Image generation method, apparatus, and computer-readable storage medium

Abstract

The application relates to the technical field of medical imaging, and discloses an image generation method. The method first acquires an original scanning image set and a target image quantity, divides images of the original scanning image set into a plurality of key regions, further determines a region image quantity corresponding to each key region according to the original scanning image quantity corresponding to each key region and the target image quantity, and finally performs merging processing on the original scanning images in each key region to obtain target images equal in quantity to the region image quantity. The target images in the above process are generated based on the key regions in a positioning image, that is, the target images can reflect more clinically valuable images of the key regions, the clinical reference value of the images is improved, the entire process does not require manual participation, and the stability and generation efficiency of the images are improved. The application also discloses an image generation device and a computer readable storage medium.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, such as an image generation method, apparatus, and computer-readable storage medium. Background Technology

[0002] Image processing involves generating new images from the original scanned image. In film printing, a specific number of images need to be generated. This is because the number of images on the film is fixed, and the film is laid out in a fixed format, requiring a fixed number of images for each layout.

[0003] In the process of implementing the embodiments of this application, at least the following problems were found in the related technology:

[0004] In existing technologies, the original scanned images need to be manually screened, which requires a high level of experience from the personnel and the film generation process is inefficient.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0007] This application provides an image generation method, apparatus, and computer-readable storage medium to improve image generation efficiency.

[0008] In some embodiments, the method includes: acquiring an original set of scanned images and a number of target images; dividing the images in the original set of scanned images into multiple key regions; determining the number of region images corresponding to each key region based on the number of original scanned images and the number of target images corresponding to each key region; and merging the original scanned images within each key region to obtain a number of target images equal to the number of region images.

[0009] Optionally, the images of the original scanned image set are divided into multiple key regions, including: displaying a positioning image; receiving one or more key regions marked by the user in the positioning image; and dividing the images of the original scanned image set into each key region in the positioning image.

[0010] Optionally, the images in the original scanned image set are divided into multiple key regions, including: dividing the positioning image into multiple regions according to the subject's body parts; selecting key regions corresponding to the subject's basic information from the multiple regions; and dividing the images in the original scanned image set into each key region in the positioning image.

[0011] Optionally, the images in the original scanned image set are divided into multiple key regions, including: in each image sequence in the original scanned image set, determining multiple images with a layer thickness difference less than a preset difference, consistent orientation, and image interval satisfying a preset interval as mergeable images in the current image sequence; removing other images in the original image set besides the mergeable images; and dividing the remaining original images in the original image set into multiple key regions.

[0012] Optionally, the number of region images corresponding to each key region is determined based on the number of original scanned images and the number of target images corresponding to each key region, including: obtaining the scan layer thickness of each key region; determining the proportion of each key region based on the number of original scanned images and the scan layer thickness corresponding to each key region; and determining the number of region images corresponding to each key region based on the number of target images and the proportion of each key region.

[0013] Optionally, the original scanned images in each key region are merged, including: dividing the original scanned images in the current key region into N groups; where N is an integer greater than or equal to 1; calculating the number of images in each group; and merging the original scanned images in each group, with the number of merged images equal to the number of images in each group.

[0014] Optionally, N is greater than or equal to 2; the original scanned images in the current key area are divided into N groups, including: obtaining the distance between the original scanned images in the current key area and the center line of the current key area; classifying the original scanned images with a distance less than a preset distance into the middle group; classifying the original scanned images with a distance greater than or equal to the preset distance into the edge group; wherein the number of edge groups is N-1.

[0015] Optionally, the number of images within a middle group is greater than the number of images within any edge group.

[0016] Optionally, the original scanned images within each group are merged separately, including: merging the original scanned images of the middle group to obtain a merged image with an image interval of a first interval; merging the original scanned images of the edge group to obtain a merged image with an image interval of a second interval; wherein the first interval is smaller than the second interval.

[0017] Optionally, the original scanned images within each key region are merged, including: obtaining a set of points in the same position in the current row of all original scanned images; calculating the average density value of all points in the set; and determining the merged image based on the average density value.

[0018] In some embodiments, the apparatus includes: an acquisition module configured to acquire an original set of scanned images and a number of target images; a division module configured to divide the images of the original set of scanned images into multiple key regions; a quantity determination module configured to determine the number of region images corresponding to each key region based on the number of original scanned images and the number of target images corresponding to each key region; and a merging module configured to merge the original scanned images within each key region to obtain a number of target images equal to the number of region images.

[0019] The image generation method, apparatus, and computer-readable storage medium provided in this application embodiment can achieve the following technical effects:

[0020] This embodiment first obtains the original scan image set and the number of target images. The images in the original scan image set are divided into multiple key regions. Further, based on the number of original scan images and the number of target images corresponding to each key region, the number of region images corresponding to each key region is determined. Finally, the original scan images within each key region are merged to obtain a target image equal to the number of region images. The target images in the above process are generated based on the key regions in the localized images. That is, the target images can reflect more clinically valuable images of the key regions, improving the clinical reference value of the images. The entire process requires no manual intervention, improving the stability and efficiency of image generation.

[0021] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0022] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0023] Figure 1 A flowchart illustrating an image generation method provided in this application embodiment;

[0024] Figure 2 This is a schematic diagram of an original image and a film image;

[0025] Figure 3 This application provides a schematic diagram of an input interface for the number of target images.

[0026] Figure 4 A schematic diagram illustrating a positioning image provided in an embodiment of this application;

[0027] Figure 5 A schematic diagram of a positioning image of multiple key regions provided in an embodiment of this application;

[0028] Figure 6 A flowchart illustrating another image generation method provided in this application embodiment;

[0029] Figure 7 This is a schematic diagram of an image of the lung region obtained after using the image generation method provided in the embodiments of this application;

[0030] Figure 8 A flowchart illustrating yet another image generation method provided in this application embodiment;

[0031] Figure 9 This is a schematic diagram of the structure of an image generation device provided in an embodiment of this application;

[0032] Figure 10 This is a schematic diagram of the structure of an image generation device provided in an embodiment of this application. Detailed Implementation

[0033] To provide a more detailed understanding of the features and technical content of the embodiments of this application, the implementation of the embodiments of this application will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this application. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0034] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0035] Unless otherwise stated, the term "multiple" means two or more.

[0036] In this embodiment, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0037] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0038] Image processing involves generating new images from the original scanned images. In film printing, a specified number of target images need to be generated. Because the number of images that can be displayed on film is fixed, and film is laid out in a fixed format, each layout requires a fixed number of images. Therefore, the original scanned images need to be merged.

[0039] For image merging, batch processing is typically used to generate images. The user inputs the desired pattern to acquire the images; for example, the user specifies the range of images to acquire in the display area, then sets the layer thickness, layer interval, and drawing mode, and then saves the image.

[0040] This application provides an image generation method in which the user only needs to input the number of target images to be displayed on the film, and the images can be automatically selected and merged without the user having to set the layer thickness and layer spacing, which effectively improves the speed and efficiency of image generation.

[0041] Combination Figure 1 As shown, this application provides an image generation method, such as... Figure 1 As shown, the method specifically includes the following steps:

[0042] S101: Obtain the original set of scanned images and the number of target images.

[0043] Raw scan images can be generated after a medical imaging scanner scans a subject. For example, raw scan images from a CT scan of the lungs or brain. The number of raw scan images is generally large to provide sufficient data for subsequent image processing. The final target images, such as those provided to doctors or films provided to patients, are often only a dozen or so images. For example, if the raw CT scan produces thin-slice images, with the entire lung measuring 25 cm and each slice spaced 0.5 mm apart, then the number of raw scan images would be 500. Within the raw scan image set, there may also be localization images. Localization images are low-dose scans performed before the formal scan to determine the scan area.

[0044] The target image number is the number of images ultimately generated; specifically, it can be the number of target images for the output film.

[0045] If a location image exists, it can be directly output as the target image. For example, if the original image set contains 500 images and the target image count is 50, then the 500 images need to be automatically merged to obtain the target film of 50 images. However, if the original image set includes 2 location images, then the 500 images need to be merged into 48 images, which, together with the 2 location images, form the film.

[0046] like Figure 2 As shown, the left side is an exemplary subset of 500 raw scan images obtained from scanning the lungs of a subject. Figure 2 The image in the middle shows the positioning image generated during the scanning process. In this example, the user selected to output 48 images, resulting in the final image. Figure 2 The right side contains 48 target images, including the positioning image, which are then output as film.

[0047] The number of target images can be set through a user interface provided by the software. Users can directly input the number of images or specify the number by clicking the quantity selection button. For example... Figure 3 As shown, the interface provides commonly used target image quantities, which users can directly set by clicking the corresponding button. Users can also choose not to select commonly used target image quantities and directly input the target image quantity.

[0048] S102: Divide the images in the original scanned image set into multiple key regions.

[0049] The key region is the area being scanned. A single scan can scan only one area, thus corresponding to only one key region. Alternatively, a single scan can scan multiple areas, for example, simultaneously scanning the head, chest, and abdomen, in which case the key regions for that scan would include three. The original scanned image is processed to obtain several target images, ensuring that each target image includes an image within each key region. Therefore, the first step is to divide the original scanned image into its corresponding key regions.

[0050] There are multiple ways to divide key areas, such as using image recognition technology or neural network automation. To ensure the accuracy of the division, you can also directly receive the division results manually divided by doctors.

[0051] S103: Determine the number of region images corresponding to each key region based on the number of original scanned images and the number of target images corresponding to each key region.

[0052] After dividing the original scanned images into key regions, each key region corresponds to a certain number of original scanned images. Therefore, the number of region images corresponding to each key region can be determined based on the number of original scanned images and the number of target images. The number of region images can also be determined based on the ratio of the number of original scanned images to the number of target images within the current key region. Furthermore, considering information such as the scan slice thickness, the number of region images can be further determined in addition to the number of original scanned images within the current key region.

[0053] S104: Merge the original scanned images within each key region to obtain a target image with the same number of region images.

[0054] Taking two key regions as an example, with 200 original scanned images corresponding to the first key region and 20 calculated region images, and 300 original scanned images corresponding to the second key region and 30 calculated region images, the original scanned images within the first key region are merged to generate 20 target images. Furthermore, the original scanned images within the second key region are merged to generate 30 target images. This ensures that there are 50 target images, reasonably encompassing the image information of each key region.

[0055] The method provided in this application first obtains the original scan image set and the number of target images. The images in the original scan image set are then divided into multiple key regions. Further, based on the number of original scan images and the number of target images corresponding to each key region, the number of region images corresponding to each key region is determined. Finally, the original scan images within each key region are merged to obtain a target image equal to the number of region images. The target image in this process is generated based on the key regions in the localized images; that is, the target image can reflect more clinically valuable images of the key regions, improving the clinical reference value of the images. The entire process requires no manual intervention, improving the stability and efficiency of image generation.

[0056] In practical applications, doctors may wish to manually calibrate key regions or regions of interest, or adjust already selected key regions. Therefore, optionally, the images of the original scan image set are divided into multiple key regions, including: displaying a positioning image; receiving one or more key regions calibrated by the user in the positioning image; and dividing the images of the original scan image set into each key region in the positioning image.

[0057] When merging from the original image, some areas are not needed by the user, such as the area around the target location. Therefore, the positioning image can be shown to the user, and the user can be provided with a range selection operation mode to receive the key areas marked by the user in the positioning image. Figure 4 This is a schematic diagram illustrating a localization map provided in an embodiment of this application. In this image, users can select key areas using lines of different colors and adjust the size and extent of each key area by dragging the lines. For example, the red line represents the first key area, the head region, and the green line represents the second key area, the abdomen region. Furthermore, users can adjust the key areas vertically, horizontally, or at any angle, for example, to include more lesion information within the key area.

[0058] The positioning images shown in the above images can be original acquisition images or positioning images of MPR in any direction generated by an image generation algorithm. This application does not limit the types of images.

[0059] The method provided in this embodiment can accurately delineate key regions. The merged target image obtained based on the key regions is more adaptable to the current application scenario, thereby improving the clinical value of the target image.

[0060] Optionally, key regions can also be automatically identified and divided. Based on this, the above-mentioned division of the images in the original scanned image set into multiple key regions includes: dividing the positioning image into multiple regions according to the body parts of the examinee; selecting the key regions corresponding to the basic information of the examinee from the multiple regions; and dividing the images in the original scanned image set into each key region in the positioning image.

[0061] To improve the efficiency of key region segmentation, key regions can be segmented automatically. For example, images with previously segmented key regions can be automatically loaded and used as a basis for segmenting the current image. Alternatively, image segmentation algorithms can be used for region segmentation. In this way, the corresponding key regions segmented through automatic selection improve the reliability and efficiency of key region segmentation, thereby improving the image quality of the output image.

[0062] The aforementioned key areas can be one or more. For example... Figure 5 As shown, three key regions are divided in a localization image, and subsequent image merging is performed based on these three key regions respectively.

[0063] Combination Figure 6The diagram shows a flowchart of another image generation method provided in this application embodiment. Before dividing the key regions of an image, this method determines the image classification and only divides the key regions of images that meet certain conditions. Specifically, the method includes:

[0064] S601: Obtain the original set of scanned images and the number of target images;

[0065] S602: In each image sequence in the original scanned image set, multiple images with a layer thickness difference less than a preset difference, consistent orientation, and image interval satisfying a preset interval are identified as mergeable images in the current image sequence.

[0066] Specifically, for DICOM images, the image types are different. The following are examples of different image types:

[0067] ORIGINAL\PRIMARY\LOCALIZER

[0068] ORIGINAL\PRIMARY\AXIAL\HELICAL

[0069] ORIGINAL\PRIMARY\AXIAL\HELICAL

[0070] ORIGINAL\PRIMARY\AXIAL\HELICAL

[0071] Among them, ORIGINAL refers to the original scan image, PRIMARY indicates a non-secondary acquisition image, AXIAL is a tomographic image, and HELICAL is a helical scan.

[0072] In the images above, according to the DICOM standard, the LOCALIZER sequence is a localization image sequence. Such images can be used for localization and can be directly output as target images. Therefore, these images are not mergingable and need to be excluded from the original image set. For the remaining images, it is necessary to determine whether they are mergingable based on other DICOM information. Specifically, other DICOM information conditions include: layer thickness information, position information, and orientation information. For a sequence image set, it is necessary to ensure that the layer thickness information of the images is consistent, the position information is that they are located on the same straight line and are evenly distributed, and the orientation information is consistent. Images that meet the above requirements are retained in the original image set and participate in subsequent image merging; otherwise, they are not mergingable images and need to be deleted from the original image set.

[0073] Image scanning is typically performed in sequences, each containing multiple images. For an original image set, there are multiple image sequences. Therefore, the process of determining which images can be merged is performed within each image sequence. This results in the remaining original image set containing multiple mergeable image groups. Images within the same image group can be merged, while images from different groups cannot be merged across groups. This ensures that the merged images retain key information from the original images, improving image accuracy.

[0074] S603: Remove images other than those that can be merged from the original image set;

[0075] It's important to note that images identified as unmergeable during the process described above can be directly output as target images. If the number of unmergeable images exceeds the number of target images, image merging is unnecessary, and the unmergeable images are output directly. For example, if a subject is scanned to obtain 100 raw scan images, and the user wants 10 target images, but there are 10 unmergeable images, such as batch screenshots of color images, these types of images do not need to be merged. In this case, the 10 images from the batch processing result can be output directly without further merging.

[0076] S604: Divide the remaining original images in the original image set into multiple key regions.

[0077] S605: Determine the number of region images corresponding to each key region based on the number of original scanned images and the number of target images corresponding to each key region;

[0078] S606: Merge the original scanned images within each key region to obtain a target image with the same number of region images.

[0079] The steps S604-S606 described above are consistent with those in the previous embodiments and will not be repeated here.

[0080] In the embodiments described above, before dividing the key regions of the original scanned image, images that can be merged are first identified, and the key regions are divided within the range of the mergeable images. For images that cannot be merged, they are directly deleted from the original scanned image, thus eliminating interference factors and improving the efficiency of image merging.

[0081] Optionally, the number of merged images generated for each key region will differ due to differences in the number of original images and the scanning layer thickness. Therefore, before merging, the number of merged images for each key region is first determined. Specifically, the number of region images corresponding to each key region is determined based on the number of original scanned images and the number of target images, including: obtaining the scanning layer thickness of each key region; determining the proportion of each key region based on the number of original scanned images and the scanning layer thickness; and determining the number of region images corresponding to each key region based on the number of target images and the proportion of each key region.

[0082] Specifically, for each key region, the number of target images that can be obtained from that key region is calculated. It is understandable that thinner slices require more images to be generated, and if there are many images, even more images need to be generated. Therefore, the number of images in the merged region of the current key region is proportional to the number of images in the original scan image corresponding to that key region, and is also proportional to the scan layer thickness of that key region.

[0083] As an example, we can first calculate the overall proportion, recursively summing all the quantities. Then, for each key region, we calculate the number of merged region images corresponding to it. Specifically, we can refer to the following formula for calculation:

[0084] currentRatio=Images.Count*SliceThickness

[0085] That is, the proportion of the current critical region is the product of the number of original scan images of the current region and the scan layer thickness of the current critical region.

[0086] totalRatio += currentRatio

[0087] That is, the total proportion is the sum of the proportions of each key area.

[0088] currentCount=remainedImageCount*currentRatio / totalRatio

[0089] That is, the number of regional images in the current area is the number of original scanned images multiplied by the proportion of each key area in the total.

[0090] The following example illustrates how to determine the number of region images for each key region.

[0091] As an example, an MRI scan of the head and abdomen can be performed on the subject, yielding the raw scan images and slice thickness information for each area as follows:

[0092] Head, 200 images, layer thickness 0.8;

[0093] Abdomen, 200 images, slice thickness 1.2.

[0094] If a user wants 40 images to be displayed on the film, then they need to select 40 images from a total of 400 images (200 + 200).

[0095] Furthermore, the proportions of the head and abdomen can be preset to select the appropriate number of images from 400 images.

[0096] As a more specific example, a CT scan of the head, chest, and abdomen was performed on the subject, and the raw scan images and slice thickness information for each area are as follows:

[0097] Head, 100 images, layer thickness 0.5;

[0098] Chest, 150 images, slice thickness 0.8;

[0099] Abdomen, 120 images, slice thickness 1.2;

[0100] Furthermore, calculate the proportion of key areas in each part:

[0101] currentratio header = 100 * 0.5 = 50

[0102] Currentratiochest=150*0.8=120

[0103] Currentratioabdomen=120*1.2=144

[0104] Therefore, the total proportion is:

[0105] TotalRatio = 50 + 120 + 144 = 314

[0106] Taking a target image set of 50 images, with 5 positioning images and 45 remaining, the number of images for each key region is as follows:

[0107] Head: 45 * 50 / 314 = 7.16

[0108] Chest: 45*120 / 314=17.19

[0109] Abdomen: 45 * 144 / 314 = 20.6

[0110] Ultimately, 7 images of the head, 17 images of the chest, and 21 images of the abdomen were selected, for a total of 45 images.

[0111] Optionally, in the above embodiments, the original scan images within each key region are merged, including: dividing the original scan images within the current key region into N groups; where N is an integer greater than or equal to 1; calculating the number of images within each group; and merging the original scan images within each group, with the number of merged images equal to the number of images within each group. In this way, by dividing the original scan images within each key region into groups and merging each image group separately, a larger number of merged images can be generated for key regions, further preserving key information from multiple original images and improving the clinical value of the output images.

[0112] It is understandable that the image groups can be divided into multiple image groups based on the size of the key region, or they can be divided into middle and edge regions in order to retain more image information in the central region.

[0113] Optionally, N is greater than or equal to 2. In the above embodiment, the original scanned images within the current key region are divided into N groups, including: obtaining the distance between the original scanned images within the current key region and the center line of the current key region; classifying the original scanned images with a distance less than a preset distance into the middle group; and classifying the original scanned images with a distance greater than or equal to the preset distance into the edge group; wherein the number of edge groups is N-1. In this embodiment, among the multiple image groups into which the current key region is divided, at least one middle group is guaranteed. Other regions outside the middle group can be uniformly classified into one edge group. Of course, in order to improve the image quality of the merged images, multiple edge groups can be further divided.

[0114] Optionally, the number of images within a middle group is greater than the number of images within any edge group.

[0115] In some examples, when merging images within each group, the characteristics of human tissue structure are considered. From a scanning perspective, relatively thinner layers are used for the central areas, while thicker layers are used towards the edges. That is, the central regions contain more key information, while the edge regions contain relatively less. Therefore, during merging, more images can be generated from the central groups to retain more key information.

[0116] Optionally, the original scanned images within each group are merged separately, including: merging the original scanned images of the middle group to obtain a merged image with an image interval of a first interval; merging the original scanned images of the edge group to obtain a merged image with an image interval of a second interval; wherein the first interval is smaller than the second interval.

[0117] By using image intervals, a larger number of target images can be generated in the intermediate group. This preserves key information in the images and improves the image quality of the final generated target images.

[0118] like Figure 7 The image shown is a schematic diagram of a lung region obtained using the image generation method provided in this application embodiment. In the final generated result, the image spacing in the foreground and background is larger than that in the middle, thus ensuring that the region of most interest in the middle has the smallest layer spacing during image generation, thereby guaranteeing the quality of image generation.

[0119] Optionally, in the above embodiments, merging the original scanned images in each key region includes: obtaining a point set consisting of points at the same position in the current row of all original scanned images; calculating the average density value of all points in the point set; and determining the merged image based on the average density value.

[0120] It is understood that existing image merging or image fusion techniques can also be used to merge the original scanned images in the key area, and this application does not limit this.

[0121] Combination Figure 8 As shown, this is another image generation method provided in an embodiment of this application. This method focuses on describing how to implement the image generation process in a practical application scenario. The method includes:

[0122] S801: Receive image set;

[0123] The image set is the raw scan data generated by the CT scanning equipment after scanning the patient.

[0124] S802: Perform image classification, dividing images into mergeable and non-mergeable types;

[0125] In each image sequence of the original scanned image set, multiple images with a layer thickness difference less than a preset difference, consistent orientation, and image interval satisfying a preset interval are identified as mergeable images in the current image sequence.

[0126] S803: Displays the positioning image;

[0127] Provide users with a display interface that includes location images.

[0128] S804: Selection of the key area for receiving users;

[0129] The interface allows users to define the range of multiple key areas.

[0130] S805: Divide the image into key regions;

[0131] That is, the images in the original scanned image set are divided into multiple key regions.

[0132] S806: Divide and merge the key areas based on their physical location.

[0133] The original scan images within each key region are divided into three groups: the middle group (for the middle region), the head group (for the upper region), and the tail group (for the lower region). The original scan images within each group are then merged to ensure that the number of images in the merged middle group is greater than the number of images in both the head and tail groups.

[0134] S807: Obtain the merged image and output it as a film display.

[0135] The above method divides the original scan image into various key regions, and then groups and merges them within the key regions. The final target image can reflect more clinically valuable images of the key regions, thus improving the clinical reference value of the images.

[0136] Combination Figure 9 As shown, this application embodiment provides an image generation apparatus 900, including:

[0137] The acquisition module 901 is configured to acquire the original set of scanned images and the number of target images;

[0138] The partitioning module 902 is configured to divide the images of the original scanned image set into multiple key regions;

[0139] The quantity determination module 903 is configured to determine the number of region images corresponding to each key region based on the number of original scanned images and the number of target images corresponding to each key region.

[0140] The merging module 904 is configured to merge the original scanned images within each key region to obtain a target image equal to the number of region images.

[0141] The apparatus provided in this application first acquires a set of original scanned images and the number of target images. It then divides the images in the original scanned image set into multiple key regions. Further, based on the number of original scanned images and the number of target images corresponding to each key region, it determines the number of region images corresponding to each key region. Finally, it merges the original scanned images within each key region to obtain a target image equal to the number of region images. The target image in this process is generated based on the key regions in the localized images; that is, the target image can reflect more clinically valuable images of the key regions, improving the clinical reference value of the images. The entire process requires no manual intervention, improving the stability and efficiency of image generation.

[0142] Optionally, the segmentation module 902 is specifically configured to display the positioning image; receive one or more key regions marked by the user in the positioning image; and segment the images of the original scanned image set into each key region in the positioning image.

[0143] Optionally, the segmentation module 902 is specifically configured to divide the positioning image into multiple regions according to the subject's body parts; select key regions corresponding to the subject's basic information from the multiple regions; and divide the images of the original scan image set into each key region in the positioning image.

[0144] Optionally, the partitioning module 902 is specifically configured to, in each image sequence of the original scanned image set, identify multiple images with a layer thickness difference less than a preset difference, consistent orientation, and image interval satisfying a preset interval as mergeable images in the current image sequence; remove other images besides mergeable images in the original image set; and partition the remaining original images in the original image set into multiple key regions.

[0145] Optionally, the quantity determination module 903 is specifically configured to: obtain the scan layer thickness of each key region; determine the proportion of each key region based on the number of original scan images corresponding to each key region and the scan layer thickness; and determine the number of region images corresponding to each key region based on the number of target images and the proportion of each key region.

[0146] Optionally, the merging module 904 is specifically configured to divide the original scanned images in the current key area into N groups; where N is an integer greater than or equal to 1; calculate the number of images in each group; and merge the original scanned images in each group, with the number of merged images equal to the number of images in each group.

[0147] Optionally, N is greater than or equal to 2; the original scanned images in the current key area are divided into N groups, including: obtaining the distance between the original scanned images in the current key area and the center line of the current key area; classifying the original scanned images with a distance less than a preset distance into the middle group; classifying the original scanned images with a distance greater than or equal to the preset distance into the edge group; wherein the number of edge groups is N-1.

[0148] Optionally, the number of images within a middle group is greater than the number of images within any edge group.

[0149] Optionally, the original scanned images within each group are merged separately, including: merging the original scanned images of the middle group to obtain a merged image with an image interval of a first interval; merging the original scanned images of the edge group to obtain a merged image with an image interval of a second interval; wherein the first interval is smaller than the second interval.

[0150] Optionally, the merging module 904 is specifically configured to obtain a point set consisting of points at the same position in the current row of all original scanned images; calculate the average density value of all points in the point set; and determine the merged image based on the average density value.

[0151] Combination Figure 10 As shown, this application embodiment provides an image generation apparatus 1000, including a processor 100 and a memory 101. Optionally, the apparatus may further include a communication interface 102 and a bus 103. The processor 100, communication interface 102, and memory 101 can communicate with each other via the bus 103. The communication interface 102 can be used for information transmission. The processor 100 can call logical instructions stored in the memory 101 to execute the image generation method of the above embodiment.

[0152] Furthermore, the logic instructions in the aforementioned memory 101 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0153] The memory 101, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 100 executes functional applications and data processing by running the program instructions / modules stored in the memory 101, thereby implementing the image generation method of the above embodiments.

[0154] The memory 101 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 101 may include high-speed random access memory and may also include non-volatile memory.

[0155] This application provides a computer-readable storage medium storing computer-executable instructions configured to perform the image generation method described above.

[0156] This application provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the image generation method described above.

[0157] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0158] The technical solutions of this application embodiment can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this application embodiment. The aforementioned storage medium can be a non-transitory storage medium, including: USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0159] The foregoing description and accompanying drawings fully illustrate embodiments of this application to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or,” as used herein, means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0160] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0161] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0162] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. An image generation method, characterized in that, include: Obtain the original set of scanned images and the number of target images; The images in the original scanned image set are divided into multiple key regions; The number of region images corresponding to each key region is determined based on the number of original scanned images and the number of target images corresponding to each key region. The original scanned images within each key region are merged to obtain a target image with the same number of region images. Based on the number of original scanned images and the number of target images corresponding to each key region, the number of region images corresponding to each key region is determined, including: obtaining the scan layer thickness of each key region; determining the proportion of each key region based on the number of original scanned images and the scan layer thickness corresponding to each key region; and determining the number of region images corresponding to each key region based on the number of target images and the proportion of each key region. The original scanned images within each key region are merged, including: obtaining the distance between the original scanned image within the current key region and the centerline of the current key region; classifying the original scanned images with a distance less than a preset distance into the middle group; classifying the original scanned images with a distance greater than or equal to the preset distance into the edge group; wherein the number of edge groups is N-1, and N is greater than or equal to 2; calculating the number of images within each group; merging the original scanned images of the middle group to obtain a merged image with an image interval of the first interval; merging the original scanned images of the edge group to obtain a merged image with an image interval of the second interval; the number of merged images is equal to the number of images within each group; wherein the first interval is less than the second interval.

2. The method according to claim 1, characterized in that, The original scanned image set was divided into several key regions, including: Display location image; Receive one or more key regions marked by the user in the positioning image; The images in the original scanned image set are divided into each key region in the localization image.

3. The method according to claim 1, characterized in that, The original scanned image set was divided into several key regions, including: The localization image is divided into multiple regions according to the body parts of the examinee; Select the key areas that correspond to the examinee's basic information from multiple regions; The images in the original scanned image set are divided into each key region in the localization image.

4. The method according to claim 1, characterized in that, The original scanned image set was divided into several key regions, including: In each image sequence in the original scanned image set, multiple images with a layer thickness difference less than a preset difference, consistent orientation, and image interval satisfying a preset interval are identified as mergeable images in the current image sequence. Remove images other than those that can be merged from the original set of scanned images; The remaining original scan images in the original scan image set are divided into multiple key regions.

5. The method according to claim 1, characterized in that, The number of images within a middle group is greater than the number of images within any edge group.

6. An image generation apparatus, characterized in that, include: The acquisition module is configured to acquire the original set of scanned images and the number of target images; The segmentation module is configured to divide the images of the original scanned image set into multiple key regions; The quantity determination module is configured to determine the number of region images corresponding to each key region based on the number of original scanned images and the number of target images corresponding to each key region. Based on the number of original scanned images and the number of target images corresponding to each key region, the number of region images corresponding to each key region is determined, including: obtaining the scan layer thickness of each key region; determining the proportion of each key region based on the number of original scanned images and the scan layer thickness corresponding to each key region; and determining the number of region images corresponding to each key region based on the number of target images and the proportion of each key region. The merging module is configured to merge the original scanned images within each key region to obtain a target image with the same number of region images. The original scanned images within each key region are merged, including: obtaining the distance between the original scanned image within the current key region and the centerline of the current key region; classifying the original scanned images with a distance less than a preset distance into the middle group; classifying the original scanned images with a distance greater than or equal to the preset distance into the edge group; wherein the number of edge groups is N-1, and N is greater than or equal to 2; calculating the number of images within each group; merging the original scanned images of the middle group to obtain a merged image with an image interval of the first interval; merging the original scanned images of the edge group to obtain a merged image with an image interval of the second interval; the number of merged images is equal to the number of images within each group; wherein the first interval is less than the second interval.

7. An image generation apparatus, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to perform the image generation method as described in any one of claims 1 to 5 when executing the program instructions.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions configured to perform the image generation method as described in any one of claims 1 to 5.

Images