Medical scanning imaging method, device and system

Abstract

The present invention relates to a medical scanning imaging method, comprising: obtaining an initial medical image of a scanned object based on an initial scanning frame; obtaining a visible light image of the scanned object; fusing the visible light image and the initial medical image to obtain a positioning guidance map; adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame; and performing medical imaging scanning on the scanned object based on the imaging scanning frame. The present invention can automatically adjust the scanning range for a specific scanned object, does not require manual positioning, and can adapt to individual differences.

Description

Technical Field

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

[0002] DICOM (Digital Imaging and Communications in Medicine) is an international standard for medical images and related information (ISO 12052). It defines a medical image format that can be used for data exchange with quality that meets clinical needs. DICOM is widely used in radiology, cardiovascular imaging, and radiology diagnostic equipment (X-ray, CT, MR, ultrasound, etc.), and is increasingly used in other medical fields such as ophthalmology and dentistry. Among the tens of thousands of medical imaging devices in use, DICOM is one of the most widely deployed medical information standards. Currently, there are about tens of billions of medical images that meet the DICOM standard for clinical use.

[0003] In the current hospital situation, the physiological structure formed by DICOM scanning Figure 1 It is generally used to locate various physiological positions and determine the condition of the lesion, providing guidance for image placement. DICOM data is generally post-processed data, which is a 2D or 3D matrix generated after acquisition and reconstruction.

[0004] The operator guides the scanning object's positioning in order to obtain more effective reconstruction data, such as a full-scale scan of the body and more accurate positioning of lesions. However, the current hospital's reference standards for positioning guidance are generally limited to video imaging guidance or AI intelligent positioning, and the influence of individual differences cannot be eliminated. Summary of the invention

[0005] In view of this, it is necessary to provide a medical scanning imaging method, device and system to solve the problem that current medical scanning cannot accurately locate the target scanning position of the scanned object, relies on the accurate positioning of the scanned object, and cannot eliminate the influence of individual differences.

[0006] An embodiment of the present invention provides a medical scanning imaging method, comprising:

[0007] Acquire an initial medical image of the scanned object based on the initial scanning frame;

[0008] Acquire a visible light image of the scanned object;

[0009] fusing the visible light image and the initial medical image to obtain a positioning guidance map;

[0010] Adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame;

[0011] A medical imaging scan is performed on the scan object based on the imaging scanning frame.

[0012] In another embodiment of the method, the method further comprises: setting an initial scanning frame;

[0013] The setting scanning frame includes:

[0014] Set scanning frame samples of different kinds of animals and establish a scanning frame database;

[0015] The type of the scan object is obtained, and a scan frame sample corresponding to the scan object is selected from the scan frame database to obtain the initial scan frame.

[0016] In another embodiment of the method, the setting of scanning frame samples for different types of animals includes:

[0017] Set the center point and size of the scanning frame according to the animal species;

[0018] The scanning frame is divided into a plurality of sub-frames for a plurality of scanning targets, and a relative position relationship between the plurality of sub-frames is set to obtain the scanning frame sample.

[0019] In another embodiment of the method, the type of the scanned object obtained includes:

[0020] The type of the scanned object is identified according to the visible light image.

[0021] In another embodiment of the method, acquiring a visible light image of the scanned object includes:

[0022] A video stream of the scanned object is acquired, and a frame in the video stream corresponding to the scanning moment of the initial medical image is acquired as the visible light image.

[0023] In another embodiment of the method, fusing the visible light image and the initial medical image to obtain a positioning guidance map includes:

[0024] respectively acquiring feature points of the visible light image and the initial medical image;

[0025] Performing point cloud registration on the visible light image and the initial medical image based on the feature points to obtain a rotation angle and a translation amount between the visible light image and the initial medical image;

[0026] Adjusting the relative positions of the visible light image and the initial medical image based on the rotation angle and the translation amount;

[0027] The visible light image and the initial medical image are pixel-superimposed to obtain the positioning guidance map.

[0028] In another embodiment of the method, adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame includes:

[0029] Setting a target scanning frame according to the initial medical image portion in the positioning guidance map;

[0030] Calculating a deviation value between the target scanning frame and the initial scanning frame;

[0031] The initial scanning frame is adjusted based on the deviation value to obtain the target scanning frame.

[0032] In another embodiment of the method, before performing medical imaging on the scanned object based on the imaging scanning frame, the method further includes:

[0033] Marking the imaging scanning frame on the scanning object, and acquiring a visible light marking image including the imaging scanning frame mark;

[0034] By comparing the visible light mark image with the positioning guidance map, it is determined whether the scanned object has moved. If it has moved, the imaging scan frame is re-determined, otherwise the scanned object is scanned for medical images with the current imaging scan frame.

[0035] Another embodiment of the present invention further provides a medical scanning imaging device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the medical scanning imaging method is implemented.

[0036] Another embodiment of the present invention further provides a medical scanning imaging system, comprising the medical scanning imaging device, a medical imaging device and a visible light image acquisition device;

[0037] The medical imaging device is used to scan the scan object based on the initial scanning frame to obtain an initial medical image, and send the initial medical image to the medical scanning imaging device;

[0038] The visible light image acquisition device is used to collect a visible light image of the scanned object and send the visible light image to the medical scanning imaging device;

[0039] The medical scanning imaging device is used to obtain the imaging scanning frame based on the initial medical image and the visible light image by using the medical scanning imaging method, and send the imaging scanning frame to the medical imaging device;

[0040] The medical imaging device is used to perform medical imaging scanning on a scanning object based on the imaging scanning frame.

[0041] Beneficial effects: The present invention first obtains the initial medical image of the scanned object based on the initial scanning frame, and at the same time obtains the visible light image of the scanned object. These two images respectively describe the internal physiological structure of the scanned object and the visualized external body structure. In order to accurately mark the clinical scanning range including the scanned target on the external body of the scanned object, the medical image that can describe the internal physiological structure is fused into the visible light image, thereby realizing the visualization of the relative position relationship between the internal physiological structure and the external body structure of the scanned object. Under the premise of visualizing the internal physiological structure, the initial scanning frame is adjusted to obtain the imaging scanning frame, thereby ensuring that the scanning target can be accurately included in the imaging scanning frame. Finally, the medical image is scanned based on the imaging scanning frame to ensure the accuracy of the scanning. The present invention realizes the automatic adjustment and positioning of the imaging scanning frame, avoids the process of positioning the scanned object based on experience during the scanning process, and eliminates the dependence of the scanning effect on the accuracy of the artificial positioning. At the same time, the scanning range can be automatically adjusted, eliminating the individual differences existing when the scanning is performed based on experience, and setting the corresponding imaging scanning frame for a specific scanning object to obtain the most suitable and accurate scanning effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A method flow chart of a first embodiment of the medical scanning imaging method provided by the present invention;

[0043] Figure 2 This is a system architecture diagram of the first embodiment of the medical scanning imaging system provided by the present invention. DETAILED DESCRIPTION

[0044] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0045] like Figure 1 As shown, one embodiment of the present invention provides a medical scanning imaging method, hereinafter referred to as the method, comprising:

[0046] S1, acquiring an initial medical image of the scanned object based on an initial scanning frame;

[0047] S2, obtaining a visible light image of the scanned object;

[0048] S3, fusing the visible light image and the initial medical image to obtain a positioning guidance map;

[0049] S4, adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame;

[0050] S5. Perform a medical imaging scan on the scan object based on the imaging scanning frame.

[0051] At present, when performing medical imaging scans, it is difficult to determine the position of the scanned object in the scan. In existing applications, because there is no real-time internal physiological structure positioning map to assist the operator in determining the scanning position in a visual way, the position is more dependent on the operator's naked eyes and intuition, which will lead to deviations in the final imaging and fail to obtain clear and effective medical images. This method proposes an effective way to visually help the operator determine the physiological position of the scanned object of interest, and at the same time, a more accurate and reliable imaging scan frame is defined based on the fused positioning guidance map.

[0052] Specifically, firstly, the initial medical image of the scanned object is obtained based on the initial scanning frame. The medical image may be a CT scout image of the scanned object. Meanwhile, the visible light image of the scanned object is obtained. The two images respectively describe the invisible internal physiological structure and the visible external body structure of the scanned object. In order to accurately locate the clinical scanning range where the scanned object is located on the external body of the scanned object, the initial medical image that can describe the internal physiological structure is fused into the visible light image, thereby realizing the visualization of the relative position relationship between the internal physiological structure and the external body structure of the scanned object, and obtaining a positioning guidance map. Based on the positioning guidance map, the initial scanning frame is adjusted on the premise of visualizing the internal physiological structure to obtain an imaging scanning frame, thereby ensuring that the scanning target (the target physiological structure to be scanned) can be accurately contained in the imaging scanning frame. At the same time, the defined imaging scanning frame is defined in the positioning guidance map, and its position information relative to the visible light image can be indirectly obtained based on the deviation from the initial scanning frame, so that the acquired imaging scanning frame can accurately describe the position information of the scanning range relative to the external body structure of the scanned object. Finally, medical scanning is performed based on the imaging scanning frame to obtain a medical image, which can ensure the accuracy of the scanning imaging without deliberately positioning the scanned object.

[0053] This method realizes the automatic adjustment and positioning of the imaging scanning frame, avoids the process of positioning the scanned object based on experience during the scanning process, and eliminates the reliance of the scanning effect on the accuracy of the manual positioning. At the same time, the scanning range can be automatically adjusted, eliminating the individual differences that exist when positioning the scan based on experience. The corresponding imaging scanning frame is set for a specific scanning object. On the premise of ensuring that the scanning target is accurately included in the imaging scanning frame, the position information of the imaging scanning frame relative to the external body structure of the scanning object is obtained, and finally the most suitable and accurate scanning effect is obtained.

[0054] In another embodiment of the method, the method further comprises: setting an initial scanning frame.

[0055] The setting of the initial scanning frame includes:

[0056] The scanning object is an animal, and scanning frame samples of different types of animals are set to establish a scanning frame database.

[0057] The type of the scan object is obtained, and a scan frame sample corresponding to the scan object is selected from the scan frame database to obtain the initial scan frame.

[0058] For humans, especially adults, their body sizes, distribution of organs, and relative positions on the body are roughly the same, and are common medical knowledge. Therefore, the initial scan frame for humans can be set based on experience. However, there are many types of animals, and different types of animals have different body sizes, organ distributions, and organ positions. If you only rely on experience and common sense to set them, it is easy to make mistakes or deviations. The embodiment of the present invention first establishes a scan frame database before setting the initial scan frame. The scan frame database stores scan frame samples of different types of animals. When setting the initial scan frame, you only need to select the corresponding scan frame sample in the scan database according to the animal type, and then scan according to the scan frame sample. This makes the setting of the initial scan frame no longer rely on experience and common sense, and improves the efficiency and accuracy of the initial scan frame setting.

[0059] In another embodiment of the method, the setting of scanning frame samples for different types of animals includes:

[0060] Set the center point and size of the scanning frame according to the animal species;

[0061] The scanning frame is divided into a plurality of sub-frames for a plurality of scanning targets, and a relative position relationship between the plurality of sub-frames is set to obtain the scanning frame sample.

[0062] Different types of animals have different body sizes, organ location distributions, and organ sizes. The scanning frame sample is determined by the two parameters of the center point and size of the scanning frame, which can accurately describe different scanning targets of different types of animals. Specifically, when setting the scanning frame sample, first determine the center point, and then determine the size. For example, when scanning a rabbit's heart, it is necessary to determine the center point of the rabbit's heart as the center point of the scanning frame sample, and then set the size of the scanning frame sample according to the size of the rabbit's heart. The shape of the scanning frame sample is set according to the scanning target, and can be a rectangle, circle, ellipse, etc. The sizes of scanning frame samples of different shapes are described using different parameters, such as length and width for rectangles, radius or diameter for circles, and major and minor axes for ellipses.

[0063] The setting of the center point and size of the scanning frame sample depends on the establishment of the coordinate system. When setting the scanning frame sample, the establishment of its coordinate system can be based on the feature points on the animal's body, such as two eyes, two ears, nose, etc. The feature points used to establish the coordinate system can be selected according to the characteristics of the animal itself, and more prominent feature points on the animal can be selected. For example, when scanning a rabbit, its two ears can be selected as the reference to establish a coordinate system, with the line connecting the two ear corners as the X-axis and the perpendicular bisector of the line connecting the two ear corners as the Y-axis to establish the coordinate system. If you need to scan the rabbit's heart, obtain the position coordinates of the center point of the heart in the established coordinate system, and then set the size of the scanning frame sample according to the size of its heart to obtain the rabbit's scanning frame sample.

[0064] In addition, if there is only one scanning target for the scanned object, such as only the heart, then when setting the scanning frame sample, you only need to set the center point position and size (i.e., dimensions) of the scanning frame. However, in many scenarios, there is a need to scan multiple organs of the scanned object, that is, multiple scanning targets, at the same time. At this time, only setting the size and position of a scanning frame cannot accurately mark the position of each organ. To address this problem, when setting the scanning frame sample, first set the scanning frame to include all the scanning targets to be scanned, and then set the sub-frames corresponding to each scanning target in the scanning frame. The setting of the sub-frame also includes the center point and size. Refer to the setting method of the aforementioned scanning frame for setting; at the same time, mark the relative position relationship between multiple sub-frames, that is, the relative position relationship between multiple organs (i.e., multiple scanning targets), so as to facilitate the precise positioning of each organ in the subsequent scanning, and scan each organ separately.

[0065] Specifically, when setting scanning frame samples for animals of the same species, although the organ distribution and organ position of animals of the same species are the same, the body sizes of animals of the same species at different ages are still different, and the relative positions of their organs on the body are also different. When setting scanning frame samples for a certain animal, animal samples with body sizes within the same set range are preferred, and multiple scanning frames are set according to multiple animal samples and their average values ​​(including the average value of the center point coordinates and the average value of the size) are taken as the final scanning frame samples. At the same time, the median value of the body size setting range of the selected animal sample is marked on the scanning frame sample. After the corresponding scanning frame sample is selected and set according to the animal species, the body size data of the animal is obtained according to the visible light image. According to the ratio of the body size data to the median value, the scanning frame sample is reduced or enlarged to obtain the final initial scanning frame, so that the initial scanning frame can adapt to animals of different body sizes of the same species. Body size data can be described by head circumference, body length, arm length, leg length, body width, etc., and can be selected according to different types of animals. Priority will be given to data that can clearly distinguish different body sizes of animals of the same type.

[0066] In another embodiment of the method, the acquiring the type of the scanned object includes:

[0067] The type of the scanned object is identified according to the visible light image.

[0068] Automatic identification of the type of the scanned object is achieved through visible light images, thereby further eliminating the dependence of the scanning process on humans and achieving a higher degree of automation in the scanning process. In one embodiment, the visible light image used to identify the type of the scanned object is different from the visible light image used to fuse with the initial medical image. In one embodiment, the visible light image used to identify the type of the scanned object is a first visible light image, and the visible light image used to fuse with the initial medical image is a second visible light image. The first visible light image and the second visible light image are images of the same type, but the images are acquired at different times. The first visible light image is obtained when the animal species is identified, and can be a plurality of photos taken from multiple angles. The second visible light image is a frame of a video stream corresponding to the scanning moment of the initial medical image or a photo taken at the same moment.

[0069] Specifically, the animal species of the scanned object can be identified based on the visible light image, which can be achieved by neural network training. First, sample images of various animals are collected, and feature points are extracted from the sample images to obtain feature point vectors. It should be noted that the sample images here should be images of the animal in the scanning position, and images of positions that are significantly different from the scanning position do not need to be obtained to reduce the difficulty of training and improve the model recognition accuracy. Each sample image is labeled with a species label, and the feature point vector is used as input and the species label is used as output to train the neural network to obtain an animal species recognition model. The animal species recognition model can be used to realize animal species recognition based on visible light images.

[0070] The extraction of feature points of sample images can be achieved by using the LLE (Locally Linear Embedding) algorithm, which includes:

[0071] A k-nearest neighbor graph is constructed based on the sample images, and the similarity between any two sample images is calculated. A similarity matrix is ​​constructed based on the similarity between every two sample images. The similarity matrix is ​​subjected to feature decomposition, and the first m feature vectors obtained by the decomposition are taken as the result of feature extraction.

[0072] The hidden layer nodes of the neural network are the cluster centers obtained by the clustering algorithm.

[0073] In one embodiment, the clustering algorithm selects the K-means algorithm, including:

[0074] The feature point vector of each sample image is used as the data point;

[0075] Set the same number of initial cluster centers as the number of animal species;

[0076] For any sample image, calculate the distance between its corresponding data point and each cluster center, and classify the corresponding sample image into the class where the nearest cluster center is located;

[0077] Calculate the average value of all data points in each class as the updated cluster center of the class, and determine whether the difference between the current cluster center of each class and the previous cluster center is less than the set threshold. If so, output the current clustering result, otherwise return to the previous step for the next clustering, until the difference between the current cluster center of all classes and the previous cluster center is less than the set threshold.

[0078] In another embodiment of the method, acquiring a visible light image of the scanned object includes:

[0079] A video stream of the scanned object is acquired, and a frame in the video stream corresponding to the scanning moment of the initial medical image is acquired as the visible light image.

[0080] In order to ensure that the visible light image and the initial medical image are images at the same time, the video stream of the scanned object is first obtained, and then the corresponding frames are selected from the video stream to obtain the visible light image and the initial medical image at the same time, so as to improve the accuracy of subsequent image fusion. When acquiring video frames, it is necessary to shoot when the scanned object remains in a stable state, so as to subsequently capture the corresponding frames in the video stream and obtain a complete and clear picture. For some scanned objects such as animals, when acquiring video streams and initial medical images, their state may be out of control and difficult to maintain stability. Generally, it is necessary to first administer medication to the animal to stabilize its state and then fix the body position, and finally obtain video frames and initial medical images.

[0081] In another embodiment, the simultaneously acquiring the visible light image of the scanned object includes: taking pictures of the scanned object in all directions using a high-resolution multi-eye camera, and then fusing the pictures in different directions to obtain the visible light image.

[0082] In another embodiment of the method, fusing the visible light image and the initial medical image to obtain a positioning guidance map includes:

[0083] respectively acquiring feature points of the visible light image and the initial medical image;

[0084] Performing point cloud registration on the visible light image and the initial medical image based on the feature points to obtain a rotation angle and a translation amount between the visible light image and the initial medical image;

[0085] The relative positions of the visible light image and the initial medical image are adjusted based on the rotation angle and the translation amount, and then the visible light image and the initial medical image are pixel-superimposed to obtain the positioning guidance map.

[0086] The visible light image and the initial medical image are fused to obtain a positioning guidance map, so that the initial scanning frame can be adjusted based on the positioning guidance map to determine the final scanning range.

[0087] Specifically, the feature points of the two images are obtained through HRNet, and the translation and rotation angle between the visible light image and the initial medical image are obtained through ICP (Iterative Closest Point) point cloud registration, and corresponding translation and rotation are performed.

[0088] Specifically, HRNet, or High Resolution NET, can maintain high-resolution representation of images during feature extraction, starting with a high-resolution subnet as the first stage, adding subnets one by one in the order of high resolution to low resolution to form more stages, and connecting multi-resolution subnets in parallel. During the feature extraction process, the information in the parallel multi-resolution subnets is repeatedly exchanged to perform repeated multi-scale fusion.

[0089] Specifically, in one embodiment, performing ICP point cloud registration on the visible light image and the initial medical image includes:

[0090] Dividing the visible light image and the initial medical image into two regions, a target region and a background region, respectively;

[0091] ICP point cloud registration is performed on the target area and the background area respectively to obtain the rotation angle and translation of the target area and the rotation angle and translation of the background area; the ICP algorithm is an iterative calculation method that minimizes the corresponding points of the source data (visible light image) and the target data (initial medical image) through iteration to achieve accurate stitching;

[0092] Set the registration weight of the target area and the registration weight of the background area respectively;

[0093] The weighted sum of the rotation angles of the target area and the background area is calculated, and the weighted sum of the translation amounts of the target area and the background area is calculated to obtain the rotation angle and translation amount between the final visible light image and the initial medical image.

[0094] The registration weight of the target region and the registration weight of the background region can be set according to the registration error of the target region and the registration error of the background region. The sum of the registration weight of the target region and the registration weight of the background region is 1.

[0095] The division of the background area and the target area is based on the region growing method: the upper and lower thresholds are set, and the range of regional points between the upper and lower thresholds is the target area, and the range of regional points less than the lower threshold or greater than the upper threshold is the background area.

[0096] After completing the point cloud registration to obtain the translation and rotation angle between the visible light image and the initial medical image, they can be fused to obtain the positioning guidance map. Specifically, the visible light image or the initial medical image is first rotated and translated according to the translation and rotation angle so that the direction of the visible light image is consistent with that of the initial medical image. Then, the image cropping size is set according to the size of the scanned object, and the visible light image and the initial medical image are cropped to the same size, such as 256*256. The cropped visible light image and the initial medical image generated above are fused at the pixel level, that is, the pixel values ​​of the corresponding pixels in the visible light image and the initial medical image are multiplied by 0.5 and then added to obtain the positioning guidance map.

[0097] In another embodiment of the method, adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame includes:

[0098] Setting a target scanning frame according to the initial medical image portion in the positioning guidance map;

[0099] Calculating a deviation value between the target scanning frame and the initial scanning frame;

[0100] The initial scanning frame is adjusted based on the deviation value to obtain the target scanning frame.

[0101] The initial scanning frame is adjusted to obtain an imaging scanning frame. Specifically, after the positioning guidance map is obtained through the above steps, the internal physiological structure of the scanned object and the relative relationship between the internal physiological structure and the external body structure can be observed in the positioning guidance map. The position and range of the scanning target are accurately selected by observing the internal physiological structure of the scanned object in the positioning guidance map, and the target scanning frame is set. The target scanning frame can be set in a sliding frame manner, that is, the position of the target scanning frame is set by moving the sliding frame, and the size of the target scanning frame is set by dragging the sliding frame. Since the position of the initial scanning frame is known, the position deviation value and the size deviation value between the initial scanning frame and the scanning target can be determined according to the position of the initial scanning frame and the position of the target scanning frame (the final sliding frame after moving and dragging), thereby finally determining the position and size of the imaging scanning frame. It should be understood that the position of the imaging scanning frame is a relative position, that is, relative to the position of the initial scanning frame, and the relative position is used to guide the user to adjust the initial scanning frame to obtain the best scanning effect. The starting position of the initial scanning frame and the deviation value of the starting position are recorded as the starting position of the imaging scanning frame, and the size of the initial scanning frame and the size deviation value are recorded as the size of the imaging scanning frame, thereby accurately defining the clinical scanning range.

[0102] Specifically, when there are multiple scanning targets, that is, when multiple organs need to be scanned simultaneously, since the initial scanning frame already contains the distribution of each sub-frame and the relative position relationship of each sub-frame, when determining the imaging scanning frame, it is only necessary to determine the initial scanning frame, that is, the deviation value of the maximum range frame, and then the size deviation values ​​and position deviation values ​​of the multiple sub-frames contained in the initial scanning frame can be obtained at the same time, which will not be elaborated here.

[0103] In another embodiment of the method, before performing medical imaging scanning on the scanned object based on the imaging scanning frame, the method further includes:

[0104] Marking the imaging scanning frame on the scanning object, and acquiring a visible light marking image including the imaging scanning frame mark;

[0105] By comparing the visible light mark image with the positioning guidance map, it is determined whether the scanned object has moved. If it has moved, the imaging scan frame is re-determined, otherwise the scanned object is scanned for medical images with the current imaging scan frame.

[0106] During the scanning process, that is, during the period from the initial medical image scanning based on the initial scanning frame to the medical image scanning based on the imaging scanning frame, the position of the scanned object should be kept stable as much as possible, so as to ensure the accuracy of the subsequent scanning results. If the scanned object undergoes a large position movement during the scanning process, the adjusted imaging scanning frame will obviously no longer be suitable. In some special cases, such as when scanning children or animals, it is obviously not particularly easy to maintain a stable state. In many cases, the scanned object has already undergone position movement, but this position movement cannot be accurately and quickly identified by the naked eye, resulting in the subsequent scanning work becoming useless, reducing the efficiency and accuracy of the scanning. In view of this, after the imaging scanning frame adjustment is confirmed, before scanning the medical image, a step of confirming the position movement of the scanned object is also performed. The specific implementation is: marking the imaging scanning frame on the scanned object. There are many ways to mark, as long as the visible imaging scanning frame mark can be reflected on the scanned object. This embodiment is implemented by projecting a visible light beam to the scanned object to form a visible light mark. After the imaging scanning frame mark is set, the visible light image of the scanned object is re-collected to obtain a visible light mark image, which accurately describes the relative position relationship between the scanned object and the imaging scanning frame at the current moment. Compare the relative position relationship between the imaging scanning frame in the positioning guidance image and the scanned object in the visible light image to determine whether the current relative position relationship has changed significantly, that is, whether the rotation angle and translation of the imaging scanning frame in the two visible light images are greater than the set threshold. If so, it means that the body position of the scanned object has changed significantly, and the current imaging scanning frame is no longer applicable and needs to be readjusted. Otherwise, it means that the body position of the scanned object has not changed significantly, and the current imaging scanning frame is still applicable. The medical image can be directly scanned with the current imaging scanning frame.

[0107] Of course, it should be understood that since the steps of obtaining the visible light image, obtaining the initial medical image, fusing the visible light image with the initial medical image, and determining the imaging scanning frame based on the positioning guidance map are all completed automatically through computer programs, the time required to complete this process is actually very short. The scanned object only needs to maintain a relatively stable position during this very short period of time, and the determination and scanning of the imaging scanning frame can be completed at one time without repetition, that is, the position verification step is a preferred optional step.

[0108] Another embodiment of the present invention provides a medical scanning imaging device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the medical scanning imaging method provided in Embodiment 1 is implemented.

[0109] The medical scanning imaging device provided in the embodiment of the present invention is used to implement the medical scanning imaging method. Therefore, the technical effects possessed by the medical scanning imaging method are also possessed by the medical scanning imaging device, which will not be described in detail herein.

[0110] like Figure 2 As shown, another embodiment of the present invention also provides a medical scanning imaging system, including a medical scanning imaging device 1, a medical imaging device 2 and a visible light image acquisition device 3; in one embodiment, the medical imaging device 2 includes a CT scanning device, and the visible light image acquisition device 3 includes an optical camera.

[0111] The medical imaging device 2 is used to scan the scan object based on the initial scanning frame to obtain an initial medical image, and send the initial medical image to the medical scanning imaging device 1.

[0112] The visible light image acquisition device 3 is used to acquire a visible light image of a scanned object and send the visible light image to the medical scanning imaging device 1 .

[0113] The medical scanning imaging device 1 is used to obtain the imaging scan frame based on the initial medical image and the visible light image using the medical scanning imaging method, and send the imaging scan frame to the medical imaging device 2.

[0114] The medical imaging device 2 is used to perform medical imaging scanning on the scanning object based on the imaging scanning frame.

[0115] The medical scanning imaging device 1 may be integrated into the medical imaging device 2, or may be a separately provided terminal.

[0116] The medical scanning imaging system provided by the embodiment of the present invention includes a medical scanning imaging device 1. Therefore, the technical effects possessed by the medical scanning imaging device 1 are also possessed by the medical scanning imaging system, which will not be elaborated herein.

[0117] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A medical scanning imaging method, characterized in that: include: Setting an initial scanning frame, and acquiring an initial medical image of the scanned object based on the initial scanning frame; Acquire a visible light image of the scanned object; fusing the visible light image and the initial medical image to obtain a positioning guidance map; Adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame; Performing medical imaging scanning on the scanned object based on the imaging scanning frame; The step of setting the initial scan frame includes: Set scanning frame samples of different kinds of animals and establish a scanning frame database; The type of the scan object is obtained, and a scan frame sample corresponding to the scan object is selected from the scan frame database to obtain the initial scan frame.

2. The medical scanning imaging method according to claim 1, characterized in that: The scanning frame samples for setting different types of animals include: Set the center point and size of the scanning frame according to the animal species; The scanning frame is divided into a plurality of sub-frames for a plurality of scanning targets, and a relative position relationship between the plurality of sub-frames is set to obtain the scanning frame sample.

3. The medical scanning imaging method according to claim 1, characterized in that: The types of scanned objects obtained include: The type of the scanned object is identified according to the visible light image.

4. The medical scanning imaging method according to claim 1, characterized in that: The obtaining of a visible light image of the scanned object comprises: A video stream of the scanned object is acquired, and a frame in the video stream corresponding to the scanning moment of the initial medical image is acquired as the visible light image.

5. The medical scanning imaging method according to claim 1, characterized in that: The fusing the visible light image and the initial medical image to obtain a positioning guidance map includes: respectively acquiring feature points of the visible light image and the initial medical image; Performing point cloud registration on the visible light image and the initial medical image based on the feature points to obtain a rotation angle and a translation amount between the visible light image and the initial medical image; Adjusting the relative positions of the visible light image and the initial medical image based on the rotation angle and the translation amount; The visible light image and the initial medical image are pixel-superimposed to obtain the positioning guidance map.

6. The medical scanning imaging method according to claim 1, characterized in that: The adjusting the initial scanning frame based on the positioning guidance map to obtain an imaging scanning frame includes: Setting a target scanning frame according to the initial medical image portion in the positioning guidance map; Calculating a deviation value between the target scanning frame and the initial scanning frame; The initial scanning frame is adjusted based on the deviation value to obtain the target scanning frame.

7. The medical scanning imaging method according to claim 1, characterized in that: Before performing medical imaging scanning on the scanned object based on the imaging scanning frame, the method further includes: Marking the imaging scanning frame on the scanning object, and acquiring a visible light marking image including the imaging scanning frame mark; By comparing the visible light mark image with the positioning guidance map, it is determined whether the scanned object has moved. If it has moved, the imaging scan frame is re-determined, otherwise the scanned object is scanned for medical images with the current imaging scan frame.

8. A medical scanning imaging device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the medical scanning imaging method according to any one of claims 1 to 7 is implemented.

9. A medical scanning imaging system, characterized in that: The medical scanning imaging device according to claim 8 further comprises a medical imaging device and a visible light image acquisition device; The medical imaging device is used to scan the scan object based on the initial scanning frame to obtain an initial medical image, and send the initial medical image to the medical scanning imaging device; The visible light image acquisition device is used to collect a visible light image of the scanned object and send the visible light image to the medical scanning imaging device; The medical scanning imaging device is used to obtain the imaging scanning frame based on the initial medical image and the visible light image by using the medical scanning imaging method, and send the imaging scanning frame to the medical imaging device; The medical imaging device is used to perform medical imaging scanning on a scanning object based on the imaging scanning frame.

Images