Image processing method, apparatus, program product, imaging device, and surgical robot

Abstract

The present application provides an image processing method, device, program product, imaging equipment and surgical robot. The image processing method comprises: acquiring a three-dimensional image of a first detection object, converting the three-dimensional image into a plurality of two-dimensional images; and performing contour extraction on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to an image processing method, device, program product, imaging equipment and surgical robot. BACKGROUND

[0002] At present, the segmentation of the skin and bed board of the CT (Computered Tomography) chest image is a key step for the precise operation of the surgical robot. Due to the number and quality of the public training set, the traditional technical method is usually used for the segmentation of the skin and bed board of the CT image. However, the traditional image processing method has the problems of low image precision and relatively low image robustness due to the technical limitation. SUMMARY

[0003] The present application aims at least to solve one of the problems in the prior art or related art.

[0004] To this end, a first aspect of the present application provides an image processing method.

[0005] A second aspect of the present application provides another image processing method.

[0006] A third aspect of the present application provides an image processing device.

[0007] A fourth aspect of the present application provides another image processing device.

[0008] A fifth aspect of the present application provides a readable storage medium.

[0009] A sixth aspect of the present application provides a computer program product.

[0010] A seventh aspect of the present application provides imaging equipment.

[0011] An eighth aspect of the present application provides a surgical robot.

[0012] Therefore, according to the first aspect of the present application, an image processing method is provided, which comprises: acquiring a three-dimensional image of a first detection object, converting the three-dimensional image into a plurality of two-dimensional images; and performing contour extraction on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0013] The image processing method in the technical solution obtains a three-dimensional image of a first detection object, converts the three-dimensional image in dimension to obtain a plurality of two-dimensional images, respectively performs contour segmentation processing on the plurality of two-dimensional images, and determines a first contour image of the first detection object, thereby improving the accuracy of contour information in the first contour image and improving the precision and robustness of the first contour image.

[0014] According to a second aspect of the present application, another image processing method is provided, which comprises: obtaining a three-dimensional image containing a first detection object and a second detection object, the second detection object being used for carrying the first detection object; determining a first contour image of the first detection object according to the three-dimensional image; and performing feature extraction on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object.

[0015] The image processing method in the technical solution obtains a three-dimensional image, performs image segmentation on the three-dimensional image to obtain a first contour image of a first detection object, and performs image segmentation on the three-dimensional image according to the first contour image to obtain a second contour image of a second detection object, thereby improving the accuracy of contour information in the second contour image and improving the precision and robustness of the second contour image.

[0016] According to a third aspect of the present application, an image processing device is provided, which comprises: a first processing module configured to obtain a three-dimensional image of a first detection object and convert the three-dimensional image into a plurality of two-dimensional images; and the first processing module is further configured to perform contour extraction on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0017] The image processing device in the technical solution obtains a three-dimensional image of a first detection object, converts the three-dimensional image in dimension to obtain a plurality of two-dimensional images, respectively performs contour segmentation processing on the plurality of two-dimensional images, and determines a first contour image of the first detection object, thereby improving the accuracy of contour information in the first contour image and improving the precision and robustness of the first contour image.

[0018] According to a fourth aspect of the present application, another image processing device is provided, which comprises: a second processing module configured to obtain a three-dimensional image containing a first detection object and a second detection object, the second detection object being used for carrying the first detection object, and determine a first contour image of the first detection object according to the three-dimensional image; and the second processing module is further configured to perform feature extraction on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object.

[0019] The image processing device in the technical solution obtains a three-dimensional image, performs image segmentation on the three-dimensional image to obtain a first contour image of a first detection object, and then performs image segmentation on the three-dimensional image according to the first contour image to obtain a second contour image of a second detection object, thereby improving the accuracy of contour information in the second contour image and improving the precision and robustness of the second contour image.

[0020] According to a fifth aspect of the present application, a readable storage medium is provided, which stores a program or instructions, and the program or instructions are executed by a processor to implement the image processing method in any of the above technical solutions. Therefore, the readable storage medium has all the beneficial effects of the image processing method in any of the above technical solutions, which will not be repeated here.

[0021] According to a sixth aspect of the present application, a computer program product is provided, which includes computer instructions, and the computer instructions are executed by a processor to implement the image processing method in any of the above technical solutions. Therefore, the readable storage medium has all the beneficial effects of the image processing method in any of the above technical solutions, which will not be repeated here.

[0022] According to a seventh aspect of the present application, an imaging device is provided, which includes the image processing device defined in the third aspect above, or the image processing device defined in the fourth aspect above, and / or the readable storage medium defined in the fifth aspect above, and / or the computer program product defined in the sixth aspect above, and thus has all the beneficial technical effects of the image processing device defined in the third aspect above, or the image processing device defined in the fourth aspect above, and / or the readable storage medium defined in the fifth aspect above, and / or the computer program product defined in the sixth aspect above, which will not be repeated here.

[0023] According to an eighth aspect of the present application, a surgical robot is provided, which plans a movement trajectory or avoids obstacles based on a processed image, wherein the image is obtained based on the image processing method defined in the first aspect above or the steps of the image processing method defined in the second aspect above, and thus has all the beneficial technical effects of the image processing method defined in the first aspect above or the image processing method defined in the second aspect above, which will not be repeated here.

[0024] Additional aspects and advantages of the present application will become apparent from the following description with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0025] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description, taken in conjunction with the accompanying drawings, in which:

[0026] Figure 1One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0027] Figure 2 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0028] Figure 3 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0029] Figure 4 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0030] Figure 5 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0031] Figure 6 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0032] Figure 7 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0033] Figure 8 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0034] Figure 9 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0035] Figure 10 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0036] Figure 11 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0037] Figure 12 One of flowcharts of the image processing method in the embodiment of the present application is shown;

[0038] Figure 13 One of structural block diagrams of the image processing device in the embodiment of the present application is shown;

[0039] Figure 14 One of structural block diagrams of the image processing device in the embodiment of the present application is shown;

[0040] Figure 15 One of structural block diagrams of the image processing device in the embodiment of the present application is shown;

[0041] Figure 16Fig. 3 shows a schematic diagram of an image processing device in an embodiment of the present application;

[0042] Figure 17 Fig. 2 shows a structural block diagram of an image processing device in an embodiment of the present application;

[0043] Figure 18 Fig. 4 shows a schematic diagram of an image processing device in an embodiment of the present application;

[0044] Figure 19 Fig. 5 shows a schematic diagram of an image processing device in an embodiment of the present application;

[0045] Figure 20 Fig. 6 shows a schematic diagram of an image processing device in an embodiment of the present application;

[0046] Figure 21 Fig. 3 shows a structural block diagram of an image processing device in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to enable a more clear understanding of the above-mentioned objects, features and advantages of the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0048] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can be practiced in other manners different from those described herein, and therefore, the scope of protection of the present application is not limited to the specific embodiments disclosed below.

[0049] The image processing method, device, program product, imaging equipment and surgical robot provided by the embodiments of the present application will be described in detail below with reference to specific embodiments and application scenarios. Figures 1 to 21

[0050] The execution subject of the technical scheme of the image processing method provided by the present application can be an image processing device, and can also be determined according to actual use requirements, which is not specifically limited here. In order to more clearly describe the image processing method provided by the present application, the image processing device will be described as the execution subject below.

[0051] In an embodiment according to the present application, as shown in Figure 1 An image processing method is provided, which comprises the following steps:

[0052] In step 102, a three-dimensional image of a first detection object is acquired, and the three-dimensional image is converted into a plurality of two-dimensional images;

[0053] ​In step 104, contour extraction is performed on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0054] In this embodiment, an image processing method is provided for segmenting contour information of a first detection object, where the first detection object is an object to be detected.

[0055] Exemplarily, the first detection object can be specifically a chest cavity of a patient.

[0056] The image processing device obtains a three-dimensional image of the first detection object, and performs dimension conversion on the three-dimensional image to obtain a plurality of two-dimensional images, where the three-dimensional image is a three-dimensional image containing the first detection object, and the two-dimensional image is a two-dimensional image containing the first detection object.

[0057] Exemplarily, the three-dimensional image can be specifically a three-dimensional CT image of the first detection object acquired by a CT device.

[0058] The image processing device performs contour segmentation processing on the plurality of two-dimensional images respectively to determine a first contour image of the first detection object.

[0059] Exemplarily, the first contour image can be specifically a chest skin contour image of the patient.

[0060] Exemplarily, the image processing device performs threshold segmentation on the input three-dimensional image, and then applies the prior knowledge that the skin layer contour in the chest image is the largest axis-like position, extracts the largest contour layer by layer, removes the redundant tissues in the non-contour area, and completes the segmentation of the skin. It should be noted that due to the difference in the CT value range of the skin in the CT images of different manufacturers, models or imaging parameters, there is no standard threshold value that can accurately segment the skin. In view of the fact that the threshold segmentation result will be subjected to contour extraction processing in the subsequent embodiment, the accuracy requirement of the set threshold value is reduced, and therefore the upper and lower limit range of the threshold value that can be set is relatively large, thereby reducing the dependence on the threshold value.

[0061] The image processing method in this embodiment obtains a three-dimensional image of a first detection object, performs dimension conversion on the three-dimensional image to obtain a plurality of two-dimensional images, and then performs contour segmentation processing on the plurality of two-dimensional images respectively to determine a first contour image of the first detection object, thereby improving the accuracy of the contour information in the first contour image, and improving the precision and robustness of the first contour image.

[0062] In one embodiment according to the present application, as shown in Figure 2 an image processing method is provided, which includes:

[0063] In step 202, a three-dimensional image of a first detection object is obtained, and the three-dimensional image is converted into a plurality of two-dimensional images.

[0064] Step 204, determining target contour information of the first detection object through the plurality of two-dimensional images;

[0065] Step 206, obtaining a range threshold of the three-dimensional image, and performing image segmentation processing on the plurality of two-dimensional images according to the range threshold and the target contour information, to obtain the first contour image.

[0066] In this embodiment, the image processing apparatus extracts contour features from the plurality of two-dimensional images to obtain target contour information of the first detection object, where the target contour information is distribution information of a contour of the first detection object.

[0067] Exemplarily, the target contour information can be specifically distribution information of a skin contour.

[0068] The image processing apparatus obtains a range threshold of the three-dimensional image, and performs image segmentation on the plurality of two-dimensional images respectively according to the range threshold and the target contour information, to further obtain the first contour image of the first detection object, where the range threshold is a threshold for image segmentation.

[0069] Exemplarily, the range threshold can be specifically [-200, 100].

[0070] Exemplarily, the plurality of two-dimensional images can include a plurality of layer images along a z-axis direction.

[0071] Exemplarily, the image processing apparatus can search for a maximum contour in a current layer and delete remaining segmentation results layer by layer along a z-axis direction of the three-dimensional image.

[0072] The image processing method in this embodiment extracts contour features from the plurality of two-dimensional images to obtain target contour information of the first detection object, and then performs image segmentation on the plurality of two-dimensional images layer by layer according to the range threshold and the target contour information, to further obtain the first contour image of the first detection object, thereby ensuring information accuracy of the target contour information and further ensuring image accuracy of the first contour image.

[0073] In an embodiment according to the present application, as shown in Figure 3 An image processing method is provided, which includes:

[0074] Step 302, obtaining a three-dimensional image of a first detection object, and converting the three-dimensional image into a plurality of two-dimensional images;

[0075] Step 304, performing contour detection on the plurality of two-dimensional images to obtain a plurality of contour information;

[0076] Step 306, performing data fusion on the plurality of contour information to obtain target contour information in the plurality of contour information;

[0077] Step 308, a range threshold of the three-dimensional image is acquired, and according to the range threshold and the target contour information, the plurality of two-dimensional images are subjected to image segmentation processing to obtain a first contour image.

[0078] In this embodiment, the image processing apparatus respectively performs contour detection on the plurality of two-dimensional images to determine a plurality of contour information, wherein the contour information is distribution information of a contour in the two-dimensional image.

[0079] Exemplarily, the contour information can be specifically distribution information of skin in the two-dimensional image.

[0080] The image processing apparatus performs data fusion on the plurality of contour information to convert the plurality of contour information into the target contour information.

[0081] Exemplarily, the image processing apparatus can perform data comparison on the plurality of contour information, and then select the target contour information from the plurality of contour information.

[0082] The image processing method in this embodiment determines a plurality of contour information by performing contour detection on a plurality of two-dimensional images, and converts the plurality of contour information into target contour information by performing data fusion on the plurality of contour information, thereby ensuring the information accuracy of the target contour information and the image accuracy of the first contour image.

[0083] In an embodiment according to the present application, as shown in Figure 4 An image processing method is provided, which comprises:

[0084] Step 402, a three-dimensional image of a first detection object is acquired, a target pixel axis of the three-dimensional image is acquired, and according to the target pixel axis, the three-dimensional image is subjected to image conversion processing to obtain a plurality of two-dimensional images.

[0085] Step 404, contour extraction is performed on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0086] In this embodiment, the image processing apparatus acquires a target pixel axis of the three-dimensional image, and then converts the three-dimensional image into a plurality of two-dimensional images along the target pixel axis, wherein the target pixel axis is a pixel axis in the three-dimensional image.

[0087] Exemplarily, the target pixel axis can be specifically an X-axis, a Y-axis or a Z-axis.

[0088] The image processing method in this embodiment converts the three-dimensional image into a plurality of two-dimensional images through the target pixel axis, thereby ensuring the image accuracy of the plurality of two-dimensional images and the information accuracy of the first contour image.

[0089] In an embodiment according to the present application, as shown in Figure 5As shown, an image processing method is provided, and the image processing method comprises:

[0090] In step 502, an original image of the first detection object is acquired, and the original image is subjected to denoising and enhancement processing to obtain a three-dimensional image, and the three-dimensional image is converted into a plurality of two-dimensional images.

[0091] In step 504, the plurality of two-dimensional images are subjected to contour extraction to obtain a first contour image of the first detection object.

[0092] In this embodiment, the image processing device acquires an original image of the first detection object, wherein the original image is an initial image of the first detection object.

[0093] Exemplarily, the original image can be specifically an initial CT image of the first detection object.

[0094] The image processing device subjects the original image to image preprocessing such as denoising and enhancement to obtain a three-dimensional image.

[0095] Exemplarily, the image processing device can subject the original image to preprocessing such as denoising to obtain a three-dimensional image.

[0096] The image processing method in this embodiment acquires an original image of the first detection object, subjects the original image to image preprocessing such as denoising and enhancement to obtain a three-dimensional image, thereby ensuring the image accuracy of the three-dimensional image and further ensuring the image accuracy of the first contour image.

[0097] In an embodiment according to the present application, as shown in Figure 6 An image processing method is provided, and the image processing method comprises:

[0098] In step 602, a three-dimensional image containing a first detection object and a second detection object is acquired, the second detection object is used to carry the first detection object, and a first contour image of the first detection object is determined according to the three-dimensional image.

[0099] In step 604, a second contour image of the second detection object is obtained by subjecting the three-dimensional image to feature extraction according to the first contour image.

[0100] In this embodiment, an image processing method is provided, and specifically, an image processing device acquires a three-dimensional image, wherein the three-dimensional image is a three-dimensional image containing a first detection object and a second detection object, and the second detection object is used to carry the first detection object.

[0101] Exemplarily, the first detection object can be specifically a chest cavity of a patient, and the first detection object can be specifically a bed plate carrying the patient.

[0102] The image processing apparatus performs image segmentation on the three-dimensional image to obtain a first contour image of the first detection object, and performs image segmentation on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object, where the second contour image is a distribution image of a contour of the second detection object.

[0103] Exemplarily, the second contour image can be specifically a contour image of a bed board in the three-dimensional image, and the bed board is a bed board in a CT imaging device.

[0104] The image processing method in this embodiment improves the accuracy of contour information in the second contour image, and improves the precision and robustness of the second contour image.

[0105] In an embodiment according to the present application, as shown in Figure 7 An image processing method is provided, which includes:

[0106] In step 702, a three-dimensional image containing a first detection object and a second detection object is obtained, the second detection object is used to carry the first detection object, and a first contour image of the first detection object is determined according to the three-dimensional image.

[0107] In step 704, non-background pixels in the three-dimensional image are determined according to the first contour image.

[0108] In step 706, a threshold combination is obtained, and a target threshold in the threshold combination is determined according to the non-background pixels.

[0109] In step 708, the three-dimensional image is processed according to the target threshold to determine a second contour image.

[0110] In this embodiment, the image processing apparatus determines non-background pixels in the three-dimensional image according to the first contour image, where the non-background pixels are pixels of a non-background part in the three-dimensional image.

[0111] Exemplarily, the non-background pixels in the three-dimensional image can be specifically pixel points of a non-bed board part in the three-dimensional image.

[0112] The image processing apparatus obtains a preset threshold combination, and determines a target threshold in the threshold combination according to the non-background pixels, where the threshold combination is a preset threshold combination, includes thresholds corresponding to second detection objects of different materials, and the target threshold is a threshold in the threshold combination.

[0113] Exemplarily, the threshold combination includes thresholds corresponding to bed boards of different materials.

[0114] Exemplarily, the threshold combination can adaptively reduce or increase the threshold within the combination according to requirements, improve the application flexibility of the threshold combination, and further expand the application range of the threshold combination.

[0115] The image processing method in this embodiment determines the non-background pixels in the three-dimensional image according to the first contour image, and then determines the target threshold in the threshold combination according to the non-background pixels, thereby ensuring the accuracy of the target threshold and further ensuring the precision and robustness of the second contour image.

[0116] In an embodiment according to the present application, as shown in Figure 8 An image processing method is provided, which includes:

[0117] In step 802, a three-dimensional image containing a first detection object and a second detection object is obtained, the second detection object is used to carry the first detection object, and a first contour image of the first detection object is determined according to the three-dimensional image.

[0118] In step 804, non-background pixels in the three-dimensional image are determined according to the first contour image.

[0119] In step 806, data processing is performed on the non-background pixels to obtain a distribution mean of the non-background pixels.

[0120] In step 808, a target threshold in the threshold combination is determined by performing difference operation on the distribution mean and the threshold combination.

[0121] In step 810, image processing is performed on the three-dimensional image according to the target threshold to determine a second contour image.

[0122] In this embodiment, the image processing device performs mean operation on the non-background pixels to obtain a distribution mean of the non-background pixels, where the distribution mean is the mean of the non-background pixel distribution information.

[0123] Exemplarily, the distribution mean can be specifically the mean of the coordinate values of the non-background pixels.

[0124] The image processing device performs difference operation on the distribution mean and the threshold combination to determine the target threshold in the threshold combination.

[0125] Exemplarily, the image processing device performs difference operation on the distribution mean and the threshold combination, and determines the target threshold in the threshold combination according to the minimum difference.

[0126] The image processing method in this embodiment performs mean operation on the non-background pixels to obtain a distribution mean of the non-background pixels, and performs difference operation on the distribution mean and the threshold combination to determine the target threshold in the threshold combination, thereby ensuring the accuracy of the target threshold and further ensuring the data accuracy of the second contour image.

[0127] In an embodiment according to the application, as shown in Figure 9 An image processing method is provided, comprising:

[0128] At step 902, a three-dimensional image containing a first detection object and a second detection object is acquired, the second detection object being used to carry the first detection object, and a first contour image of the first detection object is determined according to the three-dimensional image;

[0129] At step 904, non-background pixels in the three-dimensional image are determined according to the first contour image;

[0130] At step 906, a threshold combination is acquired, and a target threshold in the threshold combination is determined according to the non-background pixels;

[0131] At step 908, image segmentation is performed on the three-dimensional image according to the target threshold, to obtain a segmentation result image;

[0132] At step 910, noise filtering processing is performed on the segmentation result image, to determine a second contour image.

[0133] In this embodiment, the image processing device performs image segmentation processing on the three-dimensional image according to the target threshold, to obtain a segmentation result image, wherein the segmentation result image is an image after the three-dimensional image is segmented.

[0134] Exemplarily, the segmentation result image can specifically be a bed board image segmented from the three-dimensional image.

[0135] The image processing device performs noise filtering and other processing on the segmentation result image, to obtain the second contour image.

[0136] Exemplarily, the image processing device can perform denoising and enhancement and other processing on the segmentation result image, to obtain the second contour image.

[0137] The image processing method in this embodiment performs image segmentation processing on the three-dimensional image according to the target threshold, to obtain a segmentation result image, and performs noise filtering and other processing on the segmentation result image, to obtain the second contour image, thereby ensuring the image quality of the second contour image.

[0138] In an embodiment according to the application, as shown in Figure 10 An image processing method is provided, comprising:

[0139] At step 1002, a three-dimensional image containing a first detection object and a second detection object is acquired, the second detection object being used to carry the first detection object, and a first contour image of the first detection object is determined according to the three-dimensional image;

[0140] At step 1004, a pixel set of the first detection object is determined according to the first contour image.

[0141] At step 1006, a background pixel in the three-dimensional image is determined according to the pixel set.

[0142] At step 1008, a non-background pixel in the three-dimensional image is obtained by performing a classification processing on pixels in the three-dimensional image according to the background pixel.

[0143] At step 1010, a threshold combination is obtained, and a target threshold in the threshold combination is determined according to the non-background pixel.

[0144] At step 1012, a second contour image is obtained by performing an image processing on the three-dimensional image according to the target threshold.

[0145] In this embodiment, the image processing apparatus determines a pixel set corresponding to the first detection object according to the first contour image, where the pixel set is a pixel of the first detection object in the three-dimensional image.

[0146] For example, the first detection object can be a thorax, and the pixel set can include pixels of the thorax and inside the thorax.

[0147] The image processing apparatus sets the pixel set as a background pixel in the three-dimensional image, where the background pixel is a pixel of a background part in the three-dimensional image.

[0148] For example, the image processing apparatus can set the pixel set corresponding to the first detection object as the background pixel in the three-dimensional image.

[0149] The image processing apparatus classifies pixels in the three-dimensional image according to the background pixel to obtain a non-background pixel in the three-dimensional image.

[0150] For example, the pixels in the three-dimensional image can be classified into two types of pixels, i.e., the non-background pixel and the background pixel.

[0151] The image processing method in this embodiment determines a pixel set corresponding to the first detection object according to the first contour image, sets the pixel set as a background pixel in the three-dimensional image, classifies pixels in the three-dimensional image according to the background pixel to obtain a non-background pixel in the three-dimensional image, and improves the identification accuracy of the non-background pixel in the three-dimensional image.

[0152] In an embodiment according to the present application, as shown in FIG. 11, an image processing method is provided, and the image processing method includes the following steps. Figure 11

[0153] At step 1102, a three-dimensional image containing a first detection object and a second detection object is obtained, the second detection object is used to carry the first detection object, and the three-dimensional image is converted into a plurality of two-dimensional images.​

[0154] Step 1104, contour extraction is performed on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0155] Step 1106, feature extraction is performed on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object.

[0156] In this embodiment, the image processing apparatus performs dimension conversion on the three-dimensional image to obtain a plurality of two-dimensional images, wherein the three-dimensional image is a three-dimensional image containing the first detection object, and the two-dimensional image is a two-dimensional image containing the first detection object.

[0157] Exemplarily, the three-dimensional image can be specifically a three-dimensional CT image of the first detection object acquired by a CT device.

[0158] The image processing apparatus performs contour segmentation processing on the plurality of two-dimensional images respectively to determine a first contour image of the first detection object.

[0159] Exemplarily, the first contour image can be specifically a chest skin contour image of the patient.

[0160] The image processing method in this embodiment improves the accuracy of the contour information in the first contour image, and improves the precision and robustness of the first contour image.

[0161] In an embodiment according to the present application, as shown in Figure 12 An image processing method is provided, which includes:

[0162] Step 1202, a three-dimensional image containing a first detection object and a second detection object is acquired, the second detection object is used to carry the first detection object, and the three-dimensional image is converted into a plurality of two-dimensional images;

[0163] Step 1204, target contour information of the first detection object is determined according to the plurality of two-dimensional images;

[0164] Step 1206, a range threshold of the plurality of two-dimensional images is acquired, and image segmentation processing is performed on the plurality of two-dimensional images according to the range threshold and the target contour information to obtain a first contour image;

[0165] Step 1208, feature extraction is performed on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object.

[0166] In this embodiment, the image processing apparatus performs contour feature extraction on the plurality of two-dimensional images to obtain target contour information of the first detection object, wherein the target contour information is distribution information of a contour of the first detection object.

[0167] Exemplarily, the target contour information can be specifically distribution information of a skin contour.

[0168] The image processing apparatus obtains a range threshold of the plurality of two-dimensional images, and performs image segmentation on the plurality of two-dimensional images respectively according to the range threshold and the target contour information, and further obtains a first contour image of the first detection object, wherein the range threshold is a threshold for image segmentation.

[0169] The image processing method in this embodiment performs contour feature extraction on the plurality of two-dimensional images to obtain target contour information of the first detection object, and then performs image segmentation on the plurality of two-dimensional images respectively according to the range threshold and the target contour information, and further obtains a first contour image of the first detection object, thereby ensuring the information accuracy of the target contour information and further ensuring the image accuracy of the first contour image.

[0170] As shown in Figure 13 , an embodiment of the present application provides an image processing apparatus, which comprises:

[0171] A first processing module 1302 is configured to obtain a three-dimensional image of a first detection object, and convert the three-dimensional image into a plurality of two-dimensional images.

[0172] The first processing module 1302 is further configured to perform contour extraction on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0173] In this embodiment, an image processing apparatus 1300 is provided for segmenting contour information of a first detection object, wherein the first detection object is an object to be detected.

[0174] Exemplarily, the first detection object can be specifically a chest of a patient.

[0175] The first processing module 1302 obtains a three-dimensional image of a first detection object, and performs dimension conversion on the three-dimensional image to obtain a plurality of two-dimensional images, wherein the three-dimensional image is a three-dimensional image containing the first detection object, and the two-dimensional image is a two-dimensional image containing the first detection object.

[0176] Exemplarily, the three-dimensional image can be specifically a three-dimensional CT image of the first detection object acquired by a CT device.

[0177] The first processing module 1302 performs contour segmentation processing on the plurality of two-dimensional images respectively to determine a first contour image of the first detection object.

[0178] Exemplarily, the first contour image can be specifically a chest skin contour image of the patient.

[0179] Exemplarily, the image processing device performs threshold segmentation on the input three-dimensional image, and then applies the prior knowledge that the skin layer contour in the axial position of the chest image is the largest, extracts the largest contour layer by layer, removes the redundant tissues in the non-contour area, and completes the segmentation of the skin. It should be noted that due to the differences in the CT value range of the skin in the CT images of different manufacturers, models or imaging parameters, there is no standard threshold that can accurately segment the skin. Since the threshold segmentation result will be processed by extracting the contour in the subsequent embodiment, the accuracy requirement of the set threshold is reduced, and therefore the upper and lower limit range of the threshold that can be set is relatively large, thereby reducing the dependence on the threshold.

[0180] Exemplarily, as shown in Figure 14 , a three-dimensional CT image is input, preprocessed such as denoising and enhancement, and threshold segmentation is performed by setting the threshold [-200, 100] (the segmentation result is shown in Figure 15 ). The z-axis is taken as the direction, the largest contour in the current layer is searched layer by layer, and the remaining segmentation results are deleted (the segmentation result is shown in Figure 16 ). As shown in Figure 15 , the skin cannot be accurately segmented after threshold segmentation, and the influence of the bed plate and other tissues in the body is removed after the axial position slice searches layer by layer and retains the largest contour. This process can appropriately relax the requirement for the threshold, that is, even if the segmentation result includes other tissues in the body such as the lung, bone and the like, the skin layer can also be accurately retained after the largest contour is extracted.

[0181] It should be noted that the threshold [min, max] can be set to accurately segment the target region in the conventional segmentation, where min is the minimum value and max is the maximum value. In the embodiment, the threshold can be set to [min-n, max+n], where n is a random constant. Generally, the threshold is an empirical value. The embodiment does not depend on the rough segmentation result of the threshold, and there is no specific standard, that is, the threshold does not have to be set to [min, max]. As long as the rough segmentation result includes the skin and does not have too much noise, it can be accurately segmented, and the robustness of the algorithm is also improved. In addition, the skin layer in the axial position of the chest image is the largest contour, and therefore the threshold range can be set to be relatively loose, and it is not a problem to include other partial tissues, which will be removed at last.

[0182] The image processing device 1300 in the embodiment acquires a three-dimensional image of a first detection object, performs dimension conversion on the three-dimensional image to obtain a plurality of two-dimensional images, and then performs contour segmentation processing on the plurality of two-dimensional images respectively to determine a first contour image of the first detection object. The accuracy of the contour information in the first contour image is improved, and the precision and robustness of the first contour image are also improved.

[0183] In an embodiment according to the application, the image processing apparatus 1300 further comprises:

[0184] The first processing module 1302 is further configured to determine target contour information of the first detection object from the plurality of two-dimensional images.

[0185] The first processing module 1302 is further configured to obtain a range threshold of the plurality of two-dimensional images, and perform image segmentation on the plurality of two-dimensional images according to the range threshold and the target contour information to obtain the first contour image.

[0186] The image processing apparatus 1300 in this embodiment extracts contour features from the plurality of two-dimensional images to obtain target contour information of the first detection object, and then performs image segmentation on the plurality of two-dimensional images according to the range threshold and the target contour information to obtain the first contour image of the first detection object, thereby ensuring the information accuracy of the target contour information and the image accuracy of the first contour image.

[0187] In an embodiment according to the application, the image processing apparatus 1300 further comprises:

[0188] The first processing module 1302 is further configured to perform contour detection on the plurality of two-dimensional images to obtain a plurality of contour information.

[0189] The first processing module 1302 is further configured to perform data fusion on the plurality of contour information to obtain target contour information from the plurality of contour information.

[0190] The image processing apparatus 1300 in this embodiment performs contour detection on the plurality of two-dimensional images to obtain a plurality of contour information, and then performs data fusion on the plurality of contour information to convert the plurality of contour information into target contour information, thereby ensuring the information accuracy of the target contour information and the image accuracy of the first contour image.

[0191] In an embodiment according to the application, the image processing apparatus 1300 further comprises:

[0192] The first processing module 1302 is further configured to obtain a target pixel axis of the three-dimensional image, and perform image conversion processing on the three-dimensional image according to the target pixel axis to obtain the plurality of two-dimensional images.

[0193] The image processing apparatus 1300 in this embodiment converts the three-dimensional image into the plurality of two-dimensional images through the target pixel axis, thereby ensuring the image accuracy of the plurality of two-dimensional images and the information accuracy of the first contour image.

[0194] In an embodiment according to the application, the image processing apparatus 1300 further comprises:

[0195] The first processing module 1302 is further configured to acquire an original image of the first detection object, and perform denoising and enhancement processing on the original image to obtain the three-dimensional image.

[0196] The image processing device 1300 in this embodiment acquires an original image of the first detection object, and performs image preprocessing such as denoising and enhancement on the original image to obtain the three-dimensional image, thereby ensuring the image accuracy of the three-dimensional image and further ensuring the image accuracy of the first contour image.

[0197] As shown in Figure 17 , an image processing device is provided in an embodiment of the present application, and the image processing device 1700 includes:

[0198] The second processing module 1702 is configured to acquire a three-dimensional image containing a first detection object and a second detection object, the second detection object being configured to carry the first detection object, and determine a first contour image of the first detection object according to the three-dimensional image.

[0199] The second processing module 1702 is further configured to perform feature extraction on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object.

[0200] In this embodiment, an image processing device 1700 is provided, and specifically, the second processing module 1702 acquires a three-dimensional image, wherein the three-dimensional image is a three-dimensional image containing a first detection object and a second detection object, and the second detection object is configured to carry the first detection object.

[0201] Exemplarily, the first detection object can specifically be a chest cavity of a patient, and the first detection object can specifically be a bed plate carrying the patient.

[0202] The second processing module 1702 performs image segmentation on the three-dimensional image to obtain a first contour image of the first detection object, and then performs image segmentation on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object, wherein the second contour image is a distribution image of the contour of the second detection object.

[0203] Exemplarily, the second contour image can specifically be a contour image of the bed plate in the three-dimensional image, and the bed plate is a bed plate in a CT imaging device.

[0204] Exemplarily, as shown in Figure 18 , a three-dimensional CT image is inputted, preprocessed such as denoising and enhancement, the CT mean value of all non-background pixels outside the skin segmentation scheme in step 3 threshold segmentation result is calculated, and the absolute value of the difference between the CT mean value and the median value of each group of threshold pairs is calculated, and the group with the minimum absolute value is the matching threshold pair, and threshold segmentation is performed using the matching threshold pair (the segmentation result is as shown in Figure 19As shown), the portion located within the skin contour in the segmentation result is removed, and isolated point noise is removed morphologically (segmentation result as shown). Figure 20 (As shown). Through the above steps, threshold pairs for different material scanning beds can be adaptively determined, achieving automatic segmentation. Figure 19 It can be seen that the threshold segmentation result contains a lot of noise besides the CT panel. Because the CT value range of certain CT CT panels overlaps with the CT range of certain human tissues such as bones, the segmentation of redundant tissues after threshold segmentation is unavoidable. Applying the prior knowledge of spatial separation between the CT panel and the human body, areas within and around the skin contour are definitely not CT panel areas. Therefore, all pixel values ​​in the coarse threshold segmentation result of the CT panel whose coordinate positions are within and around the skin contour are set as background, reducing the dependence on the threshold and improving the accuracy of the CT panel segmentation. After removing the portion within the skin contour and morphologically removing isolated point noise and connected components with an area less than 300, as shown... Figure 20 As shown, the bed board is precisely divided.

[0205] In this embodiment, the image processing device 1700 acquires a three-dimensional image, performs image segmentation on the three-dimensional image to obtain a first contour image of the first detection object, and then performs image segmentation on the three-dimensional image based on the first contour image to obtain a second contour image of the second detection object. This improves the accuracy of the contour information in the second contour image and enhances the precision and robustness of the second contour image.

[0206] In one embodiment of this application, the image processing apparatus 1700 further includes:

[0207] The second processing module 1702 is further configured to determine non-background pixels in the three-dimensional image based on the first contour image;

[0208] The second processing module 1702 is also used to obtain a threshold combination and determine the target threshold in the threshold combination based on the non-background pixels. The threshold combination includes the thresholds corresponding to the second detection objects of different materials.

[0209] The second processing module 1702 is also used to perform image processing on the three-dimensional image according to the target threshold to determine the second contour image.

[0210] In this embodiment, the image processing device 1700 determines the non-background pixels in the three-dimensional image based on the first contour image, and then determines the target threshold in the threshold combination based on the non-background pixels, thereby ensuring the accuracy of the target threshold and thus ensuring the accuracy and robustness of the second contour image.

[0211] In one embodiment of this application, the image processing apparatus 1700 further includes:

[0212] The second processing module 1702 is further configured to perform data processing on the non-background pixels to obtain a distribution mean of the non-background pixels.

[0213] The second processing module 1702 is further configured to determine the target threshold in the threshold combination by performing difference operation on the distribution mean and the threshold combination.

[0214] The image processing apparatus 1700 in this embodiment performs mean operation on the non-background pixels to obtain the distribution mean of the non-background pixels, and performs difference operation on the distribution mean and the threshold combination to determine the target threshold in the threshold combination, thereby ensuring the accuracy of the target threshold and the data accuracy of the second contour image.

[0215] In an embodiment of the present application, the image processing apparatus 1700 further includes:

[0216] The second processing module 1702 is further configured to perform image segmentation on the three-dimensional image according to the target threshold to obtain a segmentation result image.

[0217] The second processing module 1702 is further configured to perform noise filtering processing on the segmentation result image to determine the second contour image.

[0218] The image processing apparatus 1700 in this embodiment performs image segmentation on the three-dimensional image according to the target threshold to obtain a segmentation result image, and performs noise filtering and other processing on the segmentation result image to obtain the second contour image, thereby ensuring the image quality of the second contour image.

[0219] In an embodiment of the present application, the image processing apparatus 1700 further includes:

[0220] The second processing module 1702 is further configured to determine a pixel set of the first detection object according to the first contour image.

[0221] The second processing module 1702 is further configured to determine the background pixels in the three-dimensional image according to the pixel set.

[0222] The second processing module 1702 is further configured to perform classification processing on the pixels in the three-dimensional image according to the background pixels to obtain the non-background pixels.

[0223] The image processing apparatus 1700 in this embodiment determines the pixel set corresponding to the first detection object according to the first contour image, sets the pixel set as the background pixels in the three-dimensional image, and performs classification on the pixels in the three-dimensional image according to the background pixels to obtain the non-background pixels in the three-dimensional image, thereby improving the recognition accuracy of the non-background pixels in the three-dimensional image.

[0224] In an embodiment of the present application, the image processing apparatus 1700 further includes:

[0225] The second processing module 1702 is further configured to convert the three-dimensional image into a plurality of two-dimensional images.

[0226] The second processing module 1702 is further configured to perform contour extraction on the plurality of two-dimensional images to obtain a first contour image of the first detection object.

[0227] The image processing apparatus 1700 in this embodiment obtains a three-dimensional image of a first detection object, converts the three-dimensional image in dimension to obtain a plurality of two-dimensional images, and performs contour segmentation processing on the plurality of two-dimensional images respectively to determine a first contour image of the first detection object, thereby improving the accuracy of contour information in the first contour image and improving the precision and robustness of the first contour image.

[0228] In an embodiment of the present application, the image processing apparatus 1700 further includes:

[0229] The second processing module 1702 is further configured to determine target contour information of the first detection object according to the plurality of two-dimensional images.

[0230] The second processing module 1702 is further configured to obtain a range threshold of the plurality of two-dimensional images, and perform image segmentation processing on the plurality of two-dimensional images according to the range threshold and the target contour information to obtain the first contour image.

[0231] The image processing apparatus 1700 in this embodiment extracts contour features of the plurality of two-dimensional images to obtain target contour information of the first detection object, and performs image segmentation on the plurality of two-dimensional images according to the range threshold and the target contour information to obtain the first contour image of the first detection object, thereby ensuring the information accuracy of the target contour information and the image accuracy of the first contour image.

[0232] In an embodiment of the present application, as shown in Figure 21 An image processing apparatus 2100 is provided, which includes a processor 2102 and a memory 2104, and the memory 2104 stores a program or instructions which, when executed by the processor 2102, implement the steps of the image processing method in any of the above technical solutions. Therefore, the image processing apparatus 2100 has all the beneficial effects of the image processing method in any of the above technical solutions, and details are not repeated here.

[0233] In an embodiment of the present application, a readable storage medium is provided, which stores a program that, when executed by a processor, implements the image processing method in any of the above embodiments, and thus has all the beneficial technical effects of the image processing method in any of the above embodiments.

[0234] The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, an optical disk, or the like.

[0235] In an embodiment according to the present application, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the image processing method in any of the above embodiments, and thus have all the beneficial technical effects of the image processing method in any of the above embodiments.

[0236] In an embodiment according to the present application, an imaging device is provided, comprising the image processing apparatus in any of the above embodiments, and / or the readable storage medium in any of the above embodiments, and / or the computer program product in any of the above embodiments, and thus have all the beneficial technical effects of the image processing apparatus in any of the above embodiments, and / or the readable storage medium in any of the above embodiments, and / or the computer program product in any of the above embodiments, which will not be repeated here.

[0237] In an embodiment according to the present application, the imaging device is any of an electronic computed tomography device, a nuclear magnetic resonance imaging device, and an infrared imaging device.

[0238] In an embodiment according to the present application, a surgical robot is provided, which plans a movement trajectory or avoids obstacles based on a processed image, wherein the image is obtained based on the steps of the image processing method in any of the above embodiments, and thus has all the beneficial technical effects of the image processing method in any of the above embodiments, which will not be repeated here.

[0239] It should be noted that, in the claims, the specification and the drawings of the present application, the term "a plurality of" means two or more, unless otherwise specifically defined, and the terms "upper", "lower", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are merely used for the convenience of describing the present application and simplifying the description process, and thus cannot be understood as indicating or implying that the device or element must have the particular orientation, be constructed and operated in a particular orientation, and therefore these descriptions cannot be understood as limiting the present application; the terms "connection", "installation", "fixation", and the like should be understood in a broad sense, for example, "connection" can be fixed connection between objects, can be detachable connection between objects, or integral connection; can be direct connection between objects, or indirect connection between objects through an intermediate medium. For those skilled in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances of the above data.

[0240] In the claims, specification, and drawings of the present disclosure, terms have their plain, ordinary meaning unless otherwise indicated by the context of their use. The terms "comprise", "comprising", "include", "including", "have" and "having" are used interchangeably and mean "including but not limited to". It is further noted that the claims can be drafted to exclude any elements or steps from the disclosure, or to "not include" any elements or steps, or to "not have" any elements or steps. As such these terms are intended to operate as "open" and "inclusive" rather than "closed" or "exclusive".

[0241] The preferred embodiments of the application are described herein above with the understanding that the application can be practiced otherwise than as specifically described.

Claims

1. An image processing method, characterized by, The image processing method comprises: acquiring a three-dimensional image containing a first detection object and a second detection object, the second detection object being used for carrying the first detection object, and determining a first contour image of the first detection object according to the three-dimensional image; performing feature extraction on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object; the feature extraction on the three-dimensional image according to the first contour image to obtain the second contour image of the second detection object specifically comprises: determining non-background pixels in the three-dimensional image according to the first contour image; acquiring a threshold combination, determining a target threshold in the threshold combination according to the non-background pixels, the threshold combination comprising thresholds corresponding to the second detection object of different materials; performing image processing on the three-dimensional image according to the target threshold to determine the second contour image.

2. The image processing method of claim 1, wherein, the determination of the target threshold in the threshold combination according to the non-background pixels specifically comprises: performing data processing on the non-background pixels to obtain a distribution mean of the non-background pixels; determining the target threshold in the threshold combination through difference operation on the distribution mean and the threshold combination.

3. The image processing method of claim 1, wherein, the image processing on the three-dimensional image according to the target threshold to determine the second contour image specifically comprises: performing image segmentation on the three-dimensional image according to the target threshold to obtain a segmentation result image; performing noise filtering processing on the segmentation result image to determine the second contour image.

4. The image processing method of claim 1, wherein, the determination of the non-background pixels in the three-dimensional image according to the first contour image specifically comprises: determining a pixel set of the first detection object according to the first contour image; determining background pixels in the three-dimensional image according to the pixel set; performing classification processing on pixels in the three-dimensional image according to the background pixels to obtain the non-background pixels.

5. The image processing method of any one of claims 1 to 3, characterized in that, the determination of the first contour image of the first detection object according to the three-dimensional image specifically comprises: converting the three-dimensional image into a plurality of two-dimensional images; performing contour extraction on the plurality of two-dimensional images to obtain the first contour image of the first detection object.

6. The image processing method of claim 5, wherein, the contour extraction on the plurality of two-dimensional images to obtain the first contour image of the first detection object specifically comprises: determining target contour information of the first detection object according to the plurality of two-dimensional images; acquiring a range threshold of the plurality of two-dimensional images, and performing image segmentation processing on the plurality of two-dimensional images according to the range threshold and the target contour information to obtain the first contour image.

7. An image processing apparatus characterized by comprising: The image processing device comprises: a second processing module configured to acquire a three-dimensional image containing a first detection object and a second detection object, the second detection object being used for carrying the first detection object, and determine a first contour image of the first detection object according to the three-dimensional image; the second processing module is further configured to perform feature extraction on the three-dimensional image according to the first contour image to obtain a second contour image of the second detection object; The second processing module is further configured to determine non-background pixels in the three-dimensional image according to the first contour image; The second processing module is further configured to obtain a threshold combination, determine a target threshold in the threshold combination according to the non-background pixels, and the threshold combination includes thresholds corresponding to second detection objects of different materials; The second processing module is further configured to perform image processing on the three-dimensional image according to the target threshold, and determine a second contour image.

8. A readable storage medium, characterized by, The readable storage medium stores programs or instructions, and the programs or instructions are executed by the processor to implement the steps of the image processing method according to any one of claims 1 to 6.

9. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to implement the steps of the image processing method according to any one of claims 1 to 6.

10. An image forming apparatus characterized by comprising: The imaging device is any one of the following: an electronic computed tomography device, a nuclear magnetic resonance imaging device, and an infrared imaging device, and the imaging device includes: The image processing apparatus according to claim 7; and / or The readable storage medium according to claim 8; and / or The computer program product according to claim 9.

11. A surgical robot, characterized by The surgical robot plans a movement trajectory or performs obstacle avoidance based on the processed image, and the image is obtained based on the steps of the image processing method according to any one of claims 1 to 6.

Images