Medical image positioning method and system, electronic equipment and medium
The key layer segmentation results of CT images are obtained and positioned through the segmentation model, which solves the problem of CT and PET images alignment, realizes automatic and accurate alignment of images, and improves the efficiency of medical image analysis.
Patent Information
- Application Number
- CN202411066150.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-15
AI Technical Summary
The prior art cannot automatically locate key layers to complete the alignment of CT and PET images, resulting in inefficient medical imaging analysis.
By acquiring CT and PET images, using segmentation models to perform image segmentation processing, obtaining key layer segmentation results, and positioning according to the segmentation results, realizing the key layer positioning of CT images, and then aligning the PET images with the CT images to realize the key of PET images Layer positioning.
It realizes automatic precise positioning of CT and PET images, and improves the analysis efficiency of medical images.
Smart Images

Figure CN118967761A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of medical image processing technology, and relates to a medical image positioning method, and in particular to a medical image positioning method, system, electronic equipment and medium. Background Art
[0002] Medical imaging plays a vital role in diagnosis and treatment. Computed Tomography (CT) and Positron Emission Tomography (PET) are two commonly used medical imaging technologies that provide information about the internal structure and function of the human body at different levels. However, due to their respective working principles and characteristics, aligning CT and PET images has become a challenge. Computed tomography is a technology that uses X-rays to obtain cross-sectional images of the human body. It scans the human body at different angles using a rotating X-ray beam, and then uses a computer to reconstruct the acquired data to generate high-resolution tomographic images. Positron emission tomography uses bioactive molecules labeled with radioactive isotopes (such as glucose) to observe biological metabolic processes inside the human body. In a PET scan, patients receive drugs labeled with positron-emitting nuclides, which emit positrons in the body and annihilate with electrons in the body to produce two gamma rays at opposite angles. The PET scanner detects and records the emission locations of these gamma rays to generate images of metabolic activity. CT images can clearly display structures such as bones, soft tissues and organs, and are one of the commonly used anatomical imaging methods.
[0003] In summary, although CT and PET technologies are both of great significance in the field of medical imaging, the software algorithms currently used for CT and PET image alignment have their own characteristics, but there is still a lack of a method that can automatically locate key layers and complete CT and PET alignment. Summary of the invention
[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a medical image positioning method, system, electronic device and medium, which are used to solve the problem in the prior art that key layers cannot be automatically positioned to complete CT and PET alignment.
[0005] In a first aspect, the present application provides a medical image positioning method, which includes: acquiring a computed tomography medical image and a positron emission tomography medical image; performing segmentation processing on the computed tomography medical image using a segmentation model to obtain a key layer segmentation result; positioning the key layer according to the key layer segmentation result to obtain the key layer positioning of the computed tomography medical image; and aligning the positron emission tomography medical image with the computed tomography medical image using the key layer positioning of the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image.
[0006] In the present application, a segmentation model is used to obtain a key layer segmentation result of a computed tomography medical image, and then the key layer positioning is obtained based on the key layer segmentation result. The key layer positioning is used to align a positron emission tomography medical image with the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image. The medical image positioning method can realize automatic and accurate positioning of the key layers of the computed tomography medical image and the positron emission tomography medical image, thereby improving the analysis efficiency of medical images.
[0007] In an implementation of the first aspect, obtaining a computed tomography medical image and a positron emission tomography medical image includes: obtaining an original computed tomography medical image and an original positron emission tomography medical image; and performing data annotation processing on the original computed tomography medical image and the original positron emission tomography medical image to obtain the computed tomography medical image and the positron emission tomography medical image.
[0008] In an implementation of the first aspect, the training method of the segmentation model includes: performing mask processing on the computed tomography medical image to obtain training data; and training the original segmentation model using the training data to obtain the segmentation model.
[0009] In an implementation of the first aspect, the key layers are positioned according to the key layer segmentation results, and obtaining the key layer positioning of the computed tomography medical image includes: obtaining the position of each key layer and the conditions corresponding to the key layer; positioning the key layers according to the key layer segmentation results, the positions of the key layers, and the conditions corresponding to the key layers, to obtain the key layer positioning of the computed tomography medical image.
[0010] In an implementation of the first aspect, the key layer is positioned according to the key layer segmentation result, the position of the key layer and the conditions corresponding to the key layer, and obtaining the key layer positioning of the computed tomography medical image includes: obtaining each of the key layers of the computed tomography medical image; using a function to obtain the contour similarity between the key layer segmentation result and the key layer of the computed tomography medical image; screening each of the contour similarities, and obtaining the key layer segmentation result with the highest contour similarity as the key layer positioning of the computed tomography medical image.
[0011] In an implementation of the first aspect, aligning the positron emission tomography medical image with the computed tomography medical image using the key layer positioning of the computed tomography medical image includes: acquiring the positron emission tomography medical image and the head starting layer of the computed tomography medical image; acquiring the physical distance between each key layer of the computed tomography medical image and the head starting layer; and aligning the key layers of the computed tomography medical image with the key layers of the positron emission tomography medical image one by one according to the physical distance.
[0012] In an implementation of the first aspect, obtaining a head starting layer of the positron emission tomography medical image includes: obtaining a head offset angle according to a segmentation result of the computed tomography medical image; rotating the positron emission tomography medical image to obtain a sagittal slice; obtaining a pitch angle of the positron emission tomography medical image according to the sagittal slice; and performing analysis and processing according to the head offset angle and the pitch angle to obtain a head starting layer of the positron emission tomography medical image.
[0013] In a second aspect, the present application provides a medical image positioning system, which includes: an image acquisition module for acquiring computed tomography medical images and positron emission tomography medical images; a segmentation processing module for performing segmentation processing on the computed tomography medical images using a segmentation model to obtain a key layer segmentation result; a positioning processing module for positioning the key layer according to the key layer segmentation result to obtain the key layer positioning of the computed tomography medical image; an alignment processing module for aligning the positron emission tomography medical image with the computed tomography medical image using the key layer positioning of the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image.
[0014] In a third aspect, the present application provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the electronic device performs the medical image positioning method as described in any one of the first aspects.
[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the medical image positioning method described in any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1A Shown is a schematic diagram of an application scenario of the medical image positioning method described in this application.
[0017] Figure 1B Shown are structural diagrams of the client-cloud interaction scenarios in these implementations.
[0018] Figure 2 Shown is a flow chart of the medical image positioning method described in an embodiment of the present application.
[0019] Figure 3 Shown is a flow chart of the medical image positioning method described in an embodiment of the present application.
[0020] Figure 4 Shown is a flow chart of the medical image positioning method described in an embodiment of the present application.
[0021] Figure 5 Shown is a flow chart of the medical image positioning method described in an embodiment of the present application.
[0022] Figure 6 Shown is a flow chart of the medical image positioning method described in an embodiment of the present application.
[0023] Figure 7 Shown is a flow chart of the medical image positioning method described in an embodiment of the present application.
[0024] Figure 8 Shown is a schematic diagram of the structure of the medical image positioning system described in an embodiment of the present application.
[0025] Fig. 9 Shown is a schematic diagram of the structure of an electronic device described in an embodiment of the present application.
[0026] Component number description
[0027] 1 Medical imaging positioning device
[0028] 11 Image acquisition equipment
[0029] 12 Processor
[0030] 13 Display Terminal
[0031] 2-end-cloud interactive system
[0032] 20 Terminal
[0033] 21 Cloud Server
[0034] 100 Medical Image Positioning System
[0035] 110 Image acquisition module
[0036] 120 Segmentation processing module
[0037] 130 Positioning processing module
[0038] 140 Alignment Processing Module
[0039] 900 Electronic equipment
[0040] 910 Memory
[0041] 920 processor
[0042] 930 Display
[0043] Steps S11 to S14
[0044] Steps S111 to S112
[0045] Steps S131 to S132
[0046] Steps S1321 to S1323
[0047] Steps S141 to S143
[0048] Steps S1411 to S1414 DETAILED DESCRIPTION
[0049] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application 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 application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.
[0050] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application 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 at will, and the component layout may also be more complicated.
[0051] In order to clearly describe the technical solution of the embodiment of the present application, the terms involved in the present application are first defined:
[0052] Positron Emission Tomography (PET): PET is a nuclear medicine imaging technique that detects metabolic activity in vivo by injecting radioactive tracers. PET images show the distribution and metabolic activity of biological molecules, and play an important role in the diagnosis and treatment monitoring of diseases such as tumors.
[0053] Computed Tomography (CT): CT is an X-ray imaging technology that obtains cross-sectional images of the body through X-ray scanning at multiple angles. CT images provide high-resolution anatomical information, which helps to accurately locate tumor lesions and evaluate the surrounding tissues.
[0054] Anatomical Landmarks: Using internal anatomical structures of the body as reference points, such as the location of bone structures or organs. Doctors can determine the location of key layers by identifying specific anatomical landmarks.
[0055] Image Registration: Image registration of different modalities (such as PET and CT) is performed to align them in the same coordinate system. In this way, doctors can accurately locate the anatomical structures in the CT image on the PET image and determine the location of key layers.
[0056] Functional Imaging Analysis: Use biomarkers or metabolic activity data from PET images to analyze the functional state of tissues. This approach can help doctors determine the location of key layers and assess the biological properties of tissues.
[0057] Machine Learning Methods: PET / CT images are analyzed using machine learning algorithms to identify and locate key layers. This method can combine a large amount of image data and annotation information to achieve automatic location and identification of key layers.
[0058] Functional imaging analysis usually requires accurate biomarker or metabolic activity data. When PET images are of poor quality or are affected by noise, the quantification of biomarkers may be affected, thereby affecting the accuracy of key layer positioning. Machine learning methods require a large amount of training data and expertise to ensure the accuracy and generalization ability of the model. In addition, for complex imaging data, the interpretability of the model may be limited, making it difficult for doctors to understand the decision-making process of the model.
[0059] At least to address the above-mentioned problems, an embodiment of the present application provides a medical image positioning method, which includes: acquiring a computed tomography medical image and a positron emission tomography medical image; performing segmentation processing on the computed tomography medical image using a segmentation model to obtain a key layer segmentation result; positioning the key layer according to the key layer segmentation result to obtain the key layer positioning of the computed tomography medical image; and aligning the positron emission tomography medical image with the computed tomography medical image using the key layer positioning of the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image.
[0060] In the embodiment of the present application, a segmentation model is used to obtain a key layer segmentation result of a computed tomography medical image, and then the key layer positioning is obtained based on the key layer segmentation result. The key layer positioning is used to align a positron emission tomography medical image with the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image. The medical image positioning method can realize automatic and accurate positioning of the key layers of the computed tomography medical image and the positron emission tomography medical image, thereby improving the analysis efficiency of medical images.
[0061] Figure 1A The figure shows an application scenario of the medical image positioning method described in the present application. The medical image positioning device 1 can be used to implement the medical image positioning method provided in the embodiment of the present application, but the application scenario of the medical image positioning method provided in the embodiment of the present application is not limited to Figure 1A The medical image positioning device 1 shown. Figure 1A As shown, the medical image positioning device 1 includes an image acquisition device 11, a processor 12 and a display terminal 13. The medical image positioning method provided in the embodiment of the present application can be applied to the processor 12.
[0062] in, Figure 1A The processor 12 in the embodiment may be a single processor or a processor cluster or a cloud computing center composed of multiple processors, and the specific details are not limited here. Figure 1A Only one image acquisition device 11, one processor 12 and one display terminal 13 are shown, but it should be understood that Figure 1A The examples are only used to understand the present solution, and the specific numbers of processors 12 and display terminals 13 should be flexibly determined based on actual conditions.
[0063] In some other implementations, the medical image positioning device 1 may not include the display terminal 13, but only include a processor 12 with a display function and an image acquisition device 11. The processor 12 with a display function may include a tablet computer, a laptop computer, a PDA, a mobile phone, a personal computer (PC for short), a medical detection device, etc., which is not limited here.
[0064] In still other implementations, the medical image positioning method described in the present application may be applied to end-cloud interaction scenarios. Figure 1B The following is a schematic diagram of the structure of the client-cloud interaction scenario in these implementations. Figure 1B As shown, the terminal-cloud interaction system 2 includes a terminal 20 and a cloud server 21. The terminal 20 and the cloud server 21 can communicate with each other, and the communication method is not limited to wired or wireless.
[0065] Among them, the terminal 20 can be mobile or fixed, for example, the terminal 20 can be a wireless terminal or a wired terminal, and the wireless terminal can refer to a device with wireless transceiver function, which can be deployed indoors, outdoors and in industrial workshops. The terminal 20 can be a medical detector, a mobile phone, a tablet computer, a laptop computer, etc., which is not limited here. The cloud server 21 can include one or more servers, or one or more processing nodes, or one or more virtual machines running on the server. The cloud server 21 can also be called a server cluster, a management platform, a data processing center, etc., which is not limited in the embodiments of the present application.
[0066] The technical solutions in the embodiments of the present application will be described in detail below in conjunction with the drawings in the embodiments of the present application.
[0067] The following embodiments of the present application provide a medical image positioning method. For example, the method can be Figure 1A The processor 12 shown or Figure 1B It is implemented by the cloud server 21 shown. Figure 2 The flowchart of the medical image positioning method described in the embodiment of the present application is shown as follows: Figure 2 As shown, the medical image positioning method includes steps S11 to S14.
[0068] Step S11, obtaining a computed tomography medical image and a positron emission tomography medical image, wherein the computed tomography medical image is a CT image, and the positron emission tomography medical image is a PET image.
[0069] Step S12: segmenting the computed tomography medical image using a segmentation model to obtain a key layer segmentation result.
[0070] Step S13, positioning the key layer according to the key layer segmentation result, and obtaining the key layer positioning of the computed tomography medical image.
[0071] Step S14, aligning the PET medical image with the CT medical image using the key layer positioning of the CT medical image, so as to obtain the key layer positioning of the PET medical image.
[0072] In the embodiment of the present application, a segmentation model is used to obtain a key layer segmentation result of a computed tomography medical image, and then the key layer positioning is obtained based on the key layer segmentation result. The key layer positioning is used to align a positron emission tomography medical image with the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image. The medical image positioning method can realize automatic and accurate positioning of the key layers of the computed tomography medical image and the positron emission tomography medical image, thereby improving the analysis efficiency of medical images.
[0073] Figure 3 The flowchart of the medical image positioning method described in the embodiment of the present application is shown as follows: Figure 3 As shown, the step S11 includes steps S111 to S112.
[0074] Step S111, acquiring original computed tomography medical images and original positron emission tomography medical images.
[0075] Step S112, performing data annotation processing on the original computed tomography medical image and the original positron emission tomography medical image to obtain the computed tomography medical image and the positron emission tomography medical image.
[0076] In some possible implementations, the data annotation process includes key layer selection, boundary delineation and annotation of specific organs on the CT key layer, and key layer image quality scoring. First, the original computed tomography medical image and the original positron emission tomography medical image are obtained, and the key layer is selected therefrom. Optionally, 9 layers are selected from the original computed tomography medical image, and 7 layers are selected from the original positron emission tomography medical image. The cross-sectional impact of all or part of the key layers is to outline and mark the boundaries of a group of key organs to assist in the positioning of the key layers. Including the aortic arch, right lung, tracheal carina, mediastinum, liver, pancreas, spleen, esophagus, iliac artery bifurcation, ilium, etc. Finally, the image quality is evaluated and scored.
[0077] In one embodiment of the present application, the training method of the segmentation model includes: performing mask processing on the computed tomography medical image to obtain training data; and using the training data to train the original segmentation model to obtain the segmentation model.
[0078] In some possible implementations, the computed tomography medical images are divided into training data, validation data, and internal test data in proportion. The training data is used to train the segmentation model, the validation data is used to adjust and optimize the segmentation model, and the internal test data is used to evaluate model performance, but the present application is not limited thereto.
[0079] In some other possible implementations, the original format of the computed tomography medical image is dicom, and the computed tomography medical image is masked to generate a png format image corresponding to the key layer, and the different parts are distinguished as training data. The largest public data set in the field of three-dimensional medical image segmentation, TotalSegmentator and nnUNet, are used to segment and slice 11 parts of the trunk, 1 part of the neck, and 3 parts of the head. Among them, TotalSegmentator is used for the aortic arch, liver and spleen, ilium, tracheal carina, pancreas, iliac artery bifurcation, brain and two sections of the spine, and nnUnet is used for the thyroid gland and condyle. Finally, the Dice coefficient is used to evaluate the segmentation results of the segmentation model.
[0080] Figure 4 The flowchart of the medical image positioning method described in the embodiment of the present application is shown as follows: Figure 4 As shown, the step S13 includes steps S131 to S132.
[0081] Step S131, obtaining the position of each key layer and the conditions corresponding to the key layer.
[0082] Step S132, positioning the key layer according to the key layer segmentation result, the position of the key layer and the condition corresponding to the key layer, and obtaining the key layer positioning of the computed tomography medical image.
[0083] In some possible implementations, the conditions corresponding to the key layers of the computed tomography medical image are shown in the following table.
[0084] Table 1 Conditions corresponding to key layers
[0085]
[0086]
[0087] Figure 5 The flowchart of the medical image positioning method described in the embodiment of the present application is shown as follows: Figure 5 As shown, the step S132 includes steps S1321 to S1323.
[0088] Step S1321, obtaining each of the key layers of the computed tomography medical image.
[0089] Step S1322, using a function to obtain the contour similarity between the key layer segmentation result and the key layer of the computed tomography medical image. Optionally, using a Match Shapes function to obtain the contour similarity between the key layer segmentation result and the key layer of the computed tomography medical image.
[0090] Step S1323 , screening the contour similarities, and obtaining the key layer segmentation result with the highest contour similarity as the key layer positioning of the computed tomography medical image.
[0091] Figure 6 The flowchart of the medical image positioning method described in the embodiment of the present application is shown as follows: Figure 6 As shown, the step S14 includes steps S141 to S143.
[0092] Step S141, obtaining the head starting layer of the positron emission tomography medical image and the computer tomography medical image.
[0093] Step S142, obtaining the physical distance between each key layer of the computed tomography medical image and the head starting layer.
[0094] Step S143: Align the key layers of the computed tomography medical image and the key layers of the positron emission tomography medical image one by one according to the physical distance.
[0095] In some possible implementations, the key layer of the computed tomography medical image is mapped onto the positron emission tomography medical image, wherein the physical distance between the key layers of the two is the same. The calculation formula of the physical distance is:
[0096] dp = thickness × layers,
[0097] Wherein, dp is the physical distance, thickness is the thickness, and layers is the total number of layers. If the physical distances are not equal, it is confirmed that the key layer of the computed tomography medical image and the key layer of the positron emission tomography medical image cannot be aligned, and the processing is skipped as invalid data.
[0098] Figure 7 The flowchart of the medical image positioning method described in the embodiment of the present application is shown as follows: Figure 7 As shown, the step S141 includes steps S1411 to S1414.
[0099] Step S1411, obtaining a head offset angle according to the segmentation result of the computed tomography medical image.
[0100] Step S1412: Rotate the PET medical image to obtain sagittal slices.
[0101] Step S1413, acquiring the pitch angle of the positron emission tomography medical image according to the sagittal slice.
[0102] Step S1414: Analyze and process the head offset angle and the pitch angle to obtain a head starting layer of the positron emission tomography medical image.
[0103] In some possible implementations, the whole image needs to be rotated when obtaining the head starting layer, and the key layer is selected on the rotated level. For example, the head offset angle is obtained according to the segmentation result of the condyle, and the sagittal slice is obtained by rotating the positron emission tomography medical image. After the cerebral cortex is segmented on the sagittal slice, the pitch angle is calculated. The positron emission tomography medical image is rotated according to the head offset angle and the pitch angle, and the basal ganglia key layer is found according to the inner diameter of the brain and the brain area, and this is used as the head starting layer. The cerebellar vermis key layer can be obtained 35 mm downward with the head starting layer as the reference. Among them, the head key layer includes the head starting layer, i.e., the basal ganglia key layer and the cerebellar vermis key layer. The basal ganglia key layer selects the layer with high uptake of the caudate nucleus head, putamen, and thalamus, and the cerebellar vermis key layer displays the cerebellar cortex and subcortical nuclei.
[0104] Figure 8The structure diagram of the medical image positioning system described in the embodiment of the present application is shown as follows: Figure 8 As shown, the medical image positioning system 100 includes an image acquisition module 110 , a segmentation processing module 120 , a positioning processing module 130 and an alignment processing module 140 .
[0105] The image acquisition module 110 is used to acquire computed tomography medical images and positron emission tomography medical images.
[0106] The segmentation processing module 120 is used to perform segmentation processing on the computed tomography medical image using a segmentation model to obtain a key layer segmentation result.
[0107] The positioning processing module 130 is used to position the key layer according to the key layer segmentation result to obtain the key layer positioning of the computed tomography medical image.
[0108] The alignment processing module 140 is used to align the PET medical image with the CT medical image using the key layer positioning of the CT medical image to obtain the key layer positioning of the PET medical image.
[0109] It should be noted that the modules 110 to 140 included in the medical image positioning system 100 are Figure 2 Steps S11 to S14 in the medical image positioning method are in one-to-one correspondence and are not described in detail here.
[0110] In the several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules or units, which can be electrical, mechanical or other forms.
[0111] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.
[0112] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0113] An embodiment of the present application also provides an electronic device. Fig. 9 The structure diagram of the electronic device 900 described in the embodiment of the present application is shown. Fig. 9 As shown, in this embodiment, the electronic device 900 includes a memory 910 and a processor 920 .
[0114] The memory 910 is used to store computer programs; preferably, the memory 910 includes: ROM, RAM, disk, USB flash drive, memory card or optical disk, etc., various media that can store program codes.
[0115] Specifically, the memory 910 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device 900 may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 910 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.
[0116] The processor 920 is connected to the memory 910 and is used to execute the computer program stored in the memory 910 so that the electronic device 900 executes the medical image positioning method described in any embodiment of the present application.
[0117] Optionally, the processor 920 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.
[0118] Optionally, the electronic device 900 in this embodiment may further include a display 930. The display 930 is communicatively connected to the memory 910 and the processor 920, and is used to display a graphical user interface (GUI) interaction interface related to the medical image positioning method described in the embodiment of the present application.
[0119] The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the medical image positioning method described in any embodiment of the present application is implemented.
[0120] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.
[0121] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.
Claims
1. A medical image positioning method, characterized in that: include: Obtaining computed tomography medical images and positron emission tomography medical images; Using the segmentation model to perform segmentation processing on the computed tomography medical image to obtain a key layer segmentation result; Positioning the key layer according to the key layer segmentation result to obtain the key layer positioning of the computed tomography medical image; The positron emission tomography medical image and the computed tomography medical image are aligned using the key layer positioning of the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image.
2. The medical image positioning method according to claim 1, characterized in that: Obtaining CT and PET images includes: acquiring original computed tomography medical images and original positron emission tomography medical images; Data annotation processing is performed on the original computed tomography medical image and the original positron emission tomography medical image to obtain the computed tomography medical image and the positron emission tomography medical image.
3. The medical image positioning method according to claim 1, characterized in that: The training method of the segmentation model includes: performing mask processing on the computed tomography medical image to obtain training data; The original segmentation model is trained using the training data to obtain the segmentation model.
4. The medical image positioning method according to claim 1, characterized in that: Positioning the key layer according to the key layer segmentation result, and obtaining the key layer positioning of the computed tomography medical image includes: Obtaining the position of each key layer and the conditions corresponding to the key layer; The key layer is positioned according to the key layer segmentation result, the position of the key layer and the condition corresponding to the key layer, so as to obtain the key layer positioning of the computed tomography medical image.
5. The medical image positioning method according to claim 4, characterized in that: Positioning the key layer according to the key layer segmentation result, the position of the key layer and the condition corresponding to the key layer, and obtaining the key layer positioning of the computed tomography medical image includes: Acquiring each of the key layers of the computed tomography medical image; Using a function to obtain the contour similarity between the key layer segmentation result and the key layer of the computed tomography medical image; The contour similarities are screened to obtain the key layer segmentation result with the highest contour similarity as the key layer positioning of the computed tomography medical image.
6. The medical image positioning method according to claim 1, characterized in that: The step of aligning the positron emission tomography medical image with the computed tomography medical image by using the key layer positioning of the computed tomography medical image comprises: Acquiring a head starting layer of the positron emission tomography medical image and the computer tomography medical image; Obtaining the physical distance between each key layer of the computed tomography medical image and the head starting layer; The key layers of the computed tomography medical image and the key layers of the positron emission tomography medical image are aligned one by one according to the physical distance.
7. The medical image positioning method according to claim 1, characterized in that: Acquiring the head starting layer of the positron emission tomography medical image includes: Acquiring a head offset angle according to a segmentation result of the computed tomography medical image; Rotating the positron emission tomography medical image to obtain sagittal slices; Acquire the pitch angle of the positron emission tomography medical image according to the sagittal slice; Analyze and process the head offset angle and the pitch angle to obtain a head starting layer of the positron emission tomography medical image.
8. A medical image positioning system, characterized in that: include: An image acquisition module, used for acquiring computed tomography medical images and positron emission tomography medical images; A segmentation processing module, used for performing segmentation processing on the computed tomography medical image using a segmentation model to obtain a key layer segmentation result; A positioning processing module, used for positioning the key layer according to the key layer segmentation result, and obtaining the key layer positioning of the computed tomography medical image; An alignment processing module is used to align the positron emission tomography medical image with the computed tomography medical image using the key layer positioning of the computed tomography medical image to obtain the key layer positioning of the positron emission tomography medical image.
9. An electronic device, characterized in that: The electronic device comprises: Memory for storing computer programs; A processor, wherein the processor is used to execute the computer program stored in the memory so that the electronic device executes the medical image positioning method as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the medical image positioning method described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Medical imaging systems and methods
US20040044282A1
Registration of computed tomography (CT) and positron emission tomography (PET) image scans with automatic patient motion correction
US20070232903A1
Pet-CT registration for medical imaging
US20210090212A1
Automated lung cancer detection from pet-CT scans with hierarchical image representation
US20220245821A1
Coregistration of multi-modality data in a medical imaging system
US5672877A
Cited By
Pancreatic operation key anatomical region segmentation method based on CT image
CN120672762A
Segmentation method for key anatomical regions in pancreatic surgery based on ct images
CN120672762B
Operation area inflammation degree grading method based on pancreatic peripheral fat image features
CN120747051A
Method for grading the degree of inflammation in the surgical field based on the imaging features of the peripancreatic fat
CN120747051B
