Positioning identification method, system and device for medical image system

Abstract

The embodiment of the invention provides a positioning identification method and system for a medical image system, and the method comprises the steps: detecting the execution of preset operation related to positioning; when it is detected that the preset operation related to positioning is executed, a multi-angle body position image of the target object is obtained; processing the multi-angle body position image based on an image processing model to obtain a body position recognition result; and determining the current body position of the target object based on the body position recognition result.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging, and in particular to a method, system and device for positioning recognition in a medical imaging system. Background Art

[0002] Modern medical scans may include computed tomography, magnetic resonance imaging, ultrasound imaging, X-ray imaging, positron emission tomography, etc. During medical examinations, it is usually necessary to adjust the body position of the scanned object in order to scan and image the region of interest. After the body position of the scanned object is adjusted, the positioning information in the medical imaging system needs to be updated in a timely manner.

[0003] Therefore, there is a need for a positioning recognition method, system and device for a medical imaging system so as to obtain the positioning information of the scanned object in a timely and accurate manner. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for position recognition for a medical imaging system, the method comprising: detecting the execution of a preset operation related to the position; when the execution of the preset operation related to the position is detected, acquiring a multi-angle body position image of a target object; processing the multi-angle body position image based on an image processing model to acquire a position recognition result; and determining the current body position of the target object based on the position recognition result.

[0005] In some embodiments, the preset operations related to positioning include one or more of the following: bed entry operation, laser positioning operation, and coil placement operation.

[0006] In some embodiments, the processing the multi-angle body position images based on the image processing model to obtain the body position recognition result includes: inputting the multi-angle body position images into the image processing model to obtain the body position recognition result.

[0007] In some embodiments, the processing of the multi-angle body position images based on the image processing model to obtain the body position recognition result includes: performing image segmentation on the multi-angle body position images to obtain a target structure diagram; inputting the target structure diagram into the image processing model for processing to obtain the body position recognition result.

[0008] In some embodiments, the method further includes: based on a preset quality factor, determining whether the body position recognition result meets a preset condition; if not, sending a prompt message to the user.

[0009] In some embodiments, the method further includes: acquiring pressure sensing information and / or coil placement information of the target object; determining a first body position recognition result based on the pressure sensing information and / or the coil placement information; and determining a current body position of the target object based on the first body position recognition result.

[0010] In some embodiments, the image processing model includes a skip connection structure.

[0011] In some embodiments, the multi-angle body image includes a top view, a front view, and a side view.

[0012] One or more embodiments of the present specification provide a position recognition system for a medical imaging system, the system comprising: a detection module for detecting the execution of a preset operation related to the position; an acquisition module for acquiring multi-angle body position images of a target object when the execution of the preset operation related to the position is detected; a processing module for processing the multi-angle body position images based on an image processing model to obtain a position recognition result; and a determination module for determining the current position of the target object based on the position recognition result.

[0013] One or more embodiments of the present specification provide a position recognition device for a medical imaging system, the device comprising: at least one storage medium storing computer instructions; and at least one processor executing the computer instructions to implement a position recognition method for a medical imaging system.

[0014] In some embodiments of the present specification, by detecting the execution of preset operations related to positioning, the target object's body position can be automatically identified when the positioning information of the target object changes, thereby avoiding the inconvenience caused by multiple manual input of the body position, and avoiding the situation where the positioning information changes during the scanning process but the positioning information is not changed in the system, thereby causing incorrect scanning results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0016] Figure 1 is a schematic diagram of an application scenario of a positioning recognition system for a medical imaging system according to some embodiments of this specification;

[0017] Figure 2 is an exemplary flow chart of a method for positioning recognition in a medical imaging system according to some embodiments of this specification;

[0018] Figure 3is a schematic diagram of the image processing model processing process according to some embodiments of this specification;

[0019] Figure 4 is an exemplary flow chart of determining the current position of a target object according to some embodiments of the present specification;

[0020] Figure 5 is an exemplary module diagram of a positioning recognition system for a medical imaging system according to some embodiments of this specification;

[0021] Figure 6 is a schematic diagram of multi-angle body images according to some embodiments of this specification;

[0022] Fig. 7A is an exemplary structural diagram of a standard convolution classification neural network according to some embodiments of this specification;

[0023] Figure 7B It is a convolutional classification neural network with skip connections shown in some embodiments of this specification. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0025] It should be understood that the "system", "device", "unit" and / or "module" used herein are 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.

[0026] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0027] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0028] Modern medical scans may include computed tomography, magnetic resonance imaging, ultrasound imaging, X-ray imaging, positron emission tomography, etc. In the process of medical scanning, it is usually necessary to obtain the patient's positioning information (patient's position) before performing the medical scan to generate a correct scan image. During the magnetic resonance scanning process, the patient's position on the bed may include: HFS, HFP, FFS, FFP, HFPL, HFDR, FFDR, FFDL (prone position, spinal position, head first, feet first, etc.). Before scanning, the position information of the patient registration interface should be filled in according to the actual position of the scanned object. When the patient's position is adjusted, the position information in the system also needs to be changed before scanning to obtain the correct image.

[0029] Currently, the patient's body position is manually identified and the positioning information is manually filled in. However, if multiple parts are scanned during a medical examination, it is very likely that the patient changes his body position and forgets to change the position information in the system, resulting in the scanned image being in the wrong orientation.

[0030] Therefore, some embodiments of the present specification provide a method and system for position recognition in a medical imaging system, which can automatically acquire the patient's position information in real time and quickly, reduce the doctor's manual operations, and improve scanning efficiency.

[0031] Figure 1 It is a schematic diagram of an application scenario of a positioning recognition system for a medical imaging system according to some embodiments of this specification.

[0032] like Figure 1 As shown, an application scenario 100 of a positioning recognition system for a medical imaging system (hereinafter referred to as application scenario 100 ) may include a medical imaging device 110 , a network 120 , a terminal 130 , a processing device 140 , and a storage device 150 .

[0033] The medical imaging device 110 can scan the scanned object and / or generate data about the scanned object. Exemplarily, the medical imaging device 110 may include an X-ray device, a CT device, an MRI device, a PET device, an ultrasound device, a PET / CT device, an MRI / CT device, etc. Taking the CT device as an example, the medical imaging device 110 may include a gantry 111, a detector 112, a ray source 113, and a scanning bed 114. The detector 112 and the ray source 113 may be relatively mounted on the gantry 111. The target object may be placed on the scanning bed 114 and moved into the detection channel of the CT scanner. For the convenience of explanation, a reference coordinate system is introduced, and the reference coordinate system may include an X-axis, a Y-axis, and a Z-axis. The Z-axis refers to the direction in which the target object is moved into and / or out of the detection channel of the medical imaging device 110. The X-axis and the Y-axis may form a plane perpendicular to the Z-axis. The ray source 113 may emit X-rays to scan the target object located on the scanning bed 114. The detector 112 may detect the radiation (such as X-rays) emitted by the ray source 113. In some embodiments, the detector 112 may include a plurality of detector units. The detector unit may include a scintillation detector (e.g., a cesium iodide detector) or a gas detector. The detector units may be arranged in a single row or multiple rows. The scanning bed 114 may be used to place the target object. For example, the patient may be on the scanning bed 114 in different positions. It should be noted that in appropriate scenarios, the medical imaging device 110 may be replaced by other medical devices. For example, including but not limited to electronic computer tomography equipment, magnetic resonance imaging equipment, positron emission tomography equipment, etc.

[0034] The network 120 may include any suitable network that facilitates information and / or data exchange of the application scenario 100. In some embodiments, one or more components in the application scenario 100 (e.g., the medical imaging device 110, the terminal 130, the processing device 140, or the storage device 150) may transmit information and / or data to one or more other components of the application scenario 100 via the network 120. For example, the processing device 140 may obtain preset operations related to positioning from the medical imaging device 110 via the network 120. In some embodiments, the network 120 may be any one or more of a wired network or a wireless network. In some embodiments, the network may be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures.

[0035] The terminal 130 may include a mobile device, a tablet computer, a laptop computer, etc., or any combination thereof. In some embodiments, the terminal 130 may interact with other components in the application scenario 100 through the network 120. For example, the terminal 130 may receive data such as preset operations related to positioning sent by the medical imaging device 110. In some embodiments, the terminal 130 may receive information and / or instructions input by a user (e.g., a user of the medical imaging device 110, such as a doctor), and send the received information and / or instructions to the medical imaging device 110 or the processing device 140 via the network 120. For example, a doctor may input an operating instruction for the medical imaging device 110 through the terminal 130. In some embodiments, the terminal 130 may display the body position recognition result after processing the multi-angle body position image.

[0036] In some embodiments, the terminal 130 may include a display interface for displaying information related to body position recognition. For example, information such as multi-angle body position images, body position recognition results, and the current body position of the target object may be displayed according to the display interface. In some embodiments, the terminal 130 may be integrated with the processing device 140.

[0037] The processing device 140 may process data and / or information obtained from the medical imaging device 110, the terminal 130 and / or the storage device 150. For example, the processing device 140 may detect the execution of a preset operation related to positioning.

[0038] In some embodiments, the processing device 140 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 140 can be local or remote. The processing device 140 can be directly connected to the medical imaging device 110, the terminal 130 and the storage device 150 to access the stored or acquired information and / or data. In some embodiments, the processing device 140 can be implemented on a cloud platform. As an example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc. or any combination thereof.

[0039] The storage device 150 may store data and / or instructions. In some embodiments, the storage device 150 may store data obtained from the medical imaging device 110, the terminal 130, and / or the processing device 140. For example, the storage device 150 may store multi-angle body images of the target object, etc. In some embodiments, the storage device 150 may store data and / or instructions used by the processing device 140 to execute the exemplary methods described in this specification. For example, the storage device 150 may store instructions for the processing device 140 to execute the methods shown in the various flow charts. In some embodiments, the storage device 150 may include a mass storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 150 may be implemented on a cloud platform.

[0040] In some embodiments, the storage device 150 may be connected to the network 120 to communicate with one or more components of the application scenario 100 (e.g., the medical imaging device 110, the terminal 130, the processing device 140, etc.). One or more components of the application scenario 100 may access data or instructions stored in the storage device 150 via the network 120. In some embodiments, the storage device 150 may be directly connected to or communicate with one or more components of the application scenario 100. In some embodiments, the storage device 150 may be part of the processing device 140.

[0041] In some embodiments, the application scenario 100 may include multiple medical imaging devices 110, such as medical imaging devices 110 belonging to multiple hospitals or research institutions. The processing device 140 may communicate remotely with these medical imaging devices and analyze the preset operations related to the positioning collected by them. For example, the processing device 140 may be a computing device for a positioning recognition platform for a medical imaging system, and the analysis platform may provide analysis and processing services for positioning recognition of a medical imaging system for multiple hospitals or research institutions.

[0042] Figure 2 is an exemplary flow chart of a method for positioning recognition of a medical imaging system according to some embodiments of this specification. In some embodiments, process 200 may be executed by processing device 140 or its components. Figure 2 As shown, process 200 may include the following steps.

[0043] Step 210 , detecting execution of a preset operation related to positioning. In some embodiments, step 210 may be executed by the detection module 510 .

[0044] Positioning may refer to the process of adjusting the position of the body / part of the target object during the scanning process. After the target object is positioned, its body position information (also referred to as positioning information, body position information) may include multiple types. For example, when the target object is a patient, the positioning information may include HFS (head in front, supine), HFP (head in front, prone), FFS (feet in front, supine), FFP (feet in front, prone), HFDL (head in front, left side), HFDR (head in front, right side), FFDL (feet in front, left side), and FFDR (feet in front, right side).

[0045] The preset operation may be a pre-specified action / instruction related to positioning. For example, the preset operation may be some operations to be performed after positioning the target object.

[0046] In some embodiments, the preset operations related to positioning may include one or more of the following: bed entry operation, laser positioning operation, and coil placement operation.

[0047] The bed entry operation may be an operation for controlling the scanning bed to enter the detection area. For example, the bed entry operation may be Figure 1 The target object can be placed on the scanning bed 114 and then controlled to move into the detection area of ​​the CT scanner. In some embodiments, when the user presses a button related to the bed entry operation, or inputs a related instruction for the bed entry operation, the processing device 140 can control the medical imaging system to perform the bed entry operation.

[0048] The laser positioning operation may be an operation of detecting and positioning using a laser light source. For example, in CT scanning, the laser positioning operation may be a process of projecting multiple laser beams to a target object using at least one laser positioning light (such as a top light and two side lights). In some embodiments, when a user presses a button related to the laser positioning operation, the processing device 140 may control the medical imaging system to perform the laser positioning operation.

[0049] The coil placement operation may refer to the operation of setting / placing the coil. For example, in a magnetic resonance system, the coil placement operation may be placing a radio frequency coil, an imaging coil, etc. around the head.

[0050] In some embodiments, the preset operation may also be other operations related to positioning during the scanning process, such as coil switching, etc. For example, the medical imaging device 110 may also include a positioning information acquisition button. In response to the user sending a positioning acquisition instruction through the positioning acquisition button at any time, the processing device 140 can acquire the positioning information of the target object.

[0051] In some embodiments, the processing device 140 can determine whether a preset operation related to positioning is executed by detecting instructions related to the preset operation. For example, it can be determined that the execution of the preset operation is detected in response to the user inputting the instruction related to the preset operation. For another example, when a button related to the bed entry operation is pressed, an operation instruction can be automatically generated, and the processing device 140 can determine that the preset operation is executed when the generated operation instruction is detected.

[0052] Step 220 , when it is detected that the preset operation related to positioning is executed, a multi-angle body position image of the target object is acquired. In some embodiments, step 220 may be executed by the acquisition module 520 .

[0053] The target object may be biological or non-biological. For example, the target object may be a patient, a man-made object, an animal, etc. The target object may include a specific part, organ, tissue, and / or body part of a patient. By way of example only, the target object may include the head, brain, neck, body, shoulder, arm, chest, heart, stomach, blood vessel, soft tissue, knee, foot, etc., or a combination thereof.

[0054] The multi-angle body image may be a set of (two or more) images including the target object taken from different angles. For example, the multi-angle body image may be three views of the target object. In some embodiments, the multi-angle body image may include a top view, a front view, and a side view.

[0055] like Figure 6 As shown, when the target object is a patient, the multi-angle body position image may include a top view 610, a front view 620, and a side view 630. The multi-angle body position image may reflect the body position information of the target object from different angles. For example, the top view may reflect whether the patient is lying prone or supine, and the front view may reflect whether the patient is lying head first or feet first. The multi-angle body position image may be combined with the information contained in the images of different viewing angles to accurately identify the body position of the patient.

[0056] In some embodiments, the multi-angle body position images can be obtained by a camera device. The camera device can be a camera, a webcam, etc. For example, the medical imaging device 110 can include multiple cameras, and when a preset operation is detected, the processing device 140 can control the cameras to obtain multi-angle body position images. Among them, the multiple cameras can be located at the front, side, top, bottom, etc. of the target object. In some embodiments, the camera device can also be set at other locations other than the medical imaging device, for example, on the wall or ceiling of the room.

[0057] Step 230 , processing the multi-angle body position images based on the image processing model to obtain body position recognition results. In some embodiments, step 230 may be performed by the processing module 530 .

[0058] The body position recognition result may be body position information obtained based on multi-angle body position images. For example, the body position recognition result may be a specific body position of the target object, which may include HFS (head in front, supine), HFP (head in front, prone), FFS (feet in front, supine), FFP (feet in front, prone), HFDL (head in front, left side), HFDR (head in front, right side), FFDL (feet in front, left side), FFDR (feet in front, right side), etc.

[0059] The image processing model may be a trained machine learning model. The image processing model may be used to process multi-angle body position images to obtain body position recognition results. In some embodiments, the image processing model may include but is not limited to a neural network (NN), a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), etc. or any combination thereof.

[0060] In some embodiments, the processing device 140 may input the multi-angle body position image into the image processing model for processing, and the image processing model may output the body position recognition result after processing. In some embodiments, the output of the image processing model may be represented in the form of a vector, for example, the vector may include multiple elements, each element corresponds to a body position, and the value of the element may represent the probability that the current body position of the target object is the body position corresponding to the element, for example, the element value may be a value between 0 and 1; for another example, each element of the vector may also be 0 or 1, 1 indicates that the recognition result is the body position corresponding to it, and 0 indicates that the recognition result is not the body position corresponding to it.

[0061] For more information about the image processing model and how to obtain body position recognition results, see Figure 3 and its related description.

[0062] Step 240 , based on the body position recognition result, determine the current body position of the target object. In some embodiments, step 240 may be performed by the determination module 540 .

[0063] The current body position may be the position / morphology information of the current body / part of the target object, for example, the target object is currently in a head-first supine position.

[0064] In some embodiments, the processing device 140 may use the body position corresponding to the maximum probability in the body position recognition result as the current body position of the target object.

[0065] In some embodiments of the present specification, by detecting the execution of preset operations related to positioning, when the positioning information of the target object changes, for example, when a patient lies on a new scanning bed for positioning, the positioning information can be adjusted during the scanning process, so that the change of the target object's position information can be detected in time, thereby realizing automatic recognition of the target object's position, avoiding the inconvenience caused by manual input of the position multiple times, and avoiding the situation where the positioning information changes during the scanning process but the system does not change the positioning information, thereby causing incorrect scanning results.

[0066] Figure 3 It is a schematic diagram of the image processing model processing process shown in some embodiments of this specification.

[0067] In some embodiments, the processing device 140 may process the multi-angle body image 310 (eg Figure 6 The front view, side view and top view (as shown) are input into the image processing model 330 to obtain the body position recognition result 340.

[0068] In some embodiments, the processing device 140 may also perform image segmentation on the multi-angle body position images to obtain a target structure map 320 , and input the target structure map 320 into the image processing model 330 to obtain a body position recognition result 340 .

[0069] The target structure diagram may be a structure image obtained by segmenting the target structure in the multi-angle body image. The structure may be the head, feet, hands, and body contour of the target object. For example, the target structure diagram may include a head contour diagram, a foot contour diagram, a hand contour diagram, a body contour diagram, and the like. The head position and the foot position may be conveniently determined by the head contour diagram and the foot contour diagram, and then the head-first / feet-first position may be determined. The body contour diagram may conveniently determine side-lying / lying flat. The foot contour diagram and the body contour diagram may conveniently determine left-lying / right-lying position.

[0070] In some embodiments, the target structure map can be determined by segmenting the multi-angle body position image through an image segmentation algorithm. Exemplary image segmentation algorithms may include image edge segmentation, feature threshold segmentation, cluster segmentation, region extraction segmentation, etc. In some embodiments, the target structure map can also be obtained by other methods, for example, based on deep learning, etc. This specification does not limit the specific segmentation method.

[0071] It should be noted that Figure 3 The dotted line in represents an optional step, that is, the input of the image processing model 330 can be a multi-angle body position image 310 or a target structure image 320 , and the output of the image processing model 330 is a body position recognition result 340 .

[0072] In some embodiments, the model structure of the image processing model 330 can be as follows: Fig. 7A As shown, Fig. 7A It is an exemplary structural diagram of a standard convolution classification neural network shown in some embodiments of this specification, which may include a convolution kernel 5*5, N+1 maximum pooling layers, 4N convolution layers 3*3, a fully connected layer and a Softmax classification layer. Among them, in structure 710, multiple convolution layers 3*3 can be connected in sequence to achieve data (image) transmission. N is an integer, for example, N can be 1, 2, 3, 5, 10, etc.

[0073] In some embodiments, the model structure of the image processing model 330 can be as follows: Figure 7B As shown, Figure 7B It is a convolutional classification neural network with jump connections shown in some embodiments of this specification, which may include a convolution kernel 5*5, N+1 maximum pooling layers, 4N convolution layers 3*3, a fully connected layer and a Softmax classification layer. In structure 720, multiple convolution layers 3*3 can be jump-connected (for example, the output of certain layers in the neural network is used as the input of other layers, and there may be a network layer between the two layers), which can realize the transmission of data (image). In this embodiment, by setting a long and short fast connection structure in the image processing model 330, the reuse of data features can be effectively guaranteed, the utilization rate of data features can be improved, and the classification ability of the image processing model can be enhanced. N is an integer, for example, N can be 1, 2, 3, 5, 10, etc.

[0074] In some embodiments, the image processing model 330 can be obtained by training a large number of training samples with labels. Specifically, the training samples with labels are input into the image processing model 330, and the parameters of the image processing model 330 are updated through training. In some embodiments, the training samples may include multiple groups of sample multi-angle body position images collected historically, and the labels may include body position information corresponding to each group of multi-angle body position images, for example, HFS (head in front, supine), HFP (head in front, prone), FFS (feet in front, supine), FFP (feet in front, prone), HFDL (head in front, left side), HFDR (head in front, right side), FFDL (feet in front, left side), FFDR (feet in front, right side), eight body positions, each body position corresponds to labels 0, 1, 2, 3...6, 7. The above labels can be determined by manual annotation. In some embodiments, the training samples may also include sample target structure diagrams after image segmentation based on multi-angle body position images, and each sample target structure diagram may have similar labels. In some embodiments, training can be performed by various methods based on the training samples. For example, training can be performed based on a gradient descent method or the like.

[0075] In some embodiments, the image processing model 330 may output a body position recognition result 340. For a detailed description of the body position recognition result 340, see Figure 2 and its related description.

[0076] Figure 4 is an exemplary flow chart of determining the current position of a target object according to some embodiments of this specification. Figure 4 As shown, the process 400 may include the following steps. In some embodiments, the process 400 may be performed by the processing device 140 or a component thereof.

[0077] Step 410: Based on a preset quality factor, determine whether the body position recognition result meets a preset condition.

[0078] The quality factor may be a preset probability threshold of the body position recognition result. For example, when the body position recognition result is a vector containing multiple probability values, the quality factor may be set to 0.5, 0.7, 0.8, 0.9, etc.

[0079] The preset condition may be a comparison relationship between the probability value corresponding to each body position of the body position recognition result and the quality factor. For example, the preset condition may be that the maximum value of the probability corresponding to each body position in the body position recognition result is less than the quality factor. When the maximum probability value among the probability values ​​corresponding to each body position in the body position recognition result is less than the quality factor, it indicates that the current body position recognition result may be abnormal, or the result of the body position recognition may be inaccurate. At this time, the processing device 140 may execute step 420. When the preset condition is not met, it indicates that the current body position recognition result is relatively accurate, and the current body position of the target object can be determined based on the body position recognition result.

[0080] Step 420: Send a prompt message to the user.

[0081] In some embodiments, when the maximum probability value in the body position recognition result is less than the quality factor, the processing device 140 may generate and send a prompt message to the user. Exemplary prompt messages may be "Cannot recognize the body position of the target object, please input manually", "Body position change detected, please re-enter", etc.

[0082] In some embodiments, the processing device 140 may send prompt information to the user in a variety of ways. For example, the prompt information may be sent in the form of voice, text, images, etc. For another example, the processing device 140 may send prompt information to the user in the form of a pop-up window, bubble, etc.

[0083] In some embodiments, in order to meet the needs of different users and minimize the manual operation of users, when the maximum probability value in the body position recognition result is less than the quality factor, the processing device may also execute step 430 to further recognize the current body position of the target object.

[0084] It should be noted that, when it is determined that the body position recognition result does not meet the preset condition, the processing device may execute step 420, may execute step 430, or may execute step 420 first and then step 430 (e.g., Figure 4 ).

[0085] Step 430 , obtaining pressure sensing information and / or coil placement information of the target object.

[0086] The pressure sensing information can reflect the posture information of the human body when lying flat and lying on the side. When the human body is placed on the scanning bed, the pressure value at the same position on the scanning bed will change with the change of the human body's posture. For example, the force-bearing area when lying flat and lying on the side is different, and the size of the pressure value will also change. In some embodiments, the processing device 140 can pre-store the pressure changes at different positions on the scanning bed when the human body lies flat and lying on the side as the preset pressure value for each lying posture. When the pressure sensing information of the target object is equal to or close to the preset pressure value of a certain lying posture, the processing device 140 can determine that the lying posture of the target object is that lying posture. For example, when the pressure sensing information of the current target object is equal to the pre-stored preset pressure value of the human body lying flat, the processing device 140 can determine that the lying posture of the target object is lying flat.

[0087] In some embodiments, the pressure sensing information may be determined by multiple pressure sensors installed at different locations on the scanning bed. For example, a sensor is installed in an area of ​​the scanning bed (e.g., the area corresponding to the chest of the patient when lying on the bed), and the pressure sensing information is obtained through the sensor.

[0088] The coil placement information may include various types of information related to the currently placed coil. For example, the coil placement information may include information such as the type of coil currently used, the coil placement time, and the coil size. In some embodiments, the coil placement information may have a preset correspondence with the body position of the target object. For example, when inserting a breast coil, the body position of the target object is preset to be head first, prone position. In some embodiments, the above preset correspondence can be determined by looking up a table.

[0089] In some embodiments, the coil placement information may be obtained through user input. In some embodiments, the coil placement information may be obtained through the system identifying the placement of the current coil, or may be obtained through other methods, which are not limited in this specification.

[0090] Step 440: Determine a first body position recognition result based on the pressure sensing information and / or the coil placement information.

[0091] The first body position recognition result refers to a body position recognition result determined again based on the pressure sensing information and / or the coil placement information. The first body position recognition result may be the same as or different from the body position determined based on the output result of the image processing model.

[0092] In some embodiments, the processing device 140 may directly use the body position corresponding to the pressure sensing information and / or the coil placement information as the first body position recognition result.

[0093] In some embodiments, the processing device 140 may also make a comprehensive judgment based on the body position recognition result output by the image processing model, the pressure sensing information, and the coil placement information, or determine the first body position recognition result based on machine learning or other methods.

[0094] Step 450: Determine the current body position of the target object based on the first body position recognition result.

[0095] In some embodiments, the processing device may use the body position corresponding to the first body position recognition result as the current body position of the target object.

[0096] In this embodiment, the pressure sensing information and the coil placement information are used to make the body position judgment related to the actual scanning situation. On the basis of the output results of the image processing model, constraint information is further added to obtain more accurate body position recognition results. In addition, when the recognition quality is not high (that is, the probability is less than the quality factor), feedback can be given to the user in real time to avoid the impact of body position recognition errors on subsequent scans; and feedback can be given to the user in a timely manner when the body position changes, so that the system can be compatible with multiple changing body positions in one scan, avoiding multiple scans, reducing user operations, and improving scanning efficiency.

[0097] It should be noted that the above description of each process is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to each process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, process 200 can also include a pre-processing process or a post-processing process, and for example, a storage step is added to each process step.

[0098] Figure 5 5 is an exemplary module diagram of a positioning recognition system for a medical imaging system according to some embodiments of the present specification. In some embodiments, the positioning recognition system 500 for a medical imaging system may include a detection module 510, an acquisition module 520, a processing module 530, and a determination module 540.

[0099] The detection module 510 may be used to detect the execution of a preset operation related to positioning.

[0100] The acquisition module 520 may be used to acquire multi-angle body position images of the target object when it is detected that a preset operation related to positioning is executed.

[0101] The processing module 530 can be used to process the multi-angle body position images based on the image processing model to obtain body position recognition results.

[0102] The determination module 540 may be configured to determine the current body position of the target object based on the body position recognition result.

[0103] For more information about each module of the system 500, please refer to the relevant process section, for example, Figure 2-Figure 4 Related description.

[0104] It should be understood that Figure 5 The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the system and its modules of this specification. Not only can the hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, it can also be implemented with software such as executed by various types of processors, and it can also be implemented by a combination of the above hardware circuits and software (for example, firmware).

[0105] It should be noted that the above description of the positioning recognition system and its modules for medical imaging systems is only for the convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 5 The detection module 510, acquisition module 520, processing module 530 and determination module 540 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0106] The beneficial effects of the embodiments of the present specification include at least: 1) before the preset operation is executed, the target object's body position is automatically recognized to avoid the inconvenience caused by multiple manual input of the body position; 2) the recognition process adopts a machine learning model to improve recognition accuracy and efficiency; 3) the model includes a long and short quick connection structure, which can effectively ensure the reuse of data features, improve the utilization rate of data features, and enhance the classification ability of the image processing model; 4) through pressure sensing information and coil placement information, the body position judgment can be related to the actual scanning situation, and a more accurate body position recognition result can be obtained; 5) when the recognition quality is not high (that is, the probability is less than the quality factor), feedback can be given to the user in real time to avoid the body position recognition error affecting subsequent scans; when the body position changes, feedback is given to the user in a timely manner, so that the system can be compatible with multiple changing body positions in one scan, avoiding multiple scans, thereby improving scanning efficiency.

[0107] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0108] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0109] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0110] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0111] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0112] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0113] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for positioning recognition in a medical imaging system, the method include: Detecting the execution of preset operations related to positioning; When it is detected that the preset operation related to positioning is executed, acquiring multi-angle body position images of the target object; Processing the multi-angle body position images based on an image processing model to obtain a body position recognition result; Based on the body position recognition result, a current body position of the target object is determined.

2. According to the method of claim 1, the preset operations related to positioning include one or more of the following: Bed entry, laser positioning and coil placement.

3. The method according to claim 1, wherein the multi-angle body position images are processed based on an image processing model to obtain body position recognition results. include: The multi-angle body position image is input into the image processing model to obtain the body position recognition result.

4. The method according to claim 1, wherein the multi-angle body position images are processed based on an image processing model to obtain body position recognition results. include: Performing image segmentation on the multi-angle body image to obtain a target structure diagram; The target structure diagram is input into the image processing model for processing to obtain the body position recognition result.

5. The method according to claim 1, further comprising: include: Based on a preset quality factor, determining whether the body position recognition result meets a preset condition; If not, a prompt message is sent to the user.

6. The method according to claim 5, further comprising: include: Acquiring pressure sensing information and / or coil placement information of the target object; Determining a first body position recognition result based on the pressure sensing information and / or the coil placement information; Based on the first body position recognition result, a current body position of the target object is determined.

7. According to the method of claim 1, the image processing model is a convolutional classification neural network with skip connections.

8. The method according to claim 1, wherein the multi-angle body image comprises a top view, a front view, and a side view.

9. A positioning recognition system for a medical imaging system, the system include: A detection module, used to detect the execution of preset operations related to positioning; An acquisition module, configured to acquire multi-angle body position images of the target object when it is detected that the preset operation related to the positioning is executed; A processing module, used for processing the multi-angle body position images based on an image processing model to obtain a body position recognition result; A determination module is used to determine the current body position of the target object based on the body position recognition result.

10. A device for identifying a position of a medical imaging system, the device include: at least one storage medium storing computer instructions; At least one processor executes the computer instructions to implement the method according to any one of claims 1 to 8.

Images