown, the device 500 may include: an acquisition control module 501 and an image analysis module 502 .
[0094] The acquisition control module 501 is used to trigger the 3D camera 111 installed above the bed to acquire the two-dimensional color and depth images of the current patient when the bed in the medical imaging system is at the origin position or near the origin position.
[0095] The image analysis module 502 is used to receive the two-dimensional color and depth images captured by the 3D camera 111, and input the two-dimensional color and depth images into a pre-trained first human body information model to obtain the position information of multiple human body feature points in the camera coordinate system or the bed coordinate system output by the first human body information model; when the position information is the position information in the camera coordinate system, further convert the position information of the multiple human body feature points in the camera coordinate system into the position information in the bed coordinate system according to the conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration; calculate the position information of multiple candidate scanning areas in the bed coordinate system according to the position information of the multiple human body feature points in the bed coordinate system; provide the position information of the multiple candidate scanning areas in the bed coordinate system to the medical imaging application device, so that the medical imaging application device determines the position information of the current scanning area in the bed coordinate system, and moves the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device.
[0096] Among them, the first human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as input parameter sets, and using the pre-acquired position information of multiple human body feature points corresponding to each group of two-dimensional color and depth images in the camera coordinate system or the bed coordinate system as the output parameter set.
[0097] In another embodiment, when the coil covers the patient's body area, the image analysis module 502 can further obtain the body area information covered by the coil output by the first human body information model, and further provide the body area information covered by the coil to the medical imaging application device in the medical imaging system, so that the medical imaging application device presents the candidate scanning area supported by the medical imaging system; wherein the candidate scanning area supported by the medical imaging system is determined based on any one or any combination of the candidate scanning area supported by the 3D image acquisition and analysis system, the scanning area supported by the predetermined coil, and the body area covered by the coil.
[0098] In another embodiment, the image analysis module 502 may further input the two-dimensional color and depth images into a pre-trained second human body information model, obtain the patient's height, weight and posture information output by the second human body information model, and provide the patient's height, weight and posture information to the medical imaging application device, so that the medical imaging application device uses the height, weight and posture information to register the patient's information.
[0099] The second human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as input parameter sets, and using pre-acquired height, weight and posture information corresponding to each group of two-dimensional color and depth images as output parameter sets.
[0100] Figure 6 FIG. 1 is a schematic diagram of the structure of another acquisition control and image analysis device in an embodiment of the present invention. Figure 6 As shown, the device 600 may include: at least one memory 601 and at least one processor 602. In addition, some other components may be included, such as communication ports, etc. These components communicate via a bus 603.
[0101] Among them, at least one memory 601 is used to store a computer program. In one embodiment, the computer program can be understood to include Figure 5 The modules of the acquisition control and image analysis device 500 are shown. In addition, at least one memory 601 can also store an operating system, etc. The operating system includes but is not limited to: Android operating system, Symbian operating system, Windows operating system, Linux operating system, etc.
[0102] At least one processor 602 is used to call the computer program stored in at least one memory 601 to execute the computer program in the embodiment of the present invention. Figure 2The processor 602 may be a CPU, a processing unit / module, an ASIC, a logic module or a programmable gate array, etc. It may receive and send data through the communication port.
[0103] Figure 7 FIG. 1 is an exemplary structural diagram of an image acquisition and analysis system in an embodiment of the present invention. Figure 7 As shown, the system 700 may include: a 3D camera 111 installed at a set position above the medical imaging system, and Figure 5 or Figure 6 The acquisition control and image analysis device 500 or 600 described in any embodiment.
[0104] Figure 8 FIG. 1 is an exemplary structural diagram of a scan preparation system in a medical imaging system in an embodiment of the present invention. Figure 8 As shown, the system 800 may include: Figure 7 The image acquisition and analysis system 700 and the medical imaging application device 801 described in.
[0105] Among them, the medical imaging application device 801 is used to determine the position information of the current scanning area in the bed coordinate system according to the position information of multiple candidate scanning areas in the bed coordinate system provided by the image acquisition and analysis system 700, and control the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device; register the patient's information according to the information of the patient's height, weight and posture provided by the image acquisition and analysis system 700; determine the candidate scanning areas supported by the medical imaging system according to the body area information covered by the coil provided by the image acquisition and analysis system 700 and at least one or any combination of the pre-acquired candidate scanning areas supported by the image acquisition and analysis system 700 and the scanning areas supported by the predetermined coil, and then select the current scanning area from the candidate scanning areas supported by the medical imaging system.
[0106] It should be noted that not all steps and modules in the above-mentioned processes and structure diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The division of each module is only for the convenience of describing the functional division adopted. In actual implementation, a module can be implemented by multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be located in the same device or in different devices. For example, the acquisition control module 501 and the image analysis module 502 in the acquisition control and image analysis device can be located in the same computer, such as being located in the aforementioned special-purpose computer 112 or the computer where the medical imaging application device is located, or can also be located in different computers. For example, the acquisition control module 501 can be located in the special-purpose computer 112, and the image analysis module 502 can be located in the computer where the medical imaging application device is located.
[0107] For example, Fig. 9 FIG. 2 shows an exemplary structural diagram of a scan preparation system in another medical imaging system according to an embodiment of the present invention. Fig. 9 As shown, it includes: a first device 910 and a second device 920.
[0108] The first device 910 includes a first memory 911 , a first processor 912 , and a first communication port 913 . In addition, some other components may also be included. These components communicate via a first bus 914 .
[0109] The first memory 911 is used to store computer programs. In one embodiment, the computer program can be understood to include Figure 5 The acquisition control module 501 is shown. In addition, the first memory 911 can also store an operating system, etc. The operating system includes but is not limited to: Android operating system, Symbian operating system, Windows operating system, Linux operating system, etc.
[0110] The first processor 912 is used to call the computer program stored in the first memory 911 to execute the operation corresponding to the acquisition control module 501. For example, at least including: when the bed in the medical imaging system is at the origin position or near the origin position, triggering the three-dimensional camera installed above the bed through the first communication port 913 to collect the two-dimensional color and depth images of the current patient. When the bed in the medical imaging system is at the origin position or near the origin position, notifying the three-dimensional camera to stop image acquisition through the first communication port 913. The first processor 912 can be a CPU, a processing unit / module, an ASIC, a logic module or a programmable gate array, etc.
[0111] The second device 920 includes a second memory 921 , a second processor 922 , and a second communication port 923 . In addition, some other components may also be included. These components communicate via a second bus 924 .
[0112] The second memory 921 is used to store computer programs. In one embodiment, the computer program can be understood to include Figure 5 The image analysis module 502 and Figure 8 In addition, the second memory 921 can also store an operating system, etc. The operating system includes but is not limited to: Android operating system, Symbian operating system, Windows operating system, Linux operating system, etc.
[0113] The second processor 922 is used to call the computer program stored in the second memory 921 to execute the operations corresponding to the image analysis module 502 and the medical image application device 801. For example, at least the following operations are included:
[0114] The two-dimensional color and depth images acquired by the three-dimensional camera are received through the second communication port 923, and the two-dimensional color and depth images are input into a pre-trained first human body information model to obtain the position information of multiple human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system; the first human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as an input parameter set, and using the pre-acquired position information of multiple human body feature points corresponding to each group of two-dimensional color and depth images in the camera coordinate system or the bed coordinate system as an output parameter set;
[0115] When the position information is position information in a camera coordinate system, the position information of the plurality of human body feature points in the camera coordinate system is converted into position information in the bed coordinate system according to a conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration;
[0116] Calculating the position information of multiple candidate scanning areas in the bed coordinate system according to the position information of the multiple human body feature points in the bed coordinate system;
[0117] The position information of the current scanning area in the bed coordinate system is determined based on the position information of the multiple candidate scanning areas in the bed coordinate system, and the bed is controlled to move the current scanning area to the scanning center based on the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device.
[0118] In addition, when the coil covers the patient's body area, the body area information covered by the coil output by the first human body information model can be further obtained; the candidate scanning areas supported by the medical imaging system are determined based on the body area information covered by the coil, and then the current scanning area is selected from the candidate scanning areas supported by the medical imaging system.
[0119] In other embodiments, the method further comprises the following operations: inputting the two-dimensional color and depth images into a pre-trained second human body information model to obtain the information of the height, weight and posture of the patient output by the second human body information model; the second human body information model is trained by using a plurality of pre-acquired groups of two-dimensional color and depth images as an input parameter set, and using the pre-acquired information of the height, weight and posture corresponding to each group of two-dimensional color and depth images as an output parameter set;
[0120] The patient's information is registered based on the patient's height, weight and posture information. Specifically, it may include: during the patient registration stage, the medical imaging application device pre-fills the height, weight and posture information in the corresponding information box and presents it to the user. Or it may include: upon receiving a user-triggered start scan instruction, the medical imaging application device compares the height, weight and posture information with the height, weight and posture information pre-registered by the user. When the deviation information of the height and weight exceeds the set threshold or the posture information is inconsistent, a warning message box pops up, and according to the user's choice, the height, weight and posture information used in the current scan is determined.
[0121] It is understood that the hardware modules in the above-mentioned embodiments can be implemented mechanically or electronically. For example, a hardware module may include a specially designed permanent circuit or logic device (such as a dedicated processor, such as an FPGA or ASIC) for completing a specific operation. The hardware module may also include a programmable logic device or circuit (such as a general-purpose processor or other programmable processor) temporarily configured by software for performing a specific operation. As for whether to implement the hardware module in a mechanical manner, or using a dedicated permanent circuit, or using a temporarily configured circuit (such as configured by software), it can be determined based on cost and time considerations.
[0122] In addition, a computer-readable storage medium is also provided in an embodiment of the present invention, on which a computer program is stored, and the computer program can be executed by a processor and implement the scanning preparation method in the medical imaging system described in the embodiment of the present invention. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code that implements the function of any of the embodiments in the above-mentioned embodiments is stored, and the computer (or CPU or MPU) of the system or device reads out and executes the program code stored in the storage medium. In addition, the operating system operated on the computer can also be made to complete part or all of the actual operations through instructions based on the program code. The program code read from the storage medium can also be written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then the CPU installed on the expansion board or the expansion unit is made to perform part and all of the actual operations based on the instructions of the program code, thereby realizing the function of any of the embodiments in the above-mentioned embodiments. The storage medium implementation for providing the program code includes a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
[0123] It can be seen from the above scheme that, in the embodiment of the present invention, a 3D camera is used to collect two-dimensional color and depth images of the current patient, and the image acquired by the 3D camera is input into a pre-trained first human body information model, so that the position information of the human body feature points output by the first human body information model in the camera coordinate system or the bed coordinate system can be obtained, and then the position information of multiple candidate scanning areas in the bed coordinate system can be calculated, and the information is provided to the medical imaging application device of the medical imaging system. The medical imaging application device determines the position information of the selected current scanning area in the bed coordinate system, and controls the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device, thereby realizing the automation of patient positioning during the scanning preparation process.
[0124] In addition, by further inputting the image acquired by the 3D camera into a pre-trained second human body information model, and obtaining the patient's height, weight and posture information output by the second human body information model; the patient's height, weight and posture information is provided to the medical imaging application device, so that the medical imaging application device uses the height, weight and posture information to register the patient's information, thereby realizing the automation of patient registration during the scanning preparation process.
[0125] Furthermore, by training the first human body information model, information of the body area covered by the coil is further output, and the information of the body area covered by the coil is provided to the medical imaging application device, so that the medical imaging application device uses the information of the body area covered by the coil to determine or narrow the scanning area currently supported by the medical imaging system.
[0126] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A scan preparation method in a medical imaging system, characterized in that: The method includes: When a bed in the medical imaging system is at a preset position, a three-dimensional camera installed above the bed is triggered to collect a two-dimensional color and depth image of the current patient (S21); Receive the two-dimensional color and depth images acquired by the three-dimensional camera, and input the two-dimensional color and depth images into a pre-trained first human body information model to obtain position information of a plurality of human body feature points output by the first human body information model in a camera coordinate system or a bed coordinate system (S22); wherein, when the position information is position information in the camera coordinate system, the position information of the plurality of human body feature points in the camera coordinate system is converted into position information in the bed coordinate system according to a conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration (S22); Calculating the position information of multiple candidate scanning areas in the bed coordinate system according to the position information of the multiple human body feature points in the bed coordinate system (S23); The position information of the plurality of candidate scanning areas in the bed coordinate system is provided to the medical imaging application device (S24), so that the medical imaging application device determines the position information of the current scanning area in the bed coordinate system, and controls the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device. The method further comprises: inputting the two-dimensional color and depth images into a pre-trained second human body information model to obtain information on the height, weight and posture of the patient output by the second human body information model (S22); the second human body information model is trained using a plurality of pre-acquired groups of two-dimensional color and depth images as an input parameter set, and using pre-acquired information on the height, weight and posture corresponding to each group of two-dimensional color and depth images as an output parameter set; The patient's height, weight and posture information are provided to the medical imaging application device (S24), so that the medical imaging application device uses the height, weight and posture information to register the patient's information. The medical imaging application device uses the height, weight and posture information to register the patient's information, including: when receiving a user-triggered scan start instruction, the medical imaging application device compares the height, weight and posture information with the height, weight and posture information pre-registered by the user, and when the deviation information of the height and weight exceeds the set threshold or the posture information is inconsistent, a warning message box pops up, and according to the user's choice, determines the height, weight and posture information used for the current scan.
2. The scanning preparation method in the medical imaging system according to claim 1, characterized in that: When the coil covers the patient's body area, further obtaining the body area information covered by the coil output by the first human body information model; the method further comprises: The body area information covered by the coil is provided to the medical imaging application device (S24), so that the medical imaging application device determines the candidate scanning areas supported by the medical imaging system according to the body area information covered by the coil, and then selects the current scanning area from the candidate scanning areas supported by the medical imaging system.
3. The scanning preparation method in the medical imaging system according to claim 1, characterized in that: The medical imaging application device uses the height, weight and posture information to register the patient's information, including: during the patient registration stage, the medical imaging application device pre-fills the height, weight and posture information in a corresponding information box and presents it to the user (S36).
4. The scanning preparation method in the medical imaging system according to claim 1, characterized in that: The preset position of the hospital bed is at the origin or near the origin.
5. The scanning preparation method in the medical imaging system according to claim 1, characterized in that: The first human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as an input parameter set, and using pre-acquired position information of multiple human body feature points corresponding to each group of two-dimensional color and depth images in a camera coordinate system or a bed coordinate system as an output parameter set.
6. An acquisition control and image analysis device (500), characterized in that: include: An acquisition control module (501) is used to trigger a three-dimensional camera (111) installed above the bed to acquire a two-dimensional color and depth image of the current patient when the bed in the medical imaging system is at a preset position; and An image analysis module (502) is used to receive the two-dimensional color and depth images acquired by the three-dimensional camera (111), and input the two-dimensional color and depth images into a pre-trained first human body information model to obtain position information of a plurality of human body characteristic points output by the first human body information model in a camera coordinate system or a bed coordinate system; when the position information is position information in the camera coordinate system, further convert the position information of the plurality of human body characteristic points in the camera coordinate system into position information in the bed coordinate system according to a conversion relationship between the camera coordinate system and the bed coordinate system determined during camera calibration; and calculate the position information of a plurality of candidate scanning areas in the bed coordinate system according to the position information of the plurality of human body characteristic points in the bed coordinate system; providing the position information of the plurality of candidate scanning areas in the bed coordinate system to the medical imaging application device, so that the medical imaging application device determines the position information of the current scanning area in the bed coordinate system, and moves the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device, The image analysis module (502) further inputs the two-dimensional color and depth images into a pre-trained second human body information model to obtain the height, weight and posture information of the patient output by the second human body information model; and provides the height, weight and posture information of the patient to the medical image application device, so that the medical image application device uses the height, weight and posture information to register the patient's information; The second human body information model is trained by using a plurality of pre-acquired groups of two-dimensional color and depth images as an input parameter set, and using pre-acquired information of height, weight and posture corresponding to each group of two-dimensional color and depth images as an output parameter set. The patient's height, weight and posture information are provided to the medical imaging application device (S24), so that the medical imaging application device uses the height, weight and posture information to register the patient's information. The medical imaging application device uses the height, weight and posture information to register the patient's information, including: when receiving a user-triggered scan start instruction, the medical imaging application device compares the height, weight and posture information with the height, weight and posture information pre-registered by the user, and when the deviation information of the height and weight exceeds the set threshold or the posture information is inconsistent, a warning message box pops up, and according to the user's choice, determines the height, weight and posture information used for the current scan.
7. The acquisition control and image analysis device according to claim 6, characterized in that: When the coil covers the patient's body area, the image analysis module (502) further obtains the body area information covered by the coil output by the first human body information model, and further provides the body area information covered by the coil to the medical imaging application device, so that the medical imaging application device determines the candidate scanning areas supported by the medical imaging system according to the body area information covered by the coil, and then selects the current scanning area from the candidate scanning areas supported by the medical imaging system.
8. The acquisition control and image analysis device according to claim 6, characterized in that: The first human body information model is trained using multiple groups of pre-acquired two-dimensional color and depth images as an input parameter set, and using pre-acquired position information of multiple human body feature points corresponding to each group of two-dimensional color and depth images in a camera coordinate system or a bed coordinate system as an output parameter set.
9. The acquisition control and image analysis device according to claim 6, characterized in that: The preset position of the hospital bed is at the origin or near the origin.
10. An image acquisition and analysis system (700), characterized in that: include: A three-dimensional camera (111) mounted at a set position above the medical imaging system; and The acquisition control and image analysis device (500) as claimed in any one of claims 6 to 9.
11. A scan preparation system (800) in a medical imaging system, characterized in that: include: The image acquisition and analysis system (700) as claimed in claim 10; and A medical imaging application device (801) is used to determine the position information of the current scanning area in the bed coordinate system according to the position information of multiple candidate scanning areas in the bed coordinate system provided by the image acquisition and analysis system, and control the bed to move the current scanning area to the scanning center according to the position information of the current scanning area in the bed coordinate system and the position of the bed relative to the scanning center of the medical imaging device.
12. The scanning preparation system in the medical imaging system according to claim 11, characterized in that: The medical imaging application device (801) is further used to register the patient's information based on the patient's height, weight and posture information provided by the image acquisition and analysis system.
