Emission imaging equipment and emission imaging method thereof

Abstract

The invention provides emission imaging equipment and an emission imaging method thereof, the emission imaging equipment comprises a processor module and a plurality of detectors, the plurality of detectors are electrically connected with the processor module, and at least part of the plurality of detectors can be adjusted to a detection position to form a detection group. The detection position comprises at least two different positions to form at least two detection groups, and the at least two detection groups are used for detecting and obtaining at least two groups of different detection data. According to the invention, different detection groups can be constructed by adjusting the number and position of the detectors, so that different imaging requirements can be met.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging technology, and in particular to an emission imaging device and an emission imaging method thereof. Background Art

[0002] Computed tomography is a major breakthrough in the field of medical imaging. It is usually applied to emission imaging equipment. Emission imaging equipment usually includes a detection group, which is usually ring-shaped, so it is also called a detection ring. Emission imaging equipment can use the detection group to scan and image the specimen. The images obtained are of great significance for studying the mechanism of the disease, drug distribution and physiological processes.

[0003] However, in the existing emission imaging devices, when the detection aperture of the detection group is large, the distance from the center of the detection group to each detector on the detection group is large, and the spatial resolution of the scanning imaging of the specimen by such emission imaging devices is low, which cannot meet the imaging requirements of high spatial resolution; when the detection aperture of the detection group is small, the distance from the center of the detection group to each detector on the detection group is small, and the sensitivity of the scanning imaging of the specimen by such emission imaging devices is low, which cannot meet the imaging requirements of high sensitivity. Therefore, there is an urgent need for an emission imaging device that can take into account both the imaging requirements of high spatial resolution and high sensitivity. Summary of the invention

[0004] In order to at least partially solve the problems existing in the prior art, according to one aspect of the present invention, an emission imaging device is provided. The emission imaging device includes a processor module and a plurality of detectors, the plurality of detectors are electrically connected to the processor module respectively; at least part of the plurality of detectors can be adjusted to a detection position to form a detection group, the detection position includes at least two different positions to form at least two detection groups, and the at least two detection groups are used to detect and obtain at least two groups of different detection data.

[0005] The emission imaging device provided by the present invention has at least some of the multiple detectors that can be adjusted to different positions to form different detection groups. When high-sensitivity imaging is required, the emission imaging device can adjust all or some of the detectors to be away from the center of the field of view to form a detection group to meet the high-sensitivity imaging requirements; when high-resolution imaging is required, the emission imaging device can select some of the detectors to be adjusted to be closer to the center of the field of view to form another detection group to meet the high-resolution imaging requirements. Therefore, different detection groups can be constructed by adjusting the number and positions of detectors to meet different imaging requirements.

[0006] Exemplarily, the processor module has a pre-trained deep learning model, which is pre-trained with one set of detection data as label data. The processor module is used to reconstruct the detection data except the label data through the deep learning model and output a composite image.

[0007] Exemplarily, the detection position includes a first position and a second position, at least part of the multiple detectors can be adjusted to the first position to form a first detection group, and the first detection group is used to detect and obtain first detection data; at least part of the multiple detectors can be adjusted to the second position to form a second detection group, and the second detection group is used to detect and obtain second detection data.

[0008] Exemplarily, the processor module has a pre-trained first deep learning model, and the processor module is used to reconstruct the second detection data through the first deep learning model and output a first composite image.

[0009] Exemplarily, the processor module has a pre-trained second deep learning model, and the processor module is used to reconstruct the first detection data through the second deep learning model and output a second composite image.

[0010] Exemplarily, the multiple detectors have an initial state, and the multiple detectors are distributed circumferentially around a central axis in the initial state, and the first detection group is formed on a circle with the central axis as the center and a radius R1.

[0011] Exemplarily, the second detection group is formed on a circle with the central axis as the center and a radius R2, where R2<R1.

[0012] Exemplarily, the number of detectors in the first detection group is twice the number of detectors in the second detection group.

[0013] Exemplarily, the detection position also includes a third position, at least part of the multiple detectors can be adjusted to the third position to form a third detector, the third detector and part of the detectors in the first detection group form a third detection group, and the third detection group is used to detect and obtain third detection data.

[0014] Exemplarily, the detectors in the first detection group are formed on a circle with a central axis as the center and a radius R1, and the third detector is formed on a circle with a central axis as the center and a radius R3, R3<R1.

[0015] According to another aspect of the present invention, an emission imaging method is provided. The emission imaging method uses any of the emission imaging devices described above for imaging, and the emission imaging method comprises the steps of:

[0016] Acquire at least two groups of different detection data by detecting with at least two detection groups;

[0017] Image reconstruction is performed based on at least one set of detection data and at least one set of images is output.

[0018] Exemplarily, the processor module has a pre-trained deep learning model, and the emission imaging method further includes the steps of:

[0019] Pre-training the deep learning model using one set of detection data as label data;

[0020] The detection data except the label data is reconstructed through the deep learning model and a composite image is output.

[0021] Exemplarily, the detection position includes a first position and a second position, at least part of the plurality of detectors can be adjusted to the first position to form a first detection group, and at least part of the plurality of detectors can be adjusted to the second position to form a second detection group, and the emission imaging method includes:

[0022] Acquire first detection data through detection by the first detection group;

[0023] Perform image reconstruction based on the first detection data and output a first image; or / and,

[0024] Acquire second detection data through detection by the second detection group;

[0025] Image reconstruction is performed based on the second detection data and a second image is output.

[0026] Exemplarily, the emission imaging method further comprises the steps of:

[0027] Acquire first initial data through detection by a first detection group;

[0028] Reconstructing an image based on the first initial data and outputting a first initial image;

[0029] Pre-training a first deep learning model using the first initial image as a label;

[0030] The second detection data is input into the first deep learning model and a first composite image is output.

[0031] Exemplarily, the emission imaging method further comprises the steps of:

[0032] Acquire second initial data through detection by a second detection group;

[0033] Reconstructing an image based on the second initial data and outputting a second initial image;

[0034] pre-training a second deep learning model using the second initial image as a label;

[0035] The first detection data is input into a second deep learning model and a second composite image is output.

[0036] Exemplarily, the detection position includes a third position, at least part of the plurality of detectors can be adjusted to the third position to form a third detector, the third detector and part of the detectors in the first detection group form a third detection group, and the emission imaging method further includes the steps of:

[0037] Acquire third detection data through detection by the third detection group;

[0038] Image reconstruction is performed based on the third detection data and a third image is output.

[0039] Exemplarily, the emission imaging method further comprises the steps of:

[0040] Acquire first initial data through detection by a first detection group;

[0041] Reconstructing an image based on the first initial data and outputting a first initial image;

[0042] Pre-training a first deep learning model using the first initial image as a label;

[0043] The third detection data is input into the first deep learning model and a third composite image is output.

[0044] Exemplarily, the emission imaging method further comprises the steps of:

[0045] Acquire second initial data through detection by a second detection group;

[0046] Reconstructing an image based on the second initial data and outputting a second initial image;

[0047] pre-training a second deep learning model using the second initial image as a label;

[0048] The third detection data is input into a second deep learning model and a fourth composite image is output.

[0049] A series of simplified concepts are introduced in the summary of the invention, which will be further described in detail in the detailed description. The summary of the invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0050] The advantages and features of the present invention are described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The following drawings of the present invention are used as part of the present invention for understanding the present invention. The drawings show the embodiments of the present invention and their descriptions, and are used to explain the principles of the present invention. In the drawings,

[0052] Figure 1A perspective view of a partial structure of an emission imaging device according to an exemplary embodiment of the present invention;

[0053] Figure 2 for Figure 1 A front view of a partial structure of the emission imaging device shown;

[0054] Figure 3 for Figure 1 A side view of a portion of the structure of the emission imaging device shown;

[0055] Figure 4 An exploded view of a partial structure of an emission imaging device according to an exemplary embodiment of the present invention;

[0056] Figure 5 An exploded view of a partial structure of an emission imaging device according to an exemplary embodiment of the present invention;

[0057] Figure 6a is a schematic diagram of the distribution of multiple detectors according to an exemplary embodiment of the present invention (the multiple detectors are at least partially adjusted to the second position);

[0058] Figure 6b is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention;

[0059] Figure 7a is a schematic diagram of the distribution of multiple detectors according to an exemplary embodiment of the present invention (all multiple detectors are adjusted to the first position);

[0060] Figure 7b is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention;

[0061] Figure 8 is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention;

[0062] Fig. 9 is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention;

[0063] Fig.10a is a schematic diagram of the distribution of multiple detectors according to an exemplary embodiment of the present invention (the multiple detectors are at least partially adjusted to the third position);

[0064] Fig.10b is a schematic diagram of the distribution of multiple detectors according to an exemplary embodiment of the present invention (the multiple detectors are at least partially adjusted to the third position);

[0065] Fig.11a is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention;

[0066] Fig.11b is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention;

[0067] Fig.11c FIG. 4 is a flow chart of an emission imaging method according to an exemplary embodiment of the present invention.

[0068] The above drawings include the following reference numerals:

[0069] 10. Emission imaging device; 100. Detector; 110. First detector; 120. Second detector; 130. Third detector; 210. Third detection group; 300. Transmission mechanism; 310. Connecting member; 311. Sliding portion; 312. Fixed portion; 320. Transmission member; 330. Driving member; 340. Adjusting member; 400. Mounting bracket; 410. First slide slot; 420. Second slide slot; 430. Fixed bearing. DETAILED DESCRIPTION

[0070] In the following description, a large amount of details are provided so that the present invention can be thoroughly understood. However, it will be appreciated by those skilled in the art that the following description only exemplarily illustrates a preferred embodiment of the present invention, and the present invention can be implemented without one or more such details. In addition, in order to avoid confusion with the present invention, some technical features well known in the art are not described in detail.

[0071] According to one aspect of the present invention, see Figure 1 , Figure 2 and Figure 3 , an emission imaging device 10 is provided. The emission imaging device 10 may include a processor module (not shown) and a plurality of detectors 100. The plurality of detectors 100 may work independently without interfering with each other. The processor module may process and reconstruct the data obtained by the detector 100 to output an image. Exemplarily, the emission imaging device 10 may include a mounting frame 400, and the plurality of detectors 100 may be connected to the mounting frame 400, wherein the plurality of detectors 100 may be movably connected to the mounting frame 400. See Figure 4 and Figure 5, the emission imaging device 10 may include a transmission mechanism 300, and the transmission mechanism 300 may include a connector 310, a transmission member 320 and a drive member 330. The connector 310 may be connected between the transmission member 320 and the detector 100, and the drive member 330 may drive the transmission member 320 to rotate. The connector 310 may be connected to the detector 100 in various forms such as snap-on, welding or threaded connection, and the connector 310 may drive the detector 100 to move synchronously. It can be understood that on the basis that the detector 100 may generally include a scintillation crystal layer, a sensor layer and a circuit component, the connector 310 may be connected to any one of the scintillation crystal layer, the sensor layer and the circuit component. Exemplarily, the detector 100 includes a mounting base, the scintillation crystal may be set on the mounting base, and the connector 310 may be connected to the mounting base. Exemplarily, the connecting member 310 may be provided with a through hole with an internal thread, and the transmission member 320 may be in the shape of an axial body provided with an external thread. The transmission member 320 is inserted into the through hole with the internal thread, so that when the transmission member 320 rotates, it will drive the connecting member 310 to move. Of course, the transmission member 320 may also be connected to the connecting member 310 in various other forms, as long as the driving member 330 drives the transmission member 320 to rotate, the transmission member 320 can drive the connecting member 310 to move, so that the connecting member 310 can drive the detector 100 to move. A fixed bearing 430 may be provided on the mounting frame 400, and the transmission member 320 may be rotatably connected to the fixed bearing 430. Of course, the multiple detectors 100 in the emission imaging device 10 may also be detachable, which is convenient for rapid replacement and adjustment in different positions, and improves the adaptability and maintenance convenience of the emission imaging device 10.

[0072] The plurality of detectors 100 may be electrically connected to the processor module respectively. At least part of the plurality of detectors 100 may be adjusted to a detection position to form a detection group, the detection position includes at least two different positions to form at least two detection groups, and the at least two detection groups are used to detect and obtain at least two different detection data.

[0073] The emission imaging device provided in the embodiment of the present invention has at least some of the multiple detectors 100 that can be adjusted to different positions to form different detection groups. When high-sensitivity imaging is required, the emission imaging device can adjust all or part of the detectors to be away from the center of the field of view to form a detection group to meet the high-sensitivity imaging requirements; when high-resolution imaging is required, the emission imaging device can select some of the detectors to be adjusted to be closer to the center of the field of view to form another detection group to meet the high-resolution imaging requirements. Therefore, different detection groups can be constructed by adjusting the number and positions of detectors to meet different imaging requirements.

[0074] Furthermore, in an embodiment of the present invention, the processor module may have a pre-trained deep learning model, the deep learning model is pre-trained with one set of detection data as label data, and the processor module is used to reconstruct the detection data other than the label data through the deep learning model and output a composite image. In this way, the composite image reconstructed and output by the deep learning model for the detection data other than the label data can take into account both high spatial resolution and high sensitivity, and such an emission imaging device 10 is more in line with the general needs of different application scenarios.

[0075] The deep learning model can be constructed by convolutional deep neural network (CNN) technology, which can include multiple convolutional layers, pooling layers and deconvolution layers, combined with jump connections to retain more image details. During the training process, a loss function (such as mean square error MSE or perceptual loss) can be used to measure the difference between the output image and the label image. The network weights are adjusted through back propagation and optimization algorithms to make the output image as close as possible to the high-resolution label image. Since convolutional deep neural network technology belongs to the prior art, it will not be elaborated here. It should be understood that the deep learning model is not limited to being constructed by convolutional deep neural network technology, but can also be constructed by other (such as artificial neural network) technologies, as long as the constructed deep learning model can retain more image details.

[0076] Combined with reference Figure 6a and Figure 7a The detection position includes a first position and a second position, and at least part of the plurality of detectors 100 can be adjusted to the first position to form a first detection group, such as Figure 7a As shown, eight detectors 100 (the number of detectors here is only an example, in an embodiment not shown, the number of detectors 100 may be 6, 10, etc.) are all located at the first position to form a first detection group, and the first detection group can be used to detect and obtain first detection data. Figure 6a As shown, 4 of the 8 detectors 100 are adjusted to a second position different from the first position to form a second detection group, and the second detection group can be used to detect and obtain second detection data. For the sake of distinction, the detector located at the first position is called the first detector 110, and the detector located at the second position is called the second detector 120. When high-sensitivity imaging is required, the emission imaging device can adjust all or part of the detectors away from the center of the field of view to form a first detection group to meet the high-sensitivity imaging requirements; when high-resolution imaging is required, the emission imaging device can select part of the detectors to be adjusted closer to the center of the field of view to form a second detection group to meet the high-resolution imaging requirements, so that different detection groups can be constructed by adjusting the number and position of detectors to meet different imaging requirements.

[0077] Exemplarily, the first detection group and / or the second detection group may be a closed circular ring. When the first detection group and / or the second detection group are closed circular rings, the object to be examined may be detected in all directions, so that the detection effect may be better. Exemplarily, the first detection group and / or the second detection group are closed circular rings, and the emission imaging device 10 may be a positron emission computed tomography imaging device, and when a collimation mechanism is provided on the detector 100 in the emission imaging device 10, the emission imaging device 10 may be a single photon emission computed tomography imaging device. It is worth noting that the first detection group and / or the second detection group are closed circular rings, which does not limit the detectors 100 in the emission imaging device 10 to be arranged in a ring shape, nor does it limit the arrangement mode and movement direction of the multiple detectors 100. For example, the multiple detectors 100 in the emission imaging device 10 may be arranged in a rectangular shape.

[0078] Taking the emission imaging device 10 as an example, the transmission mechanism 300 and the mounting frame 400 may be included. Figure 4 and Figure 5The mounting frame 400 may be provided with a first slide groove 410 extending in the radial direction of the detection group, and the first slide groove 410 may be a long strip groove opening toward the detector 100. The first slide groove 410 may correspond to the detector 100, and the detector 100 may be slidably connected to the first slide groove 410. The groove bottom of the first slide groove 410 may be provided with a second slide groove 420, and the second slide groove 420 may pass through the mounting frame 400. The connecting member 310 may include a sliding portion 311 and a fixing portion 312, and the sliding portion 311 may be slidably connected to the second slide groove 420, and one end of the sliding portion 311 may be fixedly connected to the detector 100, and the other end may be fixedly connected to the fixing portion 312, and the fixing portion 312 and the detector 100 may be located on both sides of the mounting frame 400, respectively, and the fixing portion 312 and the detector 100 may be connected through the sliding portion 311, and the sliding portion 311 may be slidably connected to the second slide groove 420 passing through the mounting frame 400. The fixing portion 312 can also be connected to the transmission member 320, and when the transmission member 320 rotates, the fixing portion 312 can move in the radial direction of the detection group, so that when the driving member 330 drives the transmission member 320 to rotate, the transmission member 320 can drive the fixing portion 312 to move in the radial direction of the detection group, so that the sliding portion 311 can drive the detector 100 to move in the radial direction of the detection group. The fixing portion 312 can be located outside the second slide groove 420, and the fixing portion 312 can be attached to a side of the mounting frame 400 away from the detector 100. The transmission mechanism 300 may further include an adjusting member 340. The fixing portion 312 may be provided with a through hole perpendicular to a side surface of the mounting frame 400 away from the detector 100. The adjusting member 340 may be slidably connected to the through hole, so that the adjusting member 340 may move in a direction perpendicular to a side surface of the mounting frame 400 away from the detector 100, that is, the adjusting member 340 may move between a pressing position against the mounting frame 400 and a loosening position away from the mounting frame 400. When the adjusting member 340 is in the pressing position and pressing against the mounting frame 400, the fixing portion 312 may be pressed against the mounting frame 400. In this way, the position of the detector 100 may be fixed by pressing the position of the fixing portion 312.

[0079] It should be understood that the first position and the second position in this embodiment are not limited to specific positions, but are only used to distinguish similar objects. The first position and the second position can be different positions. In addition, the detection position can also include more different positions. For example, if 16 detectors 100 are included, all of the 16 detectors 100 can be located at the first position to form a first detection group, and the first detection group can be used to detect and obtain first detection data; 4 of the 16 detectors 100 can be adjusted to a second position different from the first position to form a second detection group, and the second detection group can be used to detect and obtain second detection data; 8 of the 16 detectors 100 can be adjusted to another position different from the first position and the second position (in order to distinguish, the other position is referred to as the fourth position here) to form a fourth detection group, and the fourth detection group can be used to detect and obtain fourth detection data. The first position, the second position and the fourth position are only for example. In an embodiment not shown, the detection position can also include a fifth position, a sixth position, and so on. This means that different numbers of partial detectors 100 among the multiple detectors 100 can be adjusted to multiple other positions different from the specific position, so as to construct multiple different detection groups by adjusting the number and positions of the detectors 100 to meet different imaging requirements. Since the detection principles of different detection groups are basically similar, only the number and position of the detectors are different, they will not be repeated here.

[0080] In one embodiment of the present invention, the processor module may have a first deep learning model generated by pre-training, and the processor module may be used to reconstruct the first detection data through the first deep learning model and output a first composite image. Since the first position is different from the second position, the detection apertures of the first detection group and the second detection group are also different, and the sensitivity and resolution of the image output after the detected data is reconstructed are also different. The larger the detection aperture of the detection group, the higher the sensitivity of the image output after the detected data is reconstructed, and the resolution is reduced. The smaller the detection aperture of the detection group, the higher the resolution of the image output after the detected data is reconstructed, and the sensitivity is reduced. It can be understood that the first composite image reconstructed and output by the first detection data through the first deep learning model can take into account both high spatial resolution and high sensitivity. Such an emission imaging device 10 is more in line with the general needs of different application scenarios.

[0081] Exemplarily, the processor module may have a pre-trained second deep learning model, and the processor module may be used to reconstruct the first detection data through the second deep learning model and output a second composite image. It is understandable that the second composite image reconstructed and outputted from the first detection data through the second deep learning model can take into account both high spatial resolution and high sensitivity, which will not be described in detail here.

[0082] See also Figure 1, Figure 2 , Figure 3 , Figure 6a and Figure 7a , the multiple detectors 100 may have an initial state. The multiple detectors 100 may be distributed circumferentially around a central axis in the initial state. Specifically, the detectors 100 in the initial state are not working. The multiple detectors 100 in the initial state may be arranged in a ring shape. When the multiple detectors 100 are arranged in a ring shape, the multiple detectors 100 may move radially along the formed ring. Such an emission imaging device 10 has a simpler structure, and the moving path of the detector 100 between the first position and the second position may be simpler.

[0083] See also Figure 7a , the first detection group can be formed on a circle with the central axis as the center and a radius of R1. Taking the emission imaging device 10 including 8 detectors 100 as an example, the 8 detectors 100 are all located at the first position to form a first detection group, and the first detection group can be used to detect and obtain first detection data. Since the first detection group is relatively farther away from the center of the field of view, the first detection group can meet the high-sensitivity imaging requirements.

[0084] See also Figure 6a , the second detection group can be formed on a circle with the central axis as the center and a radius of R2, R2<R1. Still taking the emission imaging device 10 including 8 detectors 100 as an example, the 8 detectors 100 are located at the first position to form the first detection group, and 4 of the detectors (for the sake of distinction, the 4 detectors here are called second detectors 120) are adjusted to be located at the second position to form the second detection group, that is, the detection center of the first detection group is the same as the detection center position of the second detection group. When such an emission imaging device 10 detects the object to be detected, the number of detectors 100 that need to work and the positions of the detectors 100 involved in the work can be adjusted according to the situation of the object to be detected. In this structure, since some detectors are adjusted to be closer to the center of the field of view to form the second detection group, the high-resolution imaging requirements can be met.

[0085] Figure 6aIn the illustrated embodiment, the number of the first detectors 110 is twice the number of the second detectors 120, and the second detectors 120 are actually part of the first detection group when adjusted to the first position. In an embodiment not shown, the number of the first detectors 110 can also be three times the number of the second detectors 120. For example, the emission imaging device 10 includes 12 detectors 100, and the 12 detectors 100 are located at the first position to form a first detection group, and 4 of the detectors (for the sake of distinction, the 4 detectors here are called second detectors 120) are adjusted to be located at the second position to form a second detection group. Specifically, the number of the second detectors 120 and the number of the first detectors 110 can be appropriately selected according to the size of the object to be detected, as long as a detection group adapted to the object to be detected can be formed.

[0086] See again Figure 6a , at this time, the ring formed by the first detector 110 can form a first detection group, and the ring formed by the second detector 120 can form a second detection group. The first detection group and the second detection group work independently of each other. When the first detection group works, the second detection group does not work; when the second detection group works, the first detection group does not work.

[0087] See also Fig.10a and Fig.10b The detection position also includes a third position. At least part of the multiple detectors 100 can be adjusted to the third position to form a third detector 130. The third detector 130 and part of the detectors 100 in the first detection group form a third detection group 210. The third detection group 210 is used to detect and obtain third detection data.

[0088] Specifically, the detectors 100 in the first detection group are formed on a circle with a central axis as the center and a radius of R1, and the third detector 130 can be formed on a circle with a central axis as the center and a radius of R3, R3<R1. Among them, R3 can be the same as R2. Of course, R3 can also be different from R2.

[0089] exist Fig.10a and Fig.10b In the illustrated embodiment, six of the eight detectors 100 are located at the first position to form a first detector 110, two are located at the third position to form a third detector 130, two third detectors 130 and five of the first detectors 110 form a third detection group 210, and the first detector 110 located between two third detectors 130 does not participate in the work. It should be understood that the number of first detectors 110 participating in the work is not limited to five, and the number of third detectors 130 is not limited to two. In actual use, the number of first detectors 110 and the number of third detectors 130 can be appropriately selected according to the size of the object to be detected, as long as a detection group adapted to the object to be detected can be formed.

[0090] According to another aspect of the present invention, an emission imaging method is provided. The emission imaging method can be performed using any of the emission imaging devices 10 in the above embodiments, and generally comprises the steps of: obtaining at least two sets of different detection data by detecting with at least two detection groups; and reconstructing images based on at least one set of detection data and outputting at least one set of images.

[0091] Furthermore, the processor module has a pre-trained deep learning model, and the emission imaging method also includes the steps of: pre-training the deep learning model with one set of detection data as label data; reconstructing the detection data except the label data through the deep learning model and outputting a composite image.

[0092] The following still takes the emission imaging device 10 including 8 detectors as an example to describe the emission imaging method in detail.

[0093] Combined with reference Figure 7a and Figure 7b The detection position includes a first position and a second position. The eight detectors 100 can all be located at the first position to form a first detection group (eg Figure 7a ), at this time, the emission imaging method is as follows Figure 7b As shown, the steps include:

[0094] Step S09: obtaining first detection data through detection by the first detection group;

[0095] Step S11: reconstructing an image based on the first detection data and outputting a first image.

[0096] It should be understood that the first detection data is data obtained by the first detection group, which can be data obtained by the first detection group once, or the optimal data obtained by selection after multiple detections by the first detection group, or the average data obtained by averaging after multiple detections by the first detection group, and the second detection data, the third detection data, the first initial data and the second initial data in the following text are also the same. In this method, the first detection data is directly reconstructed by the processor module to output the first image, which can meet the high-sensitivity imaging requirements.

[0097] Combined with reference Figure 6a and Figure 6b , all eight detectors 100 (for distinction, the eight detectors here are referred to as first detectors 110) are first adjusted to the first position to form a first detection group, and then four of the detectors ( Figure 6aThe four detectors shown by the dotted lines on the middle outer circle are called second detectors 120 for distinction. They are located at the second position to form a second detection group. When in use, only the second detector 120 can be used, and the other four detectors 110 ( Figure 6a The four detectors shown by the solid lines on the outer circle do not participate in the work. At this time, the emission imaging method is as follows Figure 6b As shown, the steps include:

[0098] Step S04: obtaining second detection data through detection by the second detection group;

[0099] Step S12: reconstructing an image based on the second detection data and outputting a second image.

[0100] In this method, since the transmitting imaging device obtains the second detection data through the second detection group closer to the center of the field of view, the second detection data can be directly reconstructed by the processor module to output the second image, thereby meeting the high-resolution imaging requirements.

[0101] Combined with reference Figure 6a and Figure 8 , all of the eight detectors 100 can be located at the first position to form a first detection group, and after collecting data, four of the detectors are adjusted to the second position to form a second detection group to collect data. In this case, the emission imaging method can be as follows Figure 8 As shown, the steps include:

[0102] Step S01: obtaining first initial data through detection by a first detection group;

[0103] Step S02: reconstructing an image based on the first initial data and outputting a first initial image;

[0104] Step S03: pre-training a first deep learning model using the first initial image as a label;

[0105] Step S04: obtaining second detection data through detection by the second detection group;

[0106] Step S05: Input the second detection data into the first deep learning model and output a first composite image.

[0107] Since the first initial data obtained by the first detection group can be outputted as the first initial image after image reconstruction by the processor module, the first deep learning model pre-trained with the first initial image as a label can reconstruct the second detection data obtained by the second detection group into an image with high sensitivity. On this basis, since the detection aperture of the second detection group is relatively small, the image obtained by reconstructing the second detection data obtained by the second detection group already has a high spatial resolution, so the first composite image can take into account both high spatial resolution and high sensitivity. Such an emission imaging device 10 can also meet the imaging requirements of high spatial resolution and high sensitivity, and output a first composite image that takes into account both high spatial resolution and high sensitivity.

[0108] Therefore, the first composite image obtained by this method is mainly characterized by high spatial resolution, taking into account high sensitivity requirements. Such an emission imaging device 10 is more in line with the general needs of different application scenarios. Specifically, the first initial data is the data obtained by the first detection group when detecting the specimen. The first initial data can be approximately regarded as the data required for detection during equipment debugging. It can be understood that the training of the first deep learning model has nothing to do with actual detection. The first deep learning model can be understood as being pre-loaded in the processor module, and the user does not need to train the first deep learning model. The first initial data and the first initial image can also be obtained by detection by other emission imaging devices 10, which will not be elaborated here.

[0109] Combined with reference Figure 6a and Fig. 9 , all of the eight detectors 100 can be located at the first position to form a first detection group, and after collecting data, four of the detectors are adjusted to the second position to form a second detection group to collect data. In this case, the emission imaging method can be as follows Fig. 9 As shown, the steps include:

[0110] Step S06: obtaining second initial data through detection by the second detection group;

[0111] Step S07: reconstructing an image based on the second initial data and outputting a second initial image;

[0112] Step S08: pre-training a second deep learning model using the second initial image as a label;

[0113] Step S09: obtaining first detection data through detection by the first detection group;

[0114] Step S10: Input the first detection data into the second deep learning model and output a second composite image.

[0115] It is worth noting that although both the first composite image and the second composite image can meet the imaging requirements of high spatial resolution and high sensitivity, there are still some differences between the two due to the different pre-training labels of the deep learning models involved. The second composite image is mainly based on high sensitivity while taking into account the requirements of high spatial resolution, while the first composite image is mainly based on high spatial resolution while taking into account the requirements of high sensitivity.

[0116] Combined with reference Fig.10a , Fig.10b and Fig.11a , 6 of the 8 detectors 100 are located at the first position to form a first detector 110, 2 are located at the third position to form a third detector 130, 2 third detectors 130 and 5 of the first detectors 110 form a third detection group 210, and the first detector 110 located between the two third detectors 130 does not participate in the work. In this case, the emission imaging method may include the steps of:

[0117] Step S13: obtaining third detection data through detection by the third detection group 210;

[0118] Step S15: reconstruct an image based on the third detection data and output a third image.

[0119] In this method, the third detection data can be directly reconstructed by the processor module to output a third image.

[0120] Combined with reference Fig.10a , Fig.10b and Fig.11b , 6 of the 8 detectors 100 are located at the first position to form a first detector 110, 2 are located at the third position to form a third detector 130, 2 third detectors 130 and 5 of the first detectors 110 form a third detection group 210, and the first detector 110 located between the two third detectors 130 does not participate in the work. In this case, the emission imaging method may include the steps of:

[0121] Step S01: obtaining first initial data through detection by a first detection group;

[0122] Step S02: reconstructing an image based on the first initial data and outputting a first initial image;

[0123] Step S03: pre-training a first deep learning model using the first initial image as a label;

[0124] Step S13: obtaining third detection data through detection by the third detection group 210;

[0125] Step S14: Input the third detection data into the first deep learning model and output a third composite image.

[0126] The first initial data obtained by the first detection group can be reconstructed by the processor module to output the first initial image with high sensitivity. The first deep learning model pre-trained with the first initial image as a label can reconstruct the third detection data obtained by the third detection group 210 into an image with high sensitivity. On this basis, since the detection aperture of the third detection group 210 is small, the image obtained by the reconstruction of the third detection data obtained by the third detection group 210 has high spatial resolution. Therefore, the third composite image can take into account both high spatial resolution and high sensitivity. Such an emission imaging device 10 can also meet the imaging requirements of high spatial resolution and high sensitivity, and output a third composite image with both high spatial resolution and high sensitivity.

[0127] Combined with reference Fig.10a , Fig.10b and Fig.11c , 6 of the 8 detectors 100 are located at the first position to form a first detector 110, 2 are located at the third position to form a third detector 130, 2 third detectors 130 and 5 of the first detectors 110 form a third detection group 210, and the first detector 110 located between the two third detectors 130 does not participate in the work. In this case, the emission imaging method may include the steps of:

[0128] Step S06: obtaining second initial data through detection by the second detection group;

[0129] Step S07: reconstructing an image based on the second initial data and outputting a second initial image;

[0130] Step S08: pre-training a second deep learning model using the second initial image as a label;

[0131] Step S13: obtaining third detection data through detection by the third detection group 210;

[0132] Step S16: Input the third detection data into the second deep learning model and output a fourth composite image.

[0133] It can be seen from the above that the emission imaging device 10 according to the embodiment of the present invention can have multiple imaging modes, so as to meet different imaging requirements.

[0134] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by directional words such as "front", "back", "up", "down", "left", "right", "lateral", "vertical", "vertical", "horizontal", "top", "bottom", etc. is usually based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present invention; the directional words "inside" and "outside" refer to the inside and outside relative to the contour of each component itself.

[0135] For ease of description, regional relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the regional positional relationship between one or more components or features shown in the figure and other components or features. It should be understood that regional relative terms include not only the orientation of the components as described in the figure, but also different orientations in use or operation. For example, if the components in the accompanying drawings are inverted as a whole, the components "above other components or features" or "above other components or features" will include the situation where the components are "below other components or structures" or "below other components or structures". Therefore, the exemplary term "above" may include both "above" and "below". In addition, these components or features may also be positioned at other different angles (e.g., rotated 90 degrees or other angles), and this article is intended to include all of these situations.

[0136] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, parts, components and / or combinations thereof.

[0137] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0138] The present invention has been described by the above embodiments, but it should be understood that the above embodiments are only for the purpose of example and description, and are not intended to limit the present invention to the scope of the described embodiments. In addition, it can be understood by those skilled in the art that the present invention is not limited to the above embodiments, and more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the scope of the protection claimed by the present invention. The protection scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A transmission imaging device, characterized in that: It includes a processor module and a plurality of detectors, wherein the plurality of detectors are electrically connected to the processor module respectively; At least part of the plurality of detectors can be adjusted to a detection position to form a detection group, wherein the detection position includes at least two different positions to form at least two detection groups, and the at least two detection groups are used to detect and obtain at least two different detection data groups.

2. The emission imaging device according to claim 1, characterized in that: The processor module has a pre-trained deep learning model, which is pre-trained with one set of detection data as label data. The processor module is used to reconstruct the detection data except the label data through the deep learning model and output a composite image.

3. The emission imaging device according to claim 1, characterized in that: The detection position includes a first position and a second position, at least part of the plurality of detectors can be adjusted to the first position to form a first detection group, and the first detection group is used for detection to obtain first detection data; At least part of the plurality of detectors can be adjusted to the second position to form a second detection group, and the second detection group is used for detecting and obtaining second detection data.

4. The emission imaging device according to claim 3, characterized in that: The processor module has a first deep learning model generated by pre-training, and the processor module is used to reconstruct the second detection data through the first deep learning model and output a first composite image.

5. The emission imaging device according to claim 3, characterized in that: The processor module has a pre-trained second deep learning model, and the processor module is used to reconstruct the first detection data through the second deep learning model and output a second composite image.

6. The emission imaging device according to claim 3, characterized in that: The plurality of detectors have an initial state, in which the plurality of detectors are distributed circumferentially around a central axis, and the first detection group is formed on a circle with the central axis as the center and a radius R1.

7. The emission imaging device according to claim 6, characterized in that: The second detection group is formed on a circle with the central axis as the center and a radius R2, where R2<R1.

8. The emission imaging device according to claim 3, characterized in that: The number of detectors in the first detection group is twice the number of detectors in the second detection group.

9. The emission imaging device according to claim 3, characterized in that: The detection position also includes a third position, at least part of the multiple detectors can be adjusted to the third position to form a third detector, the third detector and part of the detectors in the first detection group form a third detection group, and the third detection group is used to detect and obtain third detection data.

10. The emission imaging device according to claim 9, characterized in that: The detectors in the first detection group are formed on a circle with a central axis as the center and a radius R1, and the third detector is formed on a circle with the central axis as the center and a radius R3, R3<R1.

11. A method for emission imaging, characterized in that: Imaging using the emission imaging device as described in any one of claims 1 to 10 comprises the steps of: Obtain at least two groups of different detection data by detecting with at least two of the detection groups; Image reconstruction is performed based on at least one set of the detection data and at least one set of images is output.

12. The emission imaging method according to claim 11, characterized in that: The processor module has a pre-trained deep learning model, and the emission imaging method further includes the steps of: Pre-training the deep learning model using one set of the detection data as label data; The detection data except the label data is reconstructed through the deep learning model and a composite image is output.

13. The emission imaging method according to claim 11, characterized in that: The detection position includes a first position and a second position, at least part of the plurality of detectors can be adjusted to the first position to form a first detection group, and at least part of the plurality of detectors can be adjusted to the second position to form a second detection group, and the emission imaging method includes: Acquire first detection data through detection by the first detection group; Reconstruct an image based on the first detection data and output a first image; or / and, Acquire second detection data through detection by the second detection group; Image reconstruction is performed based on the second detection data and a second image is output.

14. The emission imaging method according to claim 13, characterized in that: Also includes the steps: Acquire first initial data through detection by the first detection group; Reconstructing an image based on the first initial data and outputting the first initial image; Pre-training a first deep learning model using the first initial image as a label; The second detection data is input into the first deep learning model and a first composite image is output.

15. The emission imaging method according to claim 13, characterized in that: Also includes the steps: Acquire second initial data through detection by the second detection group; Reconstructing an image based on the second initial data and outputting the second initial image; Pre-training a second deep learning model using the second initial image as a label; The first detection data is input into the second deep learning model and a second composite image is output.

16. The emission imaging method according to claim 13, characterized in that: The detection position includes a third position, at least part of the plurality of detectors can be adjusted to the third position to form a third detector, the third detector and part of the detectors in the first detection group form a third detection group, and the emission imaging method further includes the steps of: Acquire third detection data through detection by the third detection group; Image reconstruction is performed based on the third detection data and a third image is output.

17. The emission imaging method according to claim 16, characterized in that: Also includes the steps: Acquire first initial data through detection by the first detection group; Reconstructing an image based on the first initial data and outputting the first initial image; Pre-training a first deep learning model using the first initial image as a label; The third detection data is input into the first deep learning model and a third composite image is output.

18. The emission imaging method according to claim 16, characterized in that: Also includes the steps: Acquire second initial data through detection by the second detection group; Reconstructing an image based on the second initial data and outputting the second initial image; Pre-training a second deep learning model using the second initial image as a label; The third detection data is input into the second deep learning model and a fourth composite image is output.

Images