Multimodal medical image fusion method, device and equipment based on homomorphic filtering

Abstract

The present application provides a multimodal medical image fusion method, device, equipment and computer-readable storage medium based on homomorphic filtering. The multimodal medical image fusion method based on homomorphic filtering includes: performing wavelet transform on CT images and MRI images to obtain approximate coefficients and wavelet coefficients of the CT images and MRI images respectively; performing pixel value comparison based on the approximate coefficients of the CT images and MRI images to determine the weight map; performing homomorphic filtering on the weight map to obtain a precise weight map; performing weighted fusion based on the approximate coefficients and precise weight map of the CT images and MRI images to obtain fused approximate coefficients; performing weighted fusion based on the wavelet coefficients and precise weight map of the CT images and MRI images to obtain fused wavelet coefficients; performing inverse wavelet transform based on the fused approximate coefficients and fused wavelet coefficients to obtain a fused image of the CT image and the MRI image. According to the embodiment of the present application, the problem of fuzzy fused images and image artifacts can be solved.

Description

Technical Field

[0001] The present application belongs to the field of surgical robots, and in particular, relates to a multimodal medical image fusion method, device, equipment and computer-readable storage medium based on homomorphic filtering. Background Art

[0002] CT and MRI are the most commonly used imaging methods in clinical disease diagnosis. Fusion of CT and MRI images will combine the advantages of the two imaging technologies to make up for the shortcomings of a single imaging mode. The combined image contains richer, more visual and global information. Obtaining new diagnostic information through fusion imaging will help to accurately identify the spatial location of lesions.

[0003] At present, in the related technology, in the process of multimodal image fusion, there is a phenomenon of image smoothing causing image content and image edge blurring, and there is also a phenomenon of generating fusion artifacts.

[0004] Therefore, how to solve the problem of fusion image blur and image artifacts is a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0005] The embodiments of the present application provide a multimodal medical image fusion method, apparatus, device and computer-readable storage medium based on homomorphic filtering, which can solve the problems of fused image blur and image artifacts.

[0006] In a first aspect, an embodiment of the present application provides a multimodal medical image fusion method based on homomorphic filtering, comprising:

[0007] Perform wavelet transform on CT image and MRI image to obtain approximate coefficients and wavelet coefficients of CT image and MRI image respectively;

[0008] Based on the approximate coefficients of the CT image and the MRI image, the pixel values ​​are compared to determine the weight map;

[0009] Perform homomorphic filtering on the weight graph to obtain an accurate weight graph;

[0010] Based on the approximate coefficients and precise weight maps of CT images and MRI images, weighted fusion is performed to obtain the fusion approximate coefficients;

[0011] Based on the wavelet coefficients and precise weight maps of CT images and MRI images, weighted fusion is performed to obtain fused wavelet coefficients;

[0012] Based on the fused approximation coefficients and the fused wavelet coefficients, an inverse wavelet transform is performed to obtain a fused image of the CT image and the MRI image.

[0013] Optionally, wavelet transform is performed on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image, respectively, including:

[0014] The CT image is subjected to wavelet transform to obtain the approximate coefficients of the CT image and three wavelet coefficients.

[0015] Optionally, wavelet transform is performed on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image, respectively, including:

[0016] The MRI image is subjected to wavelet transform to obtain the approximate coefficients of the MRI image and three wavelet coefficients.

[0017] Optionally, homomorphic filtering is performed on the weight graph to obtain an accurate weight graph, including:

[0018] Design a homomorphic filter;

[0019] The weight map is used as the input image of the homomorphic filter, the approximate coefficients of the CT image and the MRI image are used as the guide images, and the weight mapping is smoothed using homomorphic filtering to obtain an accurate weight map.

[0020] Optionally, use the weight map as the input image to the homomorphic filter, including:

[0021] The weight map is subjected to logarithmic operation and fast Fourier transform in sequence to obtain the input image of the homomorphic filter.

[0022] Optionally, the approximate coefficients of the CT image and the MRI image are used as guide images, and the weight mapping is smoothed using homomorphic filtering to obtain an accurate weight map, including:

[0023] The output image of the homomorphic filter is subjected to inverse fast Fourier transform and exponential operation in sequence to obtain an accurate weight map.

[0024] Optionally, based on the wavelet coefficients and precise weight maps of the CT image and the MRI image, weighted fusion is performed to obtain fused wavelet coefficients, including:

[0025] The three wavelet coefficients of the CT image and the three wavelet coefficients of the MRI image are fused respectively to obtain the corresponding three fused wavelet coefficients.

[0026] In a second aspect, an embodiment of the present application provides a multimodal medical image fusion device based on homomorphic filtering, comprising:

[0027] A wavelet transform module is used to perform wavelet transform on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image respectively;

[0028] A pixel value comparison module, used for comparing pixel values ​​based on approximate coefficients of the CT image and the MRI image, and determining a weight map;

[0029] Homomorphic filtering module, used to perform homomorphic filtering on the weight graph to obtain an accurate weight graph;

[0030] A fusion approximate coefficient acquisition module is used to perform weighted fusion based on the approximate coefficients and precise weight maps of CT images and MRI images to obtain fusion approximate coefficients;

[0031] The fusion wavelet coefficient acquisition module is used to perform weighted fusion based on the wavelet coefficients and precise weight map of CT images and MRI images to obtain fused wavelet coefficients;

[0032] The inverse wavelet transform module is used to perform inverse wavelet transform based on the fused approximate coefficients and the fused wavelet coefficients to obtain a fused image of the CT image and the MRI image.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0034] When the processor executes the computer program instructions, a multimodal medical image fusion method based on homomorphic filtering is implemented.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement a multimodal medical image fusion method based on homomorphic filtering.

[0036] The multimodal medical image fusion method, apparatus, device and computer-readable storage medium based on homomorphic filtering in the embodiments of the present application can solve the problems of fused image blur and image artifacts.

[0037] The multimodal medical image fusion method based on homomorphic filtering includes: performing wavelet transform on a CT image and an MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image respectively; performing pixel value comparison based on the approximate coefficients of the CT image and the MRI image to determine a weight map; performing homomorphic filtering on the weight map to obtain a precise weight map; performing weighted fusion based on the approximate coefficients of the CT image and the MRI image and the precise weight map to obtain fused approximate coefficients; performing weighted fusion based on the wavelet coefficients of the CT image and the MRI image and the precise weight map to obtain fused wavelet coefficients; performing inverse wavelet transform based on the fused approximate coefficients and the fused wavelet coefficients to obtain a fused image of the CT image and the MRI image. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 It is a flowchart of a multimodal medical image fusion method based on homomorphic filtering provided by an embodiment of the present application;

[0040] Figure 2 It is a flowchart of a multimodal medical image fusion method based on homomorphic filtering provided by an embodiment of the present application;

[0041] Figure 3 is a flow chart of a homomorphic filtering algorithm provided by an embodiment of the present application;

[0042] Figure 4 It is a structural schematic diagram of a multimodal medical image fusion device based on homomorphic filtering provided by an embodiment of the present application;

[0043] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0044] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0045] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0046] In order to solve the problems of the prior art, the embodiments of the present application provide a multimodal medical image fusion method, apparatus, device and computer readable storage medium based on homomorphic filtering. The multimodal medical image fusion method based on homomorphic filtering provided by the embodiments of the present application is first introduced below.

[0047] Figure 1 FIG. 1 is a flow chart of a multimodal medical image fusion method based on homomorphic filtering provided by an embodiment of the present application. Figure 1 As shown, the multimodal medical image fusion method based on homomorphic filtering includes:

[0048] S101, performing wavelet transform on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image respectively;

[0049] S102, comparing pixel values ​​based on approximate coefficients of the CT image and the MRI image to determine a weight map;

[0050] S103, performing homomorphic filtering on the weight map to obtain an accurate weight map;

[0051] S104, performing weighted fusion based on the approximate coefficients and precise weight maps of the CT image and the MRI image to obtain a fusion approximate coefficient;

[0052] S105, performing weighted fusion based on the wavelet coefficients and precise weight map of the CT image and the MRI image to obtain fused wavelet coefficients;

[0053] S106 , performing inverse wavelet transform based on the fused approximation coefficients and the fused wavelet coefficients to obtain a fused image of the CT image and the MRI image.

[0054] In one embodiment, wavelet transform is performed on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image, respectively, including:

[0055] The CT image is subjected to wavelet transform to obtain the approximate coefficients of the CT image and three wavelet coefficients.

[0056] In one embodiment, wavelet transform is performed on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image, respectively, including:

[0057] The MRI image is subjected to wavelet transform to obtain the approximate coefficients of the MRI image and three wavelet coefficients.

[0058] In one embodiment, homomorphic filtering is performed on the weight map to obtain an accurate weight map, including:

[0059] Design a homomorphic filter;

[0060] The weight map is used as the input image of the homomorphic filter, the approximate coefficients of the CT image and the MRI image are used as the guide images, and the weight mapping is smoothed using homomorphic filtering to obtain an accurate weight map.

[0061] In one embodiment, the weight map is used as an input image of a homomorphic filter, including:

[0062] The weight map is subjected to logarithmic operation and fast Fourier transform in sequence to obtain the input image of the homomorphic filter.

[0063] In one embodiment, the approximate coefficients of the CT image and the MRI image are used as guide images, and the weight mapping is smoothed using homomorphic filtering to obtain an accurate weight map, including:

[0064] The output image of the homomorphic filter is subjected to inverse fast Fourier transform and exponential operation in sequence to obtain an accurate weight map.

[0065] In one embodiment, based on the wavelet coefficients and precise weight map of the CT image and the MRI image, weighted fusion is performed to obtain fused wavelet coefficients, including:

[0066] The three wavelet coefficients of the CT image and the three wavelet coefficients of the MRI image are fused respectively to obtain the corresponding three fused wavelet coefficients.

[0067] Specifically, the algorithm performs wavelet transform on CT and MRI medical images to obtain the approximate coefficients and three wavelet coefficients of CT and MRI respectively. Since the two approximate coefficients maintain the overall shape of the source image, they can be compared pixel by pixel to determine the weight map. The obtained weight map is usually noisy and has blurred edges. The fused image obtained using weight mapping usually produces artifacts. To this end, this paper designs a guided filter, which uses the weight map as the input image and the corresponding approximate coefficients as the guided image. The weight map is smoothed using the guided filter to obtain a refined weight map. Therefore, the refined weight map of each image is different, which is determined by the characteristics of the image to be fused. A weighted fusion algorithm is used to fuse the approximate coefficients and wavelet coefficients of CT and MRI images. The fused image of CT and MRI is obtained by inverse wavelet transform. The specific process is as follows: Figure 2 As shown:

[0068] First, wavelet transform is performed on each source image after registration. The CT image is decomposed into the approximate coefficient A1 and three wavelet coefficients H1, V1, and D1. The MRI image is decomposed into the approximate coefficient A2 and three wavelet coefficients H2, V2, and D2. The purpose of wavelet transform is to separate each source image into a low-frequency coefficient containing large-scale approximate information and three high-frequency coefficients containing small-scale detail information.

[0069] Secondly, since the two approximation coefficients A1 and A2 maintain the overall shape of the source image, the weight maps W1 and W2 are obtained by comparing the pixel values ​​of the two approximation coefficients:

[0070]

[0071]

[0072] The weight map obtained by the above formula usually has noise and blurred edges. Using the weight map to directly obtain the fused image will produce artifacts. In order to determine the position more accurately, we need to provide a fused image with clearer edges.

[0073] Design a homomorphic filter, use the weight maps W1 and W2 as input images, and the corresponding approximation coefficients A1 and A2 as guide images; then, use homomorphic filtering to smooth the weight map. Then, get the refined weight maps M1 and M2:

[0074] M1=T(W1,A1)

[0075] M2=T(W2,A2)

[0076] Third, the two approximate coefficients A1 and A2 are weighted fused to obtain the fused approximate coefficient A using a fusion algorithm with a refined weight map. The three wavelet coefficients H1 and H2, V1 and V2, and D1 and D2 are fused respectively, and the fused wavelet coefficients H, V, and D are obtained using a weighted fusion algorithm.

[0077] A=A1×M1+A2×M2

[0078] H=H1×M1+H2×M2

[0079] V=V1×M1+V2×M2

[0080] D=D1×M1+D2×M2

[0081] Finally, the approximation and wavelet coefficients A, H, and V are fused to perform inverse wavelet transform on D to obtain the fused image.

[0082] The image can be divided into two parts, namely the light intensity component and the reflection component. The light intensity component is characterized by slow changes and is concentrated in the low-frequency part of the image. The reflection component contains various information about the scene and is rich in high-frequency components. The specific calculation is as follows:

[0083] I ar (x,y)=i(x,y)ir(x,y) (1)

[0084] Among them, i(x,y) is the light intensity component, r(x,y) is the reflection component, and the homomorphic filtering algorithm flow chart is as follows Figure 3 shown.

[0085] The implementation process of the homomorphic enhancement algorithm is as follows:

[0086] Taking the natural logarithm of both sides to separate the components, the intensity component i(x,y) and the reflection component r(x,y), the calculation is as follows

[0087] z(x,y)=logI ar (x,y)=λ×logi(x,y)+μ×logr(x,y) (2)

[0088] λ+μ=1 (3)

[0089] Among them, λ is the weight of the light intensity component, and μ is the weight of the reflection component. Since more detailed features need to be highlighted, μ is greater than λ in this method.

[0090] Transform the image using Fourier transform in the frequency domain.

[0091]

[0092] Where logi(x,y) and logr(x,y) are the frequency domain transforms of the intensity component and the reflection component.

[0093] The filter S(x,y) and the high frequency filter T(x,y) function filter obtain the output of S(x,y) after filtering as shown in the following formula.

[0094]

[0095] The frequency-domain filtered image is obtained by inverse Fourier transform.

[0096]

[0097] The final enhanced image is obtained using the following formula

[0098] g e (x,y)=exp{s(x,y)}=e i′(x,y) ×e r′(x,y) =i1(x,y)r1(x,y) (7)

[0099] Component reflectance and illumination separation is the main solution in this application using Equation 4. Equation 5 represents the operation of the homomorphic filter T(x,y) on each component. The filter function T(x,y) is shown below.

[0100]

[0101] Where D0 and D(x,y) are the distances between the cutoff frequency and the center frequency coordinates (u,v), respectively. Gamma(·) is the gamma function, and k is a constant used to control the steepness of the slope. h and γ l It is high frequency gain and low frequency gain.

[0102] Figure 4 FIG. 1 is a schematic diagram showing the structure of a multimodal medical image fusion device based on homomorphic filtering provided in an embodiment of the present application. Figure 4 As shown, the multimodal medical image fusion device based on homomorphic filtering includes:

[0103] The wavelet transform module 401 is used to perform wavelet transform on the CT image and the MRI image to obtain approximate coefficients and wavelet coefficients of the CT image and the MRI image respectively;

[0104] A pixel value comparison module 402 is used to compare pixel values ​​based on the approximate coefficients of the CT image and the MRI image to determine a weight map;

[0105] Homomorphic filtering module 403, used to perform homomorphic filtering on the weight map to obtain an accurate weight map;

[0106] The fusion approximation coefficient acquisition module 404 is used to perform weighted fusion based on the approximation coefficients of the CT image and the MRI image and the accurate weight map to obtain the fusion approximation coefficients;

[0107] The fused wavelet coefficient acquisition module 405 is used to perform weighted fusion based on the wavelet coefficients of the CT image and the MRI image and the accurate weight map to obtain the fused wavelet coefficients;

[0108] The inverse wavelet transform module 406 is used to perform inverse wavelet transform based on the fused approximation coefficients and the fused wavelet coefficients to obtain a fused image of the CT image and the MRI image.

[0109] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown.

[0110] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0111] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0112] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the electronic device. In a particular embodiment, the memory 502 may be a non-volatile solid-state memory.

[0113] In one embodiment, the memory 502 may be a read-only memory (ROM). In one embodiment, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0114] The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the multimodal medical image fusion methods based on homomorphic filtering in the above embodiments.

[0115] In one example, the electronic device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0116] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0117] Bus 510 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0118] In addition, in combination with the multimodal medical image fusion method based on homomorphic filtering in the above embodiments, the present application embodiment can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the multimodal medical image fusion methods based on homomorphic filtering in the above embodiments is implemented.

[0119] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0120] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0121] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0122] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0123] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A multimodal medical image fusion method based on homomorphic filtering, characterized in that: include: Perform wavelet transform on CT images and MRI images to obtain low-frequency coefficients and high-frequency coefficients of CT images and MRI images respectively; Based on the low-frequency coefficients of the CT image and the MRI image, the pixel values ​​are compared to determine the weight map; Perform homomorphic filtering on the weight graph to obtain an accurate weight graph; Based on the low-frequency coefficients of CT images and MRI images and the precise weight map, weighted fusion is performed to obtain fused low-frequency coefficients; Based on the high-frequency coefficients and precise weight maps of CT images and MRI images, weighted fusion is performed to obtain fused high-frequency coefficients; Based on the fused low-frequency coefficients and the fused high-frequency coefficients, an inverse wavelet transform is performed to obtain a fused image of the CT image and the MRI image.

2. The multimodal medical image fusion method based on homomorphic filtering according to claim 1, characterized in that: Perform wavelet transform on CT images and MRI images to obtain low-frequency coefficients and high-frequency coefficients of CT images and MRI images, respectively, including: The CT image is subjected to wavelet transform to obtain the low-frequency coefficient and three high-frequency coefficients of the CT image.

3. The multimodal medical image fusion method based on homomorphic filtering according to claim 2 is characterized in that: Perform wavelet transform on CT images and MRI images to obtain low-frequency coefficients and high-frequency coefficients of CT images and MRI images, respectively, including: The MRI image is subjected to wavelet transform to obtain the low-frequency coefficient and three high-frequency coefficients of the MRI image.

4. The multimodal medical image fusion method based on homomorphic filtering according to claim 3 is characterized in that: Perform homomorphic filtering on the weight graph to obtain an accurate weight graph, including: Design a homomorphic filter; The weight map is used as the input image of the homomorphic filter, and the low-frequency coefficients of the CT image and the MRI image are used as the guide images respectively. The weight mapping is smoothed using homomorphic filtering to obtain an accurate weight map.

5. The multimodal medical image fusion method based on homomorphic filtering according to claim 4 is characterized in that: The weight map is used as the input image of the homomorphic filter, including: The weight map is subjected to logarithmic operation and fast Fourier transform in sequence to obtain the input image of the homomorphic filter.

6. The multimodal medical image fusion method based on homomorphic filtering according to claim 5, characterized in that: The low-frequency coefficients of CT images and MRI images are used as guide images, and homomorphic filtering is used to smooth the weight mapping to obtain an accurate weight map, including: The output image of the homomorphic filter is subjected to inverse fast Fourier transform and exponential operation in sequence to obtain an accurate weight map.

7. The multimodal medical image fusion method based on homomorphic filtering according to claim 6, characterized in that: Based on the high-frequency coefficients and precise weight maps of CT images and MRI images, weighted fusion is performed to obtain fused high-frequency coefficients, including: The three high-frequency coefficients of the CT image and the three high-frequency coefficients of the MRI image are fused respectively to obtain three corresponding fused high-frequency coefficients.

8. A multimodal medical image fusion device based on homomorphic filtering, characterized in that: The device comprises: A wavelet transform module is used to perform wavelet transform on the CT image and the MRI image to obtain low-frequency coefficients and high-frequency coefficients of the CT image and the MRI image respectively; A pixel value comparison module is used to compare pixel values ​​based on low-frequency coefficients of the CT image and the MRI image to determine a weight map; Homomorphic filtering module, used to perform homomorphic filtering on the weight graph to obtain an accurate weight graph; The fusion low-frequency coefficient acquisition module is used to perform weighted fusion based on the low-frequency coefficients of CT images and MRI images and the precise weight map to obtain the fused low-frequency coefficients; The fusion high-frequency coefficient acquisition module is used to perform weighted fusion based on the high-frequency coefficients of CT images and MRI images and the precise weight map to obtain the fused high-frequency coefficients; The inverse wavelet transform module is used to perform inverse wavelet transform based on the fused low-frequency coefficients and the fused high-frequency coefficients to obtain a fused image of the CT image and the MRI image.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the multimodal medical image fusion method based on homomorphic filtering as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the multimodal medical image fusion method based on homomorphic filtering as described in any one of claims 1 to 7 is implemented.

Images