Medical image acquisition method, device and computer equipment

Abstract

The present application relates to a medical image acquisition method, device and computer equipment, wherein the medical image acquisition method includes: acquiring the identity information of a scanned object and a first image of the scanned object, the first image being acquired by a camera device; inputting the first image into a trained neural network to obtain a first positioning image, the first positioning image being a two-dimensional plane image of the scanned object; acquiring a second positioning image of the scanned object stored in a database based on the identity information; and aligning the first positioning image and the second positioning image to obtain a third positioning image. The above-mentioned medical image acquisition method, device and computer equipment acquire the first positioning image through the placement position information of the scanned object, and compare it with the second positioning image in the database, and obtain the third positioning image after alignment. Therefore, when the scanned object is scanned again, there is no need to acquire the positioning image again, which is efficient and reduces radiation damage to the scanned object.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a medical image acquisition method, device and computer equipment. Background Art

[0002] In the PET-CT workflow, the conventional scanning process is: the scanned object is scanned according to a certain body position and parameters to obtain a set of CT positioning images as positioning films, and the positioning planning is carried out according to the positioning films. Then the scanned object is positioned, and the PET scan is performed after the positioning is accurate, so as to make the scanning position more accurate and the imaging effect better.

[0003] However, the next recheck scan or rescan of the same scanned object requires the acquisition of the positioning image again, which is inefficient. In addition, CT scanning involves radiation, which may cause a certain degree of radiation damage to the scanned object.

[0004] Currently, no effective solution has been proposed for the problem that in the related technology, each time a scanning object is scanned, a positioning image needs to be acquired again, which is inefficient and may cause a certain degree of radiation damage to the scanning object. Summary of the invention

[0005] The embodiments of the present application provide a medical image acquisition method, apparatus and computer device to at least solve the problem in the related art that a positioning image needs to be acquired again each time a scanned object is scanned, which is inefficient and may cause a certain degree of radiation damage to the scanned object.

[0006] In a first aspect, an embodiment of the present application provides a medical image acquisition method, comprising:

[0007] Acquire identity information of a scanned object and a first image of the scanned object, where the first image is acquired by a camera device;

[0008] Inputting the first image into a trained neural network to obtain a first positioning image, where the first positioning image is a two-dimensional plane image of the scanned object;

[0009] Acquire a second positioning image of the scanned object stored in a database based on the identity information;

[0010] The first positioning image and the second positioning image are registered to obtain a third positioning image.

[0011] In some embodiments, the medical image acquisition method further comprises:

[0012] Selecting a scanning start position and a scanning end position on the third positioning image;

[0013] Determine the scanning range according to the scanning starting position and the scanning ending position;

[0014] The scanning object is scanned based on the scanning range.

[0015] In some embodiments, the medical image acquisition method further comprises:

[0016] The second positioning image is compared with the third positioning image, and it is determined whether the body position of the scanned object needs to be adjusted according to the comparison result.

[0017] In some embodiments, comparing the second positioning image with the third positioning image and determining whether the body position of the scanned object needs to be adjusted according to the comparison result includes:

[0018] Comparing the second positioning image with the third positioning image to obtain a position difference;

[0019] Comparing the position difference with a preset threshold;

[0020] If the position difference is greater than the preset threshold, the body position of the scanned object needs to be adjusted.

[0021] In some embodiments, the position difference includes an X-direction difference, a Y-direction difference, and a Z-direction difference, and comparing the position difference with a preset threshold value further includes:

[0022] The X-direction difference, the Y-direction difference and the Z-direction difference are respectively compared with the preset thresholds;

[0023] If the difference in any direction is greater than the preset threshold, the body position of the scanned object needs to be adjusted.

[0024] In some embodiments, before inputting the first image into a trained neural network to obtain a first scout image, the process further includes:

[0025] Acquire a first training image and a corresponding first training positioning image;

[0026] Establishing a training set based on the first training image and the first training positioning image;

[0027] An initial neural network model is trained based on the training set to obtain a trained neural network.

[0028] In some of these embodiments, the initial neural network model includes a conditional generative adversarial network model.

[0029] In some embodiments, the medical image acquisition method further comprises:

[0030] The first positioning image and the second positioning image are sent to a host computer for display.

[0031] In a second aspect, an embodiment of the present application provides a medical image acquisition device, comprising:

[0032] An acquisition module, used to acquire identity information of a scanned object and a first image of the scanned object, wherein the first image is acquired by a camera device;

[0033] A positioning module, used for inputting the first image into a trained neural network to obtain a first positioning image, where the first positioning image is a two-dimensional plane image of the scanned object;

[0034] A historical image acquisition module, used for acquiring a second positioning image of the scanned object stored in a database based on the identity information;

[0035] The registration module is used to register the first positioning image and the second positioning image to obtain a third positioning image.

[0036] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the medical image acquisition method as described in the first aspect above is implemented.

[0037] Compared with the related art, the medical image acquisition method, apparatus and computer equipment provided in the embodiments of the present application obtain the identity information of the scanned object and a first image of the scanned object, wherein the first image is obtained by a camera device; the first image is input into a trained neural network to obtain a first positioning image, which is a two-dimensional plane image of the scanned object; based on the identity information, a second positioning image of the scanned object stored in a database is obtained; the first positioning image and the second positioning image are registered to obtain a third positioning image, in which the first positioning image is obtained through the placement position information of the scanned object, and the image is compared with the second positioning image in the database, and the third positioning image is obtained after registration. When the scanned object is scanned again, there is no need to obtain a positioning image, which is more efficient and reduces radiation damage to the scanned object.

[0038] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0040] Figure 1 A schematic diagram of a flow chart of a medical image acquisition method according to an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of a flow chart of a medical image acquisition method according to another embodiment of the present invention;

[0042] Figure 3 is a structural block diagram of a medical image acquisition device according to an embodiment of the present invention;

[0043] Figure 4 The figure is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0045] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0046] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0047] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0048] The positioning image is a complete outline image of the scanned object. Each clinical protocol of the hospital contains a positioning image for the target to be detected. The positioning image is obtained by keeping the tube stationary at a preset position and not rotating, and only controlling the bed to move parallel to the z direction during scanning to obtain the positioning image. The positioning image can assist the physician in setting the starting position and scanning length of the tomography or spiral scanning, adjusting the scanning range, and providing a reference for reducing the radiation dose of the tomography or spiral scanning.

[0049] Traditional scanning methods require a pre-scan every time the scanned object is scanned to obtain a positioning image. After obtaining the positioning image, the doctor determines the area that needs to be focused on in the positioning image and uses the corresponding area as the region of interest to determine the scanning range. This not only reduces the scanning efficiency, but the process of obtaining the positioning image can also cause radiation damage to the scanned object.

[0050] See also Figure 1 , Figure 1 FIG. 4 is a flow chart of a medical image acquisition method according to an embodiment of the present invention.

[0051] In this embodiment, the medical image acquisition method includes:

[0052] S101, obtaining identity information of a scanned object and a first image of the scanned object, where the first image is obtained by a camera device.

[0053] Exemplarily, when the scanned object is scanned for the first time, a scan record will be left in the system, and the scan record includes the identity information of the scanned object. It is understandable that the identity information is the unique identification information of the scanned object, which can be an ID card number or a medical consultation number, etc., and it only needs to play the role of identifying the identity of the scanned object. In this embodiment, the first image is obtained by a camera device, which is used to show the external state of the scanned object, such as the placement information of the scanned object. It is understandable that the camera device can be a visible light camera or an infrared camera, or other camera devices, as long as it can obtain the external state of the scanned object.

[0054] S102, inputting the first image into a trained neural network to obtain a first positioning image, where the first positioning image is a two-dimensional plane image of the scanned object.

[0055] It can be understood that after the initial neural network model is trained, it can obtain a two-dimensional plane image representing the complete outline of the scanned object, namely, the first positioning image, based on the input first image through analysis and processing.

[0056] S103: Acquire a second positioning image of the scanned object stored in a database based on the identity information.

[0057] Exemplarily, when the scanned object is scanned for the first time, a pre-scan is performed to obtain a positioning image, namely a second positioning image. The second positioning image is stored in a database and bound to the identity information of the scanned object. The second positioning image can be obtained from the database through the identity information.

[0058] S104, registering the first positioning image and the second positioning image to obtain a third positioning image.

[0059] In this embodiment, the first positioning image is a current positioning image obtained through a neural network based on the current external state of the scanned object, and the second positioning image is a historical positioning image obtained through a pre-scan and stored in a database. It can be understood that the first positioning image is not an actual positioning image obtained through a pre-scan, so there is a certain deviation. The first positioning image and the second positioning image are registered to correct the deviation of the first positioning image, and a third positioning image after the deviation is corrected is obtained for subsequent scanning or other operations.

[0060] The above-mentioned medical image acquisition method obtains the identity information of the scanned object and the first image of the scanned object, and the first image is obtained by a camera device; the first image is input into a trained neural network to obtain a first positioning image, and the first positioning image is a two-dimensional plane image of the scanned object; based on the identity information, a second positioning image of the scanned object stored in a database is obtained; the first positioning image and the second positioning image are registered to obtain a third positioning image. The first positioning image is obtained through the placement position information of the scanned object, and is compared with the second positioning image in the database. After the registration, the third positioning image is obtained. Therefore, when the scanned object is scanned again, there is no need to obtain the positioning image again, which is efficient and reduces radiation damage to the scanned object.

[0061] In another embodiment, the medical image acquisition method further comprises the following steps:

[0062] Step 1, selecting a scanning start position and a scanning end position on the third positioning image;

[0063] Step 2, determining the scanning range according to the scanning start position and the scanning end position;

[0064] Step 3: Scan the scan object based on the scan range.

[0065] For example, before scanning, the physician determines the area that needs to be observed through the positioning image, and uses the corresponding area as the region of interest to determine the scanning range. Therefore, after obtaining the third positioning image representing the complete outline of the scanned object, the scanning start position and the scanning end position are delineated based on the scanning requirements and the actual situation of the scanned object, and the scanning is performed with the range framed by the scanning start position and the scanning end position as the scanning range.

[0066] In this embodiment, the medical image acquisition method can be applied in a PET-CT system, that is, firstly obtain a first positioning image through a first image, obtain a second positioning image through identity information, and obtain a third positioning image based on the first positioning image and the second positioning image, and then define a scanning range on the third positioning image according to scanning requirements to perform a PET scan. It can be understood that the above medical image acquisition method can be applied not only in a PET-CT system, but also in any scanning scenario where a positioning image needs to be obtained, and is not specifically limited here.

[0067] In another embodiment, the medical image acquisition method further comprises the following steps:

[0068] The second positioning image is compared with the third positioning image, and it is determined whether the body position of the scanned object needs to be adjusted according to the comparison result.

[0069] It is understandable that after obtaining the third positioning image, it is necessary to determine the scanning range based on the third positioning image for scanning. The scanning range can be re-planned based on the third positioning image, or the position of the scanning object can be adjusted based on the second positioning image to directly use the scanning range planning corresponding to the second positioning image for scanning.

[0070] Illustratively, the second positioning image not only represents the complete outline of the scanned object, but also performs scanning range planning. Therefore, if the second positioning image and the third positioning image can match well, it means that the current body position of the scanned object is basically consistent with the body position corresponding to the second positioning image, and the scanning range planning corresponding to the second positioning image can be directly used for scanning without re-planning the scanning range; if the matching cannot be completed, it means that the body position of the scanned object needs to be adjusted.

[0071] In another embodiment, comparing the second positioning image with the third positioning image, and determining whether the body position of the scanned object needs to be adjusted according to the comparison result includes the following steps:

[0072] Step 1, comparing the second positioning image and the third positioning image to obtain a position difference;

[0073] Step 2, comparing the position difference with a preset threshold;

[0074] Step 3: If the position difference is greater than a preset threshold, the body position of the scanned object needs to be adjusted.

[0075] Exemplarily, the position difference is the deviation value between the second positioning image and the third positioning image in each direction. The preset threshold can be set in advance by the user. If the deviation value is within the preset threshold, it means that the deviation is small, and the scanning range planning corresponding to the second positioning image can still be directly adopted; if the deviation value is greater than the preset threshold, it means that the deviation is large, and the body position of the scanned object needs to be adjusted to match the second positioning image.

[0076] This embodiment sets a preset threshold as a standard and compares it with the position difference to judge the matching degree between the second positioning image and the third positioning image. It does not need that the two completely correspond to each other to determine the match, but rather it determines the match when the difference is within the threshold range, which is more adaptable.

[0077] In another embodiment, the position difference includes an X-direction difference, a Y-direction difference, and a Z-direction difference, and comparing the position difference with a preset threshold value further includes the following steps:

[0078] Step 1, respectively comparing the X-direction difference, the Y-direction difference and the Z-direction difference with a preset threshold;

[0079] Step 2: If the difference in any direction is greater than a preset threshold, the body position of the scanned object needs to be adjusted.

[0080] In this embodiment, the second positioning image and the third positioning image are compared to obtain the position difference, including obtaining a transformation matrix based on key points of the second positioning image and the third positioning image, and obtaining the position difference based on the transformation matrix. Specifically, the rigid registration has 9 parameters, including X, Y, Z and rotation angles in various directions, and the difference between various parameters of the second positioning image and the third positioning image can be obtained based on the transformation matrix.

[0081] It can be understood that the position difference includes the difference in the X direction, the difference in the Y direction, and the difference in the Z direction. If the difference in any direction is greater than the preset threshold, it means that the deviation is too large, and the body position of the scanned object in the corresponding direction needs to be adjusted to match the second positioning image. Only when the differences in the three directions are within the preset threshold range, the second positioning image and the third positioning image are successfully matched, and the scanning range planning corresponding to the second positioning image can be directly used for scanning. In other embodiments, the difference in other directions or dimensions can be used as a judgment standard, as long as the degree of deviation of the scanned object's position can be judged.

[0082] This embodiment uses the X-direction difference, the Y-direction difference and the Z-direction difference as the position difference, and compares them with the preset threshold to judge the matching degree between the second positioning image and the third positioning image. Only when the differences in the three directions are within the preset range, it is considered a match, which makes the comparison more accurate and the scanning effect better.

[0083] In another embodiment, the step of inputting the first image into the trained neural network to obtain the first scout image further includes the following steps:

[0084] Step 1, obtaining a first training image and a corresponding first training positioning image;

[0085] Step 2, establishing a training set based on the first training image and the first training positioning image;

[0086] Step 3: Train the initial neural network model based on the training set to obtain a trained neural network.

[0087] Among them, the first training image is a training image obtained by a camera device, and the corresponding first training positioning image is a positioning image obtained by pre-scanning the scanned object when the scanned object is in the position of the first training image. It can be understood that the first training image and the first training positioning image are both known data. In this embodiment, after the initial neural network model is trained with a training set consisting of the first training image and the first training positioning image, it only needs to input the first image representing the external state of the user obtained by the camera device to output the first positioning image of the corresponding position of the scanned object.

[0088] In another embodiment, the initial neural network model includes a conditional generative adversarial network (CGAN) model. In other embodiments, other neural network models can be selected as the initial neural network model, which can be selected by the user according to actual conditions.

[0089] In another embodiment, the medical image acquisition method further comprises the following steps:

[0090] The first positioning image and the second positioning image are sent to the host computer for display.

[0091] Exemplarily, the first positioning image and the second positioning image are sent to a host computer for real-time display, and the user can compare them in real time and make corresponding adjustments, so that the registration result is more accurate.

[0092] In another embodiment, key point information can also be obtained based on the first positioning image, that is, multiple key points are obtained based on the first positioning image, and the multiple key points are connected to form a key point schematic diagram, and the key point schematic diagram and the second positioning image are sent to the host computer for display.

[0093] In this embodiment, the key point schematic diagram and the second positioning image are sent to the host computer for real-time display, so that the comparison is more intuitive and the registration effect is more accurate.

[0094] See also Figure 2 , Figure 2 FIG. 4 is a flow chart of a medical image acquisition method according to another embodiment of the present invention.

[0095] In this embodiment, the patient first registers before scanning, obtains the patient's identity information from the registration information, and determines whether the identity information exists in the database. If the identity information does not exist in the database, the scanning is performed using the traditional scanning process. If the identity information exists in the database, the camera is turned on to take a full-body photo of the patient, and the full-body photo of the patient and related information are sent to the memory. The full-body photo of the patient is input into the trained neural network to obtain a first positioning image. At the same time, based on the patient's identity information, a second positioning image is read from the database, and the first positioning image is aligned with the second positioning image to obtain a third positioning image. The second positioning image and the third positioning image are compared, and it is determined whether the patient's position needs to be adjusted based on the comparison result. If adjustment is required, the patient is guided to adjust the position, and a PET scan is performed after the adjustment is completed.

[0096] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0097] This embodiment also provides a medical image acquisition device, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module", "unit", "subunit", etc. may be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0098] Figure 3 is a structural block diagram of a medical image acquisition device according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0099] The acquisition module 10 is used to acquire the identity information of the scanned object and a first image of the scanned object, where the first image is acquired by a camera device.

[0100] The positioning module 20 is used to input the first image into the trained neural network to obtain a first positioning image, which is a two-dimensional plane image of the scanned object.

[0101] The historical image acquisition module 30 is used to acquire a second positioning image of the scanned object stored in the database based on the identity information.

[0102] The registration module 40 is used to register the first positioning image and the second positioning image to obtain a third positioning image.

[0103] The medical image acquisition device also includes: a scanning module.

[0104] Scanning module for:

[0105] Selecting a scanning start position and a scanning end position on the third positioning image;

[0106] Determine the scanning range according to the scanning start position and the scanning end position;

[0107] The scanning object is scanned based on the scanning range.

[0108] The medical image acquisition device also includes: a comparison module.

[0109] The comparison module is used to compare the second positioning image with the third positioning image, and determine whether the body position of the scanned object needs to be adjusted according to the comparison result.

[0110] The comparison module is also used to:

[0111] Compare the second positioning image with the third positioning image to obtain a position difference;

[0112] Compare the position difference with a preset threshold;

[0113] If the position difference is greater than a preset threshold, the body position of the scanned object needs to be adjusted.

[0114] The comparison module is also used to:

[0115] The X-direction difference, the Y-direction difference and the Z-direction difference are respectively compared with the preset thresholds;

[0116] If the difference in any direction is greater than a preset threshold, the position of the scanned object needs to be adjusted.

[0117] The medical image acquisition device also includes: a training module.

[0118] Training modules for:

[0119] Acquire a first training image and a corresponding first training positioning image;

[0120] Establishing a training set based on the first training image and the first training positioning image;

[0121] An initial neural network model is trained based on the training set to obtain a trained neural network.

[0122] The medical image acquisition device also includes: a display module.

[0123] The display module is used to send the first positioning image and the second positioning image to the host computer for display.

[0124] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0125] In addition, combined Figure 1 The medical image acquisition method described in the embodiment of the present application can be implemented by a computer device. Figure 4 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0126] The computer device may include a processor 51 and a memory 52 storing computer program instructions.

[0127] Specifically, the processor 51 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0128] Among them, the memory 52 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 52 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 52 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 52 may be inside or outside the data processing device. In a specific embodiment, the memory 52 is a non-volatile memory. In a specific embodiment, the memory 52 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0129] The memory 52 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 51 .

[0130] The processor 51 implements any one of the medical image acquisition methods in the above embodiments by reading and executing computer program instructions stored in the memory 52 .

[0131] In some of the embodiments, the computer device may further include a communication interface 53 and a bus 50. Figure 4 As shown, the processor 51, the memory 52, and the communication interface 53 are connected via a bus 50 and communicate with each other.

[0132] The communication interface 53 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication interface 53 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0133] The bus 50 includes hardware, software or both, and couples the components of the computer device to each other. The bus 50 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 50 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 50 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0134] The computer device can execute the medical image acquisition method in the embodiment of the present application based on the acquired computer program instructions, thereby realizing the combination Figure 1 A method for acquiring a medical image is described.

[0135] In addition, in combination with the medical image acquisition method in the above embodiments, the present application embodiment may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the medical image acquisition methods in the above embodiments is implemented.

[0136] The above-mentioned medical image acquisition method, device and computer equipment obtain the identity information of the scanned object and the first image of the scanned object, the first image is obtained by a camera device; the first image is input into a trained neural network to obtain a first positioning image, the first positioning image is a two-dimensional plane image of the scanned object; based on the identity information, a second positioning image of the scanned object stored in a database is obtained; the first positioning image and the second positioning image are registered to obtain a third positioning image, the first positioning image is obtained through the placement position information of the scanned object, and is compared with the second positioning image in the database, and the third positioning image is obtained after registration. When the scanned object is scanned again, there is no need to obtain a positioning image again, the efficiency is high, and the radiation damage to the scanned object is reduced.

[0137] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A medical image acquisition method, characterized in that: include: Acquire identity information of a scanned object and a first image of the scanned object, where the first image is acquired by a camera device; Inputting the first image into a trained neural network to obtain a first positioning image, wherein the first positioning image is a two-dimensional plane image of the complete outline of the scanned object; Acquire a second positioning image of the scanned object stored in a database based on the identity information; Registering the first locator image with the second locator image to correct the deviation of the first locator image to obtain a third locator image; comparing the second positioning image with the third positioning image, and determining whether the body position of the scanned object needs to be adjusted according to the comparison result; The comparing of the second positioning image and the third positioning image and determining whether the body position of the scanned object needs to be adjusted according to the comparison result includes: comparing the second positioning image and the third positioning image to obtain a position difference; comparing the position difference with a preset threshold; if the position difference is greater than the preset threshold, the body position of the scanned object needs to be adjusted; the comparing of the second positioning image and the third positioning image to obtain the position difference includes: obtaining a transformation matrix based on key points of the second positioning image and the third positioning image, and obtaining the position difference based on the transformation matrix.

2. The medical image acquisition method according to claim 1, characterized in that: The medical image acquisition method further comprises: Selecting a scanning start position and a scanning end position on the third positioning image; Determine the scanning range according to the scanning starting position and the scanning ending position; The scanning object is scanned based on the scanning range.

3. The medical image acquisition method according to claim 1, characterized in that: The position difference includes an X-direction difference, a Y-direction difference, and a Z-direction difference, and comparing the position difference with a preset threshold value further includes: The X-direction difference, the Y-direction difference and the Z-direction difference are respectively compared with the preset thresholds; If the difference in any direction is greater than the preset threshold, the body position of the scanned object needs to be adjusted.

4. The medical image acquisition method according to claim 1, characterized in that: Before inputting the first image into a trained neural network to obtain a first locator image, the method further includes: Acquire a first training image and a corresponding first training positioning image; Establishing a training set based on the first training image and the first training positioning image; An initial neural network model is trained based on the training set to obtain a trained neural network.

5. The medical image acquisition method according to claim 4, characterized in that: The initial neural network model includes a conditional generative adversarial network model.

6. The medical image acquisition method according to claim 1, characterized in that: The medical image acquisition method further comprises: The first positioning image and the second positioning image are sent to a host computer for display.

7. A medical image acquisition device, characterized in that: include: An acquisition module, used to acquire identity information of a scanned object and a first image of the scanned object, wherein the first image is acquired by a camera device; A positioning module, used for inputting the first image into a trained neural network to obtain a first positioning image, wherein the first positioning image is a two-dimensional plane image of the complete outline of the scanned object; A historical image acquisition module, used for acquiring a second positioning image of the scanned object stored in a database based on the identity information; A registration module, used for registering the first positioning image and the second positioning image to correct the deviation of the first positioning image and obtain a third positioning image; A comparison module, used for comparing the second positioning image with the third positioning image, and determining whether the body position of the scanned object needs to be adjusted according to the comparison result; The comparing of the second positioning image and the third positioning image and determining whether the body position of the scanned object needs to be adjusted according to the comparison result includes: comparing the second positioning image and the third positioning image to obtain a position difference; comparing the position difference with a preset threshold; if the position difference is greater than the preset threshold, the body position of the scanned object needs to be adjusted; the comparing of the second positioning image and the third positioning image to obtain the position difference includes: obtaining a transformation matrix based on key points of the second positioning image and the third positioning image, and obtaining the position difference based on the transformation matrix.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the medical image acquisition method according to any one of claims 1 to 6 is implemented.

Images