A contour drawing method, device, equipment and storage medium

Abstract

Embodiments of the present invention provide a contour drawing method, apparatus, device, and storage medium, which relate to the field of medical image processing. The method includes: obtaining a main image sequence and a secondary image sequence of a target object; the main image sequence and the secondary image sequence are image sequences of different sections of the target object; adjusting the pixel positions of the secondary image sequence to the corresponding pixel positions in the main image sequence to obtain a new image sequence; wherein, the pixel positions in the main image sequence are known; performing contour drawing on the new image sequence to generate a three-dimensional contour. By using this method, the limitation of the image direction can be eliminated during contour drawing, and medical image information can be analyzed more comprehensively and conveniently.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing, and in particular to a contouring method, device, equipment and storage medium. Background Art

[0002] Radiotherapy is a treatment method for tumors. Usually, before radiotherapy, it is necessary to first obtain the patient's medical image, then outline the tumor area in the medical image, and formulate a treatment plan for the tumor area. Finally, the patient is given radiotherapy according to the corresponding treatment plan.

[0003] Existing radiotherapy planning systems only support the delineation of medical images of one section, and can only obtain contour points based on the medical images of this section. However, due to the differences in the location of lesions, it may be necessary to delineate medical images of other sections for some lesions.

[0004] Therefore, there is an urgent need for a delineation solution for medical images of different sections to achieve contour delineation in medical images and accurate positioning of lesions. Summary of the invention

[0005] The embodiments of the present invention provide a contouring method, device, equipment and storage medium, which can be used to more comprehensively and conveniently analyze medical image information without being restricted by the image direction during contouring.

[0006] In a first aspect, an embodiment of the present invention provides a contour delineation method, the method comprising:

[0007] Acquire a primary image sequence and a secondary image sequence of a target object; the primary image sequence and the secondary image sequence are image sequences of different sections of the target object;

[0008] Adjusting the pixel positions of the secondary image sequence to corresponding pixel positions in the primary image sequence to obtain a new image sequence; wherein the pixel positions in the primary image sequence are known;

[0009] The new image sequence is contoured to generate a three-dimensional contour.

[0010] In one embodiment, adjusting the pixel positions of the secondary image sequence to corresponding pixel positions in the primary image sequence to obtain a new image sequence includes:

[0011] Registering the primary image sequence with the secondary image sequence to obtain a transformation matrix;

[0012] According to the conversion matrix, each pixel position of the secondary image sequence is adjusted to a corresponding pixel position in the primary image sequence to obtain the new image sequence.

[0013] In one embodiment, registering the main image sequence with the secondary image sequence to obtain a transformation matrix includes:

[0014] Adjusting the section direction of the secondary image sequence to the section direction of the main image sequence according to the direction matrix;

[0015] Registering the secondary image sequence adjusted according to the direction matrix with the main image sequence to obtain the transformation matrix.

[0016] In one embodiment, contouring the new image sequence to generate a three-dimensional contour includes:

[0017] Contouring the new image sequence to obtain the coordinates of contour pixel points;

[0018] Generating the three-dimensional contour according to the coordinates of the contour pixel points and the section direction of the secondary image sequence.

[0019] In one embodiment, generating the three-dimensional contour according to the coordinates of the contour pixel points and the section direction of the secondary image sequence includes:

[0020] Invoking a volume three-dimensional reconstruction algorithm according to the coordinates of the contour pixel points and the section direction of the secondary image sequence to generate the three-dimensional contour.

[0021] In one embodiment, after generating the three-dimensional contour, it includes:

[0022] Using a preset medical image filter to cut the three-dimensional contour to obtain a set of contour points in different section directions, where the different section directions are section directions different from the section direction of the secondary image sequence.

[0023] In one embodiment, before converting the pixel positions of the secondary image sequence to the pixel positions in the main image sequence to obtain a new image sequence, the method further includes:

[0024] Registering the main image sequence to obtain the pixel positions in the main image sequence, where the pixel positions in the main image sequence are the coordinates of each pixel point in the main image sequence in the treatment plan coordinate system.

[0025] In a second aspect, an embodiment of the present invention further provides a contouring device, and the device includes:

[0026] An acquisition module, configured to acquire a main image sequence and a secondary image sequence of a target object; the main image sequence and the secondary image sequence are image sequences of different sections of the target object;

[0027] A processing module, configured to adjust the pixel positions of each of the secondary image sequences to the corresponding pixel positions in the primary image sequence, so as to obtain a new image sequence; wherein, the pixel positions in the primary image sequence are known;

[0028] An outlining module, configured to perform contour outlining on the new image sequence to generate a three-dimensional contour.

[0029] In a third aspect, an embodiment of the present invention further provides a contour outlining device, including: a processor and a memory, where the memory stores a computer program executable by the processor, and the processor executes the computer program to perform the contour outlining method according to any one of the first aspects.

[0030] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the storage medium, and when the computer program is run by a processor, it performs the contour outlining method according to any one of the first aspects.

[0031] The present invention provides a contour outlining method, device, device and storage medium. By obtaining the primary image sequence and the secondary image sequence in two sectional directions of a target object, and using the known pixel positions of the primary image sequence of the target object, the pixel positions of the secondary image sequence in a sectional direction different from that of the primary image sequence are adjusted to the corresponding pixel positions of the primary image sequence, so as to obtain a new image sequence corresponding to the pixel positions of the primary image sequence, and contour outlining is performed on the new image sequence to generate a three-dimensional contour corresponding to the new image sequence, so that the radiotherapy planning system is no longer limited to the image outlining of a single section, realizing the outlining of medical images in different sections by the radiotherapy planning system, effectively avoiding information errors caused by the image outlining of a single section. By outlining the contour with images in different sections, the information of the area surrounded by the outlined contour can be displayed more comprehensively and accurately, which helps to accurately locate the lesion position, thereby effectively ensuring the accuracy and reliability of subsequent treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a schematic flowchart of a contour outlining method provided by the present invention;

[0034] Figure 2 It is a schematic flowchart of a method for adjusting pixel positions in contour outlining provided by the present invention;

[0035] Figure 3 Flow schematic diagram of an image registration method in contour drawing provided by the present invention;

[0036] Figure 4 Flow schematic diagram of a method for generating a three-dimensional contour in contour drawing provided by the present invention;

[0037] Figure 5 Flow schematic diagram of another contour drawing method provided by the present invention;

[0038] Figure 6 Flow schematic diagram of another contour drawing method provided by the present invention;

[0039] Figure 7 Schematic diagram of a contour drawing device provided by the present invention;

[0040] Figure 8 Schematic diagram of a contour drawing device provided by the present invention.

[0041] An acquisition module 1000 is used to acquire a primary image sequence and a secondary image sequence of a target object; the primary image sequence and the secondary image sequence are different modules of the target object; 2000, a processing module; 3000, a drawing module; 10, a contour drawing device; 11, a processor; 12, a memory. Detailed implementation manners

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0043] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0044] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0045] Before explaining the present invention in detail, the application scenarios of the present invention will be introduced first.

[0046] Before radiotherapy for a target object, a corresponding treatment plan usually needs to be designed for the target object through a Treatment Planning System (TPS). The design of the radiotherapy plan requires determining the location of the lesion in the target object, and the contour delineation of medical images is the main technical means for lesion localization. Therefore, before radiotherapy for the target object, medical images collected by a medical imaging device for the target object can be obtained first, and the preset image delineation algorithm in the radiotherapy plan system can be used to delineate the medical images to obtain the corresponding three-dimensional contours.

[0047] However, in traditional technologies, the image delineation algorithm of the radiotherapy plan system only supports medical images of a single section, that is, it can only delineate medical images of a single section, but cannot achieve the delineation of medical images of different sections. Due to the limitation of the section direction, the information in the medical image of a single section is limited, so that the contour obtained by delineating the medical image of a single section may be difficult to completely represent the location of the lesion. Therefore, it is also necessary to combine the contours obtained by delineating the medical images of other sections to accurately locate the lesion location.

[0048] The image sequences provided in the following embodiments of the present application are composed of multiple slice medical images of the same section. The medical imaging device for collecting the image sequences can be, for example, a CT scan (Computed Tomography) device. Correspondingly, the image sequence is a CT image sequence. The medical imaging device can also be an ultrasound image acquisition device. Correspondingly, the image sequence is an ultrasound image sequence. Of course, the image imaging device can also be other types of medical imaging devices to collect other similar image sequences. The embodiments of the present application do not limit this.

[0049] Exemplarily, taking a CT scan device as an example, if cranial CT images are to be collected, since axial medical images can better represent the lesions in the cranial region, it is necessary to take axial cranial medical images by CT; if CT images of other parts are to be collected, and the lesions in other parts need to be assisted by CT images of other sections, then CT needs to collect CT images of other sections. The radiotherapy plan system currently only supports the coordinate registration of one section, which makes the radiotherapy plan only support the delineation of images of one section and cannot directly delineate images of different sections.

[0050] Therefore, the embodiments of the present application provide a contour delineation method, device, equipment and storage medium, which can also achieve the delineation of images of different sections when the radiotherapy plan system only supports the coordinate registration of one gantry.

[0051] The contour drawing method provided by the present application will be explained below with reference to the accompanying drawings through multiple embodiments. The contour drawing device that executes the contour drawing method can be a computer device with processing functions, which can be any computer device installed with a radiotherapy planning system, such as a laptop computer or a desktop computer. Figure 1 It is a schematic flowchart of a contour drawing method provided by the present invention. As Figure 1 shown, the contour drawing method may include:

[0052] S110, obtaining a main image sequence and a secondary image sequence of a target object.

[0053] Among them, the main image sequence and the secondary image sequence are image sequences of different sections of the target object.

[0054] The target object can be a to-be-treated object or a preset phantom object. The main image sequence and the secondary image sequence are respectively image sequences of different sections collected for the same target object using the same medical imaging device. Among them, the image sequences of different sections collected by the same medical imaging device refer to the medical image sequences of different sections collected by the same medical imaging device for the same target object.

[0055] The sections of medical images are usually divided into axial, coronal, and sagittal. For example, the main image sequence can be the axial image sequence of the target object, and the secondary image sequence can be the coronal or sagittal image sequence of the target object.

[0056] S120, adjusting the pixel positions of the secondary image sequence to the corresponding pixel positions in the main image sequence to obtain a new image sequence.

[0057] Among them, the pixel positions in the main image sequence are known, that is, the positions of each pixel point in the main image sequence in the radiotherapy planning coordinate system are known. The pixel positions in the secondary image sequence are unknown, that is, the positions of each pixel point in the secondary image sequence in the radiotherapy planning coordinate system are unknown. Therefore, in possible implementation examples, the main image sequence can be used as the fixed image sequence, and the secondary image sequence can be used as the floating image sequence. Based on the pixel positions in the main image sequence, the pixel positions of the secondary image sequence are adjusted to the corresponding pixel positions in the main image sequence to obtain a new image sequence. The section of the new image sequence is the same as that of the secondary image sequence, but the pixel positions in the new image sequence correspond to the pixel positions in the main image sequence. That is, through the adjustment of the pixel positions, the positions of the pixel points in the new image sequence in the radiotherapy planning coordinate system are known, so that the positions of the same pixel point in the new image sequence and the main image sequence in the radiotherapy planning coordinate system are kept consistent.

[0058] S130, performing contour drawing on the new image sequence to generate a three-dimensional contour.

[0059] After obtaining the new image sequence by executing S120 above, the new image sequence can be outlined to generate a three-dimensional contour. In a possible example, the new image sequence can be displayed, and the new image sequence can be outlined according to the contour outlining operation input by the user for the new image sequence. Then, a three-dimensional contour can be generated based on the contour point coordinates obtained from the contour outlining. In another possible example, the new image sequence may not be displayed, and an automatic outlining algorithm can be directly used to outline the new image sequence. Then, a three-dimensional contour can be generated based on the contour point coordinates obtained from the contour outlining.

[0060] In this embodiment, by obtaining the main image sequence and the secondary image sequence in two sectional directions of the target object, and using the known pixel positions of the main image sequence of the target object, the pixel positions of the secondary image sequence in a sectional direction different from that of the main image sequence are adjusted to the pixel positions corresponding to the main image sequence, obtaining a new image sequence corresponding to the pixel positions of the main image sequence, and outlining the new image sequence to generate a three-dimensional contour corresponding to the new image sequence, so that the radiotherapy planning system is no longer limited to the image outlining of a single section, realizing the outlining of medical images in different sections by the radiotherapy planning system, effectively avoiding the information error caused by the image outlining of a single section. By outlining the contour with images in different sections, the information of the area surrounded by the outlined contour can be displayed more comprehensively and accurately, which helps to accurately locate the lesion position, thereby effectively ensuring the accuracy and reliability of the subsequent treatment plan.

[0061] In the above Figure 1 Based on a provided method for contour outlining, the present invention also discloses a possible implementation manner for adjusting pixel positions in a method for contour outlining. Figure 2 It is a flowchart of a method for adjusting pixel positions in contour outlining provided by the present invention. As Figure 2 shown, in the above method S120, adjusting the pixel positions of the secondary image sequence to the corresponding pixel positions in the main image sequence to obtain a new image sequence may include:

[0062] S201, registering the main image sequence and the secondary image sequence to obtain a transformation matrix.

[0063] In a possible implementation example, a preset medical image registration algorithm can be used to register the main image sequence and the secondary image sequence to obtain a transformation matrix. The preset medical image registration algorithm can be, for example, a registration algorithm pre-compiled by the user through an open-source program platform. Among them, the transformation matrix is used to represent the correlation relationship between the pixel positions in the main image sequence and the secondary image sequence.

[0064] S202, according to the transformation matrix, adjust the pixel positions of the secondary image sequence to the corresponding pixel positions in the main image sequence to obtain a new image sequence.

[0065] In the case where a transformation matrix is obtained through image registration, the transformation matrix can be applied to the secondary image sequence to adjust the pixel positions of the secondary image sequence to the corresponding pixel positions in the primary image sequence, so that the section planes of the new image sequence are consistent with those of the secondary image sequence, but the pixel positions of the new image sequence correspond to those of the primary image sequence, thereby making the coordinate positions of the same pixel point in the radiotherapy planning coordinate system the same in the image sequences of different section planes.

[0066] In this embodiment, by using the transformation matrix obtained by registering the primary image sequence and the secondary image sequence, and using the transformation matrix and the original secondary image sequence, a new image sequence is generated, so that the positions of the same pixel point in the new image sequence and the primary image sequence are consistent in the radiotherapy planning coordinate system, which is convenient for the radiotherapy planning system to directly perform image delineation on the new image sequence, so that the radiotherapy planning system is no longer limited to image delineation of a single section plane.

[0067] In the above Figure 2 Based on a method for adjusting pixel positions in contour delineation provided above, the present invention also provides a possible implementation manner of an image registration method in contour delineation. Figure 3 It is a schematic flowchart of an image registration method in contour delineation provided by the present invention. As Figure 3 shown, in S201 of the above method, registering the primary image sequence and the secondary image sequence to obtain a transformation matrix may include:

[0068] S301, adjusting the section plane direction of the secondary image sequence to the section plane direction of the primary image sequence according to the direction matrix.

[0069] Before performing image registration, it is necessary to first adjust the section plane direction of the secondary image sequence to the section plane direction of the primary image sequence so that the section plane directions of the adjusted primary and secondary image sequences are consistent. In a possible implementation example, the section plane direction of the secondary image sequence can be adjusted to the section plane direction of the primary image sequence according to a preset direction matrix. Among them, the preset direction matrix is used to represent the transformation relationship between the section plane direction of the secondary image sequence and the section plane direction of the primary image sequence, which can be determined in advance by the section plane directions of the primary and secondary image sequences. For example, if the primary image sequence is an axial image sequence and the secondary image sequence is a coronal image sequence, then the preset direction matrix can be the direction matrix between the axial and coronal planes.

[0070] S302, registering the secondary image sequence adjusted according to the direction matrix with the primary image sequence to obtain a transformation matrix.

[0071] After adjusting the section plane direction of the secondary image sequence, a preset medical image registration algorithm can be used to perform image registration on the secondary image sequence adjusted according to the direction matrix and the primary image sequence to obtain a transformation matrix.

[0072] In this embodiment, by adjusting the section direction of the secondary image sequence to be consistent with that of the primary image sequence before image registration, it is possible to directly use two image sequences with the same section direction for registration during subsequent medical image registration, reducing the error during image registration and making the registration result more accurate.

[0073] Based on the above Figure 1 On the basis of a provided contour drawing method, the present invention also discloses a possible implementation manner of a method for generating a three-dimensional contour in contour drawing. Figure 4 It is a schematic flowchart of a method for generating a three-dimensional contour in contour drawing provided by the present invention. As Figure 4 shown, in the above method S130, contour drawing is performed on the new image sequence to generate a three-dimensional contour, which may include:

[0074] S410, performing contour drawing on the new image sequence to obtain contour pixel point coordinates.

[0075] A contour is a commonly used feature in medical images and contains the overall shape information of a human tissue. In order to only focus on the tissue in the lesion area during subsequent radiotherapy and avoid interference from irrelevant human tissue information around the lesion, it is necessary to perform contour drawing on the lesion in the new image sequence to obtain the contour pixel point coordinates of the corresponding lesion, so as to achieve the positioning of the lesion. These contour pixel points constitute the entire contour of the lesion. Optionally, for contour drawing in medical section images, there are two methods: manual drawing and automatic drawing. For automatic drawing, it can be directly performed using a preset medical drawing algorithm in the radiotherapy technology system. In one possible example, the new image sequence can be displayed, and according to the contour drawing operation input by the user for the new image sequence, contour drawing is performed on the new image sequence, and then the contour point coordinates obtained from the contour drawing are used. In another possible example, the new image sequence may not be displayed, and an automatic drawing algorithm is directly used to perform contour drawing on the new image sequence, and then the contour point coordinates obtained from the contour drawing are used.

[0076] S420, generating a three-dimensional contour according to the contour pixel point coordinates and the section direction of the secondary image sequence.

[0077] The new image sequence is generated based on the secondary image sequence. For the new image, the section direction of the secondary image sequence is its clearest image direction, and the section of the new image sequence is consistent with that of the secondary image sequence. After obtaining the contour pixel point coordinates of the lesion in the new image sequence after contour drawing, a three-dimensional contour created based on the two-dimensional contour of the lesion can be generated according to the contour pixel point coordinates and the section direction of the secondary image sequence.

[0078] In this embodiment, since the positions of the same pixel points in the new image sequence and the main image sequence in the radiotherapy planning coordinate system remain consistent, the contour pixel point coordinates can be directly obtained by contour drawing for the new image sequence. Then, relying on the section direction of the secondary image sequence, a three-dimensional contour can be generated, which is convenient for setting treatment targets according to the three-dimensional contour of the lesion in the radiotherapy plan.

[0079] Based on the method for generating a three-dimensional contour provided in the above embodiment, in order to better explain and illustrate the generation of the three-dimensional contour, where S420, generating a three-dimensional contour according to the contour pixel point coordinates and the section direction of the secondary image sequence, includes:

[0080] S401, calling a volume three-dimensional reconstruction algorithm according to the contour pixel point coordinates and the section direction of the secondary image sequence to generate a three-dimensional contour.

[0081] Generating a three-dimensional contour is a way of three-dimensional volume reconstruction, and a volume three-dimensional reconstruction algorithm can be called to achieve it. In a possible implementation, a voxel filling algorithm can be used as the three-dimensional reconstruction algorithm, and a voxel is the basic unit that makes up the three-dimensional volume data. Specifically, a preset mesh division software can be used to divide the three-dimensional contour of the lesion into meshes first. At the same time, the size of the divided meshes can be adjusted accordingly according to needs to meet different requirements for accuracy and speed in different situations. In this embodiment, the contour pixel point coordinates are the basic units that make up the three-dimensional volume data. The contour pixel point coordinates obtained by the above-mentioned contour drawing can be filled into the meshes one by one according to the section direction of the secondary image sequence. For the meshes that are not filled, they can be filled according to the relationship between the points of these meshes and the contour pixel point coordinates. For example, when the pixel points to be filled in the mesh are inside the contour pixel point coordinates, they are filled with 1, and for the points outside the contour pixel point coordinates, they are filled with 0. When all the meshes are filled, the information of the three-dimensional contour of the lesion is generated.

[0082] In this embodiment, by adopting a three-dimensional volume reconstruction algorithm, according to the coordinates of the contour pixel points and the section direction of the secondary image sequence, the originally two-dimensional contour point set of the lesion is filled into the three-dimensional contour, making the information of the lesion in the radiotherapy system more abundant and achieving accurate positioning of the lesion.

[0083] In the above Figure 1 Based on a provided method for contour drawing, the present invention also provides a possible implementation of another method for contour drawing. Figure 5 It is a schematic flowchart of another method for contour drawing provided by the present invention. As Figure 5 shown, after S130, generating a three-dimensional contour in the above method, includes:

[0084] S140. Use a preset medical image filter to cut the three-dimensional contour to obtain contour point sets in different section directions.

[0085] Among them, the different section directions are section directions different from the section direction of the sub-image sequence.

[0086] In order to use the three-dimensional contour of the lesion to achieve accurate positioning of the lesion, a preset medical image filter can be used to cut the three-dimensional contour to obtain contour point sets in different section directions. Among them, the different section directions are section directions different from the section direction of the sub-image sequence. Optionally, an ITK (Insight Segmentation and Registration Toolkit, a medical image registration and segmentation toolkit) image filter can be used to cut out the contour point sets in the three-dimensional contour that are different from the section direction of the sub-image sequence to obtain contour information in different section directions. For example, when the sub-image sequence is a coronal image sequence, an ITK can be used to cut out the axial contour point set and sagittal contour point set of the lesion, and contour point sets at any angle can also be cut out. Then, the position of the lesion can be accurately located by combining the axial contour point set and the sagittal contour point set.

[0087] In this embodiment, by cutting the three-dimensional contour to obtain contour point sets in different directions, it is possible to draw the coronal or sagittal images to obtain the contours in two other different directions, which is convenient for accurately positioning the position of the lesion according to the contour information of the medical images in other sections in the radiotherapy planning system.

[0088] In the above Figure 1 Based on a provided contour drawing method, the present invention also discloses a possible implementation manner of another contour drawing method. Figure 6 It is a schematic flowchart of another contour drawing method provided by the present invention. As Figure 6 shown, in S120 of the above method, before adjusting the pixel positions of the sub-image sequence to the corresponding pixel positions in the main image sequence, it includes:

[0089] S115. Register the main image sequence to obtain the pixel positions in the main image sequence.

[0090] The pixel positions in the main image sequence are: the coordinates of each pixel point in the main image sequence in the treatment plan coordinate system.

[0091] In the radiotherapy planning system, only one cross-sectional image coordinate system registration is currently supported. Therefore, before contour drawing, the main image sequence needs to be registered to the radiotherapy planning coordinate system first. For example, the main image sequence is an axial image sequence. Since the axial images have been registered to the radiotherapy planning coordinate system, the pixel positions in the main image sequence can be obtained. That is to say, the coordinates of each pixel point in the main image sequence in the treatment planning coordinate system can be obtained.

[0092] In this embodiment, by completing the registration of the main image sequence, the positions of each pixel point in the main image sequence in the radiotherapy planning coordinate system are obtained, so that the sub-image sequence can adjust the pixel positions according to the positions of the main image sequence in the radiotherapy planning coordinate system, which is convenient for subsequent contour drawing of the image sequence with a direction different from that of the main image sequence in the radiotherapy planning system, and realizes the localization of the lesion.

[0093] Figure 7 It is a schematic diagram of a contour drawing device provided by the present invention, as Figure 7 shown. The contour drawing device includes:

[0094] An acquisition module 1000, configured to acquire the main image sequence and the sub-image sequence of the target object; the main image sequence and the sub-image sequence are image sequences of different cross-sections of the target object;

[0095] A processing module 2000, configured to adjust the pixel positions of the sub-image sequence to the corresponding pixel positions in the main image sequence to obtain a new image sequence; wherein, the pixel positions in the main image sequence are known;

[0096] A contour drawing module 3000, configured to perform contour drawing on the new image sequence to generate a three-dimensional contour.

[0097] In one embodiment, the processing module 2000 is further specifically configured to register the main image sequence and the sub-image sequence to obtain a transformation matrix; according to the transformation matrix, adjust the pixel positions of the sub-image sequence to the corresponding pixel positions in the main image sequence to obtain a new image sequence.

[0098] In one embodiment, the processing module 2000 is further specifically configured to adjust the cross-sectional direction of the sub-image sequence to the cross-sectional direction of the main image sequence according to the direction matrix; register the sub-image sequence adjusted according to the direction matrix with the main image sequence to obtain a transformation matrix.

[0099] In one embodiment, the contour drawing module 3000 is further specifically configured to perform contour drawing on the new image sequence to obtain the coordinates of the contour pixel points; generate a three-dimensional contour according to the coordinates of the contour pixel points and the cross-sectional direction of the sub-image sequence.

[0100] In one embodiment, the delineation module 3000 is further configured to call a volume 3D reconstruction algorithm to generate a 3D contour according to the coordinates of the contour pixel points and the direction of the section of the secondary image sequence.

[0101] In one embodiment, the contouring device also includes a cutting module for cutting the three-dimensional contour using a preset medical image filter to obtain contour point sets in different cutting plane directions, wherein the different cutting plane directions are cutting plane directions different from the cutting plane directions of the secondary image sequence.

[0102] In one embodiment, the contouring device further includes a registration module for registering the main image sequence to obtain the position of each pixel in the main image sequence, where each pixel position in the main image sequence is: the coordinates of each pixel point in the main image sequence in the treatment plan coordinate system.

[0103] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0104] Figure 8 A schematic diagram of a contour delineation device provided by the present invention, which may be a computing device or server with computing and processing capabilities.

[0105] The contour delineation device 10 includes: a processor 11 and a memory 12, the memory 12 stores a computer program executable by the processor 11, and the processor 11 executes the computer program to perform the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0106] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the contour drawing method in the above embodiment is executed.

[0107] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0110] The above-mentioned integrated units implemented in the form of software functional units can be stored in a computer-readable storage medium. The above-mentioned software functional units stored in a storage medium include several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: Processor) to execute some steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (English: Read-Only Memory, abbreviated as: ROM), random access memories (English: Random Access Memory, abbreviated as: RAM), magnetic disks or optical discs that can store program codes.

[0111] As mentioned above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A contour drawing method, characterized in that, The method comprises: Acquire a primary image sequence and a secondary image sequence of a target object; the primary image sequence and the secondary image sequence are image sequences in different section directions of the target object; Adjusting the pixel positions of the secondary image sequence to corresponding pixel positions in the primary image sequence to obtain a new image sequence; wherein the pixel positions in the primary image sequence are known; The new image sequence is contoured to generate a three-dimensional contour.

2. The method according to claim 1, wherein The step of adjusting each pixel position of the secondary image sequence to a corresponding pixel position in the primary image sequence to obtain a new image sequence includes: Registering the primary image sequence with the secondary image sequence to obtain a transformation matrix; According to the conversion matrix, each pixel position of the secondary image sequence is adjusted to a corresponding pixel position in the primary image sequence to obtain the new image sequence.

3. The method according to claim 2, wherein The primary image sequence and the secondary image sequence are registered to obtain a transformation matrix, including: Adjusting the direction of the section of the secondary image sequence to the direction of the section of the primary image sequence according to the direction matrix; The secondary image sequence adjusted according to the direction matrix is registered with the primary image sequence to obtain the conversion matrix.

4. The method according to claim 1, wherein Delineating the new image sequence to generate a three-dimensional contour comprises: Delineating the new image sequence to obtain coordinates of contour pixels; The three-dimensional contour is generated according to the coordinates of the contour pixel points and the direction of the section of the secondary image sequence.

5. The method according to claim 4, characterized in that The step of generating the three-dimensional contour according to the contour pixel coordinates and the section direction of the secondary image sequence comprises: According to the coordinates of the contour pixel points and the direction of the section of the secondary image sequence, a volume 3D reconstruction algorithm is called to generate the 3D contour.

6. The method according to claim 1, wherein After generating the three-dimensional contour, the method comprises: The three-dimensional contour is cut using a preset medical image filter to obtain contour point sets in different section directions, wherein the different section directions are section directions different from the section directions of the secondary image sequence.

7. The method according to claim 1, characterized in that, Before converting each pixel position of the secondary image sequence to a pixel position in the primary image sequence to obtain a new image sequence, the method further includes: The main image sequence is registered to obtain the position of each pixel in the main image sequence, where each pixel position in the main image sequence is: the coordinates of each pixel point in the main image sequence in the treatment plan coordinate system.

8. A contour drawing device, characterized in that, The device comprises: An acquisition module, used to acquire a primary image sequence and a secondary image sequence of a target object; the primary image sequence and the secondary image sequence are image sequences in different section directions of the target object; A processing module, used for adjusting the pixel positions of the secondary image sequence to corresponding pixel positions in the primary image sequence to obtain a new image sequence; wherein the pixel positions in the primary image sequence are known; The outlining module is used to outline the new image sequence to generate a three-dimensional outline.

9. A contour drawing device, characterized in that, include: A processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor executes the computer program to perform the contour delineation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is run by a processor, it executes the contour drawing method according to any one of claims 1-7.

Images