Method and apparatus for processing a scanned image, electronic device, and storage medium

Abstract

The present application discloses a method and apparatus for processing scanned images, an electronic device, and a storage medium. The method includes obtaining a first scanned image and a second scanned image, wherein the voxel data corresponding to the first scanned image and the second scanned image are approximately distributed; determining at least one set of characteristic voxel data for the first scanned image and the second scanned image respectively based on the number of voxel data, wherein there is a corresponding relationship between at least one set of characteristic voxel data of the first scanned image and the second scanned image, and the voxel values of the voxel data in the same set of characteristic voxel data are equal; aiming at aligning at least one set of corresponding characteristic voxel data of the first scanned image and the second scanned image, adjusting the distribution interval of the voxel data of the second scanned image. In this way, a good data basis can be provided for applications such as image registration and image segmentation, reducing the possibility of manual intervention, and thus improving the effect of downstream applications.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and particularly relates to a method and apparatus for processing scanned images, an electronic device, and a storage medium. Background Art

[0002] In the medical and industrial fields, scanning imaging devices are often used to scan and image target objects. Taking the medical field as an example, technologies such as MR or CT can be used to examine multiple lesions. Further, by combining image processing algorithms or means such as machine learning and deep learning, lesions can be segmented or compared from the obtained medical image sequences. However, in such downstream applications of scanned images, satisfactory application effects are usually not obtained, and a large amount of manual intervention is often required, and different post-processing is performed on similar scanned images.

[0003] The information disclosed in this background art section is only intended to enhance the overall understanding of this application and should not be regarded as an admission or any form of suggestion that this information constitutes prior art already known to those of ordinary skill in the art. Summary of the Invention

[0004] The purpose of this application is to provide a method for processing scanned images, which is used to solve the problem of poor downstream application effects of scanned images in the prior art.

[0005] To achieve the above purpose, this application provides a method for processing scanned images, and the method includes:

[0006] Obtain a first scanned image and a second scanned image, where the voxel data corresponding to the first scanned image and the second scanned image are approximately distributed;

[0007] Based on the quantity of the voxel data, respectively determine at least one set of characteristic voxel data of the first scanned image and the second scanned image, where there is a corresponding relationship between at least one set of characteristic voxel data of the first scanned image and the second scanned image, and the voxel values of the voxel data in the same set of characteristic voxel data are equal;

[0008] With the aim of aligning the at least one set of characteristic voxel data corresponding to the first scanned image and the second scanned image, adjust the distribution interval of the voxel data of the second scanned image.

[0009] In one embodiment, respectively determining at least one set of characteristic voxel data in the first scanned image and the second scanned image based on the quantity of the voxel data specifically includes:

[0010] Calculate the voxel data histograms of the first scan image and the second scan image respectively, where the voxel data histogram includes a number of voxel data groups, and the number of voxel data groups respectively have a quantity value and a voxel value;

[0011] Based on the quantity value ranking, determine at least one characteristic voxel data group from the voxel data groups of the first scan image and the second scan image respectively.

[0012] In one embodiment, the first scan image and the second scan image respectively include one characteristic voxel data group;

[0013] Adjust the distribution range of the voxel data of the second scan image, specifically including:

[0014] Calculate the first voxel value difference of the second scan image relative to the first voxel data characteristic voxel data group;

[0015] Based on the second voxel value differences of the respective voxel data groups of the second scan image relative to the first voxel value difference, adjust the voxel values of the respective voxel data groups of the second scan image.

[0016] In one embodiment, the method specifically includes:

[0017] When the second voxel value difference is less than 0, adjust the voxel value of the voxel data group corresponding to the second scan image to 0; and / or,

[0018] When the second voxel value difference is greater than the maximum voxel value of the respective voxel data groups of the second scan image, adjust the voxel value of the voxel data group corresponding to the second scan image to the maximum voxel value; and / or,

[0019] When the second voxel value difference is greater than or equal to 0 and less than or equal to the maximum voxel value of the respective voxel data groups of the second scan image, adjust the voxel value of the voxel data group corresponding to the second scan image to the second voxel value difference.

[0020] In one embodiment, the number of characteristic voxel data groups of the first scan image and the second scan image is equal;

[0021] Adjust the distribution range of the voxel data of the second scan image, specifically including:

[0022] Divide several voxel data groups of the first scanned image into a first interval group, and divide several voxel data groups of the second scanned image into a second interval group. Among them, the boundary values of each interval in the first interval group include the voxel values of the characteristic voxel data group of the first scanned image, the boundary values of each interval in the second interval group include the voxel values of the characteristic voxel data group of the second scanned image, and each interval in the first interval group and the second interval group has a corresponding relationship;

[0023] Map the voxel data of each interval in the second interval group to the corresponding intervals in the first interval group.

[0024] In one embodiment, the mapping method includes linear mapping.

[0025] In one embodiment, the method further includes:

[0026] Perform image registration and / or image segmentation based on the first scanned image and the adjusted second scanned image.

[0027] This application also provides a processing device for scanned images, including:

[0028] An acquisition module for acquiring a first scanned image and a second scanned image, where the voxel data corresponding to the first scanned image and the second scanned image are approximately distributed;

[0029] A determination module for respectively determining at least one characteristic voxel data group of the first scanned image and the second scanned image based on the quantity of the voxel data. Among them, there is a corresponding relationship between at least one characteristic voxel data group of the first scanned image and the second scanned image, and the voxel values of the voxel data in the same characteristic voxel data group are equal;

[0030] An adjustment module for adjusting the distribution interval of the voxel data of the second scanned image with the goal of aligning the at least one characteristic voxel data group corresponding to the first scanned image and the second scanned image.

[0031] This application also provides an electronic device, including:

[0032] At least one processor; and

[0033] A memory storing instructions, when the instructions are executed by the at least one processor, causing the at least one processor to execute the processing method for scanned images as described above.

[0034] This application also provides a machine-readable storage medium storing executable instructions, and when the instructions are executed, causing the machine to execute the processing method for scanned images as described above.

[0035] Compared with the prior art, in the method for processing a scanned image according to the present application, by determining at least one corresponding characteristic voxel data group based on the number of voxel data of the first scanned image and the second scanned image, and then aiming to align at least one characteristic voxel data group corresponding to the first scanned image and the second scanned image, adjusting the distribution interval of the voxel data of the second scanned image can make the distribution intervals of the voxel data of different scanned images consistent, and align the characteristic representations of the main features, providing a good data basis for applications such as image registration and image segmentation, reducing the possibility of manual intervention, and thus improving the effect of downstream applications. Description of the Drawings

[0036] Figure 1 is a schematic diagram of an application scenario of the method for processing a scanned image according to an embodiment of the present application;

[0037] Figure 2 is a flowchart of the method for processing a scanned image according to an embodiment of the present application;

[0038] Figure 3 is a data histogram of a scanned image with an approximate distribution including one characteristic voxel data group respectively in the method for processing a scanned image according to an embodiment of the present application;

[0039] Figure 4 is a data histogram of a scanned image including one characteristic voxel data group before and after adjusting the data distribution in the method for processing a scanned image according to an embodiment of the present application;

[0040] Figure 5 is a schematic diagram of mapping the voxel data of each interval of the second scanned image to the corresponding intervals of the first scanned image in the method for processing a scanned image according to an embodiment of the present application;

[0041] Figure 6 is a module diagram of the device for processing a scanned image according to an embodiment of the present application;

[0042] Figure 7 is a hardware structure diagram of an electronic device according to an embodiment of the present application. Detailed Embodiments

[0043] The present application will be described in detail below in conjunction with the various embodiments shown in the drawings. However, these embodiments do not limit the present application, and any structural, methodical, or functional transformations made by those of ordinary skill in the art based on these embodiments are included within the protection scope of the present application.

[0044] The terms "first", "second", "third", "fourth", etc. (if any) in the description, claims and the above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "corresponding to" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0045] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields involved, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0046] Computer vision technology (Computer Vision, CV), computer vision is a science that studies how to make machines "see". Further, it refers to using cameras and computers to replace the human eye for object recognition and measurement, etc., machine vision, and further performing graphic processing to make the computer process into an image more suitable for human eye observation or transmission to an instrument for detection. As a scientific discipline, computer vision studies related theories and technologies and attempts to establish an artificial intelligence system that can obtain information from images or multi-dimensional data. Computer vision technology usually includes technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc., and also includes common biometric recognition technologies such as face recognition and fingerprint recognition.

[0047] With the research and progress of artificial intelligence technology, artificial intelligence technology is being studied and applied in multiple fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, driverless, autonomous driving, drones, robots, smart healthcare, smart customer service, etc. In addition, artificial intelligence technology can also be applied in other fields. For example, in the embodiments of the present application, using computer vision technology, with the goal of aligning the feature voxel data groups of different scanned images, the distribution range of the voxel data of the scanned images is adjusted, so that the voxel distribution ranges of the processed scanned images are consistent, which will be better applied in subsequent image registration and image segmentation using artificial intelligence technology.

[0048] In an application scenario, for example, when collecting images of a human body through CT scanning, although the scanned objects are all human bodies, different CT manufacturers, or different scanning processes of the same manufacturer, may result in scanned images having similar distributions but being very different in display. Another example is that in industry, CT is used as a means of non-destructive testing, and 3D CT data is obtained for multiple samples of the same component using the same scanning parameters; although the conditions are set the same, the actual acquired image data may have a similar distribution but a large difference in display effect due to reasons such as detector damage and long-term uncalibration.

[0049] The applicant of the present application found in analyzing the typical scenarios shown above that such scanned images pose difficulties in subsequent image segmentation and registration processing. Even some powerful commercial 3D CT data processing or display software cannot well solve these problems, and often a large amount of human intervention is required to perform different post-processing on similar scanned images. One of the reasons is presumably the difference in the distribution range of pixel values of different scanned images and the misalignment of key feature information, and this will become one of the creative manifestations of the technical solution proposed in the present application.

[0050] See Figure 1 , in an example of an implementation environment scenario, the server, the terminal, and the scanning device are connected through a network. The user can obtain the scanned image from the scanning device through the terminal and upload it to the server. The server adjusts the distribution ranges of the voxel data of different images to be consistent by running the scanned image processing method provided by the embodiments of the present application. The server can also use the adjusted images for subsequent operations such as image registration and image segmentation.

[0051] Or, in other implementation scenarios, the processing method of the scanned images provided in this embodiment can also be jointly run by the server and the terminal. For example, after the terminal obtains the scanned image, it can first determine the feature voxel data group based on the number of voxel data therein, and then the server adjusts the distribution range of the voxel data of the scanned image with the goal of aligning the feature voxel data groups corresponding to different scanned images.

[0052] In the above implementation environment, data communication is carried out between the terminal and the server through a communication network. Optionally, the communication network can be a wired network or a wireless network, and the communication network can be at least one of a local area network, a metropolitan area network, and a wide area network. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. The server and the terminal device can be independent devices from each other, or can be integrated into the same system, which is not limited here.

[0053] From the relevant descriptions of the above processing process of the scanned image, it can be seen that the method for processing the scanned image proposed in the embodiment of the present application can be executed by any suitable computer device (terminal or server); or, the method for processing the scanned image can be jointly executed by the terminal and the server. For the convenience of description, in the following, the example of a computer device executing the method for processing the scanned image will be used for illustration.

[0054] Refer to Figure 2 , and introduce an embodiment of the method for processing the scanned image of the present application. In this embodiment, the method includes:

[0055] S11. Obtain a first scanned image and a second scanned image.

[0056] According to the image collection scheme, the target object can be examined by various technical means such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging), and a corresponding image sequence can be generated. Each image in the image sequence is called a scanned image. The first scanned image and the second scanned image in this embodiment can belong to the same image sequence or belong to different image scanning sequences.

[0057] Taking CT as an example, the image sequence can be saved as DICOM images (i.e., DICOM files). The DICOM files are saved in such a way that a medical image in a CT scan sequence corresponds to one DICOM file. If an image series is collected, such as an image series of the brain or an image series of the whole body, it will be saved as the corresponding number of DICOM files. Here, one DICOM file refers to a saved independent file (e.g., a file with the suffix *.dcm). Among them, the image data of each DICOM file corresponds to the image of one image slice in the medical image sequence, and multiple image sequences can correspond to the same examination of a subject.

[0058] Voxel (Volume) is short for Volume Pixel. The solid containing voxels can be represented by volume rendering or by extracting the polygonal isosurface of a given threshold contour. It is the smallest unit in the three-dimensional space segmentation of digital data. Voxels are used in fields such as three-dimensional imaging, scientific data, and medical imaging. Conceptually, it is similar to the smallest unit in two-dimensional space - pixel, which is used in the image data of two-dimensional computer images. Some true three-dimensional displays use voxels to describe their resolution. For example, a display that can show 512×512×512 voxels.

[0059] In a 3D image scan sequence of imaging a target object, each pixel on each scan image can be correspondingly extended to a homogeneous voxel in three-dimensional space, that is, each pixel on the scan image will correspond to voxel data. The voxel data of the scan image has a corresponding quantity distribution according to different voxel value sizes. In this embodiment, the voxel data corresponding to the first scan image and the second scan image is approximately distributed.

[0060] For a CT scan image in DICOM file format, each pixel is assigned a pixel value, also known as CT value (unit: HU, Hounsfield), which is the average value of all attenuation values in the corresponding voxel. In some embodiments, the CT value here can be used as the voxel value of the voxel data corresponding to the scan image.

[0061] S12. Respectively determine at least one characteristic voxel data group of the first scan image and the second scan image based on the quantity of the voxel data.

[0062] For a scanned image, the corresponding voxel data can be divided into several groups according to the magnitude of the voxel values, and each group will have a corresponding number of voxel data falling into it. Since the voxel data corresponding to the first scanned image and the second scanned image are approximately distributed, when determining the characteristic voxel data groups of the first scanned image and the second scanned image, at least one characteristic voxel data group with the same number can be determined based on the same standard, and there is a corresponding relationship between the at least one characteristic voxel data groups.

[0063] For example, in the first scanned image A, according to the quantity ranking of the voxel data, the corresponding voxel values are 625, 540, … respectively. In the second scanned image B, according to the quantity ranking of the voxel data, the corresponding voxel values are 610, 527, … respectively. If the voxel data groups corresponding to the top two voxel values in terms of quantity ranking are determined as the characteristic voxel data groups, then in the first scanned image A, the characteristic voxel data groups a1 (voxel value 625) and a2 (voxel value 540) can be determined, and in the second scanned image B, the characteristic voxel data groups b1 (voxel value 610) and b2 (voxel value 527) can be determined. In such an example, there is a corresponding relationship between the characteristic voxel data group a1 and the characteristic voxel data group b1, and there is a corresponding relationship between the characteristic voxel data group a2 and the characteristic voxel data group b2; conversely, the characteristic voxel data group a1 and the characteristic voxel data group b2 are not considered to have a corresponding relationship, and the characteristic voxel data group a2 and the characteristic voxel data group b1 are not considered to have a corresponding relationship either.

[0064] Cooperate with reference Figure 3 , specifically, the computer device can calculate the voxel data histograms of the first scanned image and the second scanned image respectively. Taking the horizontal axis as the voxel value and the vertical axis as the quantity value to establish a coordinate system for the voxel data histogram, it can be seen that each "rectangular block" in the voxel data histogram represents a group of voxel data with the same voxel value, and the height of the rectangular block represents the quantity of the voxel data corresponding to the voxel value. In this embodiment, the voxel data corresponding to each rectangular block is called a "voxel data group", and the computer device can determine at least one characteristic voxel data group from the voxel data groups of the first scanned image and the second scanned image respectively based on the quantity value ranking.

[0065] As shown in the above example, according to different application requirements, different numbers of characteristic voxel data groups can be determined from the first scanned image and the second scanned image based on the quantity value ranking. In the following embodiments, for the convenience of description, the characteristic voxel data groups will be determined from the first scanned image and the second scanned image based on the first in terms of quantity value ranking as the standard.

[0066] For example, in the first scanned image A, there is a voxel data group a1 (voxel value 625) with the first-ranked quantity value, and in the second scanned image B, there is a voxel data group b1 (voxel value 610) with the first-ranked quantity value. Then, the voxel data group a1 will be determined by the computer device as the characteristic voxel data group of the first scanned image A, and the voxel data group b1 will be determined by the computer device as the characteristic voxel data group of the second scanned image B. Another example, in the first scanned image A, there are two voxel data groups a1 (voxel value 625) and a2 (voxel value 625) with the first-ranked quantity value, and in the second scanned image B, there are also two voxel data groups b1 (voxel value 610) and b2 (voxel value 610) with the first-ranked quantity value. Then, both the voxel data groups a1 and a2 will be determined by the computer device as the characteristic voxel data groups of the first scanned image A, and both the voxel data groups b1 and b2 will be determined by the computer device as the characteristic voxel data groups of the second scanned image B. Similarly, if there are more voxel data groups with the first-ranked quantity value in the first scanned image and the second scanned image, the computer device can also determine these voxel data as the characteristic voxel data groups of the corresponding scanned images.

[0067] S13. Aiming at aligning at least one characteristic voxel data group corresponding to the first scanned image and the second image, adjust the distribution interval of the voxel data of the second scanned image.

[0068] According to the quantity of the characteristic voxel data groups, the present application provides multiple embodiments to adjust the distribution interval of the voxel data of the second scanned image.

[0069] ① The quantity of the characteristic voxel data groups is 1

[0070] In this embodiment, the computer device can perform normalization processing on the voxel value distributions of both the first scanned image and the second scanned image. For example, control the voxel value to be ≥0. On this basis, the computer device calculates the first voxel value difference of the second scanned image relative to the characteristic voxel data group of the first voxel data, and adjusts the voxel values of several voxel data groups of the second scanned image based on the second voxel value differences of several voxel data groups of the second scanned image relative to the first voxel value difference.

[0071] The first voxel value difference represents the voxel value deviation between the characteristic voxel data groups of the first scanned image and the second scanned image, which is manifested as the offset of the horizontal axis on the voxel data histogram. Taking the first voxel value difference as the voxel value of the characteristic voxel data group of the second scanned image minus the voxel value of the characteristic voxel data group of the first scanned image as an example, if the first voxel value difference is greater than 0 ( Figure 4In the shown situation, it indicates that the voxel data of the entire second scanned image needs to reduce the voxel value (which is manifested as the overall histogram of voxel data moving towards the origin direction of the coordinate axis); conversely, if the first voxel value difference is less than 0, it indicates that the voxel data of the entire second scanned image needs to increase the voxel value (which is manifested as the overall histogram of voxel data moving away from the origin direction of the coordinate axis); if the first voxel value difference is equal to 0, then there is no need to adjust the distribution range of the voxel data of the second scanned image.

[0072] Specifically, when the second voxel value difference is less than 0, it indicates that when the current voxel data group is adjusted according to the first voxel value difference, the voxel value of the voxel data group will shift to the negative value of the horizontal axis; at this time, the computer device can directly force the voxel value of the voxel data group corresponding to the second scanned image to be 0.

[0073] In another case, when the second voxel value difference is greater than the maximum voxel value of several voxel data groups of the second scanned image, it indicates that when the current voxel data group is adjusted according to the first voxel value difference, the voxel value of the voxel data group will overflow the maximum voxel value of the voxel data on the second scanned image on the horizontal axis; at this time, the computer device can force the voxel value of the voxel data group corresponding to the second scanned image to be the maximum voxel value.

[0074] In another case, when the second voxel value difference is greater than or equal to 0 and less than or equal to the maximum voxel value of several voxel data groups of the second scanned image, it indicates that when the current voxel data group is adjusted according to the first voxel value difference, the voxel value of the voxel data group will still fall within the voxel value range of the voxel data on the second scanned image; at this time, the computer device can adjust the voxel value of the voxel data group corresponding to the second scanned image to the second voxel value difference.

[0075] The above adjustment process can be expressed by the formula:

[0076]

[0077] where, peak x represents each voxel data group in the second scanned image, peak represents the peak x adjusted data group, and max(dataset(i)) represents the voxel data group with the largest voxel value in the second scanned image.

[0078] ② The number of characteristic voxel data groups is equal

[0079] In this embodiment, the computer device may divide a number of voxel data groups of the first scan image into a first interval group, and divide a number of voxel data groups of the second scan image into a second interval group. The first interval group and the second interval group each include at least two intervals. The boundary values of the intervals in the first interval group include the voxel values of the characteristic voxel data groups of the first scan image, and the boundary values of the intervals in the second interval group include the voxel values of the characteristic voxel data groups of the second scan image. The intervals in the first interval group and the second interval group have a corresponding relationship.

[0080] For cooperation reference Figure 5 , for example, the first scan image has characteristic voxel data groups peak(r,1) and peak(r,2), and the second scan image has characteristic voxel data groups peak(i,1) and peak(i,2). The first interval group may include: [0, peak(r,1)], [peak(r,1), peak(r,2)], [peak(r,2), max(dataset(r))], and the second interval group may include: [0, peak(i,1)], [peak(i,1), peak(i,2)], [peak(i,2), max(dataset(i))]. Wherein, max(dataset(r)) represents the voxel data group with the largest voxel value in the first scan image, max(dataset(i)) represents the voxel data group with the largest voxel value in the second scan image, the voxel value of peak(r,1) is less than that of peak(r,2), and the voxel value of peak(i,1) is less than that of peak(i,2).

[0081] It can be seen that in the above example, the voxel values of the characteristic voxel data groups in the scan image, 0, and the maximum voxel value in the scan image are used as boundaries to divide the voxel data groups of the scan image into four intervals. In an alternative embodiment, for example, the minimum voxel value in the scan image, or a reasonable voxel value, etc. may also be selected to jointly form the boundary values of each interval with the voxel values of the characteristic voxel data groups. Or, for the largest interval (the interval located on the far right of the data histogram) and the smallest interval (the interval located on the far left of the data histogram) of the scan image, the corresponding maximum boundary value and minimum boundary value may not be set. In this case, taking the first interval group as an example, it can be expressed as: [-∞, peak(r,1)], [peak(r,1), peak(r,2)], [peak(r,2), ∞].

[0082] Similarly, since the number of characteristic voxel data groups of the first scanned image and the second scanned image is equal, the number of intervals in the corresponding first interval group and second interval group is also equal. In the embodiments of the present application, after sorting each interval according to the interval value, the intervals with corresponding serial numbers are determined to have a corresponding relationship. That is: [0, peak(r,1)] and [0, peak(i,1)] have a corresponding relationship, and [peak(r,1), peak(r,2)] and [peak(i,1), peak(i,2)] have a corresponding relationship.

[0083] Based on the above corresponding relationship, the computer device can map the voxel data of each interval in the second interval group to the corresponding intervals in the first interval group. In this embodiment, different interval mapping methods can be used to perform this mapping, such as linear mapping.

[0084] Taking the mapping of [peak(i,1), peak(i,2)] to [peak(r,1), peak(r,2)] as an example, a linear interval mapping method can be expressed as:

[0085]

[0086] where peak x represents each voxel data group in [peak(i,1), peak(i,2)], peak represents the voxel data group after peak x mapping, and peak(i,2) - peak(i,1) and peak(r,2) - peak(r,1) respectively represent the lengths of the corresponding intervals.

[0087] In the above embodiments, taking the alignment of the characteristic voxel data groups of the first scanned image and the second scanned image as an example, the processing method of the scanned image of the present application is described. It can be understood that in actual applications, for example, when N scanned images are obtained simultaneously, one of the scanned images can also be randomly selected or selected according to a set standard as a reference image or a golden sample, and the characteristic voxel data groups of the other N - 1 scanned images are respectively aligned with the reference image.

[0088] See Figure 6 , an embodiment of the processing device for the scanned image of the present application is introduced. In this embodiment, the processing device for the scanned image includes an acquisition module 21, a determination module 22, and an adjustment module 23.

[0089] The acquisition module 21 is used to acquire a first scanned image and a second scanned image, wherein the voxel data corresponding to the first scanned image and the second scanned image are approximately distributed; the determination module 22 is used to respectively determine at least one set of characteristic voxel data of the first scanned image and the second scanned image based on the quantity of the voxel data, wherein there is a corresponding relationship between at least one set of characteristic voxel data of the first scanned image and the second scanned image, and the voxel values of the voxel data in the same set of characteristic voxel data are equal; the adjustment module 23 is used to adjust the distribution range of the voxel data of the second scanned image with the goal of aligning at least one set of characteristic voxel data corresponding to the first scanned image and the second scanned image.

[0090] In one embodiment, the determination module 22 is specifically configured to respectively calculate the voxel data histograms of the first scanned image and the second scanned image, wherein the voxel data histogram includes a plurality of sets of voxel data, and the plurality of sets of voxel data respectively have a quantity value and a voxel value; based on the quantity value ranking, at least one set of characteristic voxel data is respectively determined from the sets of voxel data of the first scanned image and the second scanned image.

[0091] In one embodiment, the first scanned image and the second scanned image respectively include one set of characteristic voxel data; the adjustment module 23 is specifically configured to calculate the first voxel value difference of the second scanned image relative to the set of characteristic voxel data of the first voxel data; based on the second voxel value differences of the plurality of sets of voxel data of the second scanned image relative to the first voxel value difference, the voxel values of the plurality of sets of voxel data of the second scanned image are adjusted.

[0092] In one embodiment, the adjustment module 23 is specifically configured to, when the second voxel value difference is less than 0, adjust the voxel value of the set of voxel data corresponding to the second scanned image to 0; and / or, when the second voxel value difference is greater than the maximum voxel value of the plurality of sets of voxel data of the second scanned image, adjust the voxel value of the set of voxel data corresponding to the second scanned image to the maximum voxel value; and / or, when the second voxel value difference is greater than or equal to 0 and less than or equal to the maximum voxel value of the plurality of sets of voxel data of the second scanned image, adjust the voxel value of the set of voxel data corresponding to the second scanned image to the second voxel value difference.

[0093] In one embodiment, the number of characteristic voxel data groups of the first scanned image and the second scanned image is equal; the adjustment module 23 is specifically configured to divide several voxel data groups of the first scanned image into a first interval group, and divide several voxel data groups of the second scanned image into a second interval group, where the boundary values of each interval in the first interval group include the voxel values of the characteristic voxel data groups of the first scanned image, the boundary values of each interval in the second interval group include the voxel values of the characteristic voxel data groups of the second scanned image, and each interval in the first interval group and the second interval group has a corresponding relationship; map the voxel data of each interval in the second interval group to the corresponding intervals in the first interval group.

[0094] In one embodiment, the mapping method includes linear mapping.

[0095] In one embodiment, the adjustment module 23 is further configured to perform image registration and / or image segmentation based on the first scanned image and the adjusted second scanned image.

[0096] As described above with reference to Figures 1 to 5 , the processing method of the scanned image according to the embodiments of the present specification has been described. The details mentioned in the above description of the method embodiments also apply to the scanned image processing device of the embodiments of the present specification. The above-mentioned scanned image processing device can be implemented by hardware, or by software, or by a combination of hardware and software.

[0097] Figure 7 The hardware structure diagram of an electronic device according to an embodiment of the present specification is shown. As Figure 7 shown, the electronic device 30 may include at least one processor 31, a memory 32 (such as a non-volatile memory), a memory 33, and a communication interface 34, and at least one processor 31, the memory 32, the memory 33, and the communication interface 34 are connected together via a bus 35. At least one processor 31 executes at least one computer-readable instruction stored or encoded in the memory 32.

[0098] It should be understood that the computer-executable instructions stored in the memory 32, when executed, cause at least one processor 31 to perform the various operations and functions described above in the respective embodiments of the present specification in combination with Figures 1 to 5 the description.

[0099] In the embodiments of the present specification, the electronic device 30 may include, but is not limited to: a personal computer, a server computer, a workstation, a desktop computer, a laptop computer, a notebook computer, a mobile electronic device, a smart phone, a tablet computer, a cellular phone, a personal digital assistant (PDA), a handheld device, a messaging device, a wearable electronic device, a consumer electronic device, and the like.

[0100] According to one embodiment, there is provided a program product such as a machine-readable medium. The machine-readable medium may have instructions (i.e., the elements implemented in software as described above), which when executed by a machine, cause the machine to perform the various operations and functions described above in connection with the various embodiments of this specification. Figures 1 to 5 Specifically, a system or device equipped with a readable storage medium may be provided, on which software program code for implementing the functions of any one of the above embodiments is stored, and the computer or processor of the system or device is caused to read and execute the instructions stored in the readable storage medium.

[0101] In this case, the program code read from the readable medium itself can implement the functions of any one of the above embodiments, so the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of this specification.

[0102] Examples of the readable storage medium include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Optionally, the program code can be downloaded from a server computer or a cloud via a communication network.

[0103] Those skilled in the art should understand that various modifications and variations can be made to the above-described embodiments without departing from the essence of the invention. Therefore, the protection scope of this specification should be defined by the appended claims.

[0104] It should be noted that not all steps and units in the above-described processes and system structure diagrams are necessary, and some steps or units can be omitted according to actual needs. The execution order of the steps is not fixed and can be determined as needed. The device structures described in the above embodiments can be physical structures or logical structures. That is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or some components in multiple independent devices may be jointly implemented.

[0105] In the above embodiments, the hardware units or modules can be implemented mechanically or electrically. For example, a hardware unit, module, or processor may include permanent dedicated circuits or logic (such as a dedicated processor, FPGA, or ASIC) to perform corresponding operations. The hardware unit or processor may also include programmable logic or circuits (such as a general-purpose processor or other programmable processors), which can be temporarily set by software to perform corresponding operations. The specific implementation method (mechanical method, or dedicated permanent circuit, or temporarily set circuit) can be determined based on cost and time considerations.

[0106] The specific embodiments described above in conjunction with the accompanying drawings describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration" and does not mean "preferred" or "advantageous" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, the technologies can be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described embodiments.

[0107] The foregoing description of the present disclosure has been provided to enable any ordinary skill in the art to make or use the present disclosure. Various modifications to the present disclosure will be apparent to those of ordinary skill in the art, and the general principles corresponding thereto described herein can also be applied to other variations without departing from the scope of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is consistent with the broadest scope that conforms to the principles and novel features disclosed herein.

Claims

1. A method for processing a scanned image, characterized in that, The method includes: Obtaining a first scan image and a second scan image, wherein the voxel data corresponding to the first scan image and the second scan image are approximately distributed; Based on the quantity of the voxel data, respectively determining at least one set of characteristic voxel data of the first scan image and the second scan image, wherein there is a corresponding relationship between at least one set of characteristic voxel data of the first scan image and the second scan image, and the voxel values of the voxel data in the same set of characteristic voxel data are equal; Taking aligning the at least one set of characteristic voxel data corresponding to the first scan image and the second scan image as the goal, adjusting the distribution range of the voxel data of the second scan image.

2. The processing method of the scanned image according to claim 1, characterized in that, Based on the quantity of the voxel data, respectively determining at least one set of characteristic voxel data in the first scan image and the second scan image, specifically including: Calculating the voxel data histograms of the first scan image and the second scan image respectively, wherein the voxel data histogram includes several sets of voxel data, and the several sets of voxel data respectively have quantity values and voxel values; Based on the quantity value ranking, respectively determining at least one set of characteristic voxel data from the sets of voxel data of the first scan image and the second scan image.

3. The processing method of the scanned image according to claim 2, wherein The first scan image and the second scan image respectively include one set of characteristic voxel data; Adjusting the distribution range of the voxel data of the second scan image, specifically including: Calculating the first voxel value difference of the second scan image relative to the characteristic voxel data of the first voxel data; Based on the second voxel value differences of the several sets of voxel data of the second scan image relative to the first voxel value difference, adjusting the voxel values of the several sets of voxel data of the second scan image.

4. The method for processing a scanned image according to claim 3, wherein The method specifically includes: When the second voxel value difference is less than 0, adjusting the voxel value of the set of voxel data corresponding to the second scan image to 0; and / or, When the second voxel value difference is greater than the maximum voxel value of the several sets of voxel data of the second scan image, adjusting the voxel value of the set of voxel data corresponding to the second scan image to the maximum voxel value; and / or, When the second voxel value difference is greater than or equal to 0 and less than or equal to the maximum voxel value of the several sets of voxel data of the second scan image, adjusting the voxel value of the set of voxel data corresponding to the second scan image to the second voxel value difference.

5. The method for processing a scanned image according to claim 2, wherein The number of sets of characteristic voxel data of the first scan image and the second scan image is equal; Adjusting the distribution range of the voxel data of the second scan image, specifically including: Dividing the several sets of voxel data of the first scan image into a first interval group, and dividing the several sets of voxel data of the second scan image into a second interval group, wherein the boundary values of each interval in the first interval group include the voxel value of the set of characteristic voxel data of the first scan image, the boundary values of each interval in the second interval group include the voxel value of the set of characteristic voxel data of the second scan image, and each interval in the first interval group and the second interval group has a corresponding relationship; Mapping the voxel data in each interval of the second interval group to the corresponding intervals in the first interval group.

6. The processing method of the scanned image according to claim 5, characterized in that, The mapping method includes linear mapping.

7. The processing method of a scanned image according to claim 1, characterized in that, The method further includes: Performing image registration and / or image segmentation based on the first scanned image and the adjusted second scanned image.

8. A processing device for scanned images, characterized in that, It includes: An acquisition module, configured to acquire a first scanned image and a second scanned image, wherein the voxel data corresponding to the first scanned image and the second scanned image are approximately distributed; A determination module, configured to respectively determine at least one set of feature voxel data of the first scanned image and the second scanned image based on the quantity of the voxel data, wherein there is a corresponding relationship between at least one set of feature voxel data of the first scanned image and the second scanned image, and the voxel values of the voxel data in the same set of feature voxel data are equal; An adjustment module, configured to adjust the distribution range of the voxel data of the second scanned image with the aim of aligning the at least one set of corresponding feature voxel data of the first scanned image and the second scanned image.

9. An electronic device, including: At least one processor; And A memory, the memory stores instructions, when the instructions are executed by the at least one processor, enabling the at least one processor to execute the method for processing a scanned image according to any one of claims 1 to 7.

10. A machine-readable storage medium, which stores executable instructions, the instructions when executed cause the machine to execute the method for processing a scanned image according to any one of claims 1 to 7.

Images