Method and apparatus for segmenting brain tumor images
By generating multi-scale three-dimensional brain images and utilizing a three-dimensional convolutional neural network segmentation model, the problem of two-dimensional networks being unable to capture the complex features of brain tumors was solved, achieving a higher accuracy rate for brain tumor image segmentation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY
- Filing Date
- 2024-03-29
- Publication Date
- 2026-06-05
Smart Images
Figure CN118279583B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of medical imaging technology, and in particular to a method, apparatus, computer device, storage medium, and computer program product for segmenting brain tumor images. Background Technology
[0002] With the continuous advancement of medical imaging technology, obtaining tomographic images of internal body structures through computed tomography (CT) and positron emission tomography (PET) and using these images for disease diagnosis and treatment has become an important tool in modern medicine.
[0003] In related technologies, brain tumor image segmentation generally relies on experienced physicians manually identifying the tumor region in brain images. To improve the efficiency of brain tumor image segmentation, neural network-based brain tumor image segmentation schemes have been applied to this task. Specifically, the tomographic image of the brain is first processed into an image of a preset size, and then the processed image is input into a trained two-dimensional convolutional neural network (CNN), which determines the image region corresponding to the brain tumor. However, because two-dimensional images provide limited information about the internal structure of the brain, and a single-scale two-dimensional convolutional neural network may not be able to fully capture the complex features of the brain tumor, the segmentation accuracy of brain tumor images is low. Summary of the Invention
[0004] Therefore, it is necessary to provide a brain tumor image segmentation method, apparatus, computer equipment, storage medium, and computer program product that can improve the accuracy of brain tumor image segmentation in response to the above-mentioned technical problems.
[0005] In a first aspect, this application provides a method for segmenting brain tumor images, comprising:
[0006] Acquire a set of brain computed tomography (CT) images;
[0007] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0008] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0009] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0010] In one embodiment, generating at least two scales of three-dimensional brain images based on the brain computed tomography image set includes:
[0011] The brain tomography images in the brain tomography image set are scaled to obtain at least two preprocessed image sets; wherein the brain tomography images in the same preprocessed image set have the same scale, and the brain tomography images in different preprocessed image sets have different scales.
[0012] Three-dimensional brain images are constructed based on the at least two preprocessed image sets to obtain three-dimensional brain images at the at least two scales.
[0013] In one embodiment, fusing candidate brain tumor regions from the at least two scales of three-dimensional brain images to obtain an initial brain tumor image includes:
[0014] Obtain overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images;
[0015] Based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images, determine the brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images;
[0016] The initial brain tumor image is obtained based on the confidence level of the candidate brain tumor regions belonging to the same region.
[0017] In one embodiment, obtaining the initial brain tumor image based on the confidence level of candidate brain tumor regions belonging to the same region includes:
[0018] The confidence level of a region is obtained based on the confidence level of the candidate brain tumor regions belonging to the same region. The confidence level of a region is the sum of the confidence levels of each candidate brain tumor region belonging to that region.
[0019] Determine whether the confidence level of the region is greater than a preset threshold;
[0020] If so, then the area is determined to be a brain tumor region;
[0021] Extract the image corresponding to the brain tumor region to obtain the initial brain tumor image.
[0022] In one embodiment, after obtaining an initial brain tumor image by fusing candidate brain tumor regions from the at least two scales of three-dimensional brain images, the method further includes:
[0023] The initial brain tumor image is segmented into three-dimensional image blocks of a preset size;
[0024] Determine whether each 3D image block belongs to a brain tumor lesion;
[0025] Combine three-dimensional image blocks belonging to brain tumor lesions to obtain the target brain tumor image.
[0026] In one embodiment, the step of determining whether each three-dimensional image block belongs to a brain tumor lesion includes:
[0027] Based on the lesion discrimination model, each three-dimensional image block is determined to be a brain tumor lesion;
[0028] The lesion discrimination model is a model obtained by training the Visual Geometry Group (VGG) model based on the second sample data. The second sample data includes multiple sample three-dimensional image blocks and label information of each sample three-dimensional image block. The label information of the sample three-dimensional image blocks is used to indicate whether the sample three-dimensional image block belongs to a brain tumor lesion.
[0029] In one embodiment, before obtaining candidate brain tumor regions in the at least two scales of three-dimensional brain images based on the at least two scales of brain images and the corresponding image segmentation models, the method further includes:
[0030] Tilt correction was performed on the three-dimensional brain images at at least two scales respectively.
[0031] Secondly, this application also provides a segmentation device for brain tumor images, comprising:
[0032] The acquisition module is used to acquire a set of brain computed tomography (CT) images.
[0033] A generation module is used to generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0034] The segmentation module is used to obtain brain tumor candidate regions in the brain three-dimensional images at at least two scales based on the brain three-dimensional images at at least two scales and the image segmentation models corresponding to the at least two scales respectively; the image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, the first sample data including: multiple sample brain three-dimensional images and masks of brain tumor regions in each sample brain three-dimensional image;
[0035] The processing module is used to fuse brain tumor candidate regions from the at least two scales of three-dimensional brain images to obtain an initial brain tumor image.
[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0037] Acquire a set of brain computed tomography (CT) images;
[0038] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0039] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0040] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0041] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:
[0042] Acquire a set of brain computed tomography (CT) images;
[0043] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0044] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0045] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0046] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:
[0047] Acquire a set of brain computed tomography (CT) images;
[0048] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0049] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0050] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0051] The aforementioned brain tumor image segmentation method, apparatus, computer equipment, storage medium, and computer program product, after acquiring a set of brain tomographic scan images, first generate at least two scales of three-dimensional brain images based on the brain tomographic scan image set. Then, based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, they respectively obtain brain tumor candidate regions in the at least two scales of three-dimensional brain images, and fuse the brain tumor candidate regions in the at least two scales of three-dimensional brain images to obtain an initial brain tumor image. Since the embodiments of this application can generate at least two scales of three-dimensional brain images based on the brain tomographic scan image set, and obtain brain tumor candidate regions in the at least two scales of three-dimensional brain images based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, and fuse the brain tumor candidate regions in the at least two scales of three-dimensional brain images to obtain an initial brain tumor image, the embodiments of this application can fuse the segmentation results of multiple scales of three-dimensional brain images to obtain a more accurate brain tumor image, improving the segmentation accuracy of brain tumor images. Attached Figure Description
[0052] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0053] Figure 1 This is a flowchart of the steps of a brain tumor image segmentation method in one embodiment;
[0054] Figure 2 This is a schematic diagram of a brain tomography image set in one embodiment;
[0055] Figure 3 This is a flowchart of the steps of a brain tumor image segmentation method in another embodiment;
[0056] Figure 4This is a flowchart of the steps of a brain tumor image segmentation method in another embodiment;
[0057] Figure 5 This is a structural block diagram of a brain tumor image segmentation device in one embodiment;
[0058] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0059] 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.
[0060] The brain tumor image segmentation method provided in this application embodiment can be applied to brain tumor image segmentation devices. These devices can be, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc.
[0061] In one exemplary embodiment, such as Figure 1 As shown, a method for segmenting brain tumor images is provided, including the following steps 101 to 104:
[0062] Step 101: Obtain a set of brain computed tomography (CT) images.
[0063] The brain tomography image set in this application embodiment may include: an image set obtained by scanning the brain using computed tomography (CT) technology and / or an image set obtained by scanning the brain using positron emission tomography (PET) technology.
[0064] For example, refer to Figure 2 As shown, the brain tomography image set 200 includes multiple brain tomography images 201, which are scan images of different locations of the brain. Figure 2The example shown is a brain tomography image set 200 containing 20 brain tomography images 201. However, the embodiments of this application are not limited to this. In some embodiments, the spacing when performing tomography scans on the brain can be reduced, thereby increasing the number of brain tomography images in the brain tomography image set. Alternatively, the spacing when performing tomography scans on the brain can be increased, thereby reducing the number of brain tomography images in the brain tomography image set.
[0065] Step 102: Generate at least two scales of three-dimensional brain images based on the brain tomography image set.
[0066] In some embodiments, generating at least two scales of three-dimensional brain images based on the brain computed tomography image set includes the following steps 102a and 102b:
[0067] Step 102a: Scale the brain tomography images in the brain tomography image set to obtain at least two preprocessed image sets.
[0068] Brain tomography images within the same preprocessed image set have the same scale, while brain tomography images within different preprocessed image sets have different scales.
[0069] For example, if the resolution of the brain tomography images in the brain tomography image set obtained in step 101 is 1024*1024, then each brain tomography image in the brain tomography image set can be downsampled to an image with a resolution of 768*768 to obtain a first preprocessed image set, each brain tomography image in the brain tomography image set can be downsampled to an image with a resolution of 512*512 to obtain a second preprocessed image set, and the brain tomography image set can be used as a third preprocessed image set, for a total of three preprocessed image sets.
[0070] Step 102b: Construct three-dimensional brain images based on the at least two preprocessed image sets to obtain three-dimensional brain images at the at least two scales.
[0071] Continuing with the example above, the at least two preprocessed image sets include: a first preprocessed image set where each image has a resolution of 512*512, a second preprocessed image set where each image has a resolution of 768*768, and a third preprocessed image set where each image has a resolution of 1024*1024. Then, brain 3D images are constructed based on the at least two preprocessed image sets to obtain brain 3D images at at least two scales, including:
[0072] A first three-dimensional brain image is obtained by constructing a three-dimensional brain image based on a first preprocessed image set, a second three-dimensional brain image is obtained by constructing a three-dimensional brain image based on a second preprocessed image set, and a third three-dimensional brain image is obtained by constructing a three-dimensional brain image based on a third preprocessed image set.
[0073] Since the resolution of each image in the first preprocessed image set is 512*512, the resolution of the first three-dimensional brain image can be 512*512*512. Since the resolution of each image in the second preprocessed image set is 768*768, the resolution of the second three-dimensional brain image can be 768*768*768. Since the resolution of each image in the third preprocessed image set is 1024*1024, the resolution of the third three-dimensional brain image can be 1024*1024*1024.
[0074] In some embodiments, constructing a three-dimensional image of the brain based on a preprocessed image set includes: constructing a three-dimensional image of the brain based on surface reconstruction. The construction of a three-dimensional image of the brain based on surface reconstruction is a method of describing the structure of a three-dimensional object by geometrically stitching together and fitting the object's surface. This may include: firstly, using image segmentation techniques to segment the contour curves of the brain structure from each image in the preprocessed image set, and then performing image processing to obtain the three-dimensional structure of the brain, thereby acquiring a three-dimensional image of the brain.
[0075] In some embodiments, constructing a three-dimensional image of the brain based on a preprocessed image set includes: constructing a three-dimensional image of the brain based on voxel reconstruction. The method of constructing a three-dimensional image of the brain based on voxel reconstruction is a method of projecting volume pixels with certain colors and transparency onto a display plane, and may include: generating a three-dimensional volume data set based on the preprocessed image set, and reconstructing a three-dimensional image of the brain based on the three-dimensional volume data set.
[0076] Step 103: Obtain brain tumor candidate regions in the brain three-dimensional images at the at least two scales based on the brain three-dimensional images at the at least two scales and the image segmentation models corresponding to the at least two scales respectively.
[0077] The image segmentation model is a model obtained by training a three-dimensional convolutional neural network (3D MR-CNN) based on the first sample data. The first sample data includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0078] In some embodiments, the method of training a three-dimensional convolutional neural network to obtain an image segmentation model based on the first sample data may include: inputting a three-dimensional brain image of a sample from the first sample data into the three-dimensional convolutional neural network, obtaining the brain tumor candidate region predicted by the three-dimensional convolutional neural network, calculating a loss value based on the brain tumor candidate region predicted by the three-dimensional convolutional neural network, the actual brain tumor region of the sample brain three-dimensional image, and a preset loss function, and adjusting the network parameters of the three-dimensional convolutional neural network based on the loss value.
[0079] As described in the example above, the at least two scaled three-dimensional brain images include: a first three-dimensional brain image with a resolution of 512*512*512, a second three-dimensional brain image with a resolution of 768*768*768, and a third three-dimensional brain image with a resolution of 1024*1024*1024. Therefore, the first three-dimensional brain image can be input into a first image segmentation model with a scale of 512 to obtain the brain tumor candidate region predicted by the first image segmentation model in the first three-dimensional brain image; the second three-dimensional brain image can be input into a second image segmentation model with a scale of 768 to obtain the brain tumor candidate region predicted by the second image segmentation model in the second three-dimensional brain image; and the third three-dimensional brain image can be input into a third image segmentation model with a scale of 1024 to obtain the brain tumor candidate region predicted by the third image segmentation model in the third three-dimensional brain image.
[0080] Step 104: Fuse the candidate brain tumor regions from the at least two scales of three-dimensional brain images to obtain an initial brain tumor image.
[0081] In some embodiments, fusing brain tumor candidate regions from at least two scales of three-dimensional brain images to obtain an initial brain tumor image includes: determining brain tumor candidate regions belonging to the same region based on brain tumor candidate regions from at least two scales of three-dimensional brain images, and determining that the region is a brain tumor region based on the confidence level of the brain tumor candidate regions belonging to the same region.
[0082] The aforementioned brain tumor image segmentation method, after acquiring a set of brain tomographic images, first generates at least two scales of three-dimensional brain images based on the brain tomographic image set. Then, based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, it obtains brain tumor candidate regions in the at least two scales of three-dimensional brain images, and fuses the brain tumor candidate regions in the at least two scales of three-dimensional brain images to obtain an initial brain tumor image. Since this embodiment can generate at least two scales of three-dimensional brain images based on the brain tomographic image set, and obtain brain tumor candidate regions in the at least two scales of three-dimensional brain images and the corresponding image segmentation models, and fuse the brain tumor candidate regions in the at least two scales of three-dimensional brain images to obtain an initial brain tumor image, this embodiment can fuse the segmentation results of multiple scales of three-dimensional brain images to obtain a more accurate brain tumor image, improving the segmentation accuracy of brain tumor images.
[0083] As an extension and refinement of the above embodiments, refer to Figure 3 As shown, in one exemplary embodiment, such as Figure 3 As shown, the brain tumor image segmentation method provided in the above embodiment includes the following steps 301 to 310:
[0084] Step 301: Obtain a set of brain computed tomography (CT) images.
[0085] Step 302: Scale the brain tomography images in the brain tomography image set to obtain at least two preprocessed image sets.
[0086] Brain tomography images within the same preprocessed image set have the same scale, while brain tomography images within different preprocessed image sets have different scales.
[0087] Step 303: Construct three-dimensional brain images based on the at least two preprocessed image sets to obtain three-dimensional brain images at at least two scales.
[0088] Step 304: Obtain brain tumor candidate regions in the brain three-dimensional images at the at least two scales based on the brain three-dimensional images at the at least two scales and the image segmentation models corresponding to the at least two scales respectively.
[0089] The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on the first sample data. The first sample data includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0090] Step 305: Obtain the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images.
[0091] Step 306: Based on the overlap information of the brain tumor candidate regions in the at least two scales of three-dimensional brain images, determine the brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images.
[0092] In some embodiments, determining brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images based on overlap information of brain tumor candidate regions in the at least two scales includes: determining whether the overlap rate of a first brain tumor candidate region and a second brain tumor candidate region in the at least two scales of three-dimensional brain images is greater than a threshold overlap rate; if so, determining that the first brain tumor candidate region and the second brain tumor candidate region belong to the same region. Wherein, the first brain tumor candidate region and the second brain tumor candidate region are brain tumor candidate regions in three-dimensional brain images of different scales.
[0093] Step 307: Obtain the initial brain tumor image based on the confidence level of the candidate brain tumor regions belonging to the same region.
[0094] In some embodiments, the initial brain tumor image is obtained based on the confidence level of the brain tumor candidate regions belonging to the same region, including the following steps 307a to 307d:
[0095] Step 307a: Obtain the confidence level of the region based on the confidence level of the candidate brain tumor regions belonging to the same region.
[0096] The confidence level of the region is the sum of the confidence levels of each brain tumor candidate region belonging to the region.
[0097] For example, if brain tumor candidate region A in a first-scale three-dimensional brain image, brain tumor candidate region B in a second-scale three-dimensional brain image, and brain tumor candidate region C in a third-scale three-dimensional brain image belong to the same region, and the confidence scores of brain tumor candidate region A, brain tumor candidate region B, and brain tumor candidate region C are x, y, and z respectively, then the confidence score of the region is x+y+z.
[0098] Step 307b: Determine whether the confidence level of the region is greater than a preset threshold.
[0099] In step 307 above, if the confidence level of the region is less than the preset threshold, the probability that the region is a brain tumor region is low, so the region is not identified as a brain tumor region. However, if the confidence level of the region is greater than the preset threshold, the probability that the region is a brain tumor region is high, so step 307c is executed as follows:
[0100] Step 307c: Determine that the area is a brain tumor area.
[0101] Step 307d: Extract the image corresponding to the brain tumor region to obtain the initial brain tumor image.
[0102] In some embodiments, extracting the image corresponding to the brain tumor region includes: extracting the image corresponding to the brain tumor region from the largest (highest resolution) three-dimensional brain image among the at least two scales of three-dimensional brain images.
[0103] It should be noted that, since this application involves extracting brain tumor images from three-dimensional brain images, the initial brain tumor images obtained are also three-dimensional images.
[0104] Step 308: Segment the initial brain tumor image into three-dimensional image blocks of a preset size.
[0105] In some embodiments, the initial brain tumor image can be divided into three-dimensional cubic image blocks with a size of 1.0mm*1.0mm*1.0mm.
[0106] Step 309: Determine whether each three-dimensional image block belongs to a brain tumor lesion.
[0107] In some embodiments, determining whether each three-dimensional image block belongs to a brain tumor lesion includes:
[0108] Based on the lesion discrimination model, each three-dimensional image block is determined to be a brain tumor lesion.
[0109] The lesion discrimination model is a model obtained by training a Visual Geometry Group (VGG) model based on the second sample data. The second sample data includes multiple sample three-dimensional image blocks and label information of each sample three-dimensional image block. The label information of the sample three-dimensional image blocks is used to indicate whether the sample three-dimensional image block belongs to a brain tumor lesion.
[0110] In some embodiments, a multi-scale lesion discrimination model can also be established to accurately segment brain tumor images output by image segmentation models at different scales, and finally, image blocks suspected of being brain cancer can be determined through ensemble learning.
[0111] Step 310: Combine the three-dimensional image blocks belonging to the brain tumor lesion to obtain the target brain tumor image.
[0112] Steps 308 to 310 above can further refine the initial brain tumor image to obtain a more accurate target brain tumor image.
[0113] Furthermore, compared to directly segmenting the three-dimensional image of the brain into multiple three-dimensional image blocks and then determining whether each three-dimensional image block belongs to a brain tumor lesion, the above embodiment first obtains an initial brain tumor image and then segments the three-dimensional image of the brain into multiple three-dimensional image blocks. Therefore, the above embodiment can reduce the number of three-dimensional image blocks that need to be determined, thereby reducing the amount of computation in the process of extracting brain tumor images and improving the efficiency of brain tumor image extraction.
[0114] The presence or absence of a tilt angle in brain computed tomography (CT) images has a significant impact on the accuracy of extracted brain tumor images. If the head is tilted during the acquisition of brain CT images, the acquired brain CT images will be asymmetrical, severely affecting the accuracy of brain tumor images obtained through convolutional neural networks. Therefore, in some embodiments, the above-mentioned brain tumor image extraction method further includes: before obtaining brain tumor candidate regions in the at least two scales of brain 3D images based on the at least two scales of brain 3D images and the corresponding image segmentation models, respectively, tilt correction is performed on the at least two scales of brain 3D images.
[0115] In some embodiments, combined with Figure 1 , refer to Figure 4 As shown, the method for tilt correction of the three-dimensional brain image includes the following steps 401 to 402:
[0116] Step 401: Obtain the mid-sagittal plane (MSP) of the three-dimensional brain image.
[0117] The median sagittal plane is an anatomical term that refers to a vertical plane that divides an anatomical object into two symmetrical parts. In the case of the brain, the median sagittal plane is the vertical plane that divides the brain into the left and right hemispheres.
[0118] In some embodiments, step 401 (obtaining the midsagittal plane of a three-dimensional image of the brain) is implemented in the following ways:
[0119] Step 401a: Obtain the initial sagittal plane based on the geometric center of the three-dimensional brain image.
[0120] That is, the sagittal plane passing through the center of gravity of the brain is determined as the initial sagittal plane.
[0121] Step 401b: Extract a preset number of three-dimensional image blocks from the three-dimensional brain image, with the initial sagittal plane as the plane of symmetry.
[0122] In some embodiments, extracting a predetermined number of pairs of three-dimensional image patches symmetrical about the initial sagittal plane from the three-dimensional brain image includes:
[0123] The preset number of three-dimensional image patches with the initial sagittal plane as the plane of symmetry are extracted on both sides of the initial sagittal plane using the Poisson sampling model.
[0124] Step 401c: Obtain the similarity of each pair of 3D image blocks.
[0125] In some embodiments, obtaining the similarity of each pair of 3D image patches includes:
[0126] The similarity of each pair of 3D image patches is obtained based on a similarity acquisition model;
[0127] The similarity acquisition model is a model obtained by training a multi-scale three-dimensional convolutional neural network model based on the first sample data. The first sample data includes multiple pairs of sample three-dimensional image blocks and the similarity of each pair of sample three-dimensional image blocks.
[0128] Step 401d: Obtain the symmetry of the initial sagittal plane based on the similarity of each pair of three-dimensional image blocks.
[0129] In some embodiments, obtaining the symmetry of the initial sagittal plane based on the similarity of each pair of three-dimensional image blocks includes: calculating the sum of the similarities of each pair of three-dimensional image blocks to obtain the symmetry of the initial sagittal plane.
[0130] That is, the symmetry of the initial sagittal plane is denoted as S, and the similarity of the i-th pair of three-dimensional image patches is denoted as s. i Then we have:
[0131]
[0132] Step 401e: Based on the symmetry of the initial sagittal plane, the genetic algorithm and the Powell algorithm are used to obtain the extreme value of symmetry, and the sagittal plane corresponding to the extreme value of symmetry is determined as the midsagittal plane of the three-dimensional brain image.
[0133] Step 402: Perform tilt correction on the three-dimensional image of the brain based on the median sagittal plane.
[0134] In some embodiments, tilt correction is performed on the three-dimensional brain image based on the median sagittal plane, including:
[0135] Step 402a: Based on the midsagittal plane of the three-dimensional brain image and the expression of the sagittal plane in the three-dimensional coordinate system, obtain the head and neck lateral flexion angle and head and neck rotation angle of the three-dimensional brain image.
[0136] The expression for the midsagittal plane π in a three-dimensional brain image in a three-dimensional coordinate system is:
[0137] π = Ax + By + Cz + D
[0138] A = cos(α) + cos(β)
[0139] B = sin(α) + cos(β)
[0140] C = sin(α)
[0141] Where α is the angle between the normal vector of the median sagittal plane π and the xy plane, β is the angle between the projection of the median sagittal plane π onto the xy plane and the x-axis, and D is the distance from the origin of the three-dimensional coordinate system to the median sagittal plane π.
[0142] Where α is the lateral flexion angle of the head and neck, and β is the rotation angle of the head and neck.
[0143] Step 402b: The three-dimensional image of the brain is tilted according to the head and neck lateral flexion angle and the head and neck rotation angle.
[0144] 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.
[0145] Based on the same inventive concept, this application also provides a brain tumor image segmentation apparatus for implementing the brain tumor image segmentation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more brain tumor image segmentation apparatus embodiments provided below can be found in the limitations of the brain tumor image segmentation method described above, and will not be repeated here.
[0146] In one exemplary embodiment, such as Figure 5 As shown, a brain tumor image segmentation device is provided, comprising:
[0147] Module 51 is used to acquire a set of brain tomography images;
[0148] The generation module 52 is used to generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0149] The segmentation module 53 is used to obtain brain tumor candidate regions in the brain three-dimensional images at at least two scales based on the brain three-dimensional images at at least two scales and the image segmentation models corresponding to the at least two scales respectively; the image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, the first sample data including: multiple sample brain three-dimensional images and masks of brain tumor regions in each sample brain three-dimensional image;
[0150] Processing module 54 is used to fuse brain tumor candidate regions in the at least two scales of three-dimensional brain images to obtain an initial brain tumor image.
[0151] In one embodiment, the generation module 52 is specifically used to scale the brain tomographic images in the brain tomographic image set to obtain at least two preprocessed image sets; wherein the brain tomographic images in the same preprocessed image set have the same scale, and the brain tomographic images in different preprocessed image sets have different scales; and to construct brain three-dimensional images according to the at least two preprocessed image sets to obtain brain three-dimensional images at the at least two scales.
[0152] In one embodiment, the processing module 54 is specifically used to acquire overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; determine brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; and acquire the initial brain tumor image based on the confidence level of the brain tumor candidate regions belonging to the same region.
[0153] In one embodiment, the processing module 54 is specifically configured to obtain the confidence level of a region based on the confidence level of the brain tumor candidate regions belonging to the same region, wherein the confidence level of the region is the sum of the confidence levels of each brain tumor candidate region belonging to the region; determine whether the confidence level of the region is greater than a preset threshold; if so, determine that the region is a brain tumor region; and extract the image corresponding to the brain tumor region to obtain the initial brain tumor image.
[0154] In one embodiment, the processing module 54 is further configured to, after fusing brain tumor candidate regions in the at least two scales of brain three-dimensional images to obtain an initial brain tumor image, divide the initial brain tumor image into three-dimensional image blocks of a preset size; determine whether each three-dimensional image block belongs to a brain tumor lesion; and combine the three-dimensional image blocks belonging to the brain tumor lesion to obtain a target brain tumor image.
[0155] In one embodiment, the processing module 54 is specifically used to determine whether each three-dimensional image block belongs to a brain tumor lesion based on the lesion discrimination model;
[0156] The lesion discrimination model is a model obtained by training the Visual Geometry Group (VGG) model based on the second sample data. The second sample data includes multiple sample three-dimensional image blocks and label information of each sample three-dimensional image block. The label information of the sample three-dimensional image blocks is used to indicate whether the sample three-dimensional image block belongs to a brain tumor lesion.
[0157] In one embodiment, the segmentation module 53 is further configured to perform tilt correction on the brain three-dimensional images at the at least two scales before obtaining the brain tumor candidate regions in the brain three-dimensional images at the at least two scales based on the brain three-dimensional images at the at least two scales and the image segmentation models corresponding to the at least two scales, respectively.
[0158] Each module in the aforementioned brain tumor image segmentation 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, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.
[0159] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational 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 in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. 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 executed by the processor, the computer program implements a method for segmenting brain tumor images. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0160] Those skilled in the art will understand that Figure 6 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.
[0161] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0162] Acquire a set of brain computed tomography (CT) images;
[0163] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0164] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0165] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0166] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0167] The brain tomography images in the aforementioned brain tomography image set are scaled to obtain at least two preprocessed image sets; three-dimensional brain images are then constructed based on the at least two preprocessed image sets to obtain at least two three-dimensional brain images at the aforementioned two scales. Specifically, brain tomography images within the same preprocessed image set have the same scale, while brain tomography images in different preprocessed image sets have different scales.
[0168] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0169] Obtain overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; determine brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; obtain the initial brain tumor image based on the confidence level of the brain tumor candidate regions belonging to the same region.
[0170] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0171] Based on the confidence scores of brain tumor candidate regions belonging to the same region, the confidence score of the region is obtained, and the confidence score of the region is the sum of the confidence scores of each brain tumor candidate region belonging to the region; it is determined whether the confidence score of the region is greater than a preset threshold; if so, the region is determined to be a brain tumor region; the image corresponding to the brain tumor region is extracted to obtain the initial brain tumor image.
[0172] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0173] The initial brain tumor image is segmented into three-dimensional image blocks of a preset size; each three-dimensional image block is determined to be a brain tumor lesion; and the three-dimensional image blocks belonging to the brain tumor lesion are combined to obtain the target brain tumor image.
[0174] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0175] The model determines whether each three-dimensional image patch belongs to a brain tumor lesion based on a lesion discrimination model. The lesion discrimination model is a model obtained by training the Visual Geometry Group (VGG) model based on second sample data. The second sample data includes multiple sample three-dimensional image patches and label information of each sample three-dimensional image patch. The label information of the sample three-dimensional image patch is used to indicate whether the sample three-dimensional image patch belongs to a brain tumor lesion.
[0176] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0177] Tilt correction was performed on the three-dimensional brain images at at least two scales respectively.
[0178] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0179] Acquire a set of brain computed tomography (CT) images;
[0180] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0181] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0182] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0183] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0184] The brain tomography images in the aforementioned brain tomography image set are scaled to obtain at least two preprocessed image sets; three-dimensional brain images are then constructed based on the at least two preprocessed image sets to obtain at least two three-dimensional brain images at the aforementioned two scales. Specifically, brain tomography images within the same preprocessed image set have the same scale, while brain tomography images in different preprocessed image sets have different scales.
[0185] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0186] Obtain overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; determine brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; obtain the initial brain tumor image based on the confidence level of the brain tumor candidate regions belonging to the same region.
[0187] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0188] Based on the confidence scores of brain tumor candidate regions belonging to the same region, the confidence score of the region is obtained, and the confidence score of the region is the sum of the confidence scores of each brain tumor candidate region belonging to the region; it is determined whether the confidence score of the region is greater than a preset threshold; if so, the region is determined to be a brain tumor region; the image corresponding to the brain tumor region is extracted to obtain the initial brain tumor image.
[0189] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0190] The initial brain tumor image is segmented into three-dimensional image blocks of a preset size; each three-dimensional image block is determined to be a brain tumor lesion; and the three-dimensional image blocks belonging to the brain tumor lesion are combined to obtain the target brain tumor image.
[0191] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0192] The model determines whether each three-dimensional image patch belongs to a brain tumor lesion based on a lesion discrimination model. The lesion discrimination model is a model obtained by training the Visual Geometry Group (VGG) model based on second sample data. The second sample data includes multiple sample three-dimensional image patches and label information of each sample three-dimensional image patch. The label information of the sample three-dimensional image patch is used to indicate whether the sample three-dimensional image patch belongs to a brain tumor lesion.
[0193] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0194] Tilt correction was performed on the three-dimensional brain images at at least two scales respectively.
[0195] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0196] Acquire a set of brain computed tomography (CT) images;
[0197] Generate at least two scales of three-dimensional brain images based on the brain tomography image set;
[0198] Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image.
[0199] By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained.
[0200] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0201] The brain tomography images in the aforementioned brain tomography image set are scaled to obtain at least two preprocessed image sets; three-dimensional brain images are then constructed based on the at least two preprocessed image sets to obtain at least two three-dimensional brain images at the aforementioned two scales. Specifically, brain tomography images within the same preprocessed image set have the same scale, while brain tomography images in different preprocessed image sets have different scales.
[0202] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0203] Obtain overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; determine brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; obtain the initial brain tumor image based on the confidence level of the brain tumor candidate regions belonging to the same region.
[0204] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0205] Based on the confidence scores of brain tumor candidate regions belonging to the same region, the confidence score of the region is obtained, and the confidence score of the region is the sum of the confidence scores of each brain tumor candidate region belonging to the region; it is determined whether the confidence score of the region is greater than a preset threshold; if so, the region is determined to be a brain tumor region; the image corresponding to the brain tumor region is extracted to obtain the initial brain tumor image.
[0206] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0207] The initial brain tumor image is segmented into three-dimensional image blocks of a preset size; each three-dimensional image block is determined to be a brain tumor lesion; and the three-dimensional image blocks belonging to the brain tumor lesion are combined to obtain the target brain tumor image.
[0208] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0209] The model determines whether each three-dimensional image patch belongs to a brain tumor lesion based on a lesion discrimination model. The lesion discrimination model is a model obtained by training the Visual Geometry Group (VGG) model based on second sample data. The second sample data includes multiple sample three-dimensional image patches and label information of each sample three-dimensional image patch. The label information of the sample three-dimensional image patch is used to indicate whether the sample three-dimensional image patch belongs to a brain tumor lesion.
[0210] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0211] Tilt correction was performed on the three-dimensional brain images at at least two scales respectively.
[0212] 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.
[0213] 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.
[0214] 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 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 method for segmenting brain tumor images, characterized in that, The method includes: Acquire a set of brain computed tomography (CT) images; Generate at least two scales of three-dimensional brain images based on the brain tomography image set; Based on the at least two scales of three-dimensional brain images and the corresponding image segmentation models, candidate regions for brain tumors in the at least two scales of three-dimensional brain images are obtained. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on first sample data, which includes: multiple sample three-dimensional brain images and masks of brain tumor regions in each sample three-dimensional brain image. By fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, an initial brain tumor image is obtained; The step of fusing candidate brain tumor regions from at least two scales of three-dimensional brain images to obtain an initial brain tumor image includes: Obtain overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; Based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images, determine the brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images; The initial brain tumor image is obtained based on the confidence level of the candidate brain tumor regions belonging to the same region; The step of obtaining the initial brain tumor image based on the confidence level of the candidate brain tumor regions belonging to the same region includes: The confidence level of a region is obtained based on the confidence levels of the candidate brain tumor regions belonging to the same region. The confidence level of a region is the sum of the confidence levels of each candidate brain tumor region belonging to that region. Determine whether the confidence level of the region is greater than a preset threshold; If so, then the area is determined to be a brain tumor region; Extract the image corresponding to the brain tumor region to obtain the initial brain tumor image; After obtaining an initial brain tumor image by fusing candidate brain tumor regions from at least two scales of three-dimensional brain images, the method further includes: The initial brain tumor image is segmented into three-dimensional image blocks of a preset size; Determine whether each 3D image block belongs to a brain tumor lesion; Combine three-dimensional image blocks belonging to brain tumor lesions to obtain the target brain tumor image.
2. The method according to claim 1, characterized in that, The process of generating at least two scales of three-dimensional brain images based on the brain computed tomography image set includes: The brain tomography images in the brain tomography image set are scaled to obtain at least two preprocessed image sets; wherein the brain tomography images in the same preprocessed image set have the same scale, and the brain tomography images in different preprocessed image sets have different scales. Three-dimensional brain images are constructed based on the at least two preprocessed image sets to obtain three-dimensional brain images at the at least two scales.
3. The method according to claim 1, characterized in that, The step of determining whether each three-dimensional image block belongs to a brain tumor lesion includes: Based on the lesion discrimination model, each three-dimensional image block is determined to be a brain tumor lesion; The lesion discrimination model is a model obtained by training the Visual Geometry Group (VGG) model based on the second sample data. The second sample data includes multiple sample three-dimensional image blocks and label information of each sample three-dimensional image block. The label information of the sample three-dimensional image blocks is used to indicate whether the sample three-dimensional image block belongs to a brain tumor lesion.
4. The method according to claim 1, characterized in that, Before obtaining candidate brain tumor regions in the at least two scales of three-dimensional brain images based on the at least two scales of brain images and the corresponding image segmentation models, the method further includes: Tilt correction was performed on the three-dimensional brain images at at least two scales respectively.
5. A segmentation device for brain tumor images, characterized in that, include: The acquisition module is used to acquire a set of brain computed tomography (CT) images. A generation module is used to generate at least two scales of three-dimensional brain images based on the brain tomography image set; The segmentation module is used to obtain brain tumor candidate regions in the at least two scales of brain three-dimensional images based on the at least two scales of brain three-dimensional images and the image segmentation models corresponding to the at least two scales, respectively. The image segmentation model is a model obtained by training a three-dimensional convolutional neural network based on the first sample data. The first sample data includes: multiple sample three-dimensional brain images and the mask of the brain tumor region in each sample three-dimensional brain image. The processing module is used to fuse brain tumor candidate regions in the at least two scales of three-dimensional brain images to obtain an initial brain tumor image; The step of fusing candidate brain tumor regions from at least two scales of three-dimensional brain images to obtain an initial brain tumor image includes: Obtain overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images; Based on the overlap information of brain tumor candidate regions in the at least two scales of three-dimensional brain images, determine the brain tumor candidate regions belonging to the same region in the at least two scales of three-dimensional brain images; The initial brain tumor image is obtained based on the confidence level of the candidate brain tumor regions belonging to the same region; The step of obtaining the initial brain tumor image based on the confidence level of the candidate brain tumor regions belonging to the same region includes: The confidence level of a region is obtained based on the confidence levels of the candidate brain tumor regions belonging to the same region. The confidence level of a region is the sum of the confidence levels of each candidate brain tumor region belonging to that region. Determine whether the confidence level of the region is greater than a preset threshold; If so, then the area is determined to be a brain tumor region; Extract the image corresponding to the brain tumor region to obtain the initial brain tumor image; After fusing candidate brain tumor regions from at least two scales of three-dimensional brain images to obtain an initial brain tumor image, the process further includes: The initial brain tumor image is segmented into three-dimensional image blocks of a preset size; Determine whether each 3D image block belongs to a brain tumor lesion; Combine three-dimensional image blocks belonging to brain tumor lesions to obtain the target brain tumor image.
6. 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 4.
7. 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 4.