Medical image processing method and device, computer device and storage medium

Abstract

The application relates to a medical image processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring an MR image and a PET image corresponding to a target region of a target object; the target object wears a brain function head cover in the target region; adjusting a first attenuation template image according to the MR image to obtain a second attenuation template image; the first attenuation template image is used for representing the attenuation values of each component in the brain function head cover when a PET / CT system is used to scan a scanning phantom wearing the brain function head cover; and performing attenuation correction on the PET image according to the second attenuation template image to obtain a corrected PET image. According to the method, the positions of each component of the brain function head cover in the PET image can be accurately corrected, an accurate corrected PET image is obtained, and the attenuation correction accuracy of the PET image is improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a medical image processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] In recent years, with the continuous development of medical technology, multimodal imaging technology has become increasingly mature. Common multimodal imaging technologies include PET / MR (PET (Positron Emission Tomography) and MR (Magnetic Resonance)) imaging technologies.

[0003] To achieve more accurate medical diagnosis and treatment, brain functional imaging technology can be combined with PET / MR imaging technology. However, brain functional imaging headsets can cause uncorrectable attenuation of PET photons in PET / MR imaging, resulting in very low accuracy in attenuation correction of PET images during the combination of brain functional imaging and PET / MR imaging.

[0004] Therefore, existing technologies suffer from low accuracy in PET image attenuation correction. Summary of the Invention

[0005] Therefore, it is necessary to provide a medical image processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of PET image attenuation correction in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a medical image processing method. The method includes:

[0007] Acquire MR and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region.

[0008] The first attenuation template image is adjusted based on the MR image to obtain the second attenuation template image; the first attenuation template image is used to characterize the attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned using a PET / CT system.

[0009] The PET image is attenuated and corrected based on the second attenuation template image to obtain the corrected PET image.

[0010] In one embodiment, adjusting the first attenuation template image based on the MR image to obtain the second attenuation template image includes:

[0011] The MR image is used as a reference image, and the first attenuation template image is used as a floating image;

[0012] Non-rigid body registration is performed on the reference image and the floating image to obtain the registered floating image;

[0013] The registered floating image is fused with the MR image to obtain the second attenuation template image.

[0014] In one embodiment, the step of performing non-rigid registration of the reference image and the floating image to obtain the registered floating image includes:

[0015] Determine the spatial mapping relationship between the reference image and the floating image;

[0016] Based on the spatial location mapping relationship, the floating image is mapped onto the reference image to obtain the registered floating image; the registered floating image has the same spatial location as the corresponding point in the reference image.

[0017] In one embodiment, the step of attenuating the PET image according to the second attenuation template image to obtain a corrected PET image includes:

[0018] The spatial positions of each component in the brain function headgear are determined in the second attenuation template image;

[0019] Based on the spatial mapping relationship between the MR image and the PET image, determine the target spatial position of each component in the PET image;

[0020] Based on the second attenuation template image, attenuation compensation is performed on the image region where the target spatial location is located in the PET image to obtain the corrected PET image.

[0021] In one embodiment, the method further includes:

[0022] Acquire initial phantom CT images and initial phantom PET images; the initial phantom CT images and the initial phantom PET images are obtained by scanning a phantom wearing the brain function headgear using the PET / CT system;

[0023] The initial attenuation coefficients of each component in the brain function headgear are determined based on the initial phantom CT images.

[0024] Adjust the initial attenuation coefficient to obtain the adjusted attenuation image;

[0025] The initial phantom PET image is attenuated according to the adjusted attenuation image. If the difference between the average target ingestion values ​​corresponding to each preset image region in the attenuated initial phantom PET image meets the preset difference condition, then the adjusted attenuation image is used as the first attenuation template image.

[0026] In one embodiment, adjusting the initial attenuation coefficient to obtain the adjusted attenuation image includes:

[0027] Adjust the initial attenuation coefficient to obtain the adjusted attenuation coefficient;

[0028] The adjusted attenuation coefficient is converted into the adjusted attenuation value corresponding to each component in the brain function headgear;

[0029] The adjusted attenuation image is generated based on the adjusted attenuation values ​​corresponding to each component in the brain function headgear.

[0030] Secondly, this application also provides a medical image processing apparatus. The apparatus includes:

[0031] The acquisition module is used to acquire MR images and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region;

[0032] The adjustment module is used to adjust the first attenuation template image according to the MR image to obtain a second attenuation template image; the first attenuation template image is used to characterize the attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned by the PET / CT system.

[0033] The correction module is used to perform attenuation correction on the PET image based on the second attenuation template image to obtain a corrected PET image.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] Acquire MR and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region.

[0036] The first attenuation template image is adjusted based on the MR image to obtain the second attenuation template image; the first attenuation template image is used to characterize the attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned using a PET / CT system.

[0037] The PET image is attenuated and corrected based on the second attenuation template image to obtain the corrected PET image.

[0038] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0039] Acquire MR and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region.

[0040] The first attenuation template image is adjusted based on the MR image to obtain the second attenuation template image; the first attenuation template image is used to characterize the attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned using a PET / CT system.

[0041] The PET image is attenuated and corrected based on the second attenuation template image to obtain the corrected PET image.

[0042] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0043] Acquire MR and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region.

[0044] The first attenuation template image is adjusted based on the MR image to obtain the second attenuation template image; the first attenuation template image is used to characterize the attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned using a PET / CT system.

[0045] The PET image is attenuated and corrected based on the second attenuation template image to obtain the corrected PET image.

[0046] The aforementioned medical image processing method, apparatus, computer equipment, storage medium, and computer program product acquire MR and PET images corresponding to a target region of a target object. The target object wears a brain function headgear over the target region. A first attenuation template image is adjusted based on the MR image to obtain a second attenuation template image. The first attenuation template image characterizes the attenuation values ​​of each component in the brain function headgear when the phantom wearing the headgear is scanned using a PET / CT system. The PET image is attenuated based on the second attenuation template image to obtain a corrected PET image. Thus, due to the flexibility and adaptability of the brain function headgear, PET photons are attenuated in PET / MR imaging technology. The attenuation of PET photons by the target object wearing the brain function headgear is adjusted accordingly. The MR images corresponding to the target area are insufficient to clearly determine the attenuation values ​​of each component in the brain function headgear. However, by scanning the phantom wearing the brain function headgear using a PET / CT system, a first attenuation template image can be obtained, which accurately determines the attenuation values ​​of each component in the headgear. By adjusting the first attenuation template image with an MR image that clearly shows the position of each component in the headgear, the attenuation values ​​corresponding to the positions of each component in the PET image obtained using PET / MR imaging technology can be determined, resulting in a second attenuation template image. Furthermore, the attenuation of each component in the PET image can be accurately corrected based on the second attenuation template image, resulting in an accurately corrected PET image and improving the accuracy of attenuation correction in PET images. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating a medical image processing method in one embodiment;

[0048] Figure 2 This is a schematic diagram of a brain function headgear used in one embodiment when scanning with a non-UTE sequence;

[0049] Figure 3 This is a schematic diagram of a brain function headgear used in one embodiment when scanning with a UTE sequence;

[0050] Figure 4 This is a schematic diagram of a second attenuation template image in one embodiment;

[0051] Figure 5 One embodiment shows a PET image of a phantom scanned using a PET / CT system.

[0052] Figure 6 Here is a PET image of an initial phantom in one embodiment;

[0053] Figure 7This is a schematic diagram of the imaging of a scanning phantom and a brain function headgear under a PET / CT system in one embodiment;

[0054] Figure 8(a) shows a PET image of another initial phantom in one embodiment;

[0055] Figure 8(b) shows the transverse, coronal, and sagittal views of a first attenuation template image in one embodiment.

[0056] Figure 8(c) is a uniform reconstructed phantom PET image in one embodiment;

[0057] Figure 9 This is a flowchart illustrating a medical image processing method in another embodiment;

[0058] Figure 10 This is a structural block diagram of a medical image processing device in one embodiment;

[0059] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] In one embodiment, such as Figure 1 As shown, a medical image processing method is provided, applied to computer equipment. In practical applications, the computer equipment can be a user terminal, or it can be implemented using a standalone server or a server cluster consisting of multiple servers. The user terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.

[0062] In this embodiment, the method includes the following steps:

[0063] Step S110: Obtain the MR image and PET image corresponding to the target area of ​​the target object.

[0064] The target individuals wore brain function headgear in the target area.

[0065] Among them, the brain function headgear is a medical headgear used for brain function imaging.

[0066] Among them, the brain function headgear can be, but is not limited to, an infrared imaging headgear.

[0067] Among them, MR images and PET images are images acquired by scanning the target area of ​​the target object using an integrated PET / MR device.

[0068] In practice, the PET / MR integrated device can scan the target area of ​​the target object wearing a brain function headgear, and collect the MR image and PET image corresponding to the target area of ​​the target object. Thus, the computer device can obtain the pair of MR images and PET images collected by the PET / MR integrated device.

[0069] Step S120: Adjust the first attenuation template image according to the MR image to obtain the second attenuation template image.

[0070] The first attenuation template image is determined by scanning a phantom wearing a brain function headgear using a PET / CT (Computed Tomography) system.

[0071] The first attenuation template image is used to characterize the attenuation values ​​of each component in the brain function headgear when the phantom wearing the headgear is scanned using a PET / CT system. This attenuation value is the PET attenuation value.

[0072] The brain function headgear consists of components such as probes and cables.

[0073] Among them, the PET / CT system can be an integrated PET / CT device.

[0074] In practice, a PET / CT system can be used to scan a phantom wearing a brain function headgear. The computer can then obtain CT and PET images of the phantom based on the scan results. The computer can determine the initial attenuation coefficients of each component in the brain function headgear under PET function based on the CT images. By adjusting the initial attenuation coefficients, the attenuation image used to achieve uniformity in the reconstructed PET image of the phantom is determined, thus obtaining the first attenuation template image. This first attenuation template image characterizes the PET attenuation values ​​of each component in the brain function headgear when scanned using a PET / CT system.

[0075] To ensure the stability and accuracy of imaging from medical imaging equipment such as MR, CT, PET, PET / CT, and PET / MR devices, certain parameters of the imaging equipment are typically tested and calibrated using a scanning phantom before leaving the factory or during routine maintenance. Therefore, the first attenuation template image obtained by scanning a phantom wearing a brain function headgear using a PET / CT system can accurately characterize the attenuation values ​​corresponding to each component in the brain function headgear.

[0076] Then, the computer device can adjust the first attenuation template image based on the MR image, and fuse the adjusted first attenuation template image with the MR image to obtain the second attenuation template image.

[0077] Step S130: Attenuation correction is performed on the PET image based on the second attenuation template image to obtain the corrected PET image.

[0078] In practice, the computer device can determine the PET attenuation value corresponding to the position of each component of the brain function headgear in the PET image based on the second attenuation template image, so that the PET image can be attenuated and corrected using the second attenuation template image to obtain the corrected PET image.

[0079] Thus, after attenuation correction of the PET images, PET / MR scanning and brain function scanning can be started simultaneously on the target area of ​​the subject wearing a brain function headgear.

[0080] In the aforementioned medical image processing method, MR and PET images corresponding to the target region of the target object are acquired. The target object wears a brain function headgear over the target region. A first attenuation template image is adjusted based on the MR image to obtain a second attenuation template image. The first attenuation template image characterizes the attenuation values ​​of each component in the brain function headgear when the phantom wearing the headgear is scanned using a PET / CT system. The PET image is then attenuated based on the second attenuation template image to obtain a corrected PET image. Thus, due to the flexibility and adaptability of the brain function headgear, PET photons are attenuated during PET / MR imaging. The attenuation of PET photons in the target region of the target object wearing the brain function headgear is then corrected. It is difficult to clearly determine the attenuation values ​​corresponding to each component in a brain function headgear. However, by scanning a phantom wearing a brain function headgear using a PET / CT system, the first attenuation template image can accurately determine the attenuation values ​​corresponding to each component in the headgear. Then, by adjusting the first attenuation template image using an MR image that clearly shows the position of each component in the headgear, the attenuation values ​​corresponding to the positions of each component in the PET image obtained using PET / MR imaging technology can be determined, resulting in a second attenuation template image. Furthermore, based on the second attenuation template image, the attenuation correction of each component position in the PET image can be accurately performed, resulting in an accurately corrected PET image, thus improving the accuracy of attenuation correction in PET images.

[0081] In one embodiment, adjusting a first attenuation template image based on an MR image to obtain a second attenuation template image includes: using the MR image as a reference image and the first attenuation template image as a floating image; performing non-rigid registration on the reference image and the floating image to obtain a registered floating image; and fusing the registered floating image with the MR image to obtain the second attenuation template image.

[0082] Among them, the MR images are obtained by scanning the target area using a PET / MR integrated device with a UTE sequence (magnetic resonance ultrashort echo time series).

[0083] When using a PET / MR integrated device to scan the target area of ​​a subject wearing a brain function headgear, if a UTE sequence is used for scanning, the brain function headgear can be imaged under the UTE sequence, thus accurately detecting the precise location of the headgear. This allows the final MR image to accurately and clearly display the location of each component within the headgear. However, if a traditional MRI sequence is used to scan the target area wearing the brain function headgear, the headgear cannot be imaged under the traditional MRI sequence.

[0084] For the ease of understanding of those skilled in the art, Figure 2A schematic diagram of a brain function headgear is provided when using non-UTE sequences, i.e., traditional MRI sequences. For example... Figure 2 As shown, the brain function headgear cannot produce images. This is for the convenience of those skilled in the art. Figure 3 A schematic diagram of a brain function headgear used during UTE sequence scanning is provided. Figure 3 As shown, the brain function headgear can be used for imaging, thereby enabling the detection of the positions of probes and cables within the headgear.

[0085] In specific implementation, during the process of adjusting the first attenuation template image based on the MR image to obtain the second attenuation template image, the computer device can use the MR image as a reference image, i.e., a fixed image, and the first attenuation template image as a floating image. Then, the computer device can perform non-rigid registration between the MR image (as the reference image) and the first attenuation template image (as the floating image) to obtain a registered floating image, i.e., a registered first attenuation template image. This registered floating image is aligned with the MR image in spatial position. Afterward, the registered floating image, i.e., the registered first attenuation template image, is fused with the MR image, and the fused image is used as the second attenuation template image.

[0086] For the ease of understanding of those skilled in the art, Figure 4 A schematic diagram is provided showing how a second attenuation template image is obtained by fusing a registered first attenuation template image with an MR image. For example... Figure 4 As shown, the positions of each component in the brain function headgear can be clearly displayed in the second attenuation template image; at the same time, the value corresponding to each pixel in the second attenuation template image is the PET attenuation value, so the second attenuation template image can characterize the PET attenuation value corresponding to each component in the brain function headgear.

[0087] The technical solution of this embodiment uses an MR image as a reference image and a first attenuation template image as a floating image. Non-rigid registration is performed on the reference image and the floating image to obtain a registered floating image. The registered floating image is then fused with the MR image to obtain a second attenuation template image. Since the MR image can accurately and clearly display the position of each component in the brain function headgear, and the first attenuation template image can determine the attenuation value corresponding to each component in the brain function headgear, non-rigid registration of the MR image and the first attenuation template image allows the registered first attenuation template image to be aligned with the MR image. Therefore, the second attenuation template image obtained by fusing the registered first attenuation template image with the MR image can not only accurately display the position of each component in the brain function headgear but also characterize the attenuation value corresponding to each component. Thus, the second attenuation template image can be used to accurately correct the attenuation in PET images caused by the brain function headgear, effectively improving the accuracy of attenuation correction in PET images.

[0088] In one embodiment, non-rigid registration of a reference image and a floating image is performed to obtain a registered floating image, including: determining the spatial position mapping relationship between the reference image and the floating image; and mapping the floating image onto the reference image according to the spatial position mapping relationship to obtain the registered floating image.

[0089] In this case, the registered floating image has the same spatial position as the corresponding point in the reference image.

[0090] In specific implementation, during the process of non-rigid registration of the reference image and the floating image to obtain the registered floating image, the computer device can determine the spatial mapping relationship between the MR image used as the reference image and the first attenuation template image used as the floating image. Based on this spatial mapping relationship, the first attenuation template image used as the floating image is mapped onto the MR image used as the reference image, so that the first attenuation template image and the points corresponding to the same spatial position in the MR image are matched one-to-one, thus obtaining the registered floating image, i.e., the registered first attenuation template image. Therefore, the spatial position of the corresponding point in the registered first attenuation template image is the same as that in the MR image used as the reference image.

[0091] The technical solution of this embodiment determines the spatial position mapping relationship between the reference image and the floating image; according to the spatial position mapping relationship, the floating image is mapped onto the reference image to obtain the registered floating image; wherein, the spatial positions of corresponding points in the registered floating image and the reference image are the same; in this way, the registered first attenuation template image and the MR image are accurately aligned, so that the MR image and the registered first attenuation template image can be accurately fused, so that the fused second attenuation template image can accurately display the position of each component in the brain function headgear and accurately characterize the attenuation value corresponding to each component in the brain function headgear.

[0092] In one embodiment, attenuation correction of a PET image based on a second attenuation template image to obtain a corrected PET image includes: determining the spatial position of each component in the brain function headgear in the second attenuation template image; determining the target spatial position of each component in the PET image based on the spatial position mapping relationship between the MR image and the PET image; and performing attenuation compensation on the image region where the target spatial position is located in the PET image based on the second attenuation template image to obtain a corrected PET image.

[0093] In practice, the computer equipment can determine the spatial mapping relationship between the MR image and the PET image obtained by scanning the target area of ​​the target object using a PET / MR integrated device. During the process of attenuating and correcting the PET image based on the second attenuation template image to obtain the corrected PET image, the computer equipment can determine the spatial position of each component in the brain function headgear within the second attenuation template image. Then, based on the spatial mapping relationship between the MR and PET images, the computer equipment can determine the corresponding position of each component in the PET image, which serves as the target spatial position for each component in the PET image. Finally, based on the attenuation value corresponding to each component in the second attenuation template image, the computer equipment can perform attenuation compensation on the image region containing the target spatial position of each component in the PET image, thus obtaining the corrected PET image.

[0094] In practical applications, after acquiring paired MR and PET images, the computer device can register the MR image (as a reference image) with the PET image (as a floating image) to obtain a registered PET image, aligning the registered PET image with the MR image in spatial position. Then, since the second attenuation template image is obtained by fusing the registered first attenuation template (which is spatially aligned with the MR image) with the MR image, the second attenuation template image and the registered PET image are spatially aligned. Therefore, during the attenuation correction of the PET image based on the second attenuation template image to obtain the corrected PET image, the computer device can directly use the attenuation values ​​corresponding to each component in the second attenuation template image to perform attenuation compensation on the image regions where the spatial positions of each component in the registered PET image are located, thus obtaining the corrected PET image.

[0095] The technical solution of this embodiment determines the spatial position of each component in the brain function headgear in the second attenuation template image; determines the target spatial position of each component in the PET image according to the spatial position mapping relationship between the MR image and the PET image; and performs attenuation compensation on the image region where the target spatial position is located in the PET image according to the second attenuation template image to obtain the corrected PET image. In this way, the attenuation value corresponding to each component in the brain function headgear is accurately assigned in the PET image according to the second attenuation template image, which can accurately correct the attenuation caused by the brain function headgear to the PET image and improve the accuracy of attenuation correction of the PET image.

[0096] In one embodiment, the method further includes: acquiring an initial phantom CT image and an initial phantom PET image; determining the initial attenuation coefficient corresponding to each component in the brain function headgear based on the initial phantom CT image; adjusting the initial attenuation coefficient to obtain an adjusted attenuated image; performing attenuation correction on the initial phantom PET image based on the adjusted attenuated image; if the difference between the average target uptake values ​​corresponding to each preset image region in the attenuated corrected initial phantom PET image meets a preset difference condition, then the adjusted attenuated image is used as the first attenuation template image.

[0097] Among them, the brain function headgear can be, but is not limited to, an infrared imaging headgear.

[0098] The initial phantom CT image and initial phantom PET image were obtained by scanning the phantom wearing a brain function headgear using a PET / CT system.

[0099] Among them, the PET / CT system can be an integrated PET / CT device.

[0100] The initial phantom CT image was obtained by scanning a phantom wearing a brain function headgear using the CT function of a PET / CT system.

[0101] The average target capture value corresponding to each preset image region is the average of the target capture values ​​corresponding to each pixel in each preset image region.

[0102] The target intake value can be the weight-adjusted SUV (standard uptake value). The weight-adjusted SUV can be named the weight-adjusted intake value (SUV bw).

[0103] In practical applications, the initial phantom PET image after attenuation correction can be named the reconstructed phantom PET image.

[0104] Among them, the adjusted attenuation image can characterize the adjusted attenuation value of each component in the brain function headgear.

[0105] The difference between the average target capture values ​​corresponding to each preset image region can be the difference between the average target capture values.

[0106] The preset difference condition can be that the difference between the average target intake values ​​is less than a preset difference threshold.

[0107] In practice, the PET / CT system can scan a phantom wearing a brain function headgear to obtain initial phantom CT and PET images, which are then acquired by a computer. However, due to the attenuation of PET photons by various components within the brain function headgear, the initial phantom PET image captures uneven values.

[0108] For the ease of understanding of those skilled in the art, Figure 5 This invention provides a method for scanning a phantom without a brain function headgear using a PET / CT system, resulting in a corresponding PET image of the phantom. Here, Pixels represents the number of pixels; Area represents the area of ​​a preset image region, in mm². 2 (square millimeters); Mean represents the average target acquisition value corresponding to the preset image region; Max represents the maximum value of the target acquisition value among all pixels in the preset image region; Min represents the minimum value of the target acquisition value among all pixels in the preset image region; SD represents the standard deviation of the target acquisition value among all pixels in the preset image region. The average target acquisition values ​​corresponding to each preset image region in the phantom PET image are "107.69", "109.41", "111.86", "109.08", "110.97", "111.20", and "108.12". It can be seen that the differences between the average target acquisition values ​​corresponding to each preset image region in the phantom PET image are relatively small.

[0109] For the ease of understanding of those skilled in the art, Figure 6 A schematic diagram of an initial phantom PET image is provided. (e.g.) Figure 6 As shown, the average target uptake values ​​corresponding to each preset image region are "107.46", "88.49", "94.92", "94.80", "103.47", "103.10", and "101.52". It can be seen that due to the attenuation of PET photons by various components in the brain function headgear, there are significant differences in the average target uptake values ​​corresponding to each preset image region in the initial phantom PET image.

[0110] For the ease of understanding of those skilled in the art, Figure 7 A schematic diagram of the imaging of a scanning phantom and a brain function headgear under a PET / CT system is provided. In this diagram, 710 represents the scanning phantom, and 720 represents the brain function headgear.

[0111] When scanning the phantom using a PET / CT system, a rod source is used as the radiation source. The rod source is the rod-shaped radiation source used in positron emission tomography for transmission scanning or quality control testing.

[0112] After the computer equipment acquires the initial phantom CT image and the initial phantom PET image, the initial phantom CT image can characterize the CT values ​​corresponding to each component in the brain function headgear. The computer equipment can determine the attenuation coefficient that matches the CT values ​​corresponding to each component in the brain function headgear based on the mapping relationship between the CT values ​​and the attenuation coefficients at the gamma-ray energy levels corresponding to the PET function, thus obtaining the initial attenuation coefficients (i.e., initial MU values) corresponding to each component in the brain function headgear. Then, the computer equipment can adjust the initial attenuation coefficients corresponding to each component in the brain function headgear, that is, reassign the corresponding attenuation coefficients (MU values) to each component in the brain function headgear. Based on the adjusted attenuation coefficients corresponding to each component in the brain function headgear, an adjusted attenuation image is obtained, which can characterize the adjusted PET attenuation values ​​corresponding to each component in the brain function headgear. Afterward, the computer equipment can perform attenuation correction on the initial phantom PET image based on the adjusted attenuation image, that is, perform attenuation correction on the initial phantom PET image based on the adjusted attenuation values ​​corresponding to each component in the brain function headgear, thus obtaining an attenuation-corrected initial phantom PET image.

[0113] The computer device can determine the average target acquisition value corresponding to each preset image region in the initial phantom PET image after attenuation correction, so as to determine the difference between the average target acquisition values ​​corresponding to each preset image region; if the difference between the average target acquisition values ​​corresponding to each preset image region meets the preset difference condition, then the initial phantom PET image after attenuation correction is determined as a uniform reconstructed phantom PET image, and the adjusted attenuated image is used as the first attenuation template image.

[0114] The computer device can also, after acquiring the initial attenuation coefficients corresponding to each component in the brain function headgear, generate an initial attenuation image based on the initial attenuation coefficients, and perform attenuation correction on the initial phantom PET image based on the initial attenuation image. If the difference between the average target uptake values ​​corresponding to each preset image region in the attenuation-corrected initial phantom PET image meets a preset difference condition, then the initial attenuation image is used as the first attenuation template image. If the difference between the average target uptake values ​​corresponding to each preset image region does not meet the preset difference condition, then the step of adjusting the initial attenuation coefficient to obtain an adjusted attenuation image is performed until the difference between the average target uptake values ​​corresponding to each preset image region in the attenuation-corrected initial phantom PET image meets the preset difference condition.

[0115] Thus, based on the first attenuation template image, the PET attenuation value corresponding to each component in the brain function headgear can be determined when a uniform reconstructed phantom PET image is obtained. This enables accurate assignment of the PET attenuation value corresponding to each component in the brain function headgear. Consequently, the PET image acquired by the PET / MR system can be attenuated based on the PET attenuation value corresponding to each component in the brain function headgear, resulting in a uniformly corrected PET image.

[0116] For the ease of understanding of those skilled in the art, Figures 8(a) to 8(c) A schematic diagram is provided for attenuation correction of an initial phantom PET image using a first attenuation template image.

[0117] Figure 8(a) shows another type of initial phantom PET image. As shown in Figure 8(a), the average target capture values ​​corresponding to each preset image region in the initial phantom PET image are "115.18", "117.72", "140.88", "150.94", "150.64", and "108.15". It can be seen that there are significant differences in the average target capture values ​​corresponding to each preset image region in the initial phantom PET image.

[0118] Figure 8(b) shows a horizontal axis view, a coronal view, and a sagittal view corresponding to a first attenuation template image.

[0119] Figure 8(c) shows a uniformly reconstructed phantom PET image. As shown in Figure 8(c), the average target capture values ​​corresponding to each preset image region in the uniformly reconstructed phantom PET image are "44.93", "43.97", "49.68", "44.86", and "50.09". It can be seen that the differences between the average target capture values ​​corresponding to each preset image region in this image are small.

[0120] The technical solution of this embodiment involves acquiring initial phantom CT images and initial phantom PET images. These initial phantom CT and PET images are obtained by scanning a phantom wearing a brain function headgear using a PET / CT system. Initial attenuation coefficients are determined for each component of the brain function headgear based on the initial phantom CT images. The initial attenuation coefficients are adjusted to obtain an adjusted attenuated image. Attenuation correction is applied to the initial phantom PET images based on the adjusted attenuated image. If the difference between the average target uptake values ​​corresponding to each preset image region in the attenuated corrected initial phantom PET image meets a preset difference condition, then the adjusted attenuated image is... The image serves as the first attenuation template image. Thus, when the difference between the average target uptake values ​​corresponding to each preset image region in the attenuation-corrected initial phantom PET image meets the preset difference condition, the attenuation-corrected initial phantom PET image can be used as a uniformly reconstructed phantom PET image. Therefore, the adjusted attenuation image corresponding to the uniformly reconstructed phantom PET image can be used as the first attenuation template image to accurately determine the attenuation information of each component in the brain function headgear when a uniformly reconstructed phantom PET image is obtained. Subsequently, the attenuation information can be used to accurately attenuate and correct the PET image corresponding to the target region of the target object.

[0121] In one embodiment, adjusting the initial attenuation coefficient to obtain an adjusted attenuation image includes: adjusting the initial attenuation coefficient to obtain an adjusted attenuation coefficient; converting the adjusted attenuation coefficient into adjusted attenuation values ​​corresponding to each component in the brain function headgear; and generating an adjusted attenuation image based on the adjusted attenuation values ​​corresponding to each component in the brain function headgear.

[0122] In practice, during the process of adjusting the initial attenuation coefficient to obtain the adjusted attenuation image, the computer device can adjust the initial attenuation coefficient corresponding to each component in the brain function headgear to obtain the adjusted attenuation coefficient corresponding to each component in the brain function headgear, thereby obtaining a two-dimensional distribution of the adjusted attenuation coefficients (adjusted attenuation coefficient matrix) for each component. Then, the computer device can convert the adjusted attenuation coefficients corresponding to each component in the brain function headgear into adjusted attenuation values ​​corresponding to each component in the brain function headgear according to the calculation formula of the attenuation value, thereby obtaining a two-dimensional distribution of the adjusted attenuation values ​​(adjusted attenuation value matrix). Finally, the computer device can generate the adjusted attenuation image based on the two-dimensional distribution of the adjusted attenuation values.

[0123] The technical solution of this embodiment obtains an adjusted attenuation coefficient by adjusting the initial attenuation coefficient; converts the adjusted attenuation coefficient into adjusted attenuation values ​​corresponding to each component in the brain function headgear; and generates an adjusted attenuation image based on the adjusted attenuation values ​​corresponding to each component in the brain function headgear. In this way, the adjusted attenuation image can characterize the adjusted attenuation values ​​corresponding to each component in the brain function headgear. When the adjusted attenuation image can be used as a first attenuation template image, the first attenuation template image can accurately characterize the attenuation values ​​corresponding to each component in the brain function headgear when a uniform reconstructed phantom PET image is obtained. Thus, the first attenuation template image can be used to perform high-accuracy attenuation correction on the PET image corresponding to the target area of ​​the target object.

[0124] In another embodiment, such as Figure 9 As shown, a medical image processing method is provided, and the method is illustrated using an application to a computer device as an example. The method includes the following steps:

[0125] Step S910: Acquire initial phantom CT image and initial phantom PET image; wherein, the initial phantom CT image and initial phantom PET image are obtained by scanning the phantom wearing a brain function headgear using a PET / CT system.

[0126] Step S920: Determine the initial attenuation coefficients of each component in the brain function headgear based on the initial phantom CT images.

[0127] Step S930: Adjust the initial attenuation coefficient to obtain the adjusted attenuation image.

[0128] Step S940: Attenuation correction is performed on the initial phantom PET image based on the adjusted attenuation image. If the difference between the average target acquisition values ​​corresponding to each preset image region in the attenuation-corrected initial phantom PET image meets the preset difference condition, then the adjusted attenuation image is used as the first attenuation template image.

[0129] Step S950: Obtain the MR image and PET image corresponding to the target area of ​​the target object.

[0130] Step S960: Use the MR image as the reference image and the first attenuation template image as the floating image.

[0131] Step S970: Perform non-rigid registration on the reference image and the floating image to obtain the registered floating image.

[0132] Step S980: The registered floating image is fused with the MR image to obtain the second attenuation template image.

[0133] Step S990: Attenuation correction is performed on the PET image based on the second attenuation template image to obtain the corrected PET image.

[0134] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a medical image processing method described above.

[0135] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0136] Based on the same inventive concept, this application also provides a medical image processing apparatus for implementing the aforementioned medical image processing method. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in the one or more medical image processing apparatus embodiments provided below can be found in the above-described limitations of the medical image processing method, and will not be repeated here.

[0137] In one embodiment, such as Figure 10 As shown, a medical image processing device is provided, including: an acquisition module 1010, an adjustment module 1020, and a correction module 1030, wherein:

[0138] The acquisition module 1010 is used to acquire MR images and PET images corresponding to the target area of ​​the target object; the target object is wearing a brain function headgear in the target area.

[0139] The adjustment module 1020 is used to adjust the first attenuation template image according to the MR image to obtain a second attenuation template image; the first attenuation template image is used to characterize the attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned by the PET / CT system.

[0140] The correction module 1030 is used to perform attenuation correction on the PET image based on the second attenuation template image to obtain a corrected PET image.

[0141] In one embodiment, the adjustment module 1020 is specifically used to use the MR image as a reference image and the first attenuation template image as a floating image; to perform non-rigid registration on the reference image and the floating image to obtain a registered floating image; and to fuse the registered floating image with the MR image to obtain the second attenuation template image.

[0142] In one embodiment, the adjustment module 1020 is specifically used to determine the spatial position mapping relationship between the reference image and the floating image; according to the spatial position mapping relationship, the floating image is mapped onto the reference image to obtain the registered floating image; the registered floating image and the corresponding points in the reference image have the same spatial position.

[0143] In one embodiment, the correction module 1030 is specifically used to determine the spatial position of each component in the brain function headgear in the second attenuation template image; determine the target spatial position of each component in the PET image according to the spatial position mapping relationship between the MR image and the PET image; and perform attenuation compensation on the image region where the target spatial position is located in the PET image according to the second attenuation template image to obtain the corrected PET image.

[0144] In one embodiment, the apparatus further includes: a phantom image acquisition module for acquiring an initial phantom CT image and an initial phantom PET image; the initial phantom CT image and the initial phantom PET image are obtained by scanning a scanning phantom wearing the brain function headgear using the PET / CT system; a coefficient determination module for determining an initial attenuation coefficient corresponding to each component in the brain function headgear based on the initial phantom CT image; a coefficient adjustment module for adjusting the initial attenuation coefficient to obtain an adjusted attenuated image; and a template image determination module for attenuating the initial phantom PET image based on the adjusted attenuated image, wherein if the difference between the average target uptake values ​​corresponding to each preset image region in the attenuated adjusted initial phantom PET image meets a preset difference condition, the adjusted attenuated image is used as the first attenuation template image.

[0145] In one embodiment, the coefficient adjustment module is specifically used to adjust the initial attenuation coefficient to obtain the adjusted attenuation coefficient; convert the adjusted attenuation coefficient into the adjusted attenuation value corresponding to each component in the brain function headgear; and generate the adjusted attenuation image based on the adjusted attenuation value corresponding to each component in the brain function headgear.

[0146] The various modules in the aforementioned medical image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0147] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a medical image processing method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad located on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0148] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0149] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0150] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0151] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0153] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A medical image processing method, characterized in that, The method includes: Acquire MR and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region. The first attenuation template image is adjusted based on the MR image to obtain a second attenuation template image; the first attenuation template image is used to characterize the PET attenuation values ​​of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned using a PET / CT system; the process includes: using the MR image as a reference image and the first attenuation template image as a floating image; performing non-rigid registration on the reference image and the floating image to obtain a registered floating image; and fusing the registered floating image with the MR image to obtain the second attenuation template image; The PET image is attenuated and corrected based on the second attenuation template image to obtain the corrected PET image.

2. The method according to claim 1, characterized in that, The step of performing non-rigid registration of the reference image and the floating image to obtain the registered floating image includes: Determine the spatial mapping relationship between the reference image and the floating image; Based on the spatial location mapping relationship, the floating image is mapped onto the reference image to obtain the registered floating image.

3. The method according to claim 1, characterized in that, The step of attenuating the PET image according to the second attenuation template image to obtain the corrected PET image includes: The spatial positions of each component in the brain function headgear are determined in the second attenuation template image; Based on the spatial mapping relationship between the MR image and the PET image, determine the target spatial position of each component in the PET image; Based on the second attenuation template image, attenuation compensation is performed on the image region where the target spatial location is located in the PET image to obtain the corrected PET image.

4. The method according to claim 1, characterized in that, The method further includes: Acquire initial phantom CT images and initial phantom PET images; the initial phantom CT images and the initial phantom PET images are obtained by scanning a phantom wearing the brain function headgear using the PET / CT system; The initial attenuation coefficients of each component in the brain function headgear are determined based on the initial phantom CT images. Adjust the initial attenuation coefficient to obtain the adjusted attenuation image; The initial phantom PET image is attenuated and corrected based on the adjusted attenuation image to obtain the first attenuation template image.

5. The method according to claim 4, characterized in that, The step of adjusting the initial attenuation coefficient to obtain the adjusted attenuation image includes: Adjust the initial attenuation coefficient to obtain the adjusted attenuation coefficient; The adjusted attenuation coefficient is converted into the adjusted attenuation value corresponding to each component in the brain function headgear; The adjusted attenuation image is generated based on the adjusted attenuation values ​​corresponding to each component in the brain function headgear.

6. A medical image processing device, characterized in that, The device includes: The acquisition module is used to acquire MR images and PET images corresponding to the target region of the target object; the target object is wearing a brain function headgear in the target region; The adjustment module is used to adjust the first attenuation template image according to the MR image to obtain a second attenuation template image; the first attenuation template image is used to characterize the PET attenuation value of each component in the brain function headgear when the scanning phantom wearing the brain function headgear is scanned by the PET / CT system. The adjustment module is specifically used to use the MR image as a reference image and the first attenuation template image as a floating image; to perform non-rigid registration on the reference image and the floating image to obtain a registered floating image; and to fuse the registered floating image with the MR image to obtain the second attenuation template image. The correction module is used to perform attenuation correction on the PET image based on the second attenuation template image to obtain a corrected PET image.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images