Super-resolution reconstruction method and device for medical image, equipment and medium

Abstract

The invention discloses a medical image super-resolution reconstruction method and device, equipment and a medium. The method comprises the following steps: acquiring an initial medical image detected by a flat panel detector; wherein the initial medical image comprises a pixel response array corresponding to at least one photon; for each pixel response array, determining target pixel coordinates and target response intensity of photons corresponding to the pixel response array based on initial response intensity corresponding to at least three response pixel units in the pixel response array; adding the target response intensity to a target pixel unit corresponding to the target pixel coordinate in the target medical image; wherein the response pixel units corresponding to the pixel response arrays are not overlapped with one another, the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit, and the problem that a traditional flat panel detector is poor in spatial resolution capacity is solved.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging technology, and in particular to a method, device, equipment and medium for super-resolution reconstruction of medical images. Background Art

[0002] Flat-panel detectors are one of the core components of medical imaging equipment. At present, the spatial resolution of flat-panel detectors still cannot meet the requirements of high-resolution imaging in some medical imaging scenarios. The main reason for this problem is that the size of the pixel unit of existing flat-panel detectors is not small enough.

[0003] In order to improve the spatial resolution of flat-panel detectors, the most direct method is to reduce the physical size of the pixel unit of the flat-panel detector. However, directly reducing the physical size will be accompanied by increased process complexity, increased total number of pixel units, reduced detector signal readout rate, and even lead to increased electronic noise (readout electronic noise, dark current noise, etc.), thereby affecting the imaging performance of the flat-panel detector.

[0004] Therefore, it is a certain technical challenge to improve the spatial resolution of flat-panel detectors without affecting their imaging performance. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment and medium for super-resolution reconstruction of medical images to solve the problem of poor spatial resolution of traditional flat-panel detectors, and to improve the spatial resolution of flat-panel detectors without changing the hardware structure of the flat-panel detectors and without affecting the imaging performance of the flat-panel detectors.

[0006] According to an embodiment of the present invention, a method for super-resolution reconstruction of a medical image is provided, the method comprising:

[0007] Acquire an initial medical image detected by a flat panel detector; wherein the initial medical image comprises a pixel response array corresponding to at least one photon, and the pixel response array comprises initial response intensities corresponding to at least three response pixel units;

[0008] For each pixel response array, determining a target pixel coordinate and a target response intensity of a photon corresponding to the pixel response array based on at least three initial response intensities in the pixel response array;

[0009] adding the target response intensity to a target pixel unit corresponding to the target pixel coordinate in the target medical image;

[0010] The response pixel units respectively corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit.

[0011] According to another embodiment of the present invention, a medical image super-resolution reconstruction device is provided, the device comprising:

[0012] An initial medical image acquisition module is used to acquire an initial medical image detected by the flat panel detector; wherein the initial medical image includes a pixel response array corresponding to at least one photon, and the pixel response array includes initial response intensities corresponding to at least three response pixel units;

[0013] A target response intensity determination module, configured to determine, for each pixel response array, a target pixel coordinate and a target response intensity of a photon corresponding to the pixel response array based on at least three initial response intensities in the pixel response array;

[0014] A target medical image determination module, configured to add the target response intensity to a target pixel unit corresponding to the target pixel coordinate in the target medical image;

[0015] The response pixel units respectively corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit.

[0016] According to another embodiment of the present invention, there is provided an electronic device, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the super-resolution reconstruction method of a medical image described in any embodiment of the present invention.

[0020] According to another embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the medical image super-resolution reconstruction method described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention is to obtain an initial medical image detected by a flat-panel detector, wherein the initial medical image contains at least one pixel response array corresponding to each photon, and for each pixel response array, based on the initial response intensities corresponding to at least three response pixel units in the pixel response array, determine the target pixel coordinates and target response intensity of the photons corresponding to the pixel response array, and add the target response intensity to the target pixel unit corresponding to the target pixel coordinate in the target medical image, wherein the response pixel units corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit, thereby solving the problem of poor spatial resolution of traditional flat-panel detectors, and improving the spatial resolution of the flat-panel detector without changing the hardware structure of the flat-panel detector and without affecting the imaging performance of the flat-panel detector, thereby improving the image quality of the medical image.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a method for super-resolution reconstruction of medical images provided by one embodiment of the present invention;

[0025] Figure 2 A schematic diagram of a pixel response array provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of positioning target space coordinates provided by an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of conversion between an initial medical image and a target medical image provided by an embodiment of the present invention;

[0028] Figure 5 A flowchart of another medical image super-resolution reconstruction method provided by one embodiment of the present invention;

[0029] Figure 6 A schematic diagram of a specific example of super-resolution reconstruction of a medical image provided by an embodiment of the present invention;

[0030] Figure 7 A schematic diagram of the structure of a medical image super-resolution reconstruction device provided by one embodiment of the present invention;

[0031] Figure 8 The present invention is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "initial", "target", "reference", 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 data 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. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Figure 1 This is a flowchart of a medical image super-resolution reconstruction method provided by an embodiment of the present invention. This embodiment is applicable to the case of reconstructing medical images using a flat panel detector. The method can be executed by a medical image super-resolution reconstruction device. The medical image super-resolution reconstruction device can be implemented in the form of hardware and / or software. The medical image super-resolution reconstruction device can be configured in a terminal device. Figure 1 As shown, the method includes:

[0035] S110: Acquire an initial medical image detected by a flat panel detector.

[0036] Exemplarily, the device type of the flat panel detector may be a nuclear detector or an X-ray flat panel detector. The device type of the flat panel detector is not limited here and may be customized according to actual needs.

[0037] Specifically, the initial medical image includes a plurality of initial pixel units and initial response intensities corresponding to each initial pixel unit. In this embodiment, the initial medical image includes a pixel response array corresponding to at least one photon, and the pixel response array includes initial response intensities corresponding to at least three response pixel units.

[0038] Specifically, the response pixel unit can be used to characterize the initial pixel unit that generates a certain value of initial response intensity to a single photon hitting the flat panel detector, and the initial response intensity is used to characterize the response intensity generated by the photon in the response pixel unit. Exemplarily, the certain value can be greater than 0keV, or greater than 10keV, and the setting of the certain value is not limited here.

[0039] Specifically, the number of pixels in the response pixel units included in the pixel response arrays corresponding to the photons may be the same or different.

[0040] In an optional embodiment, the method further includes: taking at least three initial pixel units in the initial medical image whose initial response intensities are greater than a first intensity threshold as response pixel units, respectively, to obtain at least one pixel response array.

[0041] Exemplarily, the first intensity threshold may be 50 keV or 60 keV. The specific parameter value of the first intensity threshold is not limited here and can be customized according to actual needs.

[0042] In another optional embodiment, the method further includes: obtaining an initial response array corresponding to at least one photon in the initial medical image, and for each initial response array, sorting each initial pixel unit in the initial response array in descending order based on the initial response intensity corresponding to each initial pixel unit in the initial response array, and taking a preset number of initial pixel units with the highest sorting order as response pixel units to obtain a pixel response array.

[0043] Specifically, the initial response array includes multiple initial pixel units whose initial response intensity is greater than a second intensity threshold. Exemplarily, the second intensity threshold may be 10keV or 20keV. The specific parameter value of the second intensity threshold is not limited here and can be customized according to actual needs.

[0044] Exemplarily, the preset number may be 3, 4 or 9. The specific parameter value of the preset number is not limited here and can be customized according to actual needs.

[0045] In an optional embodiment, the initial medical image is obtained by performing a single imaging operation on the flat panel detector, or the initial medical image is obtained by performing repeated imaging operations on the flat panel detector. In this embodiment, the response pixel units corresponding to the pixel response arrays do not overlap with each other. Based on the above embodiment, further, the initial pixel units corresponding to the initial response arrays do not overlap with each other.

[0046] Figure 2 A schematic diagram of a pixel response array provided by an embodiment of the present invention. Specifically, Figure 2 , an initial medical image including 12×9 initial pixel units is shown, and the initial medical image includes pixel response arrays corresponding to 3 photons (white solid circles), and the dotted circle represents the maximum response range that a single photon can produce. Specifically, the center of the dotted circle represents the target space coordinate of the photon, and the radius represents the maximum response distance that a single photon can produce. In this embodiment, the maximum response ranges (dotted circles) corresponding to each photon do not overlap.

[0047] Specifically, according to the offset distance of the target spatial coordinates of the photon relative to the pixel center coordinates of the hit response pixel unit, the incident mode of the photon can be divided into three different situations: Figure 2 The pixel response array in the upper left corner shows the case without offset. Figure 2 The pixel response array in the middle shows the case of axis offset. Figure 2 The pixel response array in the lower right corner shows the case of angular offset. Figure 2 The grayscale values ​​in the three pixel response arrays represent the initial response intensity corresponding to the response pixel unit, and the smaller the grayscale value, the stronger the initial response intensity.

[0048] S120 . For each pixel response array, determine a target pixel coordinate and a target response intensity of a photon corresponding to the pixel response array based on at least three initial response intensities in the pixel response array.

[0049] In an optional embodiment, based on at least three initial response intensities in a pixel response array, target pixel coordinates and target response intensity of photons corresponding to the pixel response array are determined, including: obtaining a maximum response intensity and an intensity attenuation coefficient of the photons; determining the target spatial coordinates of the photons corresponding to the pixel response array based on the maximum response intensity, the intensity attenuation coefficient, and at least three initial response intensities; mapping the target spatial coordinates to a target pixel array corresponding to a target medical image to obtain the target pixel coordinates of the photons corresponding to the pixel response array; and taking the sum of the initial response intensities as the target response intensity of the photons corresponding to the pixel response array.

[0050] Specifically, the maximum response intensity is used to characterize the maximum response intensity generated by the flat panel detector after being hit by a photon, and the intensity attenuation coefficient is used to characterize the attenuation rate of the response intensity generated by the response pixel unit as the distance from the hit position of the photon increases. Exemplarily, the maximum response intensity and the intensity attenuation coefficient can be preset according to the detection performance of the flat panel detector.

[0051] In an optional embodiment, the target spatial coordinates of the photons corresponding to the pixel response array are determined based on the maximum response intensity, the intensity attenuation coefficient and at least three initial response intensities, including: for each initial response intensity, obtaining the difference response intensity between the maximum response intensity and the initial response intensity; taking the ratio between the difference response intensity and the intensity attenuation coefficient as the intensity attenuation distance; and determining the target spatial coordinates of the photons corresponding to the pixel response array based on the at least three intensity attenuation distances.

[0052] Specifically, the target spatial coordinates can represent the spatial position coordinates of the photon in the initial medical image, or the spatial position coordinates of the photon hitting the flat panel detector. The intensity attenuation distance can be used to represent the distance of the pixel center coordinates of the response pixel unit relative to the target spatial coordinates of the photon.

[0053] For example, the intensity decay distance Satisfies the following formula:

[0054]

[0055] Among them, A0 represents the maximum response intensity, A(x i ,y j ) represents the response pixel unit p ij The corresponding initial response intensity, β represents the intensity attenuation coefficient, (x i ,y j ) represents the response pixel unit p in the i-th row and j-th column of the initial medical image ij The corresponding pixel center coordinates, (x, y) represent the target space coordinates of the photon.

[0056] Specifically, the longer the intensity attenuation distance, the farther the target space coordinates of the photon are from the pixel center coordinates of the response pixel unit, and the weaker the initial response intensity detected by the response pixel unit. Conversely, the shorter the intensity attenuation distance, the closer the target space coordinates of the photon are to the pixel center coordinates of the response pixel unit, and the stronger the initial response intensity detected by the response pixel unit.

[0057] In an optional embodiment, the target space coordinates of the photons corresponding to the pixel response array are determined based on at least three intensity attenuation distances, including: for each intensity attenuation distance, obtaining the pixel center coordinates of the response pixel unit corresponding to the intensity attenuation distance; based on the pixel center coordinates and the intensity attenuation distance, constructing a circular equation of the response pixel unit corresponding to the intensity attenuation distance; and performing a solving operation on the equation group consisting of the at least three circular equations to obtain the target space coordinates of the photons corresponding to the pixel response array.

[0058] Specifically, the number of pixels of the response pixel unit used to determine the target space coordinates is less than or equal to the number of pixels of the response pixel unit in the pixel response array. Exemplarily, assuming that the pixel response array includes 9 response pixel units, the number of pixels of the response pixel unit used to determine the target space coordinates can be any 3 or any 4 of them.

[0059] The advantage of this setting is that it can reduce the calculation time of the target space coordinates, thereby improving the efficiency of super-resolution reconstruction of medical images.

[0060] Specifically, the pixel center coordinates are used as the center coordinates of the circle equation, and the intensity attenuation distance is used as the radius of the circle equation. In this embodiment, the target space coordinates are the intersection points of circles constructed by at least three circle equations.

[0061] Figure 3 A schematic diagram of positioning a target space coordinate provided by an embodiment of the present invention, Figure 3 by Figure 2 Take the pixel response array shown as an example. Specifically, for the pixel response array in the upper left corner, a circular equation is constructed based on the response pixel units corresponding to (2,9), (3,8) and (3,7), respectively; for the pixel response array in the middle, a circular equation is constructed based on the response pixel units corresponding to (7,7), (6,6), (7,6) and (8,6), respectively; for the pixel response array in the lower right corner, a circular equation is constructed based on the response pixel units corresponding to (12,4), (11,3), (12,3) and (12,2), respectively. From Figure 3 It can be seen that the weaker the initial response intensity, the smaller the radius of the circular equation. The circles constructed by the circular equations corresponding to each pixel response array intersect at one point, and the spatial coordinates of the intersection are the target spatial coordinates of the photon.

[0062] Since the intersection of multiple circles mathematically represents a point without spatial size, the size of the intersection can be much smaller than the inherent response pixel size of the flat-panel detector, thereby improving the physical basis for the subsequent implementation of higher spatial resolution medical imaging in the embodiments of the present invention.

[0063] In an optional embodiment, the target space coordinates are mapped to a target pixel array corresponding to the target medical image to obtain the target pixel coordinates of the photons corresponding to the pixel response array, including: obtaining the target pixel size of the target pixel unit in the target pixel array corresponding to the target medical image; based on the target pixel size, performing a rounding-down operation on the target space coordinates to obtain the target pixel coordinates of the photons corresponding to the pixel response array.

[0064] Specifically, the target pixel coordinates are used to characterize the unit position of the target pixel unit of the photon in the target medical image, and the target response intensity is used to characterize the response intensity generated by the photon in the target pixel unit.

[0065] Exemplarily, the target pixel coordinates (m, n) satisfy the formula:

[0066]

[0067]

[0068] Where (m, n) represents the mth row and nth column in the target medical image, δ del represents the response pixel size of the response pixel unit, N represents the magnification factor of the target medical image relative to the initial medical image, N ≥ 2, δ del / N represents the target pixel size of the target pixel unit, and floor represents a rounding-down function.

[0069] Specifically, the number of pixels of the response pixel unit used to determine the target response intensity is equal to the number of pixels of the response pixel unit in the pixel response array.

[0070] For example, the target response intensity Satisfy the formula:

[0071]

[0072] S130 , adding the target response intensity to the target pixel unit corresponding to the target pixel coordinate in the target medical image.

[0073] Figure 4 A schematic diagram of the conversion between an initial medical image and a target medical image provided by an embodiment of the present invention. Specifically, Figure 4 The left figure in represents an initial medical image containing P×Q initial pixel units. Figure 4 The right image in represents a target medical image containing NP×NQ target pixel units.

[0074] The technical solution of this embodiment is to obtain an initial medical image detected by a flat-panel detector, wherein the initial medical image contains at least one pixel response array corresponding to each photon, and for each pixel response array, determine the target pixel coordinates and target response intensity of the photon corresponding to the pixel response array based on the initial response intensities corresponding to at least three response pixel units in the pixel response array, and add the target response intensity to the target pixel unit corresponding to the target pixel coordinate in the target medical image, wherein the response pixel units corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit, thereby solving the problem of poor spatial resolution of traditional flat-panel detectors, and improving the spatial resolution of the flat-panel detector without changing the hardware structure of the flat-panel detector and without affecting the imaging performance of the flat-panel detector, thereby improving the image quality of the medical image.

[0075] Figure 5 This is a flow chart of another medical image super-resolution reconstruction method provided by an embodiment of the present invention. This embodiment further refines the "obtaining the maximum response intensity and intensity attenuation coefficient of photons" in the above embodiment. Figure 5 As shown, the method includes:

[0076] S210, performing a single imaging operation on the flat panel detector to obtain a corrected medical image.

[0077] Specifically, the corrected medical image includes a plurality of initial pixel units and the corrected response intensities corresponding to the initial pixel units.

[0078] S220 , taking the initial pixel unit corresponding to the maximum correction response intensity in the corrected medical image as the correction pixel unit.

[0079] Specifically, multiple correction response intensities in the corrected medical image are sorted in descending order, and the initial pixel unit corresponding to the correction response intensity that ranks first is used as the correction pixel unit.

[0080] S230. When the correction response intensities respectively corresponding to at least two adjacent pixel units corresponding to the correction pixel unit meet a preset correction condition, use the correction response intensity corresponding to the correction pixel unit as the maximum response intensity of the photon.

[0081] In an optional embodiment, each adjacent pixel unit includes at least two of the initial pixel units corresponding to the top, left, right and bottom of the correction pixel unit, respectively; or, each adjacent pixel unit includes at least two of the initial pixel units corresponding to the top left, bottom left, top right and bottom right of the correction pixel unit, respectively; or, each adjacent pixel unit includes at least two of the initial pixel units corresponding to the top, left, right and bottom of the correction pixel unit, respectively, and at least two of the initial pixel units corresponding to the top left, bottom left, top right and bottom right, respectively.

[0082] In a specific embodiment, each adjacent pixel unit includes at least two of the initial pixel units corresponding to the top, left, right and bottom of the correction pixel unit, or each adjacent pixel unit includes at least two of the initial pixel units corresponding to the top left, bottom left, top right and bottom right of the correction pixel unit, respectively. Accordingly, the preset correction condition includes that the correction response intensities corresponding to each adjacent pixel unit are equal.

[0083] In another specific embodiment, each adjacent pixel unit includes at least two of the initial pixel units corresponding to the top, left, right and bottom of the correction pixel unit, and at least two of the initial pixel units corresponding to the top left, bottom left, top right and bottom right of the correction pixel unit. Accordingly, at least two of the initial pixel units corresponding to the top, left, right and bottom of the correction pixel unit are respectively used as first pixel units, and at least two of the initial pixel units corresponding to the top left, bottom left, top right and bottom right of the correction pixel unit are respectively used as second pixel units. The preset correction conditions include that the correction response intensities corresponding to each first pixel unit are equal, and / or that the correction response intensities corresponding to each second pixel unit are equal.

[0084] Specifically, the correction response intensities corresponding to at least two adjacent pixel units corresponding to the correction pixel unit respectively meet the preset correction conditions, indicating that the photons corresponding to the correction pixel unit are incident without offset.

[0085] On the basis of the above embodiment, optionally, the method further includes: if the correction response intensities respectively corresponding to at least two adjacent pixel units corresponding to the correction pixel unit do not meet the preset correction condition, returning to execute S210.

[0086] S240, determining the intensity attenuation coefficient of the photon based on the correction response intensities corresponding to the correction pixel unit and at least two adjacent pixel units respectively.

[0087] Specifically, at least two reference attenuation coefficients are determined based on the correction response intensities corresponding to the correction pixel unit and at least two adjacent pixel units, and the intensity attenuation coefficient is determined based on the statistical values ​​corresponding to the reference attenuation coefficients. Exemplarily, the statistical value may be an average value, a maximum value, a minimum value, or a median value, etc. The specific setting of the statistical value is not limited here, and can be customized according to actual needs.

[0088] Exemplarily, the reference attenuation coefficient β' satisfies the formula:

[0089]

[0090] Wherein, A0 represents the correction response intensity corresponding to the correction pixel unit, that is, the maximum response intensity, a represents the correction response intensity corresponding to the adjacent pixel unit, Represents the pixel center distance between the pixel center coordinates corresponding to two initial pixel unit decibels.

[0091] S250: Acquire an initial medical image detected by the flat panel detector.

[0092] S260, determining the target spatial coordinates of the photons corresponding to the pixel response array based on the maximum response intensity, the intensity attenuation coefficient, and at least three initial response intensities.

[0093] S270 , mapping the target space coordinates to the target pixel array corresponding to the target medical image, and obtaining the target pixel coordinates of the pixel response array corresponding to the photons.

[0094] S280 , taking the sum of the initial response intensities as the target response intensity of the corresponding photons of the pixel response array.

[0095] S290, adding the target response intensity to the target pixel unit corresponding to the target pixel coordinate in the target medical image.

[0096] In an optional embodiment, the implementation of S250-S290 in this embodiment is the same as that in the above embodiment. Figure 1 The illustrated S110 - S140 correspond to the same or similar ones, and are not described in detail in this embodiment.

[0097] As the flat-panel detector is used for a longer period of time, its detection performance will change, which will also cause the maximum response intensity and intensity attenuation coefficient to change. Using a fixed maximum response intensity and intensity attenuation coefficient will make the spatial positioning results of photons inaccurate.

[0098] The technical solution of this embodiment is to obtain a corrected medical image by performing a single imaging operation on a flat-panel detector, and use the initial pixel unit corresponding to the maximum correction response intensity in the corrected medical image as the correction pixel unit. When the correction response intensities corresponding to at least two adjacent pixel units corresponding to the correction pixel unit meet preset correction conditions, the correction response intensity corresponding to the correction pixel unit is used as the maximum response intensity of the photon. Based on the correction response intensities corresponding to the correction pixel unit and at least two adjacent pixel units, the intensity attenuation coefficient of the photon is determined, which solves the problem of the maximum response intensity and the intensity attenuation coefficient being fixed, and has the ability to correct the maximum response intensity and the intensity attenuation coefficient, thereby further ensuring the image quality of the medical image.

[0099] On the basis of the above embodiment, optionally, obtaining an initial medical image detected by the flat-panel detector includes: performing repeated imaging operations on the flat-panel detector to obtain at least two initial medical images detected by the flat-panel detector; correspondingly, adding the target response intensity to the target pixel unit corresponding to the target pixel coordinates in the target medical image includes: obtaining the target pixel unit corresponding to the target pixel coordinates in the target medical image; when there is a response intensity in the target pixel unit, superimposing the target response intensity and adding it to the target pixel unit; when there is no response intensity in the target pixel unit, adding the target response intensity to the target pixel unit.

[0100] Specifically, at least one target response intensity corresponding to the first initial medical image is added to the respectively corresponding target pixel units of the target medical image, and other initial medical images except the first initial medical image are obtained. For each target response intensity corresponding to the other initial medical images, it is determined whether there is a response intensity in the target pixel unit corresponding to the target response intensity in the target medical image. If so, the target response intensity is superimposed and added to the target pixel unit. If not, the target response intensity is added to the target pixel unit.

[0101] Figure 6 A schematic diagram of a specific example of super-resolution reconstruction of a medical image provided by an embodiment of the present invention. Specifically, Figure 6 The figure shows the initial medical images detected by the flat panel detector corresponding to three acquisition moments, namely time=0, time=1 and time=2. For each initial medical image, the target space coordinates corresponding to at least one photon are determined based on at least one pixel response array in the initial medical image ( Figure 6The target spatial coordinates are mapped to the target pixel array corresponding to the target medical image, and the target response intensities are superimposed and added to the corresponding target pixel units in the target medical image. Based on the superposition results corresponding to the three initial medical images, the target medical image corresponding to the acquisition time of time = 2 is obtained.

[0102] The advantage of this setting is that it expands the applicable scenarios of super-resolution reconstruction methods for medical images.

[0103] The following is an embodiment of a super-resolution reconstruction device for medical images provided in an embodiment of the present invention. The device and the super-resolution reconstruction method for medical images in the above-mentioned embodiment belong to the same inventive concept. For details not described in detail in the embodiment of the super-resolution reconstruction device for medical images, reference can be made to the contents of the super-resolution reconstruction method for medical images in the above-mentioned embodiment.

[0104] Figure 7 The following is a schematic diagram of the structure of a medical image super-resolution reconstruction device provided by one embodiment of the present invention. Figure 7 As shown, the apparatus includes: an initial medical image acquisition module 310 , a target response intensity determination module 320 and a target medical image determination module 330 .

[0105] The initial medical image acquisition module 310 is used to acquire the initial medical image detected by the flat panel detector; wherein the initial medical image includes a pixel response array corresponding to at least one photon, and the pixel response array includes initial response intensities corresponding to at least three response pixel units;

[0106] A target response intensity determination module 320 is used to determine, for each pixel response array, a target pixel coordinate and a target response intensity of a photon corresponding to the pixel response array based on at least three initial response intensities in the pixel response array;

[0107] A target medical image determination module 330, configured to add a target response intensity to a target pixel unit corresponding to a target pixel coordinate in the target medical image;

[0108] The response pixel units corresponding to the pixel response arrays do not overlap each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit.

[0109] The technical solution of this embodiment is to obtain an initial medical image detected by a flat-panel detector, wherein the initial medical image contains at least one pixel response array corresponding to each photon, and for each pixel response array, determine the target pixel coordinates and target response intensity of the photon corresponding to the pixel response array based on the initial response intensities corresponding to at least three response pixel units in the pixel response array, and add the target response intensity to the target pixel unit corresponding to the target pixel coordinate in the target medical image, wherein the response pixel units corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit, thereby solving the problem of poor spatial resolution of traditional flat-panel detectors, and improving the spatial resolution of the flat-panel detector without changing the hardware structure of the flat-panel detector and without affecting the imaging performance of the flat-panel detector, thereby improving the image quality of the medical image.

[0110] In an optional embodiment, the target response strength determination module 320 includes:

[0111] An intensity attenuation coefficient acquisition unit, used to acquire the maximum response intensity and intensity attenuation coefficient of photons;

[0112] a target space coordinate determination unit, for determining the target space coordinates of the photons corresponding to the pixel response array based on the maximum response intensity, the intensity attenuation coefficient and at least three initial response intensities;

[0113] A target pixel coordinate determination unit, used for mapping the target space coordinates to the target pixel array corresponding to the target medical image, and obtaining the target pixel coordinates of the photons corresponding to the pixel response array;

[0114] The target response intensity determination unit is used to take the sum of the initial response intensities as the target response intensity of the photons corresponding to the pixel response array.

[0115] In an optional embodiment, the target space coordinate determination unit includes:

[0116] A difference response intensity determination subunit, used for obtaining a difference response intensity between the maximum response intensity and the initial response intensity for each initial response intensity;

[0117] an intensity attenuation distance determination subunit, used for taking the ratio between the difference response intensity and the intensity attenuation coefficient as the intensity attenuation distance;

[0118] The target space coordinate determination subunit is used to determine the target space coordinates of the photons corresponding to the pixel response array based on at least three intensity attenuation distances.

[0119] In an optional embodiment, the target space coordinate determination subunit is specifically used to:

[0120] For each intensity attenuation distance, obtaining the pixel center coordinates of the response pixel unit corresponding to the intensity attenuation distance;

[0121] Based on the pixel center coordinates and the intensity decay distance, a circular equation of the response pixel unit corresponding to the intensity decay distance is constructed;

[0122] A solution operation is performed on a set of equations consisting of at least three circular equations to obtain target space coordinates of photons corresponding to the pixel response array.

[0123] In an optional embodiment, the target pixel coordinate determination unit is specifically configured to:

[0124] Acquire a target pixel size of a target pixel unit in a target pixel array corresponding to a target medical image;

[0125] Based on the target pixel size, the target spatial coordinates are rounded down to obtain the target pixel coordinates of the pixel response array corresponding to the photon.

[0126] In an optional embodiment, the intensity attenuation coefficient acquisition unit is specifically used to:

[0127] performing a single imaging operation on the flat panel detector to obtain a corrected medical image;

[0128] Taking the initial pixel unit corresponding to the maximum correction response intensity in the corrected medical image as the correction pixel unit;

[0129] When the correction response intensities respectively corresponding to at least two adjacent pixel units corresponding to the correction pixel unit meet the preset correction condition, the correction response intensity corresponding to the correction pixel unit is used as the maximum response intensity of the photon;

[0130] The intensity attenuation coefficient of the photon is determined based on the correction response intensities respectively corresponding to the correction pixel unit and at least two adjacent pixel units.

[0131] In an optional embodiment, the initial medical image acquisition module 310 is specifically configured to:

[0132] Performing repeated imaging operations on the flat panel detector to obtain at least two initial medical images detected by the flat panel detector;

[0133] Accordingly, the target medical image determination module 330 is specifically configured to:

[0134] Acquire a target pixel unit corresponding to a target pixel coordinate in a target medical image;

[0135] When there is a response intensity in the target pixel unit, the target response intensity is superimposed and added to the target pixel unit;

[0136] When the response intensity does not exist in the target pixel unit, the target response intensity is added in the target pixel unit.

[0137] The medical image super-resolution reconstruction device provided in the embodiment of the present invention can execute the medical image super-resolution reconstruction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0138] Figure 8 A schematic diagram of the structure of an electronic device provided for one embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0139] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor 11, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0140] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0141] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the super-resolution reconstruction method of medical images provided in the above embodiments.

[0142] In some embodiments, the super-resolution reconstruction method of medical images provided in the above embodiments may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the super-resolution reconstruction method of medical images described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the super-resolution reconstruction method of medical images in any other appropriate manner (e.g., by means of firmware).

[0143] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] The computer program for implementing the method for super-resolution reconstruction of medical images of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, partially on the machine and partially on a remote machine as an independent software package, or completely on a remote machine or server.

[0145] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0147] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0148] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0149] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0150] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A super-resolution reconstruction method for medical images, characterized in that: include: Acquire an initial medical image detected by a flat panel detector; wherein the initial medical image comprises a pixel response array corresponding to at least one photon, and the pixel response array comprises initial response intensities corresponding to at least three response pixel units; For each pixel response array, determining a target pixel coordinate and a target response intensity of a photon corresponding to the pixel response array based on at least three initial response intensities in the pixel response array; adding the target response intensity to a target pixel unit corresponding to the target pixel coordinate in the target medical image; The response pixel units respectively corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit.

2. The method according to claim 1, characterized in that The determining, based on at least three initial response intensities in the pixel response array, target pixel coordinates and target response intensities corresponding to photons in the pixel response array comprises: Obtain the maximum response intensity and intensity attenuation coefficient of photons; Determining the target spatial coordinates of the photons corresponding to the pixel response array based on the maximum response intensity, the intensity attenuation coefficient, and at least three initial response intensities; Mapping the target spatial coordinates to a target pixel array corresponding to the target medical image to obtain target pixel coordinates of photons corresponding to the pixel response array; The sum of the initial response intensities is used as the target response intensity of the corresponding photons of the pixel response array.

3. The method according to claim 2, characterized in that The determining, based on the maximum response intensity, the intensity attenuation coefficient, and at least three initial response intensities, the target spatial coordinates of the photons corresponding to the pixel response array comprises: For each initial response intensity, obtaining a difference response intensity between the maximum response intensity and the initial response intensity; The ratio between the difference response intensity and the intensity attenuation coefficient is used as the intensity attenuation distance; Based on at least three intensity decay distances, target spatial coordinates of the photons corresponding to the pixel response array are determined.

4. The method according to claim 3, characterized in that The step of determining the target spatial coordinates of the photons corresponding to the pixel response array based on at least three intensity attenuation distances includes: For each intensity attenuation distance, obtaining the pixel center coordinates of the response pixel unit corresponding to the intensity attenuation distance; Based on the pixel center coordinates and the intensity attenuation distance, construct a circular equation of a response pixel unit corresponding to the intensity attenuation distance; A solution operation is performed on a set of equations consisting of at least three circular equations to obtain target space coordinates of photons corresponding to the pixel response array.

5. The method according to claim 2, characterized in that: Mapping the target space coordinates to the target pixel array corresponding to the target medical image to obtain the target pixel coordinates of the photons corresponding to the pixel response array includes: Acquire a target pixel size of a target pixel unit in a target pixel array corresponding to the target medical image; Based on the target pixel size, a rounding-down operation is performed on the target spatial coordinates to obtain target pixel coordinates of the photons corresponding to the pixel response array.

6. The method according to claim 2, characterized in that The obtaining of the maximum response intensity and intensity attenuation coefficient of photons includes: performing a single imaging operation on the flat panel detector to obtain a corrected medical image; Taking the initial pixel unit corresponding to the maximum correction response intensity in the corrected medical image as the correction pixel unit; When the correction response intensities respectively corresponding to at least two adjacent pixel units corresponding to the correction pixel unit meet a preset correction condition, the correction response intensity corresponding to the correction pixel unit is used as the maximum response intensity of the photon; The intensity attenuation coefficient of the photon is determined based on the correction response intensities respectively corresponding to the correction pixel unit and at least two adjacent pixel units.

7. The method according to any one of claims 1 to 6, characterized in that: The step of acquiring the initial medical image detected by the flat panel detector comprises: Performing repeated imaging operations on the flat panel detector to obtain at least two initial medical images detected by the flat panel detector; Accordingly, the step of adding the target response intensity to a target pixel unit corresponding to the target pixel coordinate in the target medical image includes: Acquire a target pixel unit corresponding to the target pixel coordinates in the target medical image; When there is a response intensity in the target pixel unit, superimposing the target response intensity on the target pixel unit; When the response intensity does not exist in the target pixel unit, the target response intensity is added to the target pixel unit.

8. A super-resolution reconstruction device for medical images, characterized in that: include: An initial medical image acquisition module is used to acquire an initial medical image detected by the flat panel detector; wherein the initial medical image includes a pixel response array corresponding to at least one photon, and the pixel response array includes initial response intensities corresponding to at least three response pixel units; A target response intensity determination module, configured to determine, for each pixel response array, a target pixel coordinate and a target response intensity of a photon corresponding to the pixel response array based on at least three initial response intensities in the pixel response array; A target medical image determination module, configured to add the target response intensity to a target pixel unit corresponding to the target pixel coordinate in the target medical image; The response pixel units respectively corresponding to the pixel response arrays do not overlap with each other, and the target pixel size of the target pixel unit is smaller than the response pixel size of the response pixel unit.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the super-resolution reconstruction method for a medical image according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the medical image super-resolution reconstruction method according to any one of claims 1 to 7 when executed.

Images