Web-based Medical Image Browsing Method, Device and Computer Equipment

Abstract

The present invention discloses a web-based medical image browsing method, device and computer equipment, mainly aiming to implement the medical image browsing function in multiple platforms and reduce the installation and maintenance costs at the same time. The method includes: in response to a medical image browsing request, obtaining a CT image sequence and a PET image sequence to be registered; obtaining the fusion feature values corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively; and generating and displaying the fusion image corresponding to the target section on an html page based on the fusion feature values.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing, and in particular, to a web-based medical image browsing method, apparatus, and computer device. Background Art

[0002] Medical images, as an important basis for medical diagnosis, can effectively assist clinicians in making diagnoses. For example, PET / CT fusion images are of great value for the early diagnosis of diseases, the qualitative determination of lesions, and the diagnosis and differentiation of small lesions.

[0003] Currently, doctors usually browse and diagnose medical images on a system platform based on the C / S architecture in the radiology department. However, this browsing method based on the C / S architecture cannot be interconnected with other system platforms. Therefore, it can only be browsed on a single system platform and cannot be applied to multiple platforms. If the browsing function is to be implemented on other system platforms, reinstallation and deployment are required, which will result in relatively high operation and maintenance costs. Summary of the Invention

[0004] The present invention provides a web-based medical image browsing method, which can mainly implement the browsing function of medical images on multiple platforms and reduce the installation and maintenance costs at the same time.

[0005] According to the first aspect of the present invention, a web-based medical image browsing method is provided, including:

[0006] Responding to a browsing request for a medical image, and acquiring a CT image sequence and a PET image sequence to be registered;

[0007] According to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtaining the fusion feature values corresponding to each pixel point on the target section;

[0008] Based on the fusion feature values, generating and displaying the fusion image corresponding to the target section in the html page.

[0009] According to the second aspect of the present invention, a web-based medical image browsing apparatus is provided, including:

[0010] An acquisition unit, configured to respond to a browsing request for a medical image and acquire a CT image sequence and a PET image sequence to be registered;

[0011] A fusion unit, configured to obtain the fusion feature values corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively;

[0012] A display unit for generating and displaying a fused image corresponding to the target section in an html page based on the fused eigenvalue.

[0013] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the following steps are implemented:

[0014] In response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered;

[0015] According to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fused eigenvalue corresponding to each pixel point on the target section;

[0016] Based on the fused eigenvalue, generate and display a fused image corresponding to the target section in an html page.

[0017] According to a fourth aspect of the present invention, there is provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0018] In response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered;

[0019] According to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fused eigenvalue corresponding to each pixel point on the target section;

[0020] Based on the fused eigenvalue, generate and display a fused image corresponding to the target section in an html page.

[0021] A web-based medical image browsing method, device and computer device provided by the present invention. Compared with the current method of browsing and diagnosing medical images on a system platform built based on the C / S architecture, the present invention can, in response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered; and according to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fused eigenvalue corresponding to each pixel point on the target section; and finally, based on the fused eigenvalue, generate and display a fused image corresponding to the target section in an html page. Since the present invention adopts a web-based B / S architecture for medical image browsing, only the corresponding browsing function needs to be configured in the server, and other system platforms can display the corresponding medical images by accessing the server, so that medical images can be browsed on multiple platforms, reducing the operation and maintenance costs, and at the same time, it can also solve the problems of sharing of medical resources and remote diagnosis. Description of the Drawings

[0022] The accompanying drawings described herein are used to provide a further understanding of the present invention and form a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0023] Figure 1 A flowchart of a web-based medical image browsing method provided by an embodiment of the present invention is shown;

[0024] Figure 2 A flowchart of another web-based medical image browsing method provided by an embodiment of the present invention is shown;

[0025] Figure 3 A schematic diagram of a registration body provided by an embodiment of the present invention is shown;

[0026] Figure 4 A schematic diagram of a fused image of CT and PET provided by an embodiment of the present invention is shown;

[0027] Figure 5 A schematic structural diagram of a web-based medical image browsing device provided by an embodiment of the present invention is shown;

[0028] Figure 6 A schematic structural diagram of another web-based medical image browsing device provided by an embodiment of the present invention is shown;

[0029] Figure 7 A schematic structural diagram of an entity of a computer device provided by an embodiment of the present invention is shown. Detailed implementation manners

[0030] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0031] Currently, the medical image browsing method based on the C / S architecture cannot be interconnected with other system platforms. Therefore, it can only be browsed in a single system platform and cannot be applied in multiple platforms, resulting in relatively high operation and maintenance costs.

[0032] To solve the above problems, an embodiment of the present invention provides a web-based medical image browsing method, as Figure 1 shown, the method includes:

[0033] 101. In response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered.

[0034] Among them, when the web page is just opened, the CT image sequence to be registered is the first column of CT image sequences in the CT scan sequence, and the PET image sequence to be registered is the first column of PET image sequences in the PET scan sequence. Subsequently, sequence switching can be performed according to the doctor's selection. For example, if the doctor selects the second column of CT image sequences and the second column of PET image sequences for registration, the CT image sequence to be registered includes multiple CT images, and the PET image sequence to be registered includes multiple PET images.

[0035] The embodiments of the present invention are mainly applied to the scenario of browsing CT and PET fusion images based on the web-based B / S architecture. The execution subject of the embodiments of the present invention is a device or equipment capable of browsing CT and PET fusion images, which can be specifically set on the server side.

[0036] In order to be able to browse medical images on multiple platforms, the embodiments of the present invention adopt a web-based B / S architecture for medical image browsing. Specifically, when a doctor needs to browse medical images for diagnosis, a medical image browsing request can be sent to the server through the system platform in the current environment. After receiving the browsing request, the server will obtain the corresponding detection data information and the download addresses of all detected image sequences. Among them, the detection data information includes patient information, the scanned part of the patient, the detection time, etc. The server downloads all dicom images from the cloud to the local according to the download address. The dicom images include all CT image sequences and PET image sequences detected by the patient. Then, the first column of CT image sequences and the first column of PET image sequences are automatically selected for image registration. It should be noted that subsequently, other CT image sequences and PET image sequences can also be selected for registration according to the doctor's browsing needs.

[0037] 102. Obtain the fusion feature values corresponding to each pixel point on the target section according to the image information respectively corresponding to the CT image sequence and the PET image sequence.

[0038] Among them, the image information corresponding to the CT image sequence is specifically the DICOM information corresponding to each CT image, and the image information corresponding to the PET image sequence is specifically the DICOM information corresponding to each PET image. The target section can be any section, and the number of target sections can be one, two or more. The target section can be randomly selected and switched according to the doctor's diagnosis needs. For example, the target sections are the transverse section, the coronal section and the sagittal section. For the embodiments of the present invention, in order to display the fused images of CT and PET on the html page, it is necessary to pre-register the CT image sequence and the PET image sequence. During the registration process, the CT image sequence and the PET image sequence can be regarded as the CT original body and the PET original body respectively. According to the DICOM information corresponding to the CT image sequence, the voxel data corresponding to the CT original body can be analyzed. The voxel data includes the length, width and height corresponding to the CT original body, the first pixel point spacing of each pixel point in the CT original body in the length, width and height directions, and the first coordinate information corresponding to the target pixel point. At the same time, according to the DICOM information corresponding to the PET image, the voxel data corresponding to the PET original body can be analyzed. The voxel data includes the length, width and height corresponding to the PET original body, the second pixel point spacing of each pixel point in the PET original body in the length, width and height directions, and the second coordinate information corresponding to the target pixel point.

[0039] Further, according to the DICOM information corresponding to the CT image sequence, calculate the CT feature values corresponding to each pixel point in the CT original body, and at the same time, according to the DICOM information corresponding to the PET image sequence, calculate the PET feature values corresponding to each pixel point in the PET original body.

[0040] In addition, according to the voxel data corresponding to the CT original body and the voxel data corresponding to the PET original body, determine the voxel data corresponding to the registration body jointly corresponding to the CT original body and the PET original body. The voxel data corresponding to the registration body includes the length, width and height corresponding to the registration body, the third pixel point spacing of each pixel point in the registration body in the length, width and height directions, and the central coordinate point. Further, according to the CT feature values corresponding to each pixel point in the CT original body and the voxel data corresponding to the registration body, perform interpolation processing on the registration body to obtain the CT registration feature values corresponding to each pixel point in the registration body. Similarly, according to the PET feature values corresponding to each pixel point in the PET original body and the voxel data corresponding to the registration body, perform interpolation processing on the registration body to obtain the PET registration feature values corresponding to each pixel point in the registration body. Thus, the CT registration feature values and the PET registration feature values corresponding to each pixel point in the registration body can be obtained in the above manner. For the specific process of registering the CT image sequence and the PET image sequence, see steps 202-203.

[0041] Further, for the embodiments of the present invention, after determining the CT registration feature values and PET registration feature values corresponding to each pixel point in the registration body, the CT registration feature values and PET registration feature values corresponding to each pixel point on the target section can be selected, and then the CT registration feature values and PET registration feature values corresponding to each pixel point on the target section are linearly weighted and summed to obtain the fusion feature values corresponding to each pixel point on the target section, so as to display the fusion image of CT and PET based on the fusion feature values. Among them, the weights corresponding to the CT registration feature values and PET registration feature values can be set according to actual diagnostic requirements.

[0042] 103. Generate and display the fusion image corresponding to the target section in the html page based on the fusion feature values.

[0043] For the embodiments of the present invention, after completing the registration of the CT image sequence and the PET image sequence, the fusion feature values corresponding to each pixel point on the target section can be rendered into the canvas element of html to generate and display the fusion image of CT and PET. In addition to displaying the fusion image of CT and PET in the html page, the CT image and PET image corresponding to the target section can also be displayed separately. Based on this, the method further includes: displaying the CT image and PET image corresponding to the fusion image in the html page respectively.

[0044] In a specific application scenario, in order to be able to display the separate CT image at the same time, the method further includes: filtering the CT registration feature values corresponding to each pixel point on the target section according to the pre-configured window parameter and window level parameter to obtain the filtered CT registration feature values; generating the CT image corresponding to the target section based on the filtered CT registration feature values. Among them, the window parameter is used to represent the range of the CT registration feature values, and the window level parameter is used to represent the center point of the CT registration feature values. For example, if the window parameter is 250 and the window level parameter is 125, the range of the CT registration feature values is 0 to 250, and some CT registration feature values can be filtered out through this range, and only the CT registration feature values of the region of interest are retained.

[0045] Further, in order to be able to display a separate PET image simultaneously, the method further includes: determining the maximum PET registration eigenvalue and the minimum PET registration eigenvalue from the PET registration eigenvalues corresponding to each pixel point on the target section; calculating the index value of each pixel point on the target section in the preset color bar based on the maximum PET registration eigenvalue, the minimum PET registration eigenvalue, the PET registration eigenvalues corresponding to each pixel point on the target section, and the length of the preset color bar; querying the preset color bar based on the index value to determine the color value corresponding to each pixel point on the target section; and performing color rendering on each pixel point on the target section based on the color value to generate the PET image corresponding to the target section. Among them, the preset color bar is actually a preset color query table, which records the color values, that is, RGB values, corresponding to different index values. The length of the preset color bar is related to the number of color values included in the preset color bar. Different preset color bars have different lengths. The more color values there are, the longer the preset color bar is. On the contrary, the fewer color values there are, the shorter the preset color bar is.

[0046] The calculation formula for the index value of each pixel point on the target section in the preset color bar is as follows:

[0047] Index value = PET registration eigenvalue * (maximum PET registration eigenvalue - minimum PET registration eigenvalue) / length of the preset color bar

[0048] Specifically, after determining the PET registration eigenvalues corresponding to each pixel point on the target section, the maximum PET registration eigenvalue and the minimum PET registration eigenvalue are selected. When calculating the index value corresponding to any pixel point on the target section, the PET registration eigenvalue corresponding to this pixel point is substituted into the above formula, whereby the index value corresponding to any pixel point on the target section can be obtained. Furthermore, based on this index value and the preset color bar, the color value corresponding to any pixel point on the target section can be determined. Thus, according to this color value, a colored PET image can be generated. The colored PET image is beneficial to making the lesion area clearer and highlighting the lesion.

[0049] A web-based medical image browsing method provided by an embodiment of the present invention. Compared with the current method of browsing and diagnosing medical images on a system platform built based on the C / S architecture, the present invention can respond to a browsing request for medical images, obtain a CT image sequence and a PET image sequence to be registered; and obtain the fusion feature values corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively; finally, based on the fusion feature values, generate and display the fusion image corresponding to the target section on the html page. Since the present invention adopts a web-based B / S architecture for medical image browsing, only the corresponding browsing function needs to be configured in the server, and other system platforms can display the corresponding medical images by accessing the server, so that medical images can be browsed on multiple platforms, reducing the operation and maintenance costs, and at the same time can solve the problems of sharing of medical resources and remote diagnosis.

[0050] Further, in order to better illustrate the display process of the above CT and PET fusion images, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another web-based medical image browsing method, as Figure 2 shown, the method includes:

[0051] 201. Respond to a browsing request for medical images, and obtain a CT image sequence and a PET image sequence to be registered.

[0052] For the embodiment of the present invention, in order to display the fusion image of CT and PET, it is necessary to obtain a CT image sequence and a PET image sequence to be registered. The specific obtaining process of the CT image sequence and the PET image sequence is exactly the same as that in step 101, and will not be described in detail here.

[0053] 202. According to the image information corresponding to the CT image sequence and the PET image sequence respectively, register the CT image sequence and the PET image sequence to obtain the CT registration feature value and the PET registration feature value corresponding to each pixel point in the registration body.

[0054] Among them, the image information corresponding to the CT image sequence is specifically the DICOM information corresponding to each CT image, and the image information corresponding to the PET image sequence is specifically the DICOM information corresponding to each PET image. For the implementation of the present invention, in order to register the CT image sequence and the PET image sequence, step 202 specifically includes: determining the voxel data corresponding to the CT original body composed of the CT image sequence and the CT feature values corresponding to each pixel point in the CT original body according to the image information corresponding to the CT image sequence; determining the voxel data corresponding to the PET original body composed of the PET image sequence and the PET feature values corresponding to each pixel point in the PET original body according to the image information corresponding to the PET image sequence; determining the voxel data of the registration body jointly corresponding to the CT original body and the PET original body according to the voxel data corresponding to the CT original body and the voxel data corresponding to the PET original body; performing pixel interpolation processing on the registration body according to the CT feature values, the PET feature values and the voxel data of the registration body to obtain the CT registration feature values and the PET registration feature values corresponding to each pixel point in the registration body.

[0055] Among them, the voxel data corresponding to the CT original body includes the length, width and height corresponding to the CT original body, the first pixel point spacing of each pixel point in the CT original body in the length, width and height directions, and the first coordinate information corresponding to the target pixel point in the CT original body. The target pixel point may specifically be the upper left vertex in the CT original body. For example, Figure 3 the upper left vertex in the Z-axis direction. The upper left vertex is actually the upper left vertex of the last CT image in the CT image sequence that composes the CT original body, and the first coordinate information is the coordinate information of the upper left vertex of the last CT image in the world space.

[0056] For the embodiments of the present invention, in order to determine the voxel data corresponding to the CT original body and the CT feature values corresponding to each pixel point in the CT original body, the method for determining the voxel data corresponding to the CT original body composed of the CT image sequence and the CT feature values corresponding to each pixel point in the CT original body according to the image information corresponding to the CT image sequence includes: determining, according to the image information corresponding to the CT image sequence, the first size information corresponding to the CT original body, the first pixel point pitch of each pixel point in the CT original body in the length, width, and height directions, and the first coordinate information corresponding to the target pixel point in the CT original body; determining the voxel data corresponding to the CT original body according to the first size information, the first pixel point pitch, and the first coordinate information; and calculating the CT feature values corresponding to each pixel point in the CT original body according to the slope parameter and the intercept parameter in the image information of the CT image sequence and the pixel values corresponding to each pixel point in the CT original body. Wherein, the first size information is the length, width, and height corresponding to the CT original body, and the dicom information corresponding to the CT image includes the slope parameter and the intercept parameter.

[0057] Specifically, by analyzing the dicom information corresponding to each CT image in the CT image sequence, the length, width, and height corresponding to the CT original body, the first pixel point pitch of each pixel point in the CT original body in the length, width, and height directions, and the first coordinate information corresponding to the top left vertex can be determined, and the above information is used as the voxel data corresponding to the CT original body. Further, the pixel value corresponding to each pixel point in the CT original body is multiplied by the slope parameter, and the multiplication result is added to the intercept parameter to obtain the CT feature value corresponding to each pixel point in the CT original body, so as to register the CT original body based on the CT feature value.

[0058] Further, in the process of determining the voxel data corresponding to the PET original body and the PET feature values corresponding to each pixel point in the PET original body, the voxel data corresponding to the PET original body includes the length, width, and height corresponding to the PET original body, the second pixel point pitch of each pixel point in the PET original body in the length, width, and height directions, and the second coordinate information corresponding to the target pixel point in the PET original body. The target pixel point may specifically be the top left vertex in the PET original body, such as Figure 3 the top left vertex in the Z-axis direction in, and the top left vertex is actually the top left vertex of the last PET image in the PET image sequence constituting the PET original body, and the second coordinate information is the coordinate information of the top left vertex of the last PET image in the world space.

[0059] For the embodiments of the present invention, in order to determine the voxel data corresponding to the PET original body and the PET characteristic values corresponding to each pixel point in the PET original body, the method for determining the voxel data corresponding to the PET original body composed of the PET image sequence and the PET characteristic values corresponding to each pixel point in the PET original body according to the image information corresponding to the PET image sequence includes: determining the second size information corresponding to the PET original body, the second pixel point spacing of each pixel point in the PET original body in the length, width, and height directions, and the second coordinate information corresponding to the target pixel point in the PET original body according to the image information corresponding to the PET image sequence; determining the voxel data corresponding to the PET original body according to the second size information, the second pixel point spacing, and the second coordinate information; and calculating the PET characteristic values corresponding to each pixel point in the PET original body according to the injection dose and the patient weight in the graphic information of the PET image sequence and the lesion radiation concentration corresponding to each pixel point in the PET original body. Wherein, the second size information is the length, width, and height corresponding to the PET original body, and the dicom information corresponding to the PET image includes the injection dose, the patient weight, and the lesion radiation concentration.

[0060] Specifically, by analyzing the dicom information corresponding to each PET image in the PET image sequence, the length, width, and height corresponding to the PET original body, the second pixel point spacing of each pixel point in the PET original body in the length, width, and height directions, and the second coordinate information corresponding to the top left vertex can be determined, and the above information is used as the voxel data corresponding to the PET original body. Further, multiply the determined injection dose by the patient weight to obtain a multiplication result, and divide the lesion radiation concentration corresponding to each pixel point in the PET original body by the multiplication result to obtain the PET characteristic values corresponding to each pixel point in the PET original body, so as to register the PET original body based on the PET characteristic values.

[0061] It should be noted that in the process of calculating the PET characteristic values, the injection dose can also be multiplied by the patient's body surface area, and the lesion radiation concentration corresponding to each pixel point in the PET original body is divided by the multiplication result of the injection dose and the patient's body surface area to obtain the PET characteristic values corresponding to each pixel point in the PET original body. In addition, the injection dose can also be multiplied by the patient's body mass index, and the lesion radiation concentration corresponding to each pixel point in the PET original body is divided by the multiplication result of the injection dose and the patient's body mass index to obtain the PET characteristic values corresponding to each pixel point in the PET original body.

[0062] Further, in the process of determining the voxel data of the registration object jointly corresponding to the CT original object and the PET original object, the voxel data corresponding to the registration object includes the length, width, and height corresponding to the registration object, the third pixel point spacing of each pixel point in the registration object in the length, width, and height directions, and the center point coordinates corresponding to the registration object.

[0063] For the embodiments of the present invention, in order to determine the voxel data corresponding to the registration object, the step of determining the voxel data of the registration object jointly corresponding to the CT original object and the PET original object according to the voxel data corresponding to the CT original object and the voxel data corresponding to the PET original object includes: respectively determining the center point coordinates corresponding to the CT original object and the center point coordinates corresponding to the PET original object according to the first coordinate information and the second coordinate information; determining the center point coordinates corresponding to the registration object according to the center point coordinates corresponding to the CT original object and the center point coordinates corresponding to the PET original object; determining the third dimension information corresponding to the registration object according to the first dimension information and the second dimension information; respectively determining the number of pixel points of the CT original object in the length, width, and height directions and the number of pixel points of the PET original object in the length, width, and height directions according to the first dimension information and the first pixel point spacing, and the second dimension information and the second pixel point spacing; determining the number of pixel points of the registration object in the length, width, and height directions according to the number of pixel points of the CT original object in the length, width, and height directions and the number of pixel points of the PET original object in the length, width, and height directions; determining the third pixel point spacing of each pixel point in the registration object in the length, width, and height directions based on the number of pixel points of the registration object in the length, width, and height directions and the third dimension information; and determining the voxel data corresponding to the registration object according to the center point coordinates corresponding to the registration object, the third pixel point spacing, and the third dimension information. Wherein, the third dimension information corresponding to the registration object includes the length, width, and height corresponding to the registration object.

[0064] Specifically, first, determine the center point coordinates corresponding to the CT original object according to the coordinate information corresponding to the upper left vertex of the first CT image in the CT original object and the coordinate information corresponding to the upper left vertex of the last CT image in the CT original object. At the same time, determine the center point coordinates corresponding to the PET original object according to the coordinate information corresponding to the upper left vertex of the first PET image in the PET original object and the coordinate information corresponding to the upper left vertex of the last PET image in the PET original object. Then, select one of the center point coordinates corresponding to the CT original object and the center point coordinates corresponding to the PET original object as the center point coordinates corresponding to the registration object. Usually, based on the center point coordinates of the CT original object, that is, determine the center point coordinates corresponding to the CT original object as the center point coordinates corresponding to the registration object.

[0065] Next, based on the length, width, and height of the CT original body and the length, width, and height of the PET original body, the length, width, and height of the registration body are determined. Specifically, taking the length of the registration body as an example, if the length of the CT original body is greater than the length of the PET original body, then the length of the CT original body is determined as the length of the registration body; if the length of the CT original body is less than the length of the PET original body, then the length of the PET original body is determined as the length of the registration body. Similarly, by comparing the height and width of the CT original body and the PET original body, the width and height of the registration body can be determined, thereby determining the third dimension information corresponding to the registration body.

[0066] Furthermore, based on the length, width, and height of the CT original body and the first pixel point spacing of each pixel point in the CT original body in the length, width, and height directions, the number of pixel points of the CT original body in the length, width, and height directions can be calculated. At the same time, based on the length, width, and height of the PET original body and the second pixel point spacing of each pixel point in the PET original body in the length, width, and height directions, the number of pixel points of the PET original body in the length, width, and height directions can be calculated. Further, by comparing the number of pixel points of the CT original body and the PET original body in the length, width, and height directions, the number of pixel points of the registration body in the length, width, and height directions can be determined.

[0067] For example, the number of pixel points of the CT original body in the length, width, and height directions are 300, 200, and 500 respectively, and the number of pixel points of the PET original body in the length, width, and height directions are 320, 200, and 450 respectively. Since the number of pixel points of the CT original body in the length direction is less than the number of pixel points of the PET original body in the length direction, the number of pixel points of the registration body in the length direction is determined to be 320. Similarly, the number of pixel points of the registration body in the width and height directions can be determined to be 200 and 500 respectively. This can ensure that the registration body covers the CT original body and the PET original body as much as possible, and at the same time can ensure that the registration body contains as many pixel points as possible.

[0068] Furthermore, after determining the length, width, and height of the registration body and the number of pixel points of the registration body in the length, width, and height directions, the third pixel point spacing of each pixel point in the registration body in the length, width, and height directions can be calculated based on this length, width, and height and the number of pixel points. Thus, based on this third pixel point spacing, the center point coordinates corresponding to the registration body, and the length, width, and height, the voxel data corresponding to the registration body can be determined.

[0069] For the embodiments of the present invention, in order to determine the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration body, the method of performing pixel interpolation processing on the registration body according to the CT eigenvalue, the PET eigenvalue and the voxel data of the registration body to obtain the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration body includes: according to the CT eigenvalue and the PET eigenvalue, using the trilinear interpolation algorithm, performing interpolation along the length, width and height directions of the registration body with the third pixel point spacing in the voxel data of the registration body as the step size, to obtain the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration body.

[0070] Specifically, after determining the voxel data corresponding to the registration body, it is possible to start from the upper left corner vertex of the registration body and perform pixel interpolation along the length, width and height directions with the third pixel point spacing as the step size, as Figure 3 shown. When calculating the CT registration eigenvalue corresponding to any pixel point in the registration body, determine the 6 pixel points in the CT original body that are closest to this pixel point in the front, back, left, right, up and down directions, and calculate the CT registration eigenvalue corresponding to any pixel point in the registration body according to the CT eigenvalues corresponding to these 6 pixel points. Similarly, when calculating the PET registration eigenvalue corresponding to any pixel point in the registration body, determine the 6 pixel points in the PET original body that are closest to this pixel point in the front, back, left, right, up and down directions, and calculate the PET registration eigenvalue corresponding to any pixel point in the registration body according to the PET eigenvalues corresponding to these 6 pixel points, so as to display the CT image, the PET image and the fusion image on the corresponding section respectively according to the CT registration eigenvalue and the PET registration eigenvalue. Since the embodiments of the present invention pre-calculate the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration body, it is possible to ensure the smoothness of subsequent image switching and rendering, and avoid the lag situation caused by real-time calculation.

[0071] 203. Fuse the CT registration eigenvalues and the PET registration eigenvalues corresponding to each pixel point on the target section in the registration body to obtain the fusion eigenvalue corresponding to each pixel point on the target section.

[0072] For the embodiments of the present invention, the calculation process of the fusion eigenvalue is exactly the same as that in step 102, and will not be elaborated here.

[0073] 204. Based on the fusion eigenvalue, generate and display the fusion image corresponding to the target section on the html page.

[0074] For the embodiments of the present invention, after determining the CT eigenvalue, PET eigenvalue, and fusion eigenvalue corresponding to each pixel point in the registration body, the target section is determined according to the doctor's diagnosis requirements, that is, according to the center point and normal vector selected by the doctor, the target section can be determined. Further, the CT eigenvalue, PET eigenvalue, and fusion eigenvalue corresponding to each pixel point on the target section in the registration body are determined.

[0075] In order to display the CT image, PET image, and fusion image in the display window, display window parameters are required to scale the CT eigenvalue, PET eigenvalue, and fusion eigenvalue corresponding to each pixel point on the target section. Specifically, the display window parameters include the length and width of the display window. Based on the display window parameters, the scaling ratio coefficient can be determined, and the CT eigenvalue, PET eigenvalue, and fusion eigenvalue corresponding to each pixel point on the target section are multiplied by the scaling ratio coefficient respectively to obtain the scaled CT eigenvalue, scaled PET eigenvalue, and scaled fusion eigenvalue. Further, the color value corresponding to the scaled PET eigenvalue is determined using a preset color bar, and then, based on the color value, a colored PET image is generated. At the same time, the CT eigenvalue is filtered using the window parameters and window level parameters. The above color rendering process for the PET image and the gray rendering process for the CT image are exactly the same as those in step 104 and will not be elaborated here. Finally, the CT image, PET image, and fusion image on the target section can be displayed in the html page. As Figure 4 shown, the target section is specifically the transverse section, coronal section, and sagittal section. Among the Figure 4 nine images in, the first row are the CT images of the transverse section, coronal section, and sagittal section respectively, the second row are the PET images of the transverse section, coronal section, and sagittal section respectively, and the third row are the fusion images of the transverse section, coronal section, and sagittal section.

[0076] Another web-based medical image browsing method provided by the embodiments of the present invention, compared with the current method of browsing and diagnosing medical images using a system platform based on the C / S architecture, the present invention can respond to a medical image browsing request, obtain a CT image sequence and a PET image sequence to be registered; and obtain the fusion eigenvalue corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively; finally, based on the fusion eigenvalue, generate and display the fusion image corresponding to the target section in the html page. Since the present invention adopts a web-based B / S architecture for medical image browsing, only the corresponding browsing function needs to be configured in the server, and other system platforms can display the corresponding medical images by accessing the server, so that medical images can be browsed on multiple platforms, reducing the operation and maintenance costs, and at the same time, it can also solve the problems of sharing of medical resources and remote diagnosis.

[0077] Further, as a Figure 1 specific implementation, an embodiment of the present invention provides a web-based medical image browsing device, as Figure 5 shown, the device includes: an acquisition unit 31, a fusion unit 32, and a display unit 33.

[0078] The acquisition unit 31 can be used to obtain a CT image sequence and a PET image sequence to be registered in response to a medical image browsing request.

[0079] The fusion unit 32 can be used to obtain the fusion feature values corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively.

[0080] The display unit 33 can be used to generate and display the fusion image corresponding to the target section in the html page based on the fusion feature values.

[0081] In a specific application scenario, in order to fuse the CT image sequence and the PET image sequence, as Figure 6 shown, the fusion unit 32 includes: a registration module 321 and a fusion module 322.

[0082] The registration module 321 can be used to register the CT image sequence and the PET image sequence according to the image information corresponding to the CT image sequence and the PET image sequence respectively, and obtain the CT registration feature values and the PET registration feature values corresponding to each pixel point in the registration volume.

[0083] The fusion module 322 can be used to fuse the CT registration feature values and the PET registration feature values corresponding to each pixel point on the target section in the registration volume to obtain the fusion feature values corresponding to each pixel point on the target section.

[0084] In a specific application scenario, the registration module 321 includes: a determination sub-module and an interpolation sub-module.

[0085] The determination sub-module can be used to determine the voxel data corresponding to the CT original volume composed of the CT image sequence and the CT feature values corresponding to each pixel point in the CT original volume according to the image information corresponding to the CT image sequence.

[0086] The determination sub-module can also be used to determine the voxel data corresponding to the PET original volume composed of the PET image sequence and the PET feature values corresponding to each pixel point in the PET original volume according to the image information corresponding to the PET image sequence.

[0087] The determining sub-module can also be used to determine the voxel data of the registration volume jointly corresponding to the CT original volume and the PET original volume according to the voxel data corresponding to the CT original volume and the voxel data corresponding to the PET original volume.

[0088] The interpolation sub-module can be used to perform pixel point interpolation processing on the registration volume according to the CT eigenvalue, the PET eigenvalue, and the voxel data of the registration volume, so as to obtain the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration volume.

[0089] In a specific application scenario, the determining sub-module can specifically be used to determine the first dimension information corresponding to the CT original volume, the first pixel point spacing of each pixel point in the CT original volume in the length, width, and height directions, and the first coordinate information corresponding to the target pixel point in the CT original volume according to the image information corresponding to the CT image sequence; determine the voxel data corresponding to the CT original volume according to the first dimension information, the first pixel point spacing, and the first coordinate information; calculate the CT eigenvalue corresponding to each pixel point in the CT original volume according to the slope parameter and the intercept parameter in the image information of the CT image sequence, and the pixel value corresponding to each pixel point in the CT original volume.

[0090] Furthermore, the determining sub-module can specifically also be used to determine the second dimension information corresponding to the PET original volume, the second pixel point spacing of each pixel point in the PET original volume in the length, width, and height directions, and the second coordinate information corresponding to the target pixel point in the PET original volume according to the image information corresponding to the PET image sequence; determine the voxel data corresponding to the PET original volume according to the second dimension information, the second pixel point spacing, and the second coordinate information; calculate the PET eigenvalue corresponding to each pixel point in the PET original volume according to the injection dose and the patient weight in the graphic information of the PET image sequence, and the lesion radiation concentration corresponding to each pixel point in the PET original volume.

[0091] In a specific application scenario, the determining sub-module may specifically be further configured to determine the center point coordinates corresponding to the CT original body and the center point coordinates corresponding to the PET original body according to the first coordinate information and the second coordinate information respectively; determine the center point coordinates corresponding to the registration body according to the center point coordinates corresponding to the CT original body and the center point coordinates corresponding to the PET original body; determine the third dimension information corresponding to the registration body according to the first dimension information and the second dimension information; determine the number of pixel points of the CT original body in the length, width, and height directions and the number of pixel points of the PET original body in the length, width, and height directions respectively according to the first dimension information and the first pixel point pitch, and the second dimension information and the second pixel point pitch; determine the number of pixel points of the registration body in the length, width, and height directions according to the number of pixel points of the CT original body in the length, width, and height directions and the number of pixel points of the PET original body in the length, width, and height directions; determine the third pixel point pitch of each pixel point in the registration body in the length, width, and height directions respectively based on the number of pixel points of the registration body in the length, width, and height directions and the third dimension information; determine the voxel data corresponding to the registration body according to the center point coordinates corresponding to the registration body, the third pixel point pitch, and the third dimension information.

[0092] In a specific application scenario, the interpolation sub-module may specifically be configured to perform interpolation along the length, width, and height directions of the registration body at a step size of the third pixel point pitch in the voxel data of the registration body by using a trilinear interpolation algorithm according to the CT eigenvalue and the PET eigenvalue, so as to obtain the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration body.

[0093] In a specific application scenario, the display unit 33 may further be configured to display the CT image and the PET image corresponding to the fusion image in the html page respectively.

[0094] It should be noted that for other corresponding descriptions of each functional module involved in a web-based medical image browsing device provided in an embodiment of the present invention, reference may be made to Figure 1 the corresponding description of the method shown, which will not be elaborated herein.

[0095] Based on the above as Figure 1For the method described above, correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the following steps are implemented: in response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered; according to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fusion feature values corresponding to each pixel point on the target section; based on the fusion feature values, generate and display the fusion image corresponding to the target section in an html page.

[0096] Based on the above as Figure 1 shown method and as Figure 5 shown in the embodiment of the device, an embodiment of the present invention further provides an entity structure diagram of a computer device, as Figure 7 shown. The computer device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor. The memory 42 and the processor 41 are both arranged on a bus 43. When the processor 41 executes the program, the following steps are implemented: in response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered; according to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fusion feature values corresponding to each pixel point on the target section; based on the fusion feature values, generate and display the fusion image corresponding to the target section in an html page.

[0097] Through the technical solution of the present invention, the present invention can, in response to a browsing request for a medical image, obtain a CT image sequence and a PET image sequence to be registered; and according to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fusion feature values corresponding to each pixel point on the target section; finally, based on the fusion feature values, generate and display the fusion image corresponding to the target section in an html page. Since the present invention adopts a web-based B / S architecture medical image browsing method, only the corresponding browsing function needs to be configured in the server, and other system platforms can display the corresponding medical images by accessing the server, so that the medical images can be browsed on multiple platforms, reducing the operation and maintenance costs, and at the same time, it can also solve the problems of sharing of medical resources and remote diagnosis.

[0098] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0099] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A web-based medical image browsing method, characterized in that, it includes: In response to a medical image browsing request, obtain a CT image sequence and a PET image sequence to be registered; According to the image information corresponding to the CT image sequence and the PET image sequence respectively, obtain the fusion feature values corresponding to each pixel point on the target section; Based on the fusion feature values, generate and display the fusion image corresponding to the target section on the html page; Among them, the step of obtaining the fusion feature values corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively includes: According to the image information corresponding to the CT image sequence, determine the first size information of the CT original body, the first pixel point spacing of each pixel point in the CT original body in the length, width, and height directions, and the first coordinate information corresponding to the target pixel point in the CT original body; According to the first size information, the first pixel point spacing, and the first coordinate information, determine the voxel data corresponding to the CT original body; According to the slope parameter and intercept parameter in the image information of the CT image sequence, and the pixel values corresponding to each pixel point in the CT original body, calculate the CT feature values corresponding to each pixel point in the CT original body; According to the image information corresponding to the PET image sequence, determine the second size information of the PET original body, the second pixel point spacing of each pixel point in the PET original body in the length, width, and height directions, and the second coordinate information corresponding to the target pixel point in the PET original body; According to the second size information, the second pixel point spacing, and the second coordinate information, determine the voxel data corresponding to the PET original body; According to the injection dose and patient weight in the graphic information of the PET image sequence, and the lesion radiation concentration corresponding to each pixel point in the PET original body, calculate the PET feature values corresponding to each pixel point in the PET original body; According to the voxel data corresponding to the CT original body and the voxel data corresponding to the PET original body, determine the voxel data of the registration body jointly corresponding to the CT original body and the PET original body; According to the CT feature values, the PET feature values, and the voxel data of the registration body, perform pixel point interpolation processing on the registration body to obtain the CT registration feature values and PET registration feature values corresponding to each pixel point in the registration body; Fuse the CT registration feature values and PET registration feature values corresponding to each pixel point on the target section of the registration body to obtain the fusion feature values corresponding to each pixel point on the target section.

2. The method according to claim 1, characterized in that, the step of determining the voxel data of the registration body jointly corresponding to the CT original body and the PET original body according to the voxel data corresponding to the CT original body and the voxel data corresponding to the PET original body includes: According to the first coordinate information and the second coordinate information, respectively determine the center point coordinates corresponding to the CT original body and the center point coordinates corresponding to the PET original body; Determine the center point coordinates of the registration volume according to the center point coordinates of the corresponding CT original volume and the center point coordinates of the corresponding PET original volume; Determine the third dimension information of the registration volume according to the first dimension information and the second dimension information; Determine the number of pixel points of the CT original volume in the length, width, and height directions and the number of pixel points of the PET original volume in the length, width, and height directions respectively according to the first dimension information and the first pixel point spacing, and the second dimension information and the second pixel point spacing; Determine the number of pixel points of the registration volume in the length, width, and height directions according to the number of pixel points of the CT original volume in the length, width, and height directions and the number of pixel points of the PET original volume in the length, width, and height directions; Based on the number of pixel points of the registration volume in the length, width, and height directions and the third dimension information, determine the third pixel point spacing of each pixel point in the registration volume in the length, width, and height directions respectively; Determine the voxel data of the registration volume according to the center point coordinates, the third pixel point spacing, and the third dimension information of the registration volume; 3. The method according to claim 1, wherein, the performing pixel interpolation processing on the registration volume according to the CT eigenvalue, the PET eigenvalue, and the voxel data of the registration volume to obtain the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration volume includes: Interpolate along the length, width, and height directions of the registration volume with the third pixel point spacing in the voxel data of the registration volume as the step size according to the CT eigenvalue and the PET eigenvalue by using the trilinear interpolation algorithm to obtain the CT registration eigenvalue and the PET registration eigenvalue corresponding to each pixel point in the registration volume; 4. The method according to claim 1, wherein, the method further includes: Display the CT image and the PET image corresponding to the fusion image in the html page respectively; 5. A web-based medical image browsing device, wherein, comprises: An acquisition unit, configured to acquire a CT image sequence and a PET image sequence to be registered in response to a medical image browsing request; A fusion unit, configured to obtain the fusion eigenvalue corresponding to each pixel point on the target section according to the image information corresponding to the CT image sequence and the PET image sequence respectively; A display unit, configured to generate and display the fusion image corresponding to the target section in the html page based on the fusion eigenvalue; The fusion unit is specifically configured to determine the first dimension information of the corresponding CT original volume, the first pixel point spacing of each pixel point in the CT original volume in the length, width, and height directions, and the first coordinate information of the target pixel point in the CT original volume according to the image information corresponding to the CT image sequence; determine the voxel data of the CT original volume according to the first dimension information, the first pixel point spacing, and the first coordinate information; Calculate the CT eigenvalue corresponding to each pixel point in the CT original volume according to the slope parameter and intercept parameter in the image information of the CT image sequence and the pixel value corresponding to each pixel point in the CT original volume; Determine the second dimension information corresponding to the PET original volume, the second pixel point spacing of each pixel point in the PET original volume in the length, width, and height directions, and the second coordinate information corresponding to the target pixel point in the PET original volume according to the image information corresponding to the PET image sequence; Determine the voxel data corresponding to the PET original volume according to the second dimension information, the second pixel point spacing, and the second coordinate information; Calculate the PET eigenvalue corresponding to each pixel point in the PET original volume according to the injection dose and patient weight in the graphic information of the PET image sequence and the lesion radiation concentration corresponding to each pixel point in the PET original volume; Determine the voxel data of the registration volume jointly corresponding to the CT original volume and the PET original volume according to the voxel data corresponding to the CT original volume and the voxel data corresponding to the PET original volume; Perform pixel point interpolation processing on the registration volume according to the CT eigenvalue, the PET eigenvalue, and the voxel data of the registration volume to obtain the CT registration eigenvalue and PET registration eigenvalue corresponding to each pixel point in the registration volume; Fuse the CT registration eigenvalue and PET registration eigenvalue corresponding to each pixel point on the target section in the registration volume to obtain the fusion eigenvalue corresponding to each pixel point on the target section.

6. A computer-readable storage medium, on which a computer program is stored, Characterized in that, When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 4 are implemented.

7. A computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, Characterized in that, When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 4 are implemented.

Images