Multi-phase medical image processing method, system, computer storage medium and device

Abstract

The present invention provides a method, system, computer storage medium and device for processing multi-phase medical images, the method comprising: determining the distribution position information of the organ to be diagnosed in each phase of the multi-phase medical images in the medical images of the organ to be diagnosed in the vertical direction; using the distribution position information of the organ to be diagnosed in each phase of the medical images, amplifying the organ to be diagnosed in each phase of the medical images to form each phase of the amplified medical images of the organ to be diagnosed; aligning the organ to be diagnosed in each phase of the amplified medical images of the organ to be diagnosed in the vertical and horizontal directions to obtain the registered medical images of each phase; restoring the registered medical images of each phase to the original images of each phase. The present invention has low requirements on the resolution of medical images, has strong robustness and adaptability, can align multi-phase or multi-modal medical images, match the anatomical points in the images, and improve the accuracy of the subsequent diagnosis process.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image processing, and relates to a processing method and system, and in particular to a processing method, system, computer storage medium and device for multi-period medical images. Background Art

[0002] Medical image registration technology is a branch of medical image processing and is widely used in clinical diagnosis and treatment. It means that for different medical images of the same entity, a spatial transformation mapping is found to make the corresponding positions on different medical images consistent in space. This consistency means that the same anatomical point on the human body has the same spatial position in two matching images. The result of registration should match all anatomical points on the two images, or at least all anatomical points with diagnostic significance.

[0003] According to the difference of image information used in medical image registration, image registration methods are divided into three main categories: grayscale information-based method, transform domain method and feature-based method. The current mainstream registration method is mainly a multi-parameter optimization process, which consists of four components: feature space, search space, search algorithm and similarity measure. The feature space is to extract the features of the image to be registered, the search space is the way and range of transformation; the search algorithm determines the specific method of the next transformation to obtain the optimal transformation parameters; the similarity measure is a standard used to measure the similarity between images.

[0004] The effect of the above registration method depends largely on the resolution of the medical image. In the application scenario of CT tomography, the requirements for the slice distance are relatively high. When the image resolution is low, the CT image may lose information due to improper interpolation selection, which will affect the use of subsequent diagnosis and treatment. At the same time, the search process of parameter optimization in this process generally has a large amount of calculation, a long processing time, and may also be difficult to converge.

[0005] Therefore, how to provide a multi-phase medical image processing method, system, computer storage medium and device to solve the problem that the existing technology relies on the resolution of medical images. When the image resolution is low, the CT image may lose information due to improper interpolation selection, which affects the subsequent diagnosis and treatment. At the same time, due to the large amount of calculation and long processing time in the parameter optimization search process, it leads to defects such as difficulty in convergence. This has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0006] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a multi-phase medical image processing method, system, computer storage medium and device, which are used to solve the problem that the prior art relies on the resolution of medical images. When the resolution of the image is low, the CT image may lose information due to improper interpolation selection, which affects the use of subsequent diagnosis and treatment; at the same time, due to the large amount of calculation and long processing time in the parameter optimization search process, it leads to the problem of difficulty in convergence.

[0007] To achieve the above-mentioned purpose and other related purposes, the present invention provides, on one hand, a method for processing multi-phase medical images, wherein the multi-phase medical images are multi-phase medical images of an organ to be diagnosed; the method for processing the multi-phase medical images comprises: determining the distribution position information of the organ to be diagnosed in the vertical direction in each phase medical image of the multi-phase medical images; using the distribution position information of the organ to be diagnosed in each phase medical image, enlarging the organ to be diagnosed in each phase medical image to form enlarged medical images of each phase of the organ to be diagnosed; aligning the organ to be diagnosed in the enlarged medical images of each phase of the organ to be diagnosed in the vertical and horizontal directions to obtain registered medical images of each phase; and restoring the registered medical images of each phase into original images of each phase.

[0008] In one embodiment of the present invention, the step of determining the distribution position information of the organ to be diagnosed along the vertical direction includes: in the vertical direction of each period of medical images, determining whether the pixels of the organ to be diagnosed contained in each slice exceed a preset pixel threshold; if so, it means that the slice contains the organ to be diagnosed; if not, it means that the slice does not contain the organ to be diagnosed; in the medical images containing the organ to be diagnosed, searching for the medical image of the maximum continuous slice containing the organ to be diagnosed, so as to determine the distribution position information of the organ to be diagnosed along the vertical direction in the medical images of each period; the distribution position information of the organ to be diagnosed along the vertical direction is the number sequence of voxels of the organ to be diagnosed.

[0009] In one embodiment of the present invention, the step of utilizing the distribution position information of the organ to be diagnosed in each period of medical images to enlarge the organ to be diagnosed in each period of medical images to form enlarged medical images of each period of the organ to be diagnosed includes: taking the medical image of the largest continuous section containing the organ to be diagnosed as the reference medical image; calculating the length difference between the reference medical image and the organ to be diagnosed in each period of medical images to obtain the number of to-be-supplemented insertion layers in each period of medical images; eliminating positions that are not suitable for inserting to-be-supplemented insertion layers from each period of medical images, determining the insertion positions of to-be-supplemented insertion layers, and marking the insertion positions; inserting to-be-supplemented insertion layers at the determined insertion positions; wherein the insertion content of the to-be-supplemented insertion layers comes from the upper adjacent layer of the insertion position.

[0010] In one embodiment of the present invention, the step of determining the insertion position of the to-be-supplemented insertion layer includes: traversing all insertion positions, calculating the Euclidean distance between the number sequences of the organs to be diagnosed after insertion; and selecting the insertion position corresponding to the minimum Euclidean distance between the number sequences of the organs to be diagnosed as the determined insertion position.

[0011] In one embodiment of the present invention, the step of removing positions that are not suitable for inserting the to-be-supplemented insertion layer includes: removing insertion positions inserted on one side of the organ to be diagnosed and removing insertion positions that are inserted continuously.

[0012] In one embodiment of the present invention, the step of aligning the organ to be diagnosed in each period of medical images in which the organ to be diagnosed is enlarged in the vertical direction includes: comparing the reference medical image with the medical images of each period, deleting the slices other than the organ to be diagnosed in the medical images of each period to align the organ to be diagnosed in the medical images of each period in the vertical direction, and marking the deleted positions.

[0013] In one embodiment of the present invention, the step of aligning the organ to be diagnosed in each period of medical images in which the organ to be diagnosed is enlarged in the horizontal direction includes: calculating the centroid coordinates of the organ to be diagnosed in each period of medical images; selecting any one period of medical images as a reference medical image, and translating the remaining medical images in the horizontal direction so that the centroids in the medical images of each period coincide.

[0014] On the other hand, the present invention provides a multi-phase medical image processing system, wherein the multi-phase medical image is a multi-phase medical image of an organ to be diagnosed; the multi-phase medical image processing system comprises: a determination module, used to determine the distribution position information of the organ to be diagnosed in each phase of the multi-phase medical image along the vertical direction; an amplification module, used to amplify the organ to be diagnosed in each phase of the medical image using the distribution position information of the organ to be diagnosed in each phase of the medical image to form a magnified medical image of each phase of the organ to be diagnosed; an alignment module, used to align the organ to be diagnosed in the magnified medical images of each phase of the organ to be diagnosed in the vertical direction and the horizontal direction to obtain the registered medical images of each phase; and a restoration module, used to restore the registered medical images of each phase into the original images of each phase of the medical image.

[0015] Yet another aspect of the present invention provides a computer storage medium having a computer program stored thereon, which implements the method for processing multi-phase medical images when executed by a processor.

[0016] The last aspect of the present invention provides a device, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the device executes the method for processing multi-phase medical images.

[0017] As described above, the method, system, computer storage medium and device for processing multi-period medical images of the present invention have the following beneficial effects:

[0018] The present invention can achieve the effect of registration and alignment in a relatively short time. It has low requirements on the resolution of medical images and has strong robustness and adaptability. It can be well applied to the preprocessing stage of machine diagnosis to register and align multi-phase or multi-modal medical images so that the anatomical points in the images match and improve the accuracy of the subsequent diagnosis process. After registration, it can ensure that the CT image reflects the integrity and continuity of the medical structure, retains valuable medical features, and has high usability. At the same time, operations such as marking and modification made on the processed medical image will not be destroyed in the restoration operation, and can be reflected while retaining the original CT image. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 FIG. 4 is a flow chart of a method for processing multi-phase medical images in one embodiment of the present invention.

[0020] Figure 2 The display is a distribution diagram of the liver distribution position information along the vertical direction according to the present invention.

[0021] Figure 3 It is a schematic flow chart of S12 in the method for processing multi-phase medical images of the present invention.

[0022] Figure 4 Shown is a schematic diagram of a reference medical image and a first-phase CT medical image of the present invention.

[0023] Figure 5 Shown is a comparison diagram of the liver portion in the reference medical image of the present invention and the first-phase CT medical image in which the layer to be supplemented is inserted.

[0024] Figure 6 FIG. 1 is a schematic diagram showing the principle structure of a multi-phase medical image processing system in one embodiment of the present invention.

[0025] Component number description

[0026] 1 Multi-phase medical image processing system

[0027] 61 Determine module

[0028] 62 Amplification module

[0029] 63 Alignment Module

[0030] 64 Restore Module

[0031] Steps S11 to S14

[0032] Steps S121 to S124 DETAILED DESCRIPTION

[0033] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0034] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0035] Embodiment 1

[0036] This embodiment provides a method for processing a multi-phase medical image, wherein the multi-phase medical image is a multi-phase medical image of an organ to be diagnosed; the method for processing the multi-phase medical image comprises:

[0037] Determining the distribution position information of the organ to be diagnosed in the vertical direction in each medical image of the plurality of medical images;

[0038] Using the distribution position information of the organ to be diagnosed in each period of medical images, the organ to be diagnosed in each period of medical images is enlarged to form enlarged medical images of each period of the organ to be diagnosed;

[0039] Aligning the organs to be diagnosed in the magnified medical images of each phase of the organs to be diagnosed in the vertical direction and the horizontal direction to obtain the registered medical images of each phase;

[0040] The registered medical images of each period are restored to the original images of the medical images of each period.

[0041] The following will describe in detail the method for processing multi-phase medical images provided by this embodiment in conjunction with the diagram. In this embodiment, the medical image adopts a CT medical image. The organs to be diagnosed include the liver, lungs, brain, etc. In this embodiment, the organ to be diagnosed is the liver.

[0042] See also Figure 1 , which is a flow chart of a method for processing a multi-phase medical image in one embodiment. Figure 1 As shown, the method for processing multiple medical images specifically includes the following steps:

[0043] S11, determining distribution position information of the liver along the vertical direction in each phase CT medical image of the liver in the multi-phase CT medical images.

[0044] Specifically, the S11 includes:

[0045] In the vertical direction of each phase of the CT medical image, determine whether the liver pixels contained in each slice exceed a preset pixel threshold, if yes, it means that the slice contains the liver; if no, it means that the slice does not contain the liver;

[0046] In the CT medical image containing the liver, the CT medical image containing the largest continuous slice of the liver is searched to determine the distribution position information of the liver along the vertical direction in each phase of the CT medical image. The distribution position information of the liver along the vertical direction is a sequence of the number of liver voxels. The distribution map of the distribution position information of the liver along the vertical direction is as follows: Figure 2 As shown, each column represents the area of ​​the liver on a slice on the CT image.

[0047] S12, using the distribution position information of the liver in the CT medical images of each period, the liver in the CT medical images of each period is enlarged to form enlarged CT medical images of the liver in each period. The area distribution of the liver in the vertical direction in the enlarged CT medical images of the liver in each period is maximally similar.

[0048] See also Figure 3 , which is a schematic diagram of the process of S12. Figure 3 As shown, the S12 includes:

[0049] S121, using the CT medical image containing the largest continuous slice of the liver as the reference medical image. The CT medical image containing the largest continuous slice of the liver is a reference medical image and a first-phase CT medical image. Figure 4 shown.

[0050] S122, calculating the length difference between the reference medical image and the liver in each phase of the CT medical image, so as to obtain the number of layers to be supplemented and inserted in each phase of the CT medical image. Figure 5 , which is a comparison diagram of the liver in the reference medical image and the first-phase CT medical image in which the layer to be supplemented is inserted. Figure 5 As shown, the length of the liver part of the reference medical image is 13 layers, the length of the liver part in a certain period of CT medical image is 1, and the number of layers to be supplemented and inserted in each period of CT medical image is 2.

[0051] S123, removing positions that are not suitable for inserting the to-be-supplemented insertion layer from the CT medical images of each phase, determining the insertion positions of the to-be-supplemented insertion layer, and marking the insertion positions.

[0052] To reduce the complexity of the search algorithm, the step of eliminating positions that are not suitable for inserting the to-be-supplemented insertion layer in this embodiment includes: eliminating insertion positions inserted on one side of the liver and eliminating insertion positions that are continuously inserted.

[0053] Since the deformation of both sides of the liver is large when it is squeezed, the setting of eliminating the insertion position on one side of the liver is more in line with the actual situation.

[0054] In order to disperse the insertion positions throughout the liver and make the enlargement of the liver closer to the actual deformation, the insertion positions that are inserted continuously are eliminated.

[0055] In this embodiment, the insertion positions where the volume difference of the liver in the two-phase CT medical images is large can be eliminated by eliminating the positions that are not suitable for inserting the to-be-supplemented insertion layer.

[0056] The step of determining the insertion position of the to-be-supplemented insertion layer comprises:

[0057] Traverse all insertion positions and calculate the Euclidean distance between the number sequences of the liver after insertion;

[0058] The Euclidean distance D between two images i1 and i2 in a CT medical image is calculated as follows:

[0059]

[0060] Among them, {A ni} i＝1,2,3,n＝1,…,d is the vertical distribution sequence in a certain period of CT images, A ni is the area of ​​the liver in the n-th layer CT image at the i-th stage, and d is the depth of the 3D CT image.

[0061] The insertion position corresponding to the minimum Euclidean distance between the number sequences of the liver is selected as the determined insertion position.

[0062] S124, inserting a to-be-supplemented insertion layer at the determined insertion position; wherein the insertion content of the to-be-supplemented insertion layer comes from the upper adjacent layer of the insertion position.

[0063] S13, aligning the liver in the enlarged medical images of each phase of the liver in the vertical direction and the horizontal direction to obtain the registered CT medical images of each phase.

[0064] Specifically, the step of aligning the organs to be diagnosed in the enlarged CT medical images of the liver in each phase in the vertical direction includes:

[0065] The reference medical image is compared with the CT medical images of each period, and the slices other than the liver in the CT medical images of each period are deleted to align the liver in the CT medical images of each period in the vertical direction (that is, the total number of layers of the liver in the reference medical image is the same, and the vertical position of the liver is the same), and the deleted positions are marked.

[0066] Specifically, the step of aligning the liver in the enlarged CT medical images of the liver in the horizontal direction includes:

[0067] Calculate the centroid coordinates of the liver in each phase of CT medical images, that is, the average coordinates of all liver voxels;

[0068]

[0069] Among them, {x i} i＝1,2,…,k It is a set of points in the liver.

[0070] A CT medical image of any period is selected as a control medical image, and the remaining CT medical images of each period are translated in the horizontal direction so that the centroids of the CT medical images of each period coincide.

[0071] In this embodiment, the registration and alignment process of the multi-phase CT images of the liver has been completed. The multi-phase CT images of the liver after the registration and alignment can be used for various purposes such as clinical diagnosis.

[0072] S14, restoring the registered medical images of each period into the original images of each period, and during the restoration process, retaining the information such as the insertion position, deletion position and vertical / horizontal displacement of the CT medical image in the original image.

[0073] The method for processing multi-phase medical images described in this embodiment can achieve the effect of registration and alignment in a relatively short time. It has low requirements on the resolution of medical images and has strong robustness and adaptability. It can be well applied to the preprocessing stage of machine diagnosis to register and align multi-phase or multi-modal medical images so that the anatomical points in the images match and improve the accuracy of the subsequent diagnosis process. After registration, it can ensure that the CT image reflects the integrity and continuity of the medical structure, retains valuable medical features, and has high usability. At the same time, the marking, modification and other operations performed on the processed medical image will not be destroyed in the restoration operation, and can be reflected while retaining the original CT image.

[0074] This embodiment also provides a computer storage medium (also called computer-readable storage medium) on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for processing multi-phase medical images is implemented.

[0075] A person skilled in the art can understand that computer-readable storage media: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0076] Embodiment 2

[0077] This embodiment provides a multi-phase medical image processing system, wherein the multi-phase medical image is a multi-phase medical image of an organ to be diagnosed; the multi-phase medical image processing system comprises:

[0078] A determination module, used to determine the distribution position information of the organ to be diagnosed in the vertical direction in each medical image of the plurality of medical images;

[0079] An enlargement module, used to enlarge the organs to be diagnosed in the medical images of each period by using the distribution position information of the organs to be diagnosed in the medical images of each period, so as to form enlarged medical images of the organs to be diagnosed in each period;

[0080] An alignment module, used for aligning the organs to be diagnosed in the magnified medical images of each period of the organs to be diagnosed in the vertical direction and the horizontal direction to obtain the registered medical images of each period;

[0081] The restoration module is used to restore the registered medical images of each period to the original images of each period.

[0082] The following will describe in detail the multi-phase medical image processing system provided by this embodiment in conjunction with the diagrams. In this embodiment, the medical image is a CT medical image, and the organ to be diagnosed is the liver.

[0083] See also Figure 6 , which is a schematic diagram showing the principle structure of a multi-phase medical image processing system in one embodiment. Figure 6 As shown, the multi-phase medical image processing system 6 includes a determination module 61 , an enlargement module 62 , an alignment module 63 and a restoration module 64 .

[0084] The determination module 61 is used to determine the distribution position information of the liver along the vertical direction in each phase CT medical image of the liver in the multi-phase CT medical image.

[0085] Specifically, the determination module 61 determines whether the liver pixels contained in each slice in the vertical direction of each CT medical image exceed the preset pixel threshold. If so, it means that the slice contains the liver; if not, it means that the slice does not contain the liver. In the CT medical image containing the liver, the CT medical image with the largest continuous slice containing the liver is searched to determine the distribution position information of the liver in the vertical direction in each CT medical image. The distribution position information of the liver in the vertical direction is the number sequence of liver voxels. The distribution position information of the liver in the vertical direction is as follows: Figure 2 As shown, each column represents the area of ​​the liver on a slice on the CT image.

[0086] The enlargement module 62 is used to enlarge the liver in each CT medical image using the distribution position information of the liver in each CT medical image to form an enlarged CT medical image of the liver in each period. The area distribution of the liver in the vertical direction in the enlarged CT medical image of the liver in each period is maximally similar.

[0087] Specifically, the amplification module 62 uses the CT medical image containing the largest continuous section of the liver as a reference medical image; calculates the length difference between the reference medical image and the liver in each period of the CT medical image to obtain the number of layers to be supplemented in each period of the CT medical image; removes positions that are not suitable for inserting the layers to be supplemented from the CT medical images of each period, determines the insertion position of the layers to be supplemented, and marks the insertion position; inserts the layers to be supplemented at the determined insertion position; wherein the insertion content of the layers to be supplemented comes from the upper adjacent layer of the insertion position.

[0088] The alignment module 63 is used to align the liver in the enlarged medical images of each phase of the liver in the vertical direction and the horizontal direction to obtain the registered CT medical images of each phase.

[0089] Specifically, the alignment module 63 compares the reference medical image with the CT medical images of each period, deletes the slices other than the liver in the CT medical images of each period, so as to align the liver in the CT medical images of each period in the vertical direction (even if the total number of slices of the liver is the same as that of the reference medical image, and the vertical position of the liver is the same), and marks the deleted positions.

[0090] Specifically, the alignment module 63 calculates the centroid coordinates of the liver in each phase of the CT medical image, that is, the coordinate average of all liver voxels; selects any phase of the CT medical image as the control medical image, and translates the remaining phases of the CT medical image in the horizontal direction so that the centroids in the CT medical images of each phase coincide.

[0091] In this embodiment, the registration and alignment process of the multi-phase CT images of the liver has been completed. The multi-phase CT images of the liver after the registration and alignment can be used for various purposes such as clinical diagnosis.

[0092] The restoration module 64 is used to restore the registered medical images of each period to the original images of each period, and to preserve the information such as the insertion position, deletion position and vertical / horizontal displacement of the CT medical image in the original image during the restoration process.

[0093] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements, or they can all be implemented in the form of hardware, or some modules can be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example: the x module can be a separately established processing element, or it can be integrated in a certain chip of the above system. In addition, the x module can also be stored in the memory of the above system in the form of program code, and called and executed by a certain processing element of the above system. The implementation of other modules is similar. These modules can be integrated together in whole or in part, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software. The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), one or more digital singnal processors (DSP), one or more field programmable gate arrays (FPGA), etc. When a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. These modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0094] Embodiment 3

[0095] This embodiment provides a device, which includes: a processor, a memory, a transceiver, a communication interface and / or a system bus; the memory and the communication interface are connected to the processor and the transceiver through the system bus and complete communication with each other, the memory is used to store computer programs, the communication interface is used to communicate with other devices, and the processor and the transceiver are used to run the computer program, so that the device executes each step of the multi-phase medical image processing method as described above.

[0096] The system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize the communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM), and may also include non-volatile memory, such as at least one disk storage.

[0097] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0098] The protection scope of the multi-phase medical image processing method described in the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0099] The present invention also provides a multi-phase medical image processing system, which can implement the multi-phase medical image processing method described in the present invention. However, the implementation device of the multi-phase medical image processing method described in the present invention includes but is not limited to the structure of the multi-phase medical image processing system listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0100] In summary, the present invention can achieve the effect of registration and alignment in a relatively short time. It has low requirements on the resolution of medical images and has strong robustness and adaptability. It can be well applied to the preprocessing stage of machine diagnosis to register and align multi-phase or multi-modal medical images so that the anatomical points in the image match and improve the accuracy of the subsequent diagnosis process. After registration, it can ensure that the CT image reflects the integrity and continuity of the medical structure, retains valuable medical features, and has high usability. At the same time, operations such as marking and modification made on the processed medical image will not be destroyed in the restoration operation, and can be reflected while retaining the original CT image. It effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0101] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for processing multi-period medical images, characterized in that: The multi-phase medical image is a multi-phase medical image of an organ to be diagnosed; the processing method of the multi-phase medical image includes: Determining the distribution position information of the organ to be diagnosed in the vertical direction in each medical image of the plurality of medical images; Using the distribution position information of the organ to be diagnosed in each period of medical images, the organ to be diagnosed in each period of medical images is enlarged to form enlarged medical images of each period of the organ to be diagnosed; Aligning the organs to be diagnosed in the magnified medical images of each phase of the organs to be diagnosed in the vertical direction and the horizontal direction to obtain the registered medical images of each phase; Restoring the registered medical images of each period to the original images of the medical images of each period; The step of utilizing the distribution position information of the organ to be diagnosed in each period of medical images to enlarge the organ to be diagnosed in each period of medical images to form enlarged medical images of each period of the organ to be diagnosed comprises: Taking the medical image containing the largest continuous slice of the organ to be diagnosed as the reference medical image; Calculating the length difference between the reference medical image and the organ to be diagnosed in each period of medical images to obtain the number of layers to be supplemented and inserted in each period of medical images; Eliminate positions that are not suitable for inserting the to-be-supplemented insertion layer from each medical image, determine the insertion position of the to-be-supplemented insertion layer, and mark the insertion position; Inserting a to-be-supplemented insertion layer at the determined insertion position; wherein the insertion content of the to-be-supplemented insertion layer comes from the upper adjacent layer of the insertion position; The step of determining the insertion position of the to-be-supplemented insertion layer comprises: Traversing all insertion positions, and calculating the Euclidean distance between the number sequences of the organs to be diagnosed after insertion; The insertion position corresponding to the minimum Euclidean distance between the number sequences of the organs to be diagnosed is selected as the determined insertion position.

2. The method for processing multi-phase medical images according to claim 1, characterized in that: The step of determining the distribution position information of the organ to be diagnosed along the vertical direction comprises: In the vertical direction of each medical image, determine whether the pixels of the organ to be diagnosed included in each slice exceed a preset pixel threshold. If yes, it means that the slice includes the organ to be diagnosed; if no, it means that the slice does not include the organ to be diagnosed; In the medical image containing the organ to be diagnosed, the medical image containing the largest continuous section of the organ to be diagnosed is searched to determine the distribution position information of the organ to be diagnosed along the vertical direction in each period of medical images; the distribution position information of the organ to be diagnosed along the vertical direction is the number sequence of voxels of the organ to be diagnosed.

3. The method for processing multi-phase medical images according to claim 1, characterized in that: The steps of eliminating the position that is not suitable for inserting the to-be-supplemented insertion layer include: Insertion positions inserted at one side of the organ to be diagnosed and insertion positions inserted continuously are eliminated.

4. The method for processing multi-phase medical images according to claim 1, characterized in that: The step of vertically aligning the organ to be diagnosed in each phase of the magnified medical image of the organ to be diagnosed comprises: The reference medical image is compared with the medical images of each period, and the slices other than the organ to be diagnosed in the medical images of each period are deleted to align the organs to be diagnosed in the medical images of each period in the vertical direction, and the deleted positions are marked.

5. The method for processing multi-phase medical images according to claim 1, characterized in that: The step of aligning the organs to be diagnosed in the magnified medical images of each phase of the organs to be diagnosed in the horizontal direction comprises: Calculate the centroid coordinates of the organs to be diagnosed in each period of medical images; A medical image of any period is selected as a control medical image, and the other medical images of each period are translated in the horizontal direction so that the centroids of the medical images of each period coincide.

6. A multi-period medical image processing system, characterized in that: The multi-phase medical image is a multi-phase medical image of an organ to be diagnosed; the multi-phase medical image processing system comprises: A determination module, used to determine the distribution position information of the organ to be diagnosed in the vertical direction in each medical image of the plurality of medical images; An enlargement module, used to enlarge the organs to be diagnosed in the medical images of each period by using the distribution position information of the organs to be diagnosed in the medical images of each period, so as to form enlarged medical images of the organs to be diagnosed in each period; An alignment module, used for aligning the organs to be diagnosed in the magnified medical images of each period of the organs to be diagnosed in the vertical direction and the horizontal direction to obtain the registered medical images of each period; A restoration module, used for restoring the registered medical images of each period to the original images of each period; The step of utilizing the distribution position information of the organ to be diagnosed in each period of medical images to enlarge the organ to be diagnosed in each period of medical images to form enlarged medical images of each period of the organ to be diagnosed comprises: Taking the medical image containing the largest continuous slice of the organ to be diagnosed as the reference medical image; Calculating the length difference between the reference medical image and the organ to be diagnosed in each period of medical images to obtain the number of layers to be supplemented and inserted in each period of medical images; Eliminate positions that are not suitable for inserting the to-be-supplemented insertion layer from each medical image, determine the insertion position of the to-be-supplemented insertion layer, and mark the insertion position; Inserting a to-be-supplemented insertion layer at the determined insertion position; wherein the insertion content of the to-be-supplemented insertion layer comes from the upper adjacent layer of the insertion position; The step of determining the insertion position of the to-be-supplemented insertion layer comprises: Traversing all insertion positions, and calculating the Euclidean distance between the number sequences of the organs to be diagnosed after insertion; The insertion position corresponding to the minimum Euclidean distance between the number sequences of the organs to be diagnosed is selected as the determined insertion position.

7. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing multi-phase medical images as described in any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method for processing multi-phase medical images as described in any one of claims 1 to 5.

Images