Image processing method and device, radiotherapy system

Abstract

The application discloses an image processing method and device and a radiotherapy system, and belongs to the technical field of images. The method comprises the following steps: a first processing mode is used to process a DRR image to be processed, and an updated DRR image is obtained. The first processing mode is an inverse processing mode of a second processing mode. The second processing mode is used to process a first image of a target object collected by an imaging device in a radiotherapy device, and a second image can be obtained. The similarity between the second image and the blur degree of the DRR image of the target object is greater than a similarity threshold. The application can solve the problem of low accuracy of image registration, and can improve the definition of the DRR image, thereby improving the accuracy of image registration.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image technology, in particular to an image processing method and device, and a radiotherapy system. BACKGROUND

[0002] With the rapid development of computers and imaging technology, radiotherapy technology is also constantly mature, which promotes the rapid development of real-time image guided radiotherapy (IGRT) technology. Real-time IGRT technology can achieve precise radiotherapy of tumors and improve the success rate of tumor radiotherapy.

[0003] Image registration is an important part of real-time IGRT technology, which can be used for accurate positioning of tumors. Generally, image registration refers to registration of an image collected by an imaging device in a radiotherapy device with a digitally reconstructed radiography (DRR) image generated by simulation.

[0004] However, the accuracy of image registration depends on the clarity of the DRR image, but the clarity of the DRR image is currently low, resulting in low accuracy of image registration. SUMMARY

[0005] The present application provides an image processing method and device, and a radiotherapy system, which can solve the problem of low accuracy of image registration. The technical solution is as follows.

[0006] In a first aspect, an image processing method is provided, which includes:

[0007] obtaining a first processing mode, wherein the first processing mode is an inverse processing mode of a second processing mode, and the second processing mode is a convolution processing mode; processing a first image of a target object collected by an imaging device in a radiotherapy device using the second processing mode to obtain a second image; and the similarity of the blurring degree of the second image and a DRR image of the target object is greater than a similarity threshold value;

[0008] obtaining a DRR image to be processed;

[0009] processing the DRR image to be processed using the first processing mode to obtain an updated DRR image.

[0010] Optionally, the obtaining of the first processing mode includes:

[0011] display a plurality of blurred images corresponding to a plurality of deformation processing modes; wherein the blurred images are obtained by processing the first image using the corresponding deformation processing mode, and the deformation processing mode is obtained by adjusting a value of at least one processing parameter of a third processing mode, and the third processing mode and the deformation processing mode are both convolution processing modes;

[0012] in response to a selection instruction for a target blurred image in the plurality of blurred images, determining that the deformation processing mode corresponding to the target blurred image is the second processing mode;

[0013] determining that the inverse processing mode of the second processing mode is the first processing mode.

[0014] Optionally, the obtaining the first processing mode further comprises:

[0015] when displaying any blurred image in the plurality of blurred images, displaying the DDR image of the target object.

[0016] Optionally, the obtaining the first processing mode further comprises:

[0017] when displaying any blurred image in the plurality of blurred images, displaying reference information of the any blurred image;

[0018] wherein the reference information of the any blurred image is used to indicate the similarity of the blurred degree of the any blurred image and the DRR image of the target object.

[0019] Optionally, the reference information of the any blurred image comprises at least one of the following:

[0020] the mutual information of the any blurred image and the DRR image of the target object;

[0021] the root mean square error of the any blurred image and the DRR image of the target object;

[0022] the peak signal-to-noise ratio of the any blurred image and the DRR image of the target object;

[0023] the cross entropy of the any blurred image and the DRR image of the target object;

[0024] the structural similarity of the any blurred image and the DRR image of the target object;

[0025] the gray level histogram of the any blurred image and the gray level histogram of the DRR image of the target object;

[0026] and the pixel surface of the any blurred image and the pixel surface of the DRR image of the target object.

[0027] Optionally, the third processing mode includes a first processing parameter and a second processing parameter; and the displaying of the plurality of blurred images each corresponding to one of the plurality of first deformation processing modes includes:

[0028] displaying a plurality of first blurred images each corresponding to one of a plurality of first deformation processing modes, the first deformation processing mode being obtained by changing a value of the first processing parameter in the third processing mode;

[0029] in response to a selection instruction for any one of the plurality of first blurred images, obtaining a plurality of second deformation processing modes corresponding to the any one of the first blurred images; wherein for the first deformation processing mode and the second deformation processing mode corresponding to the any one of the first blurred images, the second deformation processing mode is obtained by changing a value of the second processing parameter in the first deformation processing mode;

[0030] displaying a second blurred image corresponding to each of the second deformation processing modes;

[0031] wherein the selection instruction for the target blurred image of the plurality of blurred images is a selection instruction for any one of the displayed second blurred images.

[0032] Optionally, the method further includes:

[0033] updating the first processing mode.

[0034] Optionally, the updating of the first processing mode includes:

[0035] updating the first processing mode according to a time factor, the time factor being used to reflect a change of the first processing mode over time.

[0036] Optionally, the method further includes:

[0037] updating the first processing mode a plurality of times;

[0038] determining the time factor according to the first processing mode after each of the plurality of times of updating.

[0039] Optionally, the processing of the DRR image to be processed using the first processing mode to obtain an updated DRR image includes:

[0040] obtaining a horizontal gradient amplitude and a vertical gradient amplitude; wherein the horizontal gradient amplitude is a gradient amplitude of the DRR image to be processed in a horizontal direction in an image coordinate system, and the vertical gradient amplitude is a gradient amplitude of the DRR image to be processed in a vertical direction in the image coordinate system;

[0041] multiply the horizontal gradient amplitude by a first weight to obtain an updated horizontal gradient amplitude, the first weight being less than 1;

[0042] multiply the vertical gradient amplitude by a second weight to obtain an updated vertical gradient amplitude, the second weight being less than 1;

[0043] process the DRR image to be processed by using the first processing mode according to the updated horizontal gradient amplitude and the updated vertical gradient amplitude, to obtain an updated DRR image.

[0044] Optionally, the second weight is less than the first weight.

[0045] In a second aspect, an image processing apparatus is provided, which comprises:

[0046] a first obtaining module configured to obtain a first processing mode; wherein the first processing mode is an inverse processing mode of a second processing mode, and the second processing mode is a convolution processing mode; the second processing mode is used to process a first image of a target object collected by an imaging device in a radiotherapy device, and a second image can be obtained; a similarity degree between the second image and a DRR image of the target object is greater than a similarity threshold;

[0047] a second obtaining module configured to obtain a DRR image to be processed;

[0048] a processing module configured to process the DRR image to be processed by using the first processing mode, to obtain an updated DRR image.

[0049] Optionally, the first obtaining module is configured to:

[0050] display a plurality of blur images corresponding to a plurality of deformation processing modes; wherein the blur image is obtained by processing the first image by using the corresponding deformation processing mode, and the deformation processing mode is obtained by changing a value of at least one processing parameter in a third processing mode; the third processing mode and the deformation processing mode are both convolution processing modes;

[0051] in response to a selection instruction for a target blur image in the plurality of blur images, determine that the deformation processing mode corresponding to the target blur image is the second processing mode;

[0052] determine that the inverse processing mode of the second processing mode is the first processing mode.

[0053] Optionally, the first obtaining module is further configured to:

[0054] displaying a DDR image of the target object while displaying any one of the plurality of blurred images.

[0055] Optionally, the first obtaining module is further configured to:

[0056] displaying reference information of any one of the plurality of blurred images while displaying the any one of the plurality of blurred images;

[0057] The reference information of the any one of the plurality of blurred images is used to indicate a similarity of a blur degree of the any one of the plurality of blurred images and a DRR image of the target object.

[0058] Optionally, the reference information of the any one of the plurality of blurred images comprises at least one of:

[0059] a mutual information of the any one of the plurality of blurred images and the DRR image of the target object;

[0060] a root mean square error of the any one of the plurality of blurred images and the DRR image of the target object;

[0061] a peak signal to noise ratio of the any one of the plurality of blurred images and the DRR image of the target object;

[0062] a cross entropy of the any one of the plurality of blurred images and the DRR image of the target object;

[0063] a structural similarity of the any one of the plurality of blurred images and the DRR image of the target object;

[0064] a gray scale histogram of the any one of the plurality of blurred images and a gray scale histogram of the DRR image of the target object;

[0065] and a pixel surface of the any one of the plurality of blurred images and a pixel surface of the DRR image of the target object.

[0066] Optionally, the third processing mode comprises a first processing parameter and a second processing parameter; and the first obtaining module is configured to:

[0067] displaying a plurality of first blurred images corresponding to a plurality of first deformation processing modes, the first deformation processing mode being a processing mode obtained by changing a value of the first processing parameter in the third processing mode;

[0068] in response to a selection instruction for any one of the plurality of first blurred images, obtaining a plurality of second deformation processing modes corresponding to the any one of the plurality of first blurred images; wherein for the first deformation processing mode and the second deformation processing mode corresponding to the any one of the plurality of first blurred images, the second deformation processing mode is a processing mode obtained by changing a value of the second processing parameter in the first deformation processing mode;

[0069] display a second blurred image corresponding to each of the second deformation processing modes;

[0070] The selection instruction for the target blurred image in the plurality of blurred images is a selection instruction for any of the displayed second blurred images.

[0071] Optionally, the image processing apparatus further comprises:

[0072] The first updating module is configured to perform first updating on the first processing mode.

[0073] Optionally, the first updating module is configured to:

[0074] The first processing mode is updated according to a time factor, and the time factor is used to reflect a change of the first processing mode over time.

[0075] Optionally, the image processing apparatus further comprises:

[0076] The second updating module is configured to perform multiple second updating on the first processing mode.

[0077] The determining module is configured to determine the time factor according to the first processing mode after each of the multiple second updating.

[0078] Optionally, the processing module is configured to:

[0079] Obtain a horizontal gradient amplitude and a vertical gradient amplitude, wherein the horizontal gradient amplitude is a gradient amplitude of the DRR image to be processed in a horizontal direction of an image coordinate system, and the vertical gradient amplitude is a gradient amplitude of the DRR image to be processed in a vertical direction of the image coordinate system.

[0080] Multiply the horizontal gradient amplitude by a first weight to obtain an updated horizontal gradient amplitude, and the first weight is less than 1.

[0081] Multiply the vertical gradient amplitude by a second weight to obtain an updated vertical gradient amplitude, and the second weight is less than 1.

[0082] Process the DRR image to be processed by using the first processing mode according to the updated horizontal gradient amplitude and the updated vertical gradient amplitude to obtain the updated DRR image.

[0083] Optionally, the second weight is less than the first weight.

[0084] In a third aspect, an image processing apparatus is provided, comprising a processor and a memory, and the memory stores a program.

[0085] The processor is configured to invoke a program stored in the memory, so that the communication device executes the image processing method according to any one of the first aspect.

[0086] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program.

[0087] The computer program, when running on a computer, causes the computer to execute the image processing method according to any one of the first aspect.

[0088] In a fifth aspect, a radiotherapy system is provided, and the radiotherapy system includes a radiotherapy device having an imaging device, and the image processing device according to any one of the third aspect (or the image processing device according to any one of the fourth aspect).

[0089] The image processing method provided in the embodiments of the present application can process the DRR image by using the first processing manner to obtain an updated DRR image. Moreover, the first image of the target object collected by the imaging device of the radiotherapy device is processed by using the second processing manner (the inverse processing manner of the first processing manner) to obtain a second image, and the second image has a high similarity in blur degree with the DRR image of the target object. Therefore, the image obtained by processing the DRR image by using the first processing manner has a high similarity in blur degree with the image collected by the imaging device. Since the image collected by the imaging device has a low blur degree and a high definition, the image obtained by processing the DRR image by using the first processing manner also has a low blur degree and a high definition.

[0090] The updated DRR image obtained by the image processing device in the embodiments of the present application can be used for registration with the image collected by the imaging device. Since the updated DRR has a high definition, the accuracy of registration according to the updated DRR image and the image collected by the imaging device is high. BRIEF DESCRIPTION OF DRAWINGS

[0091] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0092] Figure 1 A flowchart of an image processing method provided in the embodiments of the present application is provided.

[0093] Figure 2 A flowchart of an image processing device provided in the embodiments of the present application is provided.

[0094] Figure 3 A display interface schematic diagram of an image processing device provided by an embodiment of the present application is shown in FIG. 1.

[0095] Figure 4 A flowchart of the image processing device provided by an embodiment of the present application displaying a plurality of blurred images corresponding to a plurality of deformation processing modes is shown in FIG. 2.

[0096] Figure 5 A structure schematic diagram of an image processing device provided by an embodiment of the present application is shown in FIG. 3.

[0097] Figure 6 A structure schematic diagram of another image processing device provided by an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0098] In order to make the principles, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0099] Real-time IGRT technology can achieve precise radiotherapy of tumors and improve the success rate of tumor radiotherapy. Image registration is a relatively important part of real-time IGRT technology and can be used for accurate positioning of tumors.

[0100] For example, assuming that the object to be radiotherapied is a target object, before image registration, a DRR image of the target object can be simulated and generated according to a three-dimensional CT image of the target object. In addition, the target object needs to be placed on a radiotherapy bed of a radiotherapy device, and an image of the target object is acquired by an imaging device in the radiotherapy device, such as CBCT. Then, the DRR image and the image acquired by the imaging device can be registered.

[0101] However, the accuracy of image registration depends on the clarity of the DRR image and the image acquired by the imaging device. At present, although the clarity of the image acquired by the imaging device is high, the clarity of the DRR image is low (for example, the edges of the DRR image are blurred), which leads to low accuracy of image registration.

[0102] The embodiments of the present application provide an image processing method, which can process a DRR image to improve the clarity of the DRR image, and the accuracy of image registration based on the processed DRR image and the image acquired by the imaging device is high.

[0103] For example, Figure 1A flowchart of an image processing method is provided for an embodiment of the present application. The image processing method can be executed by an image processing device in a radiotherapy device, which also includes other devices, such as an imaging device, etc. As shown in FIG. 18, the method includes the following steps. Figure 1

[0104] In S101, a first processing mode is acquired. The first processing mode is an inverse processing mode of a second processing mode, and the second processing mode is a convolution processing mode. The first image of the target object collected by the imaging device in the radiotherapy device is processed using the second processing mode, and a second image can be obtained. The similarity of the blur degree of the second image to the DRR image of the target object is greater than a similarity threshold.

[0105] The image processing device can acquire the first processing mode in S101 by reading the first processing mode locally or remotely.

[0106] The first processing mode is an inverse processing mode of the second processing mode. The second processing mode has a certain function: the first image of the target object collected by the imaging device in the radiotherapy device is processed using the second processing mode, and a second image can be obtained. The similarity of the blur degree of the second image to the DRR image of the target object is greater than a similarity threshold.

[0107] The second image has a high similarity (e.g., greater than a similarity threshold) to the blur degree of the DRR image of the target object simulated. Generally, the clarity of the image collected by the imaging device is greater than the clarity of the DRR image, and thus the second processing mode can be regarded as a processing mode for blurring the image.

[0108] For example, the second processing mode can be represented as: wherein x represents the image to be processed (e.g., the first image described above), y represents the processed image (e.g., the second image described above), h represents the convolution kernel, represents convolution, n = 0, and the second processing mode can be represented as When the first image is processed using the second processing mode, the first image can be converted into a frequency domain image to be processed first, and then the frequency domain image is substituted into In the equivalent formula in the image frequency domain Y = H * X + N, the obtained image is called the processed frequency domain image. Wherein X represents the frequency domain image to be processed, Y represents the processed frequency domain image, H is the frequency domain representation of the convolution kernel h described above, * represents multiplication, and N = 0, The equivalent formula in the image frequency domain can be represented as Y = H * X. Finally, the processed frequency domain image is converted into a spatial domain image, and the second image can be obtained.

[0109] ​The first processing manner is an inverse processing manner of the second processing manner. When a certain image is processed by using the first processing manner, the certain image can be converted into a frequency domain image, and then the frequency domain image is substituted into an inverse function of Y=H*X to obtain a processed certain image, and then the processed certain image is converted into a spatial domain image. The spatial domain image is the image obtained by processing the certain image by using the first processing manner.

[0110] In the embodiments of the present application, the imaging device can be any device capable of acquiring images. For example, the imaging device is any one of an X-ray imaging device, a CT imaging device, a CBCT imaging device, an MR imaging device, a positron emission computed tomography (PET-CT) imaging device, or the imaging device comprises at least one of the devices. The imaging device can be a kilovoltage (KV) level imaging device, and the image acquired by the imaging device can be referred to as a KV image.

[0111] In S102, a DRR image to be processed is acquired.

[0112] After the first processing manner is acquired, the DRR image can be processed by using the first processing manner to improve the clarity of the DRR image. The DRR image to be processed in S102 can be a DRR image used for registration by a radiotherapy device, and the DRR image can be generated according to a three-dimensional CT image.

[0113] In S103, the DRR image to be processed is processed by using the first processing manner to obtain an updated DRR image.

[0114] The second processing manner is a processing manner for blurring an image, and therefore, the first processing manner is a processing manner for sharpening an image.

[0115] Since the clarity of the DRR image is low, after the DRR image is processed by using the first processing manner to improve the clarity of the DRR image, a DRR image with improved clarity can be obtained. The DRR image with improved clarity can be used as an updated DRR image.

[0116] For example, when the second processing manner is the convolution processing manner described above, the first processing manner is an inverse convolution processing manner, and the DRR image to be processed is processed by using the first processing manner to obtain an inverse convolution processed DRR image. The inverse convolution processed DRR image is the DRR image with improved clarity.

[0117] The image processing method provided in the embodiments of the present application can process the DRR image by using a first processing manner to obtain an updated DRR image. In addition, the second image can be obtained by using a second processing manner (the inverse processing manner of the first processing manner) and the first image of the target object collected by the imaging device in the radiotherapy device, and the second image has a high similarity in blur degree with the DRR image of the target object. Therefore, the image obtained by processing the DRR image by using the first processing manner has a high similarity in blur degree with the image collected by the imaging device. Since the image collected by the imaging device has a low blur degree and a high definition, the image obtained by processing the DRR image by using the first processing manner also has a low blur degree and a high definition.

[0118] The updated DRR image obtained by the image processing device in the embodiments of the present application can be used for registration with the image collected by the imaging device. Since the updated DRR has a high definition, the registration accuracy of the updated DRR image and the image collected by the imaging device is high.

[0119] It should be noted that the registration in the embodiments of the present application can be automatic registration or manual registration, and the embodiments of the present application do not limit the registration.

[0120] In the embodiments of the present application, the image processing device can process the DRR image used for registration by using the image processing method shown in Figure 1 to obtain an updated DRR image before each registration.

[0121] Optionally, Figure 1 The first processing manner in the image processing method shown in the embodiments of the present application can be a processing manner calculated by the image processing device. In this case, the process of obtaining the first processing manner by the image processing device can further include the process of determining the second processing manner by the image processing device and obtaining the first processing manner according to the second processing manner.

[0122] For example, as shown in Figure 2 the process of obtaining the first processing manner by the image processing device in S101 can include the following steps.

[0123] S1011, obtaining a plurality of deformation processing manners according to a third processing manner.

[0124] The deformation processing manner is a processing manner obtained by changing the value of at least one processing parameter in the third processing manner, and the third processing manner and the deformation processing manner are both convolution processing manners.

[0125] For example, the parameters of the third processing manner include: the size of the convolution kernel and the variance of the convolution kernel. The image processing apparatus can adjust the value of at least one of the size of the convolution kernel and the variance of the convolution kernel to obtain the deformation processing manner.

[0126] S1012, display a plurality of blur images corresponding to a plurality of deformation processing manners, wherein the blur images are obtained by processing the first image using the corresponding deformation processing manner.

[0127] S1013, in response to a selection instruction for a target blur image in the plurality of blur images, determine that the deformation processing manner corresponding to the target blur image is the second processing manner.

[0128] It can be seen that the image processing apparatus can process the first image using a plurality of deformation processing manners to obtain a plurality of blur images. After displaying these blur images, the second processing manner in the plurality of deformation processing manners can be determined according to the target blur image selected by the user from the blur images, which has a blur degree similar to the DRR image of the target object. In this process, the user needs to compare the blur degree of the plurality of blur images displayed by the image processing apparatus with the DRR image of the target object to filter out the target blur image in the blur images, which has the blur degree most similar to the DRR image.

[0129] For example, please refer to Figure 3 , assuming that the plurality of blur images include: blur images A, B and C, and the correspondence between the three blur images and the plurality of deformation processing manners is shown in Table 1. The image processing apparatus can display the three blur images, and the user can select (e.g., click) the blur image in the three blur images that has the blur degree most similar to the DRR image of the target object. If the user clicks the blur image B, the image processing apparatus can receive the selection instruction for the blur image B, and can determine that the deformation processing manner 2 corresponding to the blur image B is the second processing manner in response to the selection instruction.

[0130] Table 1

[0131] Blurred image Deformation processing mode A 1 B 2 C 3

[0132] S1014, determine that the inverse processing manner of the second processing manner is the first processing manner.

[0133] Optionally, in order to facilitate the user to compare the blur image with the DRR image of the target object, the image processing apparatus can also display the DRR image of the target object when displaying any blur image in the plurality of blur images. For example, please continue to refer to Figure 3 , the image processing apparatus can also display the DRR image of the target object when displaying the blur images A, B and C.

[0134] Optionally, in order to facilitate the user to compare the blurred image with the DRR image of the target object, the image processing apparatus can display reference information of the blurred image when displaying any one of the plurality of blurred images. The reference information of the blurred image is used to indicate the similarity between the blurred image and the DRR image of the target object.

[0135] For example, the reference information of any one of the blurred images includes at least one of the following: mutual information between the any one of the blurred images and the DRR image of the target object; root mean square error between the any one of the blurred images and the DRR image of the target object; peak signal-to-noise ratio between the any one of the blurred images and the DRR image of the target object; cross entropy between the any one of the blurred images and the DRR image of the target object; structural similarity between the any one of the blurred images and the DRR image of the target object; gray histogram of the any one of the blurred images and gray histogram of the DRR image of the target object; and, pixel parabolic line of the any one of the blurred images and pixel parabolic line of the DRR image of the target object.

[0136] It should be noted that the pixel parabolic line of the image is used to indicate the change of the value of the qth row of pixels in the image, the pixel parabolic line of the any one of the blurred images is used to indicate the change of the value of the qth row of pixels in the any one of the blurred images, and the pixel parabolic line of the DRR image of the target object is used to indicate the change of the value of the qth row of pixels in the DRR image of the target object. q can be any integer greater than or equal to 1.

[0137] Optionally, when the image processing apparatus displays at least two of the plurality of blurred images at the same time, the image processing apparatus can display the pixel parabolic lines of the at least two of the plurality of blurred images and the pixel parabolic line of the DRR image of the target object in the same coordinate system, so as to facilitate the user to compare the pixel parabolic lines of the images.

[0138] For example, the image processing apparatus displays the blurred images A, B and C at the same time, and the image processing apparatus can display the pixel parabolic lines of the blurred images A, B and C and the pixel parabolic line of the DRR image of the target object in the same coordinate system (the pixel parabolic lines are not shown in FIG. 8). Figure 3

[0139] Optionally, the image processing apparatus can also display the first image of the target object, i.e., the original image of the plurality of blurred images, when displaying any one of the plurality of blurred images. The image processing apparatus can also display reference information of the first image when displaying the reference information of any one of the plurality of blurred images. The reference information of the first image is used to indicate the similarity between the first image and the DRR image of the target object. The explanation of the reference information of the first image can refer to the explanation of the reference information of the blurred image, which will not be repeated here. ​

[0140] For example, please continue to refer to Figure 3 , when displaying the blurred images A, B and C, the image processing apparatus can also display the first image. Further, the image processing apparatus can also display the pixel epipolar lines of the first image, such as displaying the pixel epipolar lines of the blurred images, the pixel epipolar lines of the DRR image of the target object and the pixel epipolar lines of the first image in the same coordinate system. Figure 3 These pixel epipolar lines are not shown in the figure.

[0141] Optionally, when displaying any one of the plurality of blurred images, the image processing apparatus can also display the processing parameters of the deformation processing mode corresponding to the blurred image.

[0142] For example, please continue to refer to Figure 3 , the image processing apparatus can display the processing parameters of the deformation processing mode corresponding to the blurred images A, B and C respectively. The processing parameters of the deformation processing mode corresponding to the blurred image A include: P (representing the size of the convolution kernel) = 7, Q (representing the variance of the convolution kernel) = 5; the processing parameters of the deformation processing mode corresponding to the blurred image C include: P = 9, Q = 3, and the processing parameters of the deformation processing mode corresponding to the blurred image C include: P = 11, Q = 2.5.

[0143] In the embodiments of the present application, the image processing apparatus displays the plurality of blurred images in various ways, and the above content takes the image processing apparatus simultaneously displaying the plurality of blurred images as an example. Alternatively, the image processing apparatus can also display the plurality of blurred images in other ways.

[0144] For example, the process of the image processing apparatus displaying the plurality of blurred images will be illustrated in the case where the third processing mode includes the first processing parameter and the second processing parameter. As shown in Figure 4 , the process of the image processing apparatus displaying the plurality of blurred images corresponding to the plurality of deformation processing modes can include the following steps.

[0145] S10121, obtaining a plurality of first deformation processing modes according to the third processing mode.

[0146] The first deformation processing mode is obtained by changing the value of the first processing parameter in the third processing mode, and the values of the second processing parameters in the plurality of first deformation processing modes are all the value of the second processing parameter in the third processing mode. Assuming that the first processing parameter is the size of the convolution kernel, the image processing apparatus can set the size of the convolution kernel in the third processing mode to a plurality of different size values to obtain a plurality of first deformation processing modes.

[0147] The image processing apparatus can select a value of the first processing parameter in a first numerical range. For example, when the first processing parameter is a convolution kernel size, the first numerical range can be [5, 15]. The plurality of first deformation processing manners can include 11 first deformation processing manners, and the 11 first deformation processing manners include 11 values of the first processing parameter, which are 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, and 15 respectively.

[0148] S10122, respectively process the first image by using the plurality of first deformation processing manners to obtain a plurality of first blurred images corresponding to the plurality of first deformation processing manners one by one.

[0149] S10123, display the plurality of first blurred images.

[0150] The display process of the plurality of first blurred images by the image processing apparatus can refer to the display process of the plurality of blurred images in Figure 3 The image processing apparatus can display the plurality of blurred images one by one, and details are not described herein.

[0151] S10124, in response to a selection instruction for any image in the plurality of first blurred images, obtain a plurality of second deformation processing manners corresponding to the any image; wherein for the first deformation processing manner and the second deformation processing manner corresponding to the any image, the second deformation processing manner is a processing manner obtained by changing a value of a second processing parameter in the first deformation processing manner.

[0152] It should be noted that after the image processing apparatus displays the plurality of first blurred images, the user needs to compare the blurring degrees of the plurality of first blurred images and the DRR image of the target object to screen at least one first blurred image in the plurality of first blurred images that is similar to the DRR image in terms of the blurring degree. The user can also click any image in the at least one first blurred image to make the image processing apparatus receive a selection instruction for the any image.

[0153] The image processing apparatus can change the value of the second processing parameter in the first deformation processing manner corresponding to the any image in response to the selection instruction to obtain a plurality of second deformation processing manners corresponding to the any image. The values of the first processing parameter in the plurality of second deformation processing manners are all the value of the first processing parameter in the first deformation processing manner corresponding to the any image.

[0154] For example, assuming that the first processing parameter is a convolution kernel size and the second processing parameter is a convolution kernel variance, the image processing apparatus can determine a first deformation processing mode corresponding to the first blurred image to which the selection instruction is directed, and set the convolution kernel variance in the first deformation processing mode to a plurality of different variance values respectively, to obtain a plurality of second deformation processing modes corresponding to the first blurred image.

[0155] The image processing apparatus can select a value of the changed second processing parameter within a second numerical range. For example, when the second processing parameter is a convolution kernel variance, the second numerical range can be [1, 5]. The plurality of second deformation processing modes corresponding to a certain image can include 9 second deformation processing modes, which include 9 values of the second processing parameter, i.e., 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, and 5.

[0156] It should be noted that if the image processing apparatus receives a selection instruction directed to at least two first blurred images, the image processing apparatus will obtain at least two groups of second deformation processing modes corresponding to the at least two first blurred images one by one, and each group of second deformation processing modes includes a plurality of second deformation processing modes.

[0157] S10125, for each obtained second deformation processing mode, obtaining a second blurred image according to the second deformation processing mode and the first image.

[0158] After obtaining at least one group of second deformation processing modes, the image processing apparatus can process the first image by using each second deformation processing mode to obtain a second blurred image corresponding to the second deformation processing mode.

[0159] S10126, displaying the obtained second blurred image.

[0160] The image processing apparatus will obtain a plurality of second blurred images, and the image processing apparatus can display the plurality of second blurred images according to the display process of the plurality of blurred images in the method 1000, or the image processing apparatus can display the plurality of second blurred images in sequence, which will not be described herein. Figure 3

[0161] Regardless of how the image processing apparatus displays the plurality of second blurred images, the user needs to select a second blurred image with a blur degree most similar to the blur degree of the DRR image of the target object from the plurality of second blurred images, and click the second blurred image, so that the image processing apparatus receives a selection instruction directed to the second blurred image. The selection instruction is also the above-mentioned selection instruction directed to the target blurred image.

[0162] ​The image processing apparatus can determine, in response to the selection instruction, that the second blurred image is a target blurred image, and determine that the second deformation processing mode corresponding to the second blurred image is a second processing mode. The second blurred image is processed on the first image using the corresponding second deformation processing mode.

[0163] In the embodiments of the present application, the process of obtaining the second processing mode according to the third processing mode is exemplified by taking the third processing mode including the first processing parameter and the second processing parameter as an example. In this process, the image processing apparatus determines the value of the first processing parameter through S10121 to S10124, and determines a value of the second processing parameter through S10124 to S10126 and S1013, thereby obtaining the second processing mode. It can be seen that the image processing apparatus determines the values of the first processing parameter and the second processing parameter in the third processing mode in sequence, thereby obtaining the second processing mode.

[0164] Alternatively, the third processing mode can further include other processing parameters. In this case, the image processing apparatus can determine the values of the plurality of processing parameters in the third processing mode in sequence, thereby obtaining the second processing mode.

[0165] Alternatively, on the basis of the foregoing embodiments, the method provided by the embodiments of the present application can further include that the image processing apparatus performs first updating on the first processing mode. Then, the image processing apparatus can process the DRR image to be processed using the first updated first processing mode, so as to improve the resolution of the DRR image.

[0166] The manner in which the image processing apparatus performs first updating on the first processing mode is various, and the embodiments of the present application do not limit it.

[0167] For example, when performing first updating on the first processing mode, the image processing apparatus can refer to the manner of obtaining the first processing mode to reacquire a new first processing mode, and update the old first processing mode with the new first processing mode. For example, the image processing apparatus updates the parameters in the original second processing mode to obtain a new second processing mode, and determines that the inverse processing mode of the new second processing mode is a new first processing mode. The second processing mode is a convolution processing mode, and updating the parameters of the second processing mode is also called updating the spread of the second processing mode.

[0168] For example, when the first processing mode is updated for the first time, the image processing apparatus can process the existing first processing mode according to a time factor to obtain a new first processing mode, and update the old first processing mode with the new first processing mode. The time factor is used to reflect the change of the first processing mode over time. When the image processing apparatus processes the first processing mode according to the time factor, the time factor can be multiplied by the existing parameters in the first processing mode to obtain the updated first processing mode.

[0169] For example, the first processing mode is a deconvolution processing mode, and the image processing apparatus can multiply the convolution kernel in the first processing mode by a time factor to update the convolution kernel, thereby obtaining the updated first processing mode.

[0170] The time factor can be determined by the image processing apparatus according to the first processing mode after multiple second updates (e.g., the new first processing mode is obtained by referring to the above-mentioned method for obtaining the first processing mode) of the first processing mode. Of course, the time factor can also be obtained in other ways, such as being input by the user to the image processing apparatus, which is not limited in the present embodiment.

[0171] The image processing apparatus can periodically update the first processing mode (e.g., the first update and / or the second update described above), such as updating the first processing mode once a year (or once every half year).

[0172] It should be noted that as the working time of the imaging apparatus increases, the clarity of the images collected by the imaging apparatus will gradually decrease. For example, when the imaging apparatus is a CT device, as the use time of the CT device accumulates, the service life of the CT device gradually decreases, and the clarity of the images collected by the CT device gradually decreases. In the present embodiment, the first processing mode can be updated, so that the first processing mode can be adapted to the current imaging apparatus. The first image of the target object collected by the imaging apparatus in the radiotherapy device is processed by using the current first processing mode, and the second image is obtained. The similarity between the second image and the blur degree of the DRR image of the target object is greater than the similarity threshold.

[0173] In this way, the image obtained by processing the DRR image using the first processing mode is always similar to the blur degree of the image collected by the imaging apparatus, and the clarity of the image obtained by processing the DRR image is always high.

[0174] Optionally, when the image processing apparatus in S103 adopts the first processing manner to process the DRR image to be processed to obtain the updated DRR image, the horizontal gradient amplitude and the vertical gradient amplitude can be obtained first, and then the first processing manner is adopted to process the DRR image to be processed according to the horizontal gradient amplitude and the vertical gradient amplitude to obtain the updated DRR image. The horizontal gradient amplitude is the gradient amplitude of the DRR image to be processed in the horizontal direction of the image coordinate system, and the vertical gradient amplitude is the gradient amplitude of the DRR image to be processed in the vertical direction of the image coordinate system.

[0175] Further, the image processing apparatus can multiply the horizontal gradient amplitude by the first weight to obtain the updated horizontal gradient amplitude, and multiply the vertical gradient amplitude by the second weight to obtain the updated vertical gradient amplitude. When the image processing apparatus adopts the first processing manner to process the DRR image to be processed according to the horizontal gradient amplitude and the vertical gradient amplitude to obtain the updated DRR image, the first processing manner can be adopted to process the DRR image to be processed according to the updated horizontal gradient amplitude and the updated vertical gradient amplitude to obtain the updated DRR image.

[0176] The first weight and the second weight can both be less than or equal to 1. For example, the range of the two weights is (0.8, 1). Optionally, the second weight is less than the first weight.

[0177] It should be noted that the DRR image is an image obtained by forward projection of a three-dimensional CT image, and the DRR image will be blurred and have noise interference after forward projection. In the embodiment of the present application, the first processing manner is adopted to process the DRR image to be processed according to the horizontal gradient amplitude and the vertical gradient amplitude to obtain the updated DRR image. The size of the horizontal gradient amplitude and the vertical gradient amplitude can be positively correlated with the size of the noise in the updated DRR image, so when the first weight and / or the second weight is less than 1, the horizontal gradient amplitude and the vertical gradient amplitude can be reduced, thereby alleviating the noise in the updated DRR image. In addition, the noise of the DRR image is mainly concentrated in the vertical direction, and when the second weight in the embodiment of the present application is less than the first weight, the reduction degree of the vertical gradient amplitude is higher, so as to further alleviate the noise of the updated DRR image in the vertical direction, and more details of the updated DRR image in the horizontal direction can be retained.

[0178] Based on the image processing method provided in the embodiment of the present application, the embodiment of the present application provides an image processing apparatus. As shown in the example of FIG. 8, the image processing apparatus includes the following modules. Figure 5

[0179] ​The first obtaining module 501 is configured to obtain a first processing mode; wherein the first processing mode is an inverse processing mode of a second processing mode, and the second processing mode is a convolution processing mode; the first image of the target object collected by the imaging device in the radiotherapy device is processed by using the second processing mode, and a second image can be obtained; the similarity of the blur degree of the second image and a digital reconstructed radiograph (DRR) image of the target object is greater than a similarity threshold value.

[0180] The second obtaining module 502 is configured to obtain a DRR image to be processed.

[0181] The processing module 503 is configured to process the DRR image to be processed by using the first processing mode, and obtain an updated DRR image.

[0182] The image processing device provided by the embodiment can process the DRR image by using the first processing mode, and obtain an updated DRR image. Moreover, the first image of the target object collected by the imaging device in the radiotherapy device is processed by using the second processing mode (the inverse processing mode of the first processing mode), and a second image can be obtained, and the similarity of the blur degree of the second image and the DRR image of the target object is relatively high. Therefore, the similarity of the blur degree of the image obtained by processing the DRR image by using the first processing mode and the image collected by the imaging device is relatively high. Since the blur degree of the image collected by the imaging device is relatively low and the definition is relatively high, the blur degree of the image obtained by processing the DRR image by using the first processing mode is also relatively low, and the definition is also relatively high.

[0183] Optionally, the first obtaining module 501 is configured to:

[0184] display a plurality of blur images corresponding to a plurality of deformation processing modes; wherein the blur image is obtained by processing the first image by using the corresponding deformation processing mode, the deformation processing mode is obtained by changing the value of at least one processing parameter in the third processing mode, and the third processing mode and the deformation processing mode are both convolution processing modes;

[0185] in response to a selection instruction for a target blur image in the plurality of blur images, determine that the deformation processing mode corresponding to the target blur image is the second processing mode;

[0186] determine that the inverse processing mode of the second processing mode is the first processing mode.

[0187] Optionally, the first obtaining module 501 is further configured to:

[0188] when any blur image in the plurality of blur images is displayed, display the DDR image of the target object.

[0189] Optionally, the first obtaining module 501 is further configured to:

[0190] display reference information of any one of the plurality of blurred images when displaying the any one of the plurality of blurred images;

[0191] The reference information of the any one of the plurality of blurred images is used to indicate the similarity of the blurred degree between the any one of the plurality of blurred images and the DRR image of the target object.

[0192] For example, the reference information of the any one of the plurality of blurred images includes at least one of the following:

[0193] The mutual information between the any one of the plurality of blurred images and the DRR image of the target object;

[0194] The root mean square error between the any one of the plurality of blurred images and the DRR image of the target object;

[0195] The peak signal-to-noise ratio between the any one of the plurality of blurred images and the DRR image of the target object;

[0196] The cross entropy between the any one of the plurality of blurred images and the DRR image of the target object;

[0197] The structural similarity between the any one of the plurality of blurred images and the DRR image of the target object;

[0198] The gray histogram of the any one of the plurality of blurred images and the gray histogram of the DRR image of the target object;

[0199] And the pixel surface of the any one of the plurality of blurred images and the pixel surface of the DRR image of the target object.

[0200] Optionally, the third processing mode includes a first processing parameter and a second processing parameter; the first obtaining module 501 is configured to:

[0201] display a plurality of first blurred images corresponding to a plurality of first deformation processing modes, the first deformation processing mode being obtained by changing the value of the first processing parameter in the third processing mode;

[0202] In response to a selection instruction for any one of the plurality of first blurred images, obtain a plurality of second deformation processing modes corresponding to the any one of the plurality of first blurred images; wherein for the first deformation processing mode and the second deformation processing mode corresponding to the any one of the plurality of first blurred images, the second deformation processing mode is obtained by changing the value of the second processing parameter in the first deformation processing mode;

[0203] display a second blurred image corresponding to each of the second deformation processing modes;

[0204] The selection instruction for the target blurred image among the plurality of blurred images is: the selection instruction for any of the displayed second blurred images.

[0205] Optionally, the image processing apparatus further includes: a first update module ( Figure 5 (not shown in the image), used to update the first processing method.

[0206] Optionally, the first update module is used to:

[0207] The first processing method is updated according to a time factor, which is used to reflect the change of the first processing method over time.

[0208] Optionally, the image processing apparatus further includes:

[0209] Second update module ( Figure 5 (not shown in the image), used to perform multiple second updates on the first processing method;

[0210] Determine module ( Figure 5 (not shown in the image), used to determine the time factor based on the first processing method after each update in the multiple second updates.

[0211] Optionally, the processing module 503 is used for:

[0212] Obtain the horizontal gradient magnitude and the vertical gradient magnitude; wherein, the horizontal gradient magnitude is the gradient magnitude of the DRR image to be processed in the horizontal direction in the image coordinate system, and the vertical gradient magnitude is the gradient magnitude of the DRR image to be processed in the vertical direction in the image coordinate system;

[0213] The horizontal gradient magnitude is multiplied by a first weight to obtain the updated horizontal gradient magnitude, where the first weight is less than 1;

[0214] The updated vertical gradient magnitude is obtained by multiplying the vertical gradient magnitude by the second weight, where the second weight is less than 1.

[0215] Based on the updated horizontal gradient magnitude and the updated vertical gradient magnitude, the DRR image to be processed is processed using the first processing method to obtain the updated DRR image.

[0216] For example, the second weight is less than the first weight.

[0217] Based on the image processing method provided in the embodiments of the present application, another image processing apparatus is provided. The image processing apparatus includes a processor and a memory, and the memory stores a program. The processor is configured to invoke the program stored in the memory, so that the image processing apparatus performs any one of the image processing methods provided in the embodiments of the present application, such as the image processing method shown in FIG. 7. Figure 1

[0218] For example, Figure 6 The structure of another image processing apparatus provided in the embodiments of the present application is shown in FIG. 9. Generally, the image processing apparatus 900 includes a processor 901 and a memory 902. In some embodiments, the image processing apparatus 900 can further include a display screen 905.

[0219] The processor 901 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 901 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 901 can also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 901 can be integrated with a GPU (Graphics Processing Unit) that is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 901 can further include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations.

[0220] The memory 902 can include one or more computer-readable storage media, which can be non-transitory. The memory 902 can also include a high-speed random access memory and a non-volatile memory such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is configured to store at least one instruction for execution by the processor 901.

[0221] ​In some embodiments, the image processing apparatus 900 can further include a peripheral device interface 903 and at least one peripheral device. The processor 901, the memory 902 and the peripheral device interface 903 can be connected through a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 903 through a bus, a signal line or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 904, a display screen 905, a camera 906, an audio circuit 907, a positioning component 908 and a power supply 909.

[0222] The peripheral device interface 903 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, the memory 902 and the peripheral device interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902 and the peripheral device interface 903 can be implemented on a separate chip or circuit board, and the present embodiments are not limited in this regard.

[0223] The radio frequency circuit 904 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 904 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 904 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and the like. The radio frequency circuit 904 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 904 can also include NFC (Near Field Communication) related circuitry, which is not limited in the present application.

[0224] The display screen 905 is configured to display a UI (User Interface). The UI can include graphics, text, icons, video, and any combination thereof, such as the at least one blurred image described above. When the display screen 905 is a touch display screen, the display screen 905 is further configured to capture touch signals on or above the surface of the display screen 905. The touch signals can be input to the processor 901 as control signals for processing. In this case, the display screen 905 can also be configured to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 905 can be one, configured on the front panel of the image processing apparatus 900; in other embodiments, the display screen 905 can be at least two, respectively configured on different surfaces of the image processing apparatus 900 or in a folding design; in still other embodiments, the display screen 905 can be a flexible display screen, configured on a curved surface or a folding surface of the image processing apparatus 900. Even, the display screen 905 can also be configured in an irregular shape, i.e., a special-shaped screen. The display screen 905 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.

[0225] The camera assembly 906 is configured to capture images or videos. Optionally, the camera assembly 906 includes a front camera and a rear camera. Typically, the front camera is configured on the front panel of the terminal, and the rear camera is configured on the back of the terminal. In some embodiments, the rear camera is at least two, respectively any one of a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, to realize the background blurring function of the main camera and the depth-of-field camera, the panoramic shooting and VR (Virtual Reality) shooting function of the main camera and the wide-angle camera, or other fusion shooting functions. In some embodiments, the camera assembly 906 can further include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. The dual-color temperature flash refers to the combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0226] The audio circuit 907 can include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into an electrical signal input to the processor 901 for processing, or input to the radio frequency circuit 904 to realize voice communication. For the purpose of stereo sound collection or noise reduction, the microphone can be multiple, respectively arranged at different parts of the image processing device 900. The microphone can also be an array microphone or an omnidirectional collection type microphone. The speaker is used to convert the electrical signal from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker can be a traditional diaphragm speaker, or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only can it convert electrical signals into sound waves that humans can hear, but it can also convert electrical signals into sound waves that humans cannot hear for ranging purposes. In some embodiments, the audio circuit 907 can also include a headphone jack.

[0227] The positioning component 908 is used to position the current geographic location of the image processing device 900 to realize navigation or LBS (Location Based Service). The positioning component 908 can be a positioning component based on the GPS (Global Positioning System) of the United States, the Beidou system of China, or the Galileo system of Russia.

[0228] The power supply 909 is used to supply power to each component in the image processing device 900. The power supply 909 can be alternating current, direct current, disposable battery or rechargeable battery. When the power supply 909 includes a rechargeable battery, the rechargeable battery can be a wired charging battery or a wireless charging battery. The wired charging battery is a battery charged through a wired line, and the wireless charging battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0229] In some embodiments, the image processing device 900 further includes one or more sensors 910. The one or more sensors 910 include but are not limited to: an acceleration sensor 911, a gyroscope sensor 912, a pressure sensor 913, a fingerprint sensor 914, an optical sensor 915, and a proximity sensor 916.

[0230] The acceleration sensor 911 can detect the acceleration magnitude in the three coordinate axes of the coordinate system established by the image processing device 900. For example, the acceleration sensor 911 can be used to detect the components of the gravitational acceleration in the three coordinate axes. The processor 901 can control the display screen 905 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 911. The acceleration sensor 911 can also be used for game or user motion data collection.

[0231] The gyroscope sensor 912 can detect the body direction and rotation angle of the image processing device 900, and the gyroscope sensor 912 can cooperate with the acceleration sensor 911 to collect the 3D action of the user on the image processing device 900. According to the data collected by the gyroscope sensor 912, the processor 901 can realize the following functions: action sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0232] The pressure sensor 913 can be arranged on the side frame of the image processing device 900 and / or the lower layer of the display screen 905. When the pressure sensor 913 is arranged on the side frame of the image processing device 900, the user's holding signal on the image processing device 900 can be detected, and the left and right hand recognition or shortcut operation can be performed by the processor 901 according to the holding signal collected by the pressure sensor 913. When the pressure sensor 913 is arranged on the lower layer of the display screen 905, the controllable control on the UI interface can be controlled by the processor 901 according to the pressure operation of the user on the display screen 905. The controllable control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0233] The fingerprint sensor 914 is used to collect the fingerprint of the user, and the identity of the user can be recognized by the processor 901 according to the fingerprint collected by the fingerprint sensor 914, or by the fingerprint sensor 914 according to the collected fingerprint. When the identity of the user is recognized as a trusted identity, the processor 901 authorizes the user to perform related sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, payment, and changing settings. The fingerprint sensor 914 can be arranged on the front, back or side of the image processing device 900. When the image processing device 900 is provided with a physical button or a manufacturer's logo, the fingerprint sensor 914 can be integrated with the physical button or the manufacturer's logo.

[0234] The optical sensor 915 is used to collect the ambient light intensity. In one embodiment, the processor 901 can control the display brightness of the display screen 905 according to the ambient light intensity collected by the optical sensor 915. Specifically, when the ambient light intensity is high, the display brightness of the display screen 905 is increased; when the ambient light intensity is low, the display brightness of the display screen 905 is decreased. In another embodiment, the processor 901 can also dynamically adjust the shooting parameters of the camera assembly 906 according to the ambient light intensity collected by the optical sensor 915.

[0235] The proximity sensor 916, also called distance sensor, is usually arranged on the front panel of the image processing apparatus 900. The proximity sensor 916 is used to collect the distance between the user and the front face of the image processing apparatus 900. In one embodiment, when the proximity sensor 916 detects that the distance between the user and the front face of the image processing apparatus 900 gradually becomes smaller, the display screen 905 is switched from the bright screen state to the screen-off state under the control of the processor 901; when the proximity sensor 916 detects that the distance between the user and the front face of the image processing apparatus 900 gradually becomes larger, the display screen 905 is switched from the screen-off state to the bright screen state under the control of the processor 901.

[0236] Those skilled in the art can understand that the structure shown in the above Figure 6 The structure shown in the above does not constitute a limitation on the image processing apparatus 900, and can include more or less components than those shown, or combine certain components, or adopt a different component arrangement.

[0237] The embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program; and the computer program enables a computer to execute any of the image processing methods provided by the embodiments of the present application when the computer program is run on the computer. Figure 1 The image processing method shown in the above.

[0238] The embodiment of the present application further provides a computer program product, which enables a computer to execute any of the image processing methods provided by the embodiments of the present application when the computer program product is run on the computer. Figure 1 The image processing method shown in the above.

[0239] The embodiment of the present application further provides a radiotherapy system, which comprises a radiotherapy device having an imaging device, and any of the image processing apparatuses provided by the embodiments of the present application.

[0240] In the present application, the terms "first" and "second" and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. The term "at least one" refers to one or more, and the term "multiple" refers to two or more, unless otherwise explicitly limited. The term "and / or", only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone.

[0241] The method embodiments, display device embodiments and display system embodiments provided by the embodiments of the present application can be mutually referenced, which is not limited by the embodiments of the present application. The order of operations of the method embodiments provided by the embodiments of the present application can be adjusted appropriately, and the operations can be increased or decreased as appropriate according to the circumstances. Any person skilled in the art can easily think of various methods within the technical range disclosed by the present application, which should be covered within the protection scope of the present application, and thus will not be described here.

[0242] In the corresponding embodiments provided by the present application, it should be understood that the disclosed system and device can be implemented by other constitutions. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical or other forms.

[0243] The units described as separate components can or can not be physically separate, and the components described as units can or can not be physical units, which can be located in one place or distributed on multiple devices. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0244] The above is only an optional implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An image processing method, characterized by, The method comprises: displaying a plurality of first blurred images corresponding to a plurality of first deformation processing modes, the first deformation processing mode being obtained by changing the value of a first processing parameter in a third processing mode, the third processing mode further comprising a second processing parameter; any blurred image is obtained by processing a first image of a target object collected by an imaging device in a radiotherapy device using a corresponding deformation processing mode, the third processing mode and the deformation processing mode are convolution processing modes; in response to a selection instruction for any image in the plurality of first blurred images, displaying a second blurred image corresponding to each second deformation processing mode in the plurality of second deformation processing modes corresponding to the any image; for the first deformation processing mode and the second deformation processing mode corresponding to the any image, the second deformation processing mode is obtained by changing the value of the second processing parameter in the first deformation processing mode; in response to a selection instruction for a target blurred image, determining that the second deformation processing mode corresponding to the target blurred image is a second processing mode; the target blurred image is any second blurred image; processing the first image using the second processing mode can obtain a second image; the similarity between the second image and the blurred degree of a digital reconstructed radiograph (DRR) image of the target object is greater than a similarity threshold; obtaining a DRR image to be processed; processing the DRR image to be processed using a first processing mode to obtain an updated DRR image, the first processing mode being an inverse processing mode of the second processing mode.

2. The method of claim 1, wherein, The method further comprises: when displaying any blurred image in the plurality of first blurred images and the plurality of second blurred images, displaying a DDR image of the target object.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: when displaying any blurred image in the plurality of first blurred images and the plurality of second blurred images, displaying reference information of the any blurred image; wherein the reference information of the any blurred image is used to indicate the similarity between the any blurred image and the blurred degree of the DRR image of the target object.

4. The method of claim 3, wherein, The reference information of the any blurred image comprises at least one of: the mutual information between the any blurred image and the DRR image of the target object; the root mean square error between the any blurred image and the DRR image of the target object; the peak signal-to-noise ratio between the any blurred image and the DRR image of the target object; the cross entropy between the any blurred image and the DRR image of the target object; the structural similarity between the any blurred image and the DRR image of the target object; the gray histogram of the any blurred image and the gray histogram of the DRR image of the target object; and the pixel parabolic surface of the any blurred image and the pixel parabolic surface of the DRR image of the target object.

5. The method according to claim 1 or 2, characterized in that, The method further comprises: updating the first processing mode.

6. The method of claim 5, wherein, The first updating of the first processing mode comprises: updating the first processing mode according to a time factor, the time factor being used to reflect the change of the first processing mode over time.

7. The method of claim 6, wherein, The method further comprises: updating the first processing mode multiple times; determining the time factor according to the first processing mode after each of the multiple times of updating.

8. The method of claim 1 or 2, wherein, processing the to-be-processed DRR image by using the first processing mode to obtain an updated DRR image, comprising: obtaining a horizontal gradient amplitude and a vertical gradient amplitude; wherein the horizontal gradient amplitude is a gradient amplitude of the to-be-processed DRR image in a horizontal direction of an image coordinate system, and the vertical gradient amplitude is a gradient amplitude of the to-be-processed DRR image in a vertical direction of the image coordinate system; multiplying the horizontal gradient amplitude by a first weight to obtain an updated horizontal gradient amplitude, wherein the first weight is less than 1; multiplying the vertical gradient amplitude by a second weight to obtain an updated vertical gradient amplitude, wherein the second weight is less than 1; processing the to-be-processed DRR image by using the first processing mode according to the updated horizontal gradient amplitude and the updated vertical gradient amplitude to obtain the updated DRR image.

9. The method of claim 8, wherein, The second weight is less than the first weight.

10. An image processing apparatus characterized by comprising: The image processing apparatus comprises: a first obtaining module configured to display a plurality of first blurred images corresponding to a plurality of first deformation processing modes, wherein the first deformation processing mode is obtained by changing a value of a first processing parameter in a third processing mode, the third processing mode further comprises a second processing parameter, and any blurred image is obtained by processing a first image of a target object collected by an imaging device of a radiotherapy device by using a corresponding deformation processing mode, the third processing mode and the deformation processing mode are convolution processing modes; in response to a selection instruction for any image in the plurality of first blurred images, display a second blurred image corresponding to each second deformation processing mode in a plurality of second deformation processing modes corresponding to the any image; for the first deformation processing mode and the second deformation processing mode corresponding to the any image, the second deformation processing mode is obtained by changing a value of the second processing parameter in the first deformation processing mode; in response to a selection instruction for a target blurred image, determine that a second deformation processing mode corresponding to the target blurred image is a second processing mode; the target blurred image is any second blurred image; processing the first image by using the second processing mode can obtain a second image; a similarity between the second image and a blurred degree of a digital reconstructed radiograph (DRR) image of the target object is greater than a similarity threshold; a second obtaining module configured to obtain a to-be-processed DRR image; a processing module configured to process the to-be-processed DRR image by using a first processing mode to obtain an updated DRR image, wherein the first processing mode is an inverse processing mode of the second processing mode.

11. An image processing apparatus characterized by comprising: The image processing apparatus comprises a processor and a memory, and the memory stores a program; The processor is configured to call the program stored in the memory to implement the image processing method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer storage medium stores a computer program. The computer program, when running on a computer, causes the computer to perform the image processing method of any one of claims 1 to 9.

13. A radiotherapy system, characterized by, Comprising: A radiotherapy device having an imaging device, and the image processing apparatus of claim 11.

Images