Medical imaging method and system

Abstract

An embodiment of the present invention provides a medical imaging method and system, which includes: receiving clinical background information of an object; automatically determining a scanning protocol based on the clinical background information; receiving three-dimensional surface information of the object; analyzing the three-dimensional surface information based on a trained first deep learning network; positioning the object based on the analysis results of the three-dimensional surface information; performing a positioning scan to obtain a positioning image; automatically determining object properties based on the positioning image; automatically setting scanning parameters for precise scanning based on the object properties; and performing precise scanning based on the set scanning parameters.

Description

Technical Field

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

[0002] In CT (Computing Tomography) imaging technology, an X-ray source is controlled to rotate around the part of the object to be imaged and radiate X-rays toward the part to be imaged. After the X-rays penetrate the object, an attenuation signal is formed and received by a detector arranged on the opposite side of the X-ray source. The attenuation signal is collected and digitized by a data acquisition system (Direct Acquisition System, DAS) to generate image data. Based on the image data, the volume of the part to be imaged of the object can be reconstructed.

[0003] During the scanning imaging process, such as the process of acquiring data, the user needs to make multiple settings according to different clinical needs to define the scanning process and its related details. These settings jointly affect the quality of the subsequent reconstructed image and the radiation dose received by the object.

[0004] In the prior art, multiple scanning protocols can be preset, and each scanning protocol defines a set of parameter settings, such as one or more of the following parameter settings: current / voltage of the X-ray source, scanning range, gantry speed, duration, focal spot size, tilt angle of the inspection table, injection flow rate / flow / pressure / delay of the contrast agent, post-processing filter type, reconstruction kernel type, reconstruction layer thickness, etc. The doctor can select one of the protocols to perform the current scan according to the part to be imaged. However, for most clinical needs, these preset protocols cannot help the doctor obtain an ideal image or allow the patient to receive a sufficiently small radiation dose. The doctor is often required to manually adjust the scanning parameters, which not only requires very high experience and professional knowledge of the doctor, but also consumes a lot of time.

[0005] Therefore, there is a need to provide a new medical imaging method and system that can ensure the quality of reconstructed images and help to quickly complete the scanning process. Summary of the invention

[0006] An object of the present invention is to provide a new medical imaging method and system, which can ensure the quality of reconstructed images and help to quickly complete the scanning process.

[0007] An exemplary embodiment of the present invention provides a medical imaging method, comprising:

[0008] Receive the subject's clinical background information;

[0009] Automatically determine scanning protocols based on clinical background information;

[0010] receiving three-dimensional surface information of an object;

[0011] Analyze the three-dimensional surface information based on the trained first deep learning network;

[0012] Positioning the object based on the analysis results of the three-dimensional surface information;

[0013] performing a scout scan to obtain a scout image;

[0014] Automatically determine object properties based on positioning images;

[0015] Automatically set scanning parameters for precise scanning based on object properties; and

[0016] Performs precise scanning based on the set scanning parameters.

[0017] Optionally, the above clinical background information includes one or more of the subject's anatomical part, clinical purpose, and physical characteristics.

[0018] Optionally, the step of automatically determining the object attributes in the positioning image includes: determining the object attributes in the positioning image based on a trained second deep learning network.

[0019] Optionally, the second deep learning network includes an input layer, an output layer, and at least one hidden layer connected between the input layer and the output layer, the input layer includes multiple neurons having multiple positioning images, the output layer includes multiple neurons having multiple positioning images in which object attributes are determined, and the hidden layer includes multiple neurons having multiple clinical background information related to the positioning images.

[0020] Optionally, the object attributes include a region of interest of the object and / or anatomical structure features within the region of interest, and the scanning parameters for precise scanning include a scanning range and / or a scanning angle.

[0021] Optionally, the object attributes automatically determined based on the positioning image include the body shape standard of the object, each scanning parameter includes multiple sub-value sets corresponding to different body shape standards, and the step of automatically setting the scanning parameters based on the object attributes also includes: selecting the sub-value set corresponding to the body shape standard of the object; and determining the parameter values ​​of the scanning parameters for precise scanning in the selected sub-value set.

[0022] Optionally, the method further includes: receiving a target indication related to image quality and / or radiation dose; and setting scanning parameters for precise scanning based on the target indication.

[0023] An exemplary embodiment of the present invention further provides a medical imaging system, comprising:

[0024] An X-ray source for radiating X-rays toward a subject;

[0025] a detector for receiving the X-rays after attenuation by the object;

[0026] a data acquisition system for acquiring and digitizing the attenuated X-rays; and,

[0027] A computing device is used to execute instructions in a non-volatile memory to implement the above medical imaging method.

[0028] Optionally, the system further comprises an operating console connected to the computing device, and the computing device receives clinical background information of the subject through the operating console.

[0029] Optionally, the system further comprises a display connected to the computing device, and the computing device receives the clinical background information of the subject via a graphical user interface on the display.

[0030] Other features and aspects will become apparent from the following detailed description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention may be better understood by describing exemplary embodiments of the present invention in conjunction with the accompanying drawings, in which:

[0032] Figure 1 A schematic diagram of an exemplary CT imaging system of the present invention;

[0033] Figure 2 is a block diagram of an exemplary CT imaging system;

[0034] Figure 3 A flow chart showing a medical imaging method according to an embodiment of the present invention;

[0035] Figure 4 An example of a second deep learning network is shown;

[0036] Figure 5 A flow chart showing a medical imaging method according to another embodiment of the present invention. DETAILED DESCRIPTION

[0037] The specific embodiments of the present invention will be described below. It should be noted that in the specific description of these embodiments, in order to provide a concise description, it is impossible for this specification to provide a detailed description of all the features of the actual embodiments. It should be understood that in the actual implementation of any embodiment, just as in the process of any engineering project or design project, in order to achieve the specific goals of the developer and to meet system-related or business-related restrictions, various specific decisions are often made, and this will also change from one embodiment to another. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the content disclosed by the present invention, some changes such as design, manufacturing or production based on the technical content disclosed in this disclosure are just conventional technical means, and should not be understood as insufficient content of this disclosure.

[0038] Unless otherwise defined, the technical or scientific terms used in the claims and the specification shall have the usual meaning understood by persons with ordinary skills in the technical field to which the invention belongs. The words "first", "second" and similar words used in the patent application specification and the claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "One" or "one" and other similar words do not indicate a quantitative limitation, but indicate the existence of at least one. "Include" or "comprises" and other similar words mean that the elements or objects appearing before "include" or "comprises" include the elements or objects listed after "include" or "comprises" and their equivalent elements, and do not exclude other elements or objects. "Connected" or "connected" and other similar words are not limited to physical or mechanical connections, nor are they limited to direct or indirect connections.

[0039] The medical imaging system of the embodiment of the present invention can be used to collect image data of an object 112 and perform image reconstruction based on the image data. The object 112 can be, for example, a patient, an object, a component, a foreign object in the human body such as a dental implant, a vascular scaffold and / or a contrast enhancement agent, etc.

[0040] An example of a medical imaging system of an embodiment of the present invention may be a CT imaging system. Other examples include, for example, a magnetic resonance imaging system, a C-arm imaging system, a positron emission tomography (PET) imaging system, a single photon emission computed tomography (SPECT) imaging system, and the like.

[0041] Figure 1 FIG. 1 is a schematic diagram of an exemplary CT imaging system of the present invention, as shown in FIG. Figure 1As shown, the CT imaging system 100 includes a gantry 102, and the gantry 102 further includes an X-ray source 104 disposed thereon, and the X-ray source 104 is used to radiate X-ray beams to an object 112. Figure 1 Only one X-ray source is shown, and in other examples, there may be multiple X-ray sources. The gantry 102 also includes an X-ray detector 106 disposed on an opposite side of the X-ray source 104 , the X-ray detector including a plurality of detector elements formed into a detector array 108 .

[0042] In one embodiment, the CT imaging system further includes an image processor 110, which can reconstruct an image of a target volume of the object 112 based on an image reconstruction method. The image reconstruction algorithm may include, for example, a forward projection (FBP) reconstruction method, an adaptive statistical iterative reconstruction (ASIR) method, a common gradient (CG) method, a maximum likelihood expectation maximization (MLEM) method, a model-based iterative reconstruction (MBIR) method, etc.

[0043] In one embodiment, the X-ray source 104 is used to project an X-ray beam, such as a fan beam, through the object 112. The X-ray beam is beam-shaped to an XY plane of a Cartesian coordinate system, which is generally referred to as an imaging plane. The X-ray detector 106 is used to receive the X-ray beam whose intensity is attenuated after passing through the object 112. Each detector element generates a corresponding electrical signal based on the intensity of the received X-ray. The electrical signal generated by each detector element is related to the attenuation degree of the received X-ray. Therefore, the detector array including a plurality of detector elements can generate an X-ray attenuation condition of an imaging volume to be imaged of the object 112.

[0044] In one embodiment, the X-ray source 104 and the X-ray detector 106 rotate around the object 112 in the imaging plane as the gantry 102, so the angle at which the X-ray beam intersects the object keeps changing. The radiation attenuation data received by the X-ray detector 106 at one angle (or viewing angle), that is, the projection data, can be called a field of view (View). One scan of the object 112 includes multiple fields of view obtained from multiple angles during the rotation of the X-ray source 104 and the X-ray detector 106.

[0045] The above-mentioned CT imaging system can perform axial scanning. In the axial scanning, the projection data can be processed to reconstruct a two-dimensional slice image. For example, the above-mentioned image reconstruction method can be used to reconstruct an image based on the projection data. In this process, the attenuation data generated by the scanning is converted into CT values ​​(or Hu), which can be reflected by the brightness of the pixels.

[0046] The CT imaging system may also perform a spiral scan, in which the object 112 is moved to acquire multiple slices, for example, multiple slices may be acquired along a spiral trajectory by cone beam X-ray spiral scanning.

[0047] Figure 2 1 is a block diagram of an exemplary CT imaging system. The exemplary CT imaging system 200 is similar in structure and principle to the system 100 shown in FIG1 . For example, the system 200 includes a gantry 102 on which an X-ray source 104 and a detector array 108 are relatively arranged. In one embodiment, the system 200 is used to collect projection data of an object 204 at different angles. Therefore, the gantry 102 and its components are used to rotate around a rotation center 206 to collect projection data. During the rotation process, the X-ray radiation source 104 is used to project X-rays 106 that penetrate the object 204 toward the detector array 108. The detector array 108 collects attenuated X-ray beam data. The attenuated X-ray beam data is pre-processed as projection data of the target volume of the object. Based on the projection data, an image of the object 204 can be reconstructed. The reconstructed image can display internal features of the object 204. These features include, for example, lesions, size, shape, etc. of body tissue structures.

[0048] In one embodiment, the system 200 includes a control mechanism 208. The control mechanism 208 may include an X-ray controller 210 for providing power and timing signals to the X-ray radiation source 104. The control mechanism 208 may also include a gantry motor controller 212 for controlling the rotational speed and / or position of the gantry 102 based on imaging requirements.

[0049] In one embodiment, the system 200 further includes a data acquisition system (DAS) 214 for converting the sampled analog attenuation data received by the detector array 108 into digital signals for subsequent processing.

[0050] In one embodiment, the system 200 further includes a computing device 216, and the data sampled and digitized by the DAS 214 is transmitted to a computer or computing device 216 for processing. In one example, the computing device 216 stores the data in a storage device such as a mass storage device 218. The mass storage device 218 may include a hard drive, a floppy disk drive, a compact disk read / write (CD-R / W) drive, a digital versatile disk (DVD) drive, a flash drive, and / or a solid-state storage device, etc.

[0051] In addition, the computing device 216 is also used to provide commands and parameters to the DAS 214, the X-ray controller 210, and the gantry motor controller 212 to control system operations, such as data acquisition and / or processing. In one embodiment, the computing device 216 controls system operations based on user input. For example, the computing device 216 can receive user input, including commands, scanning protocols, and / or scanning parameters, through an operation console 220 connected thereto. The operation console 220 may include a keyboard (not shown) and / or a touch screen to allow a user to input / select commands, scanning protocols, and / or scanning parameters.

[0052] Although Figure 2 Only one console 220 is shown, but the computing device 216 can be connected to more consoles, for example, for inputting or outputting system parameters, requesting medical examinations and / or viewing images. In one embodiment, the computing device 216 can be connected to local or remote displays, printers, workstations and / or similar devices, for example, such devices in a medical institution or hospital, or remote devices can be connected via one or more configured wires or wireless networks such as the Internet and / or a virtual private network.

[0053] In one embodiment, the system 200 may include or be connected to a picture archiving and communication system (PACS) 224. In a variant embodiment, the PACS 224 is further connected to a remote system such as a radiology department information system, a hospital information system, and / or an internal or external network (not shown) to allow operators located in different locations to provide commands and parameters, and / or access image data.

[0054] The computing device 216 uses user-provided and / or system-defined commands and parameters to operate a couch motor controller 226 to further control a couch 228, which includes a drive table. The couch motor controller 226 is used to move the couch 228 to a suitable position to position the object 204 in the gantry 102 to acquire projection data of a target volume of the object 204.

[0055] The system 200 further includes an image reconstructor 230. As described above, the DAS 214 samples and digitizes the projection data collected by the detector elements 202. Then, the image reconstructor 230 performs high-speed image reconstruction based on the sampled and digitized projection data. Figure 2200 as a separate entity, but in some embodiments, the image reconstructor 230 may form part of the computing device 216. Alternatively, the image reconstructor 230 may not be present in the system 200, or the computing device 216 may perform one or more functions of the image reconstructor 230. In addition, the image reconstructor 230 may be located at a local or remote location and may be connected to the system 200 using a wired or wireless network. In a variant embodiment, computing resources concentrated in a cloud network may be used for the image reconstructor 230.

[0056] In one embodiment, the image reconstructor 230 stores the reconstructed image in a storage device or mass storage 218. Alternatively, the image reconstructor 230 transmits the reconstructed image to the computing device 216 to generate patient information for diagnosis and evaluation. In one embodiment, the computing device 216 transmits the reconstructed image and / or the above-mentioned patient information to a display 232, which is communicatively connected to the computing device 216 and / or the image reconstructor 230.

[0057] The methods or processes further described below may be stored as executable instructions in a non-volatile memory on a computing device of the system 200. For example, the computing device 216 may include executable instructions in a non-volatile memory, and may apply the methods described herein to automatically perform part or all of the scanning process, such as selecting a suitable protocol, determining suitable parameters, etc. For another example, the image reconstructor 230 may include executable instructions in a non-volatile memory, and may apply the methods described herein to perform image reconstruction tasks.

[0058] In one embodiment, the display 232 can allow the user to assess the imaging site and allow the user to enter, select or confirm scanning / imaging related protocols or parameters, such as selecting a volume of interest for a subsequent scanning or treatment procedure and / or requesting patient information for the procedure via a graphical user interface.

[0059] Figure 3 A flowchart of a medical imaging method according to an embodiment of the present invention is shown. In one example, the method can be implemented by executing relevant instructions by the computing device 216, for example, by performing a scanning process on the object to obtain image data of the object. The image data can be a visualization image or projection data for image reconstruction.

[0060] like Figure 3 As shown, in one embodiment, the medical imaging method comprises the following steps:

[0061] Step S301: receiving clinical background information of a subject;

[0062] Step S303: determining a scanning protocol based on the clinical background information;

[0063] Step S305: receiving three-dimensional surface information of the object;

[0064] Step S307: analyzing the three-dimensional surface information based on the trained first deep learning network;

[0065] Step S309: positioning the object based on the analysis result of the three-dimensional surface information;

[0066] Step S311: performing a positioning scan to obtain a positioning image;

[0067] Step S313: automatically determining object attributes based on the positioning image;

[0068] Step S315: automatically setting scanning parameters for precise scanning based on the object attributes; and,

[0069] Step S317: Perform precise scanning based on the set scanning parameters.

[0070] The above-mentioned clinical background information may include basic information of clinical examination, for example, the clinical background information may include the anatomical part of the object, for example, the part of clinical examination may be the head, heart, ribs, etc. of the object (patient). The clinical background information may also include clinical purpose, for example, to examine lumbar disc herniation, cardiovascular blockage, etc. The clinical background information may also include one or more of the physical characteristics, such as weight, age, gender, medical history, implant information in the body, etc. The clinical background information may also include auxiliary examination methods, such as whether contrast enhancement agents are used.

[0071] The clinical context information may be received by the computing device 216 via, for example, a console 220 coupled to the computing device 216 or a graphical user interface on a display 232 .

[0072] Each item of clinical background information may correspond individually or collectively to one or more standard scanning protocols for selection, which are pre-stored in the storage device of the system. For example, for head scanning, one or more scanning protocols for cardiac examination may be stored, and one or more scanning protocols for cardiac examination using contrast agent (or not using contrast agent) may also be stored. When the above clinical background information is received through user input or selection in step S301, in step S303, a scanning protocol matching at least one item of clinical background information may be automatically selected. The selected scanning protocol is considered to have one or more sets of optimized scanning parameter settings, so that the patient can be prevented from receiving excessive radiation dose while also having a better quality of the subsequently reconstructed image, such as having better time resolution, material identification accuracy (MDA), contrast-to-noise ratio (CNR), coverage, spatial resolution, artifact suppression properties, etc. Each group of scanning parameter settings may include one or more combinations of the following parameters: for example, tube (X-ray tube) current, tube voltage, Bowtie (X-ray filter) type, etc. related to radiation dose, gantry speed, focal spot size, tilt angle of the examination bed, collimator parameters, etc. related to data acquisition, contrast agent flow rate, flow rate, pressure, scanning delay, etc. related to contrast agent.

[0073] The above-mentioned standard scanning protocols can be determined by experts in related fields based on their experience for different clinical descriptions, and different clinical background information reflected in the clinical descriptions can be linked to one or more sets of standard scanning protocols. In one embodiment, different clinical background information can also be linked to one or more specific scanning parameters, so that when the clinical background information is received in step S301, the relevant scanning parameters can be reorganized in step S303 to obtain a new scanning protocol for selection. For example, the new scanning protocol can be obtained by reorganizing the relevant scanning parameters through an artificial intelligence method.

[0074] The three-dimensional surface received in step S305 may be a three-dimensional image of an object captured by a 3D camera disposed on the rack, which may include RGB information and depth information. For example, before the object enters the scanning cavity of the rack, the 3D camera may capture a 3D image of the object having the three-dimensional surface information, and send the 3D image to, for example, the computing device 216. In step S307, the computing device 216 may call a trained first deep learning network stored in a storage device to analyze the 3D image, so as to at least determine / mark the position of the part to be imaged. In step S309, the object may be positioned based on the determined / marked position, for example, the computing device 216 may control the inspection bed 226 by operating the inspection bed motor controller to control the inspection bed 226 to move to align the center of the part to be scanned of the object with the scanning center. In this way, rapid positioning of the object is achieved, and process redundancy caused by manual positioning is avoided.

[0075] Since the scanning protocol is determined in step S303 and the positioning of the object is achieved in step S309, a positioning scan may be performed on the positioned object based on the determined scanning protocol in step S311 to obtain a positioning image.

[0076] The positioning image obtained in step S311 covers a rough range of the part to be imaged. In the traditional scanning process, the doctor manually sets more precise parameters such as scanning range and scanning angle in the positioning image so that precise scanning can be performed based on the set parameters later. Compared with the positioning image used for positioning, the precise scanning obtains a clear image for the doctor to diagnose or evaluate. In the embodiment of the present invention, the parameter presetting of the precise scanning can be automatically realized by artificial intelligence method.

[0077] For example, in one embodiment, first step 313 can determine the object attributes in the positioning image based on the trained second deep learning network. The second deep learning network can be, for example, obtained by intelligent learning training by using a large number of positioning images with clinical background information as the data input set of the second deep learning network, and using the object attributes marked or determined in each positioning image as the output set of the second deep learning network.

[0078] Figure 4An example of a second deep learning network is shown, which may include an input layer 401, an output layer 403, and at least one hidden layer 405 connected between the input layer and the output layer. For example, the input layer 401 includes a plurality of neurons having a plurality of positioning images, the output layer 403 includes a plurality of neurons having a plurality of positioning images in which object attributes are determined, and the hidden layer 405 includes a plurality of neurons having a plurality of clinical background information related to the positioning images, wherein each neuron of the input layer is connected to one or more neurons in the adjacent hidden layer, and is transmitted layer by layer until it reaches one or more neurons of the output layer. Although Figure 4 An example of one hidden layer 405 is shown, and in other examples, the number of hidden layers 405 may be multiple. In other examples, the second deep learning network may also have other architectures.

[0079] In one embodiment, the object attributes include: the region of interest of the object and / or the anatomical structure features within the region of interest, corresponding to the rougher region of interest determined in the positioning image, and a more precise region of interest can be determined in step S313, ideally covering the part to be examined to avoid applying additional radiation dose to the object. The anatomical structure features may include, for example, the shape, size, position, angle, etc. of the tissue of the part to be imaged. Taking the lumbar intervertebral disc as an example, the anatomical structure features may at least include the center position of the intervertebral disc and the inclination angle of its center line.

[0080] In one embodiment, the scanning parameters for precise scanning include scanning range and / or scanning angle. After the above-mentioned region of interest and / or anatomical structure features are determined in the positioning image, corresponding scanning parameters can be determined / set in step S315 for subsequent precise scanning. Taking the above-mentioned lumbar intervertebral disc as an example, parameters related to the scanning range, such as the size of the collimator opening, can be set based on the region of interest determined in the positioning image, and parameters related to the scanning angle can be determined based on the determined anatomical structure features, such as setting the inclination angle of the examination bed to correspond to the inclination angle of the centerline of the intervertebral disc so as to obtain an examination image that is easier to evaluate.

[0081] Through the above method, the scanning parameters can be set automatically and accurately, avoiding image quality or patient dose problems caused by doctors' experience-based settings.

[0082] In step S313, the body size standard of the object can also be determined by, for example, calculating the size of the emotional interest area determined in the positioning image, that is, the object attribute determined in the positioning image also includes the body size standard of the object, for example, the body size standard can be divided into three categories: large, medium, and small. Each scanning parameter can include multiple sub-value sets corresponding to different body size standards. For example, for the scanning dose, there can be a general value set, a larger value set, and a smaller value set. The parameter values ​​in these value sets can be set as dose parameter values ​​for medium-sized, large-sized, and small-sized objects, respectively.

[0083] At this time, step S315 may also include the following steps: selecting a sub-value set corresponding to the body size standard of the subject; and determining parameter values ​​of scanning parameters for accurate scanning in the selected sub-value set. In this way, suitable scanning parameters are automatically provided for patients of different body sizes without the need for doctors to observe and set manually through naked eyes.

[0084] When step S317 is executed, appropriate projection data may be obtained, and a reconstructed image obtained based on the projection data has good quality to facilitate examination or evaluation by a doctor.

[0085] Figure 5 A flow chart of a medical imaging method according to another embodiment of the present invention is shown. In one embodiment, in addition to determining scanning parameters for precise scanning based on patient attributes determined in a positioning image, scanning parameters can also be automatically set based on the image quality and / or radiation dose to be achieved. Figure 5 Compared with the embodiment shown Figure 3 The embodiment shown is different in that the following steps may also be included:

[0086] Step S501: receiving a target indication related to image quality and / or radiation dose;

[0087] Step S503: Automatically setting scanning parameters for precise scanning based on the target indication.

[0088] As mentioned above, target indications related to image quality may include indicator values ​​regarding temporal resolution, MDA, CNR, coverage, spatial resolution, artifact suppression properties, etc. input / selected by the user. In one embodiment, different indicator values / levels / ranges may be linked to relevant scanning parameters. When an indicator indication is received, the linked scanning parameters are selected (or selected based on weights) as appropriate for precise scanning.

[0089] In this way, an optimized trade-off between image quality and radiation dose can be further achieved.

[0090] In the above-mentioned embodiment of the present invention, during the entire process from receiving clinical background information to starting the scanning process until completing the precise scanning of the object, the user does not need to perform any setting actions, so that the scanning process can be completed within a few seconds. In addition, the scanning protocol is automatically determined based on the clinical background information, the object properties are automatically determined in the positioning image using an intelligent learning method, and appropriate scanning parameters are configured based on the object properties, so that the parameter settings in the scanning process are associated with clinical needs, thereby achieving optimized scanning parameter configuration.

[0091] Some exemplary embodiments have been described above, however, it should be understood that various modifications may be made. For example, if the described techniques are performed in a different order and / or if the components in the described systems, architectures, devices, or circuits are combined in different ways and / or replaced or supplemented by other components or their equivalents, suitable results may be achieved. Accordingly, other implementations also fall within the scope of protection of the claims.

Claims

1. A medical imaging method, comprising: Receive the subject's clinical background information; automatically determining a scanning protocol based on the clinical background information; receiving three-dimensional surface information of the object; Analyzing the three-dimensional surface information based on the trained first deep learning network; Positioning the object based on the analysis result of the three-dimensional surface information; performing a scout scan to obtain a scout image; Automatically determining object properties based on the scout image, including determining object properties in the scout image based on a trained second deep learning network, the object properties including anatomical features within a region of interest of the object; automatically setting scanning parameters for accurate scanning based on the object attributes; receiving target indications related to image quality and / or radiation dose; setting scanning parameters for precise scanning based on the target indication; and Performs precise scanning based on the set scanning parameters.

2. The method according to claim 1, characterized in that The clinical background information includes one or more of the anatomical part, clinical purpose, and physical characteristics of the subject.

3. The method according to claim 1, characterized in that The second deep learning network includes an input layer, an output layer, and at least one hidden layer connected between the input layer and the output layer, the input layer includes a plurality of neurons having a plurality of positioning images, the output layer includes a plurality of neurons having a plurality of positioning images in which object attributes are determined, and the hidden layer includes a plurality of neurons having a plurality of clinical background information related to the positioning images.

4. The method according to claim 1, characterized in that: The scanning parameters for precise scanning include a scanning range and / or a scanning angle.

5. The method according to claim 1, characterized in that: The object attributes automatically determined based on the positioning image include a body size standard of the object, each scanning parameter includes a plurality of sub-value sets corresponding to different body size standards, and the step of automatically setting the scanning parameters based on the object attributes further includes: selecting a sub-value set corresponding to the body size standard of the subject; and, Parameter values ​​of scanning parameters of the fine scanning are determined in the selected sub-value set.

6. A medical imaging system comprising: An X-ray source for radiating X-rays toward a subject; a detector, for receiving the X-rays attenuated by the object; a data acquisition system for acquiring and digitizing the attenuated X-rays; and, A computing device, configured to execute instructions in a non-volatile memory to implement the method according to any one of claims 1 to 5.

7. The system according to claim 6, characterized in that The invention also includes an operation console connected to the computing device, wherein the computing device receives clinical background information of the subject through the operation console.

8. The system according to claim 6, characterized in that Also included is a display connected to the computing device, wherein the computing device receives clinical background information of the subject via a graphical user interface on the display.

Images