A method for regional feature recognition and processing of CT images based on image processing technology

Abstract

The present invention relates to the field of CT image segmentation and recognition processing, and in particular to a CT image regional feature recognition processing method based on image processing technology, comprising: S1, using CT images to obtain basic features of CT images based on image processing technology; S2, establishing a quantitative feature database of CT images according to the basic features of the CT images; S3, using the quantitative feature database to perform regional segmentation processing on the CT images to obtain multi-region feature recognition processing results of the CT images, extracting and classifying image features or regional features involved in the CT images, establishing a reasonable and reliable hierarchical feature database, and dividing, processing and verifying the high, medium and low three-level regions of CT image processing respectively, to ensure the overall logic of the scheme and the rationality of its own implementation, and to improve the overall output accuracy.

Description

Technical Field

[0001] The present invention relates to the field of CT image segmentation, recognition and processing, and in particular to a CT image region feature recognition and processing method based on image processing technology. Background Art

[0002] CT images are reconstructed analog images after digital conversion. They are composed of a certain number of pixels with different gray levels from black to white arranged in an inherent matrix. The density resolution of CT images is high, equivalent to 10 to 20 times that of traditional X-ray images. The basic unit of CT images is pixels, but there are still problems such as errors in pixel conversion in image conversion processing or recognition between overall image areas. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a method for identifying and processing regional features of CT images based on image processing technology, which realizes comprehensive identification and processing of multi-regional features of CT images by establishing a multi-level and multi-type database and image labels.

[0004] To achieve the above object, the present invention provides a method for identifying and processing regional features of CT images based on image processing technology, comprising:

[0005] S1. Obtain basic features of CT images using CT images based on image processing technology;

[0006] S2. Establishing a quantitative feature database of CT images according to the basic features of the CT images;

[0007] S3. Performing region segmentation processing on the CT image using the quantitative feature database to obtain a multi-region feature recognition processing result of the CT image.

[0008] Preferably, the method of obtaining basic features of CT images using CT images based on image processing technology includes:

[0009] The CT images are used to divide the density regions and obtain high-density regions, medium-density regions and low-density regions.

[0010] According to the high-density area, the medium-density area and the low-density area, pixels corresponding to the high-density area, the medium-density area and the low-density area are obtained respectively;

[0011] The high-density area pixels, medium-density area pixels and low-density area pixels are used as basic features of the CT image.

[0012] Furthermore, establishing a quantitative feature database of a CT image according to the basic features of the CT image includes:

[0013] Establishing a high-density regional feature database of CT images by using high-density regional pixels of the basic features of the CT images and corresponding historical approximate high-density regional pixels;

[0014] Establishing a medium-density region feature database of CT images using medium-density region pixels of the basic features of the CT images and corresponding historical approximate medium-density region pixels;

[0015] Establishing a low-density area feature database of CT images using low-density area pixels of the basic features of the CT images and corresponding historical approximate low-density area pixels;

[0016] The high-density region feature database, the medium-density region feature database and the low-density region feature database of the CT image are used as the quantitative feature database of the CT image.

[0017] Further, using the high-density region pixels of the basic features of the CT image and the corresponding historical approximate high-density region pixels to establish a high-density region feature database of the CT image includes:

[0018] Acquiring a historical CT image set according to the CT image basic features corresponding to the CT image;

[0019] Determine whether the pixel value of the CT image is consistent with the pixel value of each historical image in the historical CT image set, if so, retain the current historical image, otherwise, delete the historical images in the historical CT image set with inconsistent pixel values;

[0020] Using the historical CT image set to obtain historical high-density area pixels according to high-density area pixels of basic features of CT images to establish a historical high-density area pixel set;

[0021] Using each historical high-density region pixel in the historical high-density region pixel set to obtain the region contour corresponding to the historical high-density region pixel to establish a historical high-density region label;

[0022] The historical high-density region pixel set and the historical high-density region label are used as a high-density region feature database of the CT image.

[0023] Furthermore, using the medium-density region pixels of the basic features of the CT image and the corresponding historical approximate medium-density region pixels to establish a medium-density region feature database of the CT image includes:

[0024] Acquiring a historical CT image set according to the CT image basic features corresponding to the CT image;

[0025] Using the historical CT image set to obtain historical medium-density area pixels in the historical CT image set according to medium-density area pixels of the basic features of the CT image;

[0026] Determine whether the regions corresponding to the historical medium-density region pixels are independent of each other, if so, use the historical medium-density region pixels to perform region isolation to obtain updated historical medium-density region pixels, otherwise, retain the current historical medium-density region pixels;

[0027] Obtaining the relative position of pixels in the density area of ​​the current history;

[0028] Using the relative point positions of the pixels, a regional point cloud matrix of pixels in the historical medium-density region is established;

[0029] Using the historical medium-density region pixels and the regional point cloud matrix of the historical medium-density region pixels as a medium-density region feature database of the CT image;

[0030] The regional point cloud matrix is ​​composed of pixel points of historical medium-density regional pixels, and the pixel relative point positions are corresponding point positions of historical medium-density regional pixels in historical CT images.

[0031] Furthermore, using the low-density area pixels of the basic features of the CT image and the corresponding historical approximate low-density area pixels to establish a low-density area feature database of the CT image includes:

[0032] Obtaining adjacent pixels at the edge of a region corresponding to pixels in a low-density region of the basic features of the CT image;

[0033] Obtaining the geometric center of the area corresponding to the pixels in the low-density area of ​​the basic features of the CT image;

[0034] Using the low-density area pixels and the adjacent pixels at the edge of the corresponding area to establish a corresponding mapping of adjacent pixels;

[0035] Establishing a divergent pixel correspondence mapping using the geometric center of the region and adjacent pixels at the edge of the region;

[0036] The adjacent pixel correspondence map and the divergent pixel correspondence map are used as a low-density region feature database of the CT image.

[0037] Furthermore, the CT image is subjected to region segmentation processing using the quantitative feature database to obtain a CT image multi-region feature recognition processing result including:

[0038] S3-1, performing artifact filtering processing using the quantitative feature database to obtain a reconstructed quantitative feature database;

[0039] S3-2, using the CT image to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result.

[0040] Further, performing artifact filtering processing using the quantitative feature database to obtain a reconstructed quantitative feature database includes:

[0041] Acquire an image artifact mark corresponding to a historical CT image according to the CT image;

[0042] Using the image center of the historical CT image as the coordinate origin;

[0043] Establishing a two-dimensional coordinate system of the CT image according to the coordinate origin;

[0044] Using the image artifact marker, obtaining corresponding image artifact coordinates and image artifact vectors according to a two-dimensional coordinate system of the CT image;

[0045] Using the high-density region feature database of the quantitative feature database to obtain a high-density region vector according to the coordinate origin;

[0046] Using the medium-density region feature database of the quantitative feature database to obtain a medium-density region vector according to a coordinate origin;

[0047] Using the low-density region feature database of the quantitative feature database to obtain a low-density region vector according to the coordinate origin;

[0048] The image artifact coordinates, the image artifact vectors, the high-density region vectors, the medium-density region vectors, the low-density region vectors and the quantitative feature database are used as a reconstructed quantitative feature database.

[0049] Furthermore, the CT image is used to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result, which includes:

[0050] S3-2-3-1, using the gray value matrix of the CT image to obtain a gray value matrix vector of the CT image;

[0051] S3-2-3-2, using the gray value matrix vector of the CT image to obtain the corresponding image artifact vector, high-density area vector, medium-density area vector and low-density area vector as image artifact verification labels, high-density area verification labels, medium-density area verification labels and low-density area verification labels according to the reconstruction quantitative feature database;

[0052] S3-2-3-3, using the gray value matrix vector of the CT image to obtain the corresponding image artifact coordinates as the CT image addressing label according to the reconstructed quantitative feature database;

[0053] S3-2-3-4, using the CT image addressing tag to obtain a historical CT image with the same image artifact coordinates according to the quantitative feature database of the reconstructed quantitative feature database as the historical CT image to be verified;

[0054] S3-2-3-5, determine whether the historical high-density area label corresponding to the historical CT image to be verified corresponds to the high-density area verification label, if so, divide the CT image into high-density areas according to the high-density area verification label, and execute S3-2-3-6, otherwise, abandon the process;

[0055] S3-2-3-6, determine whether the regional point cloud matrix of the historical medium-density area pixels corresponding to the historical CT image to be verified corresponds to the medium-density area verification label, if so, divide the CT image into medium-density areas according to the medium-density area verification label, and execute S3-2-3-7, otherwise, abandon the process;

[0056] S3-2-3-7, determine whether the corresponding mapping of the adjacent pixels corresponding to the historical CT image to be verified corresponds to the low-density area verification label, if so, divide the CT image into low-density areas according to the low-density area verification label, and execute S3-2-3-8, otherwise, abandon the process;

[0057] S3-2-3-8. Determine whether the divergent pixel mapping corresponding to the historical CT image to be verified corresponds to the grayscale value matrix vector of the CT image. If so, retain the current CT image as the result of the CT image multi-region feature recognition processing. Otherwise, abandon the processing.

[0058] Compared with the closest prior art, the present invention has the following beneficial effects:

[0059] The image features or regional features involved in the CT image are extracted and classified, and a reasonable and reliable hierarchical feature database is established. The high, medium and low level areas of CT image processing are divided and processed and verified separately to ensure the overall logic of the solution and the rationality of its own implementation, and to improve the overall output accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 The present invention provides a flowchart of a method for identifying and processing regional features of CT images based on image processing technology. DETAILED DESCRIPTION

[0061] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Embodiment 1: The present invention provides a method for identifying and processing regional features of CT images based on image processing technology, such as Figure 1 As shown, including:

[0064] S1. Obtain basic features of CT images using CT images based on image processing technology;

[0065] S2. Establishing a quantitative feature database of CT images according to the basic features of the CT images;

[0066] S3. Performing region segmentation processing on the CT image using the quantitative feature database to obtain a multi-region feature recognition processing result of the CT image.

[0067] S1 specifically includes:

[0068] S1-1, using CT images to perform density area division processing to obtain high-density areas, medium-density areas and low-density areas respectively;

[0069] S1-2, obtaining corresponding high-density area pixels, medium-density area pixels and low-density area pixels respectively according to the high-density area, medium-density area and low-density area;

[0070] S1-3. Utilize the high-density region pixels, the medium-density region pixels and the low-density region pixels as basic features of the CT image.

[0071] S2 specifically includes:

[0072] S2-1, using the high-density area pixels of the basic features of the CT image and the corresponding historical approximate high-density area pixels to establish a high-density area feature database of the CT image;

[0073] S2-2, using the medium-density region pixels of the basic features of the CT image and the corresponding historical approximate medium-density region pixels to establish a medium-density region feature database of the CT image;

[0074] S2-3, using the low-density area pixels of the basic features of the CT image and the corresponding historical approximate low-density area pixels to establish a low-density area feature database of the CT image;

[0075] S2-4. Utilize the high-density region feature database, the medium-density region feature database, and the low-density region feature database of the CT image as a quantitative feature database of the CT image.

[0076] S2-1 specifically includes:

[0077] S2-1-1, obtaining a historical CT image set according to the CT image corresponding to the basic features of the CT image;

[0078] S2-1-2, determining whether the pixel value of the CT image is consistent with the pixel value of each historical image in the historical CT image set, if so, retaining the current historical image, otherwise, deleting the historical images in the historical CT image set with inconsistent pixel values;

[0079] S2-1-3, using the historical CT image set to obtain historical high-density area pixels according to high-density area pixels of the basic features of the CT image to establish a historical high-density area pixel set;

[0080] S2-1-4, using each historical high-density region pixel in the historical high-density region pixel set to obtain the region contour corresponding to the historical high-density region pixel to establish a historical high-density region label;

[0081] S2-1-5. Utilize the historical high-density region pixel set and the historical high-density region label as a high-density region feature database of the CT image.

[0082] S2-2 specifically includes:

[0083] S2-2-1, obtaining a historical CT image set according to the CT image corresponding to the basic features of the CT image;

[0084] S2-2-2, using the historical CT image set to obtain historical medium-density area pixels in the historical CT image set according to medium-density area pixels of the basic features of the CT image;

[0085] S2-2-3, determining whether the regions corresponding to the historical medium-density region pixels are independent of each other, if so, using the historical medium-density region pixels to perform region isolation to obtain updated historical medium-density region pixels, otherwise, retaining the current historical medium-density region pixels;

[0086] S2-2-4, obtaining the relative position of the pixels in the current historical medium-density area;

[0087] S2-2-5, using the relative position of the pixels to establish a regional point cloud matrix of pixels in the historical medium-density region;

[0088] S2-2-6, using the historical medium-density region pixels and the regional point cloud matrix of the historical medium-density region pixels as a medium-density region feature database of the CT image;

[0089] The regional point cloud matrix is ​​composed of pixel points of historical medium-density regional pixels, and the pixel relative point positions are corresponding point positions of historical medium-density regional pixels in historical CT images.

[0090] S2-3 specifically includes:

[0091] S2-3-1, obtaining pixels adjacent to the edge of the area corresponding to the low-density area pixels of the basic features of the CT image;

[0092] S2-3-2, obtaining the geometric center of the area corresponding to the pixels in the low-density area of ​​the basic features of the CT image;

[0093] S2-3-3, using the low-density area pixels and the adjacent pixels at the edge of the corresponding area to establish a corresponding mapping of adjacent pixels;

[0094] S2-3-4, using the geometric center of the region and the adjacent pixels at the edge of the region to establish a corresponding mapping of divergent pixels;

[0095] S2-3-5. Use the adjacent pixel correspondence mapping and the divergent pixel correspondence mapping as a low-density area feature database of the CT image.

[0096] S3 specifically includes:

[0097] S3-1, performing artifact filtering processing using the quantitative feature database to obtain a reconstructed quantitative feature database;

[0098] S3-2, using the CT image to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result.

[0099] S3-1 specifically includes:

[0100] S3-1-1, obtaining an image artifact mark corresponding to a historical CT image according to the CT image;

[0101] S3-1-2, using the image center of the historical CT image as the coordinate origin;

[0102] S3-1-3, establishing a two-dimensional coordinate system of the CT image according to the coordinate origin;

[0103] S3-1-4, using the image artifact marker to obtain corresponding image artifact coordinates and image artifact vectors according to the two-dimensional coordinate system of the CT image;

[0104] S3-1-5, using the high-density region feature database of the quantitative feature database to obtain a high-density region vector according to the coordinate origin;

[0105] S3-1-6, using the medium-density region feature database of the quantitative feature database to obtain a medium-density region vector according to the coordinate origin;

[0106] S3-1-7, using the low-density region feature database of the quantitative feature database to obtain a low-density region vector according to the coordinate origin;

[0107] S3-1-8. Use the image artifact coordinates, image artifact vectors, high-density region vectors, medium-density region vectors, low-density region vectors and the quantitative feature database as a reconstructed quantitative feature database.

[0108] S3-2 specifically includes:

[0109] S3-2-1, using the CT image to obtain pixel grayscale values ​​of the CT image;

[0110] S3-2-2, using the pixel gray values ​​to establish a gray value matrix of the CT image according to the CT image;

[0111] S3-2-3. Use the gray value matrix of the CT image to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result.

[0112] S3-2-3 specifically includes:

[0113] S3-2-3-1, using the gray value matrix of the CT image to obtain a gray value matrix vector of the CT image;

[0114] S3-2-3-2, using the gray value matrix vector of the CT image to obtain the corresponding image artifact vector, high-density area vector, medium-density area vector and low-density area vector as image artifact verification labels, high-density area verification labels, medium-density area verification labels and low-density area verification labels according to the reconstruction quantitative feature database;

[0115] S3-2-3-3, using the gray value matrix vector of the CT image to obtain the corresponding image artifact coordinates as the CT image addressing label according to the reconstructed quantitative feature database;

[0116] S3-2-3-4, using the CT image addressing tag to obtain a historical CT image with the same image artifact coordinates according to the quantitative feature database of the reconstructed quantitative feature database as the historical CT image to be verified;

[0117] S3-2-3-5, determine whether the historical high-density area label corresponding to the historical CT image to be verified corresponds to the high-density area verification label, if so, divide the CT image into high-density areas according to the high-density area verification label, and execute S3-2-3-6, otherwise, abandon the process;

[0118] S3-2-3-6, determine whether the regional point cloud matrix of the historical medium-density area pixels corresponding to the historical CT image to be verified corresponds to the medium-density area verification label, if so, divide the CT image into medium-density areas according to the medium-density area verification label, and execute S3-2-3-7, otherwise, abandon the process;

[0119] S3-2-3-7, determine whether the corresponding mapping of the adjacent pixels corresponding to the historical CT image to be verified corresponds to the low-density area verification label, if so, divide the CT image into low-density areas according to the low-density area verification label, and execute S3-2-3-8, otherwise, abandon the process;

[0120] S3-2-3-8. Determine whether the divergent pixel mapping corresponding to the historical CT image to be verified corresponds to the grayscale value matrix vector of the CT image. If so, retain the current CT image as the result of the CT image multi-region feature recognition processing. Otherwise, abandon the processing.

[0121] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0122] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying and processing regional features of CT images based on image processing technology, characterized in that: include: S1. Obtain basic features of CT images using CT images based on image processing technology; S1-1, using CT images to perform density area division processing to obtain high-density areas, medium-density areas and low-density areas respectively; S1-2, obtaining corresponding high-density area pixels, medium-density area pixels and low-density area pixels respectively according to the high-density area, medium-density area and low-density area; S1-3, using the high-density area pixels, the medium-density area pixels and the low-density area pixels as basic features of the CT image; S2. Establishing a quantitative feature database of CT images according to the basic features of the CT images; S2-1, using the high-density area pixels of the basic features of the CT image and the corresponding historical approximate high-density area pixels to establish a high-density area feature database of the CT image; S2-1-1, obtaining a historical CT image set according to the CT image corresponding to the basic features of the CT image; S2-1-2, determining whether the pixel value of the CT image is consistent with the pixel value of each historical image in the historical CT image set, if so, retaining the current historical image, otherwise, deleting the historical images in the historical CT image set with inconsistent pixel values; S2-1-3, using the historical CT image set to obtain historical high-density area pixels according to high-density area pixels of the basic features of the CT image to establish a historical high-density area pixel set; S2-1-4, using each historical high-density region pixel in the historical high-density region pixel set to obtain the region contour corresponding to the historical high-density region pixel to establish a historical high-density region label; S2-1-5, using the historical high-density region pixel set and the historical high-density region label as a high-density region feature database of the CT image; S2-2, using the medium-density region pixels of the basic features of the CT image and the corresponding historical approximate medium-density region pixels to establish a medium-density region feature database of the CT image; S2-2-1, obtaining a historical CT image set according to the CT image corresponding to the basic features of the CT image; S2-2-2, using the historical CT image set to obtain historical medium-density area pixels in the historical CT image set according to medium-density area pixels of the basic features of the CT image; S2-2-3, determining whether the regions corresponding to the historical medium-density region pixels are independent of each other, if so, using the historical medium-density region pixels to perform region isolation to obtain updated historical medium-density region pixels, otherwise, retaining the current historical medium-density region pixels; S2-2-4, obtaining the relative position of the pixels in the current historical medium-density area; S2-2-5, using the relative position of the pixels to establish a regional point cloud matrix of pixels in the historical medium-density region; S2-2-6, using the historical medium-density region pixels and the regional point cloud matrix of the historical medium-density region pixels as a medium-density region feature database of the CT image; Wherein, the regional point cloud matrix is ​​composed of pixel points of historical medium-density regional pixels, and the pixel relative point positions are corresponding point positions of historical medium-density regional pixels in historical CT images; S2-3, using the low-density area pixels of the basic features of the CT image and the corresponding historical approximate low-density area pixels to establish a low-density area feature database of the CT image; S2-3-1, obtaining pixels adjacent to the edge of the area corresponding to the low-density area pixels of the basic features of the CT image; S2-3-2, obtaining the geometric center of the area corresponding to the pixels in the low-density area of ​​the basic features of the CT image; S2-3-3, using the low-density area pixels and the adjacent pixels at the edge of the corresponding area to establish a corresponding mapping of adjacent pixels; S2-3-4, using the geometric center of the region and the adjacent pixels at the edge of the region to establish a corresponding mapping of divergent pixels; S2-3-5, using the adjacent pixel correspondence mapping and the divergent pixel correspondence mapping as a low-density area feature database of the CT image; S2-4, using the high-density region feature database, the medium-density region feature database, and the low-density region feature database of the CT image as a quantitative feature database of the CT image; S3. Performing region segmentation processing on the CT image using the quantitative feature database to obtain a multi-region feature recognition processing result of the CT image.

2. A method for identifying and processing regional features of CT images based on image processing technology as claimed in claim 1, characterized in that: The CT image is segmented using the quantitative feature database to obtain a CT image multi-region feature recognition processing result, including: S3-1, performing artifact filtering processing using the quantitative feature database to obtain a reconstructed quantitative feature database; S3-2, using the CT image to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result.

3. A method for identifying and processing regional features of CT images based on image processing technology as claimed in claim 2, characterized in that: Using the quantitative feature database to perform artifact filtering to obtain a reconstructed quantitative feature database includes: Acquire an image artifact mark corresponding to a historical CT image according to the CT image; Using the image center of the historical CT image as the coordinate origin; Establishing a two-dimensional coordinate system of the CT image according to the coordinate origin; Using the image artifact marker, obtaining corresponding image artifact coordinates and image artifact vectors according to a two-dimensional coordinate system of the CT image; Using the high-density region feature database of the quantitative feature database to obtain a high-density region vector according to the coordinate origin; Using the medium-density region feature database of the quantitative feature database to obtain a medium-density region vector according to a coordinate origin; Using the low-density region feature database of the quantitative feature database to obtain a low-density region vector according to the coordinate origin; The image artifact coordinates, the image artifact vectors, the high-density region vectors, the medium-density region vectors, the low-density region vectors and the quantitative feature database are used as a reconstructed quantitative feature database.

4. A method for identifying and processing CT image region features based on image processing technology as claimed in claim 3, characterized in that: The CT image is used to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result, which includes: S3-2-1, using the CT image to obtain pixel grayscale values ​​of the CT image; S3-2-2, using the pixel gray values ​​to establish a gray value matrix of the CT image according to the CT image; S3-2-3. Use the gray value matrix of the CT image to perform region segmentation processing according to the reconstructed quantitative feature database to obtain a CT image multi-region feature recognition processing result.

5. The method for identifying and processing regional features of CT images based on image processing technology according to claim 4, characterized in that: The gray value matrix of the CT image is used to perform region segmentation processing according to the reconstructed quantitative feature database to obtain the CT image multi-region feature recognition processing result, including: S3-2-3-1, using the gray value matrix of the CT image to obtain a gray value matrix vector of the CT image; S3-2-3-2, using the gray value matrix vector of the CT image to obtain the corresponding image artifact vector, high-density area vector, medium-density area vector and low-density area vector as image artifact verification labels, high-density area verification labels, medium-density area verification labels and low-density area verification labels according to the reconstruction quantitative feature database; S3-2-3-3, using the gray value matrix vector of the CT image to obtain the corresponding image artifact coordinates as the CT image addressing label according to the reconstructed quantitative feature database; S3-2-3-4, using the CT image addressing tag to obtain a historical CT image with the same image artifact coordinates according to the quantitative feature database of the reconstructed quantitative feature database as the historical CT image to be verified; S3-2-3-5, determine whether the historical high-density area label corresponding to the historical CT image to be verified corresponds to the high-density area verification label, if so, divide the CT image into high-density areas according to the high-density area verification label, and execute S3-2-3-6, otherwise, abandon the process; S3-2-3-6, determine whether the regional point cloud matrix of the historical medium-density area pixels corresponding to the historical CT image to be verified corresponds to the medium-density area verification label, if so, divide the CT image into medium-density areas according to the medium-density area verification label, and execute S3-2-3-7, otherwise, abandon the process; S3-2-3-7, determine whether the corresponding mapping of the adjacent pixels corresponding to the historical CT image to be verified corresponds to the low-density area verification label, if so, divide the CT image into low-density areas according to the low-density area verification label, and execute S3-2-3-8, otherwise, abandon the process; S3-2-3-8. Determine whether the divergent pixel mapping corresponding to the historical CT image to be verified corresponds to the grayscale value matrix vector of the CT image. If so, retain the current CT image as the result of the CT image multi-region feature recognition processing. Otherwise, abandon the processing.

Images