Tumor magnetic sensitive signal extraction method, device and equipment based on ESWAN sequence and medium

Abstract

The invention provides a tumor magnetic sensitive signal extraction method and device based on an ESWAN sequence, equipment and a medium. The method comprises the following steps: acquiring a tumor phase diagram of a target part; inputting the tumor phase diagram into a preset medical image processing model, and sketching a suspected focus area in the tumor phase diagram to generate a focus sketching area; generating a three-dimensional region of interest according to the focus sketching region; based on the three-dimensional region of interest, the ratio of the magnetically sensitive signals within the volume of the tumor is obtained, and evaluation of the overall structure and heterogeneity of the tumor can be provided.

Description

Technical Field

[0001] The present application relates to the technical field of tumor imaging, and more specifically to a method, device, equipment and medium for extracting tumor magnetic susceptibility signals based on an ESWAN sequence. Background Art

[0002] Intratumoral susceptibility signal intensities (ITSS) represent continuous dot-like or thin-line low-signal areas on the phase image of the tumor. The main source is microbleeding and neovascularization inside the lesion. It can reflect the density and size of microvessels in pathological tissue and is a non-invasive and intuitive imaging sign that shows vascular proliferation inside the tumor.

[0003] Currently, the main methods for measuring ITSS include semiquantitative and quantitative assessments. However, due to cumbersome measurement methods, subjectivity, and poor repeatability, the results of semiquantitative and quantitative ITSS grading methods are inconsistent. Furthermore, these studies have focused on the head, which is less susceptible to respiratory and motion artifacts. Their applicability and reliability for abdominal organs require further exploration. Furthermore, large artifacts in phase images are not addressed, potentially leading to inaccurate results. Furthermore, quantitative ITSS measurement requires pre-screening of ITSS images visible to the naked eye. Summary of the Invention

[0004] The present application is made in order to solve the above-mentioned problems.

[0005] In a first aspect, the present application provides a method for extracting tumor magnetic susceptibility signals based on an ESWAN sequence, the method comprising:

[0006] Obtaining a tumor phase image of the target site; wherein the phase image is a susceptibility-weighted imaging image;

[0007] Inputting the tumor phase image into a preset medical image processing model, outlining the lesion area in the tumor phase image, and generating a lesion outlining area;

[0008] Delineating the area according to the lesion, generating a three-dimensional region of interest;

[0009] Based on the three-dimensional region of interest, a ratio of magnetic susceptibility signals within the tumor volume is obtained.

[0010] In one embodiment of the present application, before inputting the tumor phase image into a preset medical image processing model, the method further includes:

[0011] Performing a median filter transformation on the tumor phase image to obtain a median filter result;

[0012] Subtracting the tumor phase image from the median filtering result to obtain an intermediate image;

[0013] Extracting adjacent regions of low and high pixels of the intermediate image, and dilating a first preset number of pixels in a cross section to obtain abnormal pixels;

[0014] The abnormal pixels are re-assigned to obtain a tumor phase image after artifact removal.

[0015] In one embodiment of the present application, delineating the lesion region in the tumor phase image to generate a lesion delineated region includes:

[0016] Obtain a doctor's instruction, and perform closed-loop delineation on the lesion area in the tumor phase image according to the doctor's instruction to generate the lesion delineation area.

[0017] In one embodiment of the present application, performing closed-loop delineation on the lesion region in the tumor phase image to generate the lesion delineation region includes:

[0018] Delineate the lesion in each layer within the image range covered by the lesion. When outlining each layer, obtain the control points of the lesion contour, and use spline curves to automatically connect the control points to form a closed curve.

[0019] Fine-tune the contour line to fit the lesion boundary.

[0020] In one embodiment of the present application, generating a three-dimensional region of interest based on the lesion delineation area includes:

[0021] Calculate a distance map on the labeled layer, wherein the values ​​within the range of the region of interest are positive, and the values ​​outside the range are negative;

[0022] Create an empty three-dimensional array covering all layers that the region of interest passes through; among them, the annotated layers are filled with distance maps;

[0023] Spline interpolation is performed along a preset direction to fill in the pixel values ​​of the unlabeled layer to generate the three-dimensional region of interest.

[0024] In one embodiment of the present application, obtaining the ratio of magnetic susceptibility signals within the tumor volume based on the three-dimensional region of interest includes:

[0025] The ratio of the magnetic susceptibility signal within the tumor volume is obtained based on the ratio of the number of low-signal pixels displayed in the three-dimensional region of interest to the total number of pixels in the three-dimensional region of interest.

[0026] In one embodiment of the present application, the method further comprises: obtaining, based on the three-dimensional region of interest, a ratio of the intratumor magnetic susceptibility signal area on a layer having the largest intratumor magnetic susceptibility signal area to the area of ​​the region of interest; and / or,

[0027] Based on the three-dimensional region of interest, the position of the layer with the largest ratio of the magnetic susceptibility signal area in the tumor to the area of ​​the region of interest on each layer is obtained.

[0028] In a second aspect, the present application provides a device for extracting tumor magnetic susceptibility signals based on an ESWAN sequence, the device comprising:

[0029] An image acquisition module, configured to acquire a phase image of a tumor at a target site; wherein the phase image is a susceptibility-weighted imaging image;

[0030] a lesion delineation module, configured to input the tumor phase image into a preset medical image processing model, delineate the lesion region in the tumor phase image, and generate a lesion delineation region;

[0031] A three-dimensional image generation module, configured to generate a three-dimensional region of interest based on the lesion outline area;

[0032] The result output module is used to obtain the ratio of magnetic susceptibility signals within the tumor volume based on the three-dimensional region of interest.

[0033] In a third aspect of the present application, a computing device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 7.

[0034] In a fourth aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed, the method described above is executed.

[0035] According to the tumor magnetic susceptibility signal extraction method, device, equipment and medium based on the ESWAN sequence of the present application, the 3D tumor ITSS ratio (ITSSv) is automatically extracted and calculated based on the ratio of the number of pixels in the low signal area of ​​the tumor to the total number of pixels in the entire tumor. The entire processing flow is completed by a medical image processing model. The method is simple to operate, highly repeatable, and significantly reduces subjectivity. In addition, the ITSS ratio can more accurately reflect the relationship between the ITSS component and the tumor as a whole than the volume value, and is conducive to the comparison between different lesions. Compared with the two-dimensional ITSS ratio (ITSSs), the three-dimensional ITSS ratio (ITSSv) can provide an assessment of the overall structure and heterogeneity of the tumor, especially for evaluating lesions with complex or irregular morphology. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0037] Figure 1 A schematic flowchart of a method for extracting tumor magnetic susceptibility signals based on an ESWAN sequence according to an embodiment of the present application is shown;

[0038] Figure 2 Shows the wavy artifacts in the ESWAN sequence images;

[0039] Figures 3A-3F The flowchart of removing the wavy artifacts in ESWAN sequence images is shown;

[0040] Figure 4 Schematic diagram showing the calculation of the ITSS ratio (ITSSv) within the tumor volume by the AS software according to an embodiment of the present application;

[0041] Figure 5 A block diagram of a tumor magnetic susceptibility signal extraction device based on an ESWAN sequence according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present application more apparent, the following is a detailed description of example embodiments of the present application with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in this application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of this application.

[0043] Currently, the primary method for measuring ITSS is semiquantitative, grading ITSS based on their frequency and size. Park et al. categorized the severity of ITSS in gliomas into four grades based on the morphology and number of hypointense areas on high-resolution susceptibility-weighted imaging (HR-SWI) images: grade 0, no ITSS; grade 1, 1-5 punctate or thin linear ITSS; grade 2, 6-10 punctate or thin linear ITSS; and grade 3, 11 or more punctate or thin linear ITSS within a continuous region within the tumor. This semiquantitative method has been widely used in their subsequent ITSS-related studies of head and neck tumors. Bhattacharjee et al. explored the quantitative assessment of ITSS, using Matlab software and built-in functions to quantitatively measure ITSS within gliomas. A segmentation algorithm based on connected component analysis was used to calculate the total ITSS volume (TIV) and the ITSS vasculature volume (IVV).

[0044] The aforementioned ITSS semiquantitative grading method and the ITSS quantitative measurement method by Bhattacharjee et al. have inconsistent results due to cumbersome measurement techniques, subjectivity, and poor repeatability. Furthermore, these studies focused on the head, which is less susceptible to respiratory and motion artifacts. Their applicability and reliability for abdominal organs require further exploration. Furthermore, they fail to address large artifacts in phase images, potentially leading to inaccurate results. Furthermore, the ITSS quantitative measurement method by Bhattacharjee et al. requires pre-screening of ITSS images visible to the naked eye.

[0045] The two-dimensional ITSS ratio (ITSSs) only evaluates the ratio of the number of low-signal pixels displayed in the ROI of the largest ITSS area to the total number of pixels in the ROI. It lacks the assessment of the overall structure and heterogeneity of the tumor, and its application is particularly limited for lesions with complex or irregular morphology.

[0046] The following describes in detail the solution of the tumor magnetic susceptibility signal extraction method based on the ESWAN sequence according to the embodiment of the present application in conjunction with the accompanying drawings. The features of the various embodiments of the present application can be combined with each other without conflict.

[0047] Figure 1 FIG. 5 is a schematic flow chart of a method for extracting tumor magnetic susceptibility signals based on an ESWAN sequence according to an embodiment of the present application. Figure 1 As shown, the method for extracting tumor magnetic susceptibility signals based on the ESWAN sequence in an embodiment of the present application includes:

[0048] S101, obtaining a phase image of a tumor at a target site; wherein the phase image is a susceptibility-weighted imaging image;

[0049] It is understood that the Enhanced T2*-weighted angiography (ESWAN) sequence is a new technology based on susceptibility-weighted imaging (SWI), which uses susceptibility differences and blood oxygen level-dependent effects to generate quantitative values ​​such as phase, amplitude, and R2*. The ESWAN sequence is a new magnetic resonance imaging technology that utilizes susceptibility differences and blood oxygen level-dependent effects for imaging. It acquires intensity and phase data and performs post-processing by superimposing the phase information on the intensity data, producing images based on the differences in magnetic susceptibility of different tissues.

[0050] S102, inputting the tumor phase image into a preset medical image processing model, outlining the lesion area in the tumor phase image, and generating a lesion outlining area;

[0051] In some embodiments, step S102 may include:

[0052] Obtain the doctor's instructions, perform closed-loop delineation of the lesion area in the tumor phase image according to the doctor's instructions, and generate a lesion delineation area.

[0053] Among them, the NII format phase image was imported into Anatomy Sketch (AS) software, and then a physician with experience in abdominal and pelvic imaging diagnosis identified tumor lesions based on axial T2-weighted imaging (T2WI) and reference to diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) images. The ROI was interactively and semi-automatically outlined on the phase image, and finally a three-dimensional ROI area (Volume of interest, VOI) was obtained.

[0054] Perform closed-loop delineation on the lesion area in the tumor phase image to generate a lesion delineation area, including:

[0055] Delineate the lesion in each layer within the image range covered by the lesion. When outlining each layer, obtain the control points of the lesion contour, and use spline curves to automatically connect the control points to form a closed curve.

[0056] Fine-tune the contour line to fit the lesion boundary.

[0057] During specific implementation, outline the lesion in alternate layers within the image range covered by the lesion. When outlining each layer, use the left mouse button to click on the lesion outline to add control points. The software will automatically connect the control points using a spline curve to eventually form a closed curve.

[0058] After completing the outline, use the two-dimensional contour adjustment function of the AS software to fine-tune the contour line by dragging and dropping the mouse to make it fit the lesion boundary more closely.

[0059] The software automatically generates a 3D surface based on the interpolated layers. Users can continue to use the 3D surface correction function of the AS software to fine-tune the surface by dragging and dropping the mouse to correct errors caused by interpolation.

[0060] S103, delineating the area according to the lesion to generate a three-dimensional region of interest;

[0061] In some embodiments, step S103 may include:

[0062] The distance map is calculated on the annotated layer. The values ​​within the range of the area of ​​interest are positive, and the values ​​outside the range are negative.

[0063] A distance map is a tool for representing distance relationships between objects using a graph or data structure. It can be used to describe the positional relationships of objects in space, as well as the distance or similarity between objects. A two-dimensional distance map is typically used to represent distance relationships between objects on a plane. It can represent distances by plotting the positions of objects and the lines connecting them. A three-dimensional distance map is used to represent distance relationships between objects in space. It can represent distances by plotting the three-dimensional coordinates of objects and the lines connecting them.

[0064] Create an empty three-dimensional array covering all layers that the region of interest passes through; among them, the annotated layers are filled with distance maps;

[0065] Spline interpolation is performed along the preset direction to fill the pixel values ​​of the unlabeled layer and generate a three-dimensional region of interest.

[0066] In specific implementation, the distance map is calculated in the annotated layer. In the distance map result, the value within the ROI range is positive, and the value outside is negative; and the farther away from the boundary, the greater the absolute value of the pixel value.

[0067] Create an empty 3D array covering all layers that the ROI passes through. The annotated layers are filled with the distance map.

[0068] Spline interpolation is performed along the Z direction to fill in the pixel values ​​of the unlabeled layer. Finally, a three-dimensional distance map is obtained.

[0069] The position with a value of 0 in the three-dimensional distance map is the boundary of the final ROI.

[0070] S104. Based on the three-dimensional region of interest, obtain the ratio of the magnetic susceptibility signals within the tumor volume.

[0071] Due to the limitation of imaging technology, there are Figure 2 The red arrow indicates a wavy artifact. This artifact consists of a band of adjacent bright and dark pixels. An artifact removal algorithm was designed based on the characteristic that adjacent bright and dark pixel bands form wavy artifacts.

[0072] In some embodiments, step S104 may include:

[0073] Based on the ratio of the number of low-signal pixels displayed in the 3D ROI to the total number of pixels in the 3D ROI, the ratio of the magnetic susceptibility signal within the tumor volume was obtained.

[0074] The interpolation and annotation tools of AS software were used to obtain the ITSS ratio (ITSSv) within the tumor volume, where ITSSv was defined as the number of low-signal pixels displayed in the tumor volume divided by the total number of pixels in the tumor volume.

[0075] In some embodiments, step S104 may further include:

[0076] Based on the three-dimensional region of interest, obtaining the ratio of the magnetic susceptibility signal area in the tumor to the area of ​​the region of interest on the layer with the largest magnetic susceptibility signal area in the tumor; and / or,

[0077] Based on the three-dimensional region of interest, the position of the layer with the largest ratio of the magnetic susceptibility signal area in the tumor to the area of ​​the region of interest on each layer is obtained.

[0078] like Figure 4 Figure 2 shows the AS software's schematic diagram for calculating the ITSS ratio (ITSSv) within a tumor volume. Using the cervical cancer lesion shown in the figure as an example, the lesion was delineated on the phase image using interslice delineated with reference to T2WI, DWI, and ADC images to create a VOI. Using the AS software's interpolation and annotation tools, the ITSS ratio (ITSSv) within the tumor volume was calculated. ITSSv is defined as the number of low-signal pixels displayed within the tumor volume divided by the total number of pixels within the tumor volume, i.e., the area of ​​the green region in the figure divided by the total area within the ROI.

[0079] In some embodiments, after the VOI is generated, a plug-in within the Anatomy Sketch (AS) software is used to determine the ITSS area within the VOI using a set threshold, and then the ITSS ratio within the tumor volume (Intratumoral Susceptibility Signal Volume, ITSSv) is automatically obtained. ITSSv is defined as the number of low-signal pixels displayed in the tumor volume VOI divided by the total number of pixels within the tumor volume. The Anatomy Sketch (AS) software can automatically generate the following parameters: the ratio of the ITSS area to the ROI area on the layer with the largest ITSS area; the position of the layer with the largest ITSS area; c) the ITSS area on the layer with the largest ITSS area; the position of the layer with the largest ratio of ITSS area to ROI area on each layer; and e) the ITSS ratio within the tumor volume.

[0080] In some embodiments, before step S01, the method further includes:

[0081] Perform median filtering transformation on the tumor phase image to obtain the median filtering result; specifically, Figure 3A As shown, Figure 3A is the original input image, which is obtained after median filtering transformation Figure 3B .

[0082] The tumor phase image and the median filter result are subtracted to obtain the intermediate image. Specifically, the original image and the median filter result are subtracted, and the pixels with pixel values ​​lower than -150 in the result are identified as low signal, and the pixels with pixel values ​​higher than 200 are identified as high signal. The result is thresholded, and low signal pixels are represented by -1, high signal pixels are represented by 1, and the rest of the pixels are represented by 0 to obtain the result. Figure 3C .

[0083] Extract the adjacent areas of low and high pixels of the middle image, expand the first preset number of pixels in the cross section, and obtain abnormal pixels; specifically, extract the result Figure 3C The adjacent area of ​​1 and -1 is expanded by 1 pixel in the cross section to obtain the result Figure 3D The pixels within this area are considered to be abnormal pixels.

[0084] The abnormal pixels are reassigned to obtain the tumor phase map after artifact removal. Specifically, the abnormal pixels are reassigned to a new pixel value equal to the average of the pixel values ​​of the abnormal pixel and its 26 adjacent non-abnormal pixels. The result is Figure 3E .use Figure 3E replace Figure 3A The pixel value of the corresponding pixel in the final result is obtained Figure 3F ,but Figure 3Fis the result of the artifact removal operation.

[0085] According to the tumor magnetic susceptibility signal extraction method based on the ESWAN sequence according to an embodiment of the present invention, the 3D tumor ITSS ratio (ITSSv) is automatically extracted and calculated based on the ratio of the number of pixels in the low signal area of ​​the tumor to the total number of pixels in the entire tumor. The entire processing flow is completed through a medical image processing model. The method is simple to operate, highly repeatable, and significantly reduces subjectivity. In addition, the ITSS ratio can more accurately reflect the relationship between the ITSS component and the tumor as a whole than the volume value, and is conducive to the comparison between different lesions. Compared with the two-dimensional ITSS ratio (ITSSs), the three-dimensional ITSS ratio (ITSSv) can provide an assessment of the overall structure and heterogeneity of the tumor, especially for evaluating lesions with complex or irregular morphology.

[0086] like Figure 5 As shown, in one embodiment, a device for extracting tumor magnetic susceptibility signals based on an ESWAN sequence is provided, and the device may specifically include:

[0087] An image acquisition module 511 is used to acquire a phase image of the tumor at the target site; wherein the phase image is a susceptibility-weighted imaging image;

[0088] The lesion delineation module 512 is used to input the tumor phase image into a preset medical image processing model, delineate the lesion area in the tumor phase image, and generate a lesion delineation area;

[0089] A three-dimensional image generation module 513 is used to generate a three-dimensional region of interest based on the lesion outline area;

[0090] The result output module 514 is configured to obtain the ratio of magnetic susceptibility signals within the tumor volume based on the three-dimensional region of interest.

[0091] In some embodiments, the device also includes an artifact processing module, which is used to perform a median filtering transformation on the tumor phase image before inputting the tumor phase image into a preset medical image processing model to obtain a median filtering result; subtract the tumor phase image and the median filtering result to obtain an intermediate image; extract the adjacent areas of low pixels and high pixels of the intermediate image, and expand a first preset number of pixels in the cross section to obtain abnormal pixels; and reassign the abnormal pixels to obtain a tumor phase image after artifact removal.

[0092] In some embodiments, the lesion delineation module is further used to obtain a doctor's instruction, perform closed-loop delineation on the lesion area in the tumor phase image according to the doctor's instruction, and generate a lesion delineation area.

[0093] In some embodiments, the lesion delineation module is also used to delineate the lesion in alternate layers within the image range covered by the lesion. When outlining each layer, the control points of the lesion contour are obtained, and the control points are automatically connected using a spline curve to eventually form a closed curve; the contour line is fine-tuned to make the contour line fit the lesion boundary.

[0094] In some embodiments, the three-dimensional image generation module is configured to calculate a distance map on the annotated layer, wherein the values ​​within the range of the region of interest in the distance map are positive, and the values ​​outside the range are negative;

[0095] Create an empty three-dimensional array covering all layers that the region of interest passes through; among them, the annotated layers are filled with the distance map; perform spline interpolation along the preset direction, fill the pixel values ​​of the unannotated layers, and generate a three-dimensional region of interest.

[0096] In some embodiments, the result output module is configured to obtain a ratio of magnetic susceptibility signals within the tumor volume based on a ratio of the number of low-signal pixels displayed in the three-dimensional region of interest to the total number of pixels in the three-dimensional region of interest.

[0097] In some embodiments, the result output module is also used to obtain the ratio of the area of ​​the magnetic sensitivity signal in the tumor to the area of ​​the region of interest on the layer with the largest area of ​​the magnetic sensitivity signal in the tumor based on the three-dimensional region of interest; and / or, based on the three-dimensional region of interest, obtain the position of the layer with the largest ratio of the area of ​​the magnetic sensitivity signal in the tumor to the area of ​​the region of interest on each layer.

[0098] According to the tumor magnetic susceptibility signal extraction device based on the ESWAN sequence of an embodiment of the present invention, the 3D tumor ITSS ratio (ITSSv) is automatically extracted and calculated based on the ratio of the number of pixels in the low-signal area of ​​the tumor to the total number of pixels in the entire tumor. The entire processing flow is completed through a medical image processing model. This method is simple to operate, highly repeatable, and significantly reduces subjectivity. In addition, the ITSS ratio can more accurately reflect the relationship between the ITSS component and the tumor as a whole than the volume value, and is conducive to the comparison between different lesions. Compared with the two-dimensional ITSS ratio (ITSSs), the three-dimensional ITSS ratio (ITSSv) can provide an assessment of the overall structure and heterogeneity of the tumor, especially for evaluating lesions with complex or irregular morphology.

[0099] In another embodiment, the present invention provides a computing device that may include a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, causes the processor to execute the above-described method for extracting tumor magnetic susceptibility signals based on the ESWAN sequence.

[0100] Those skilled in the art can understand the specific operations of the computing device according to the embodiment of the present invention in combination with the above content. For the sake of brevity, the specific details are not repeated here. Only some main operations of the processor are described as follows:

[0101] Obtaining a tumor phase image of the target site; wherein the phase image is a susceptibility-weighted imaging image;

[0102] Inputting the tumor phase image into a preset medical image processing model, outlining the suspected lesion area in the tumor phase image, and generating a lesion outline area;

[0103] Delineate the area based on the lesion and generate a three-dimensional region of interest;

[0104] Based on the three-dimensional region of interest, the ratio of magnetic susceptibility signals within the tumor volume was obtained.

[0105] A computing device according to an embodiment of the present invention can implement the aforementioned method for extracting tumor magnetic susceptibility signals based on an ESWAN sequence. Those skilled in the art can understand the specific operation of the computing device according to an embodiment of the present invention in conjunction with the above description, and for the sake of brevity, a detailed description thereof will not be given here.

[0106] The computing device according to the present invention can intelligently determine whether the user needs to touch up their makeup based on multiple factors that affect touch-up and remind the user without the need for manual detection by the user. It is easy to use and has high detection efficiency. Moreover, as the number of times the user uses it increases, the reminder becomes more accurate, greatly improving the user experience.

[0107] In another embodiment, the present invention provides a computer-readable medium storing a computer program that, when executed, executes the ESWAN sequence-based tumor magnetic susceptibility signal extraction method described in the above-described embodiment. Any tangible, non-transitory computer-readable medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray Discs, etc.), flash memory, and / or the like. These computer program instructions can be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing device to form a machine, such that the instructions executed on the computer or other programmable data processing device can generate a device that implements a specified function. These computer program instructions can also be stored in a computer-readable memory, which can instruct the computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory can form an article of manufacture that includes an implementation device that implements the specified function. The computer program instructions can also be loaded onto a computer or other programmable data processing device to execute a series of operational steps on the computer or other programmable device to generate a computer-implemented process, such that the instructions executed on the computer or other programmable device provide the steps for implementing the specified function.

[0108] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present invention. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as claimed in the appended claims.

[0109] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0110] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach to the present invention should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More precisely, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0111] It will be understood by those skilled in the art that, except where mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus disclosed herein may be combined in any combination. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0112] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0113] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0114] The above is merely a description of specific embodiments of the present invention, and the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention are intended to be covered by the scope of protection of the present invention. The scope of protection of the present invention shall be based on the scope of protection of the claims.

Claims

1. A method for extracting tumor magnetic susceptibility signals based on ESWAN sequence, characterized in that: The method comprises: Obtaining a tumor phase image of the target site; wherein the phase image is a susceptibility-weighted imaging image; Inputting the tumor phase image into a preset medical image processing model, outlining the lesion area in the tumor phase image, and generating a lesion outlining area; Delineating the area according to the lesion, generating a three-dimensional region of interest; Based on the three-dimensional region of interest, a ratio of magnetic susceptibility signals within the tumor volume is obtained.

2. The method according to claim 1, wherein Before inputting the tumor phase image into a preset medical image processing model, the method further includes: Performing a median filter transformation on the tumor phase image to obtain a median filter result; Subtracting the tumor phase image from the median filtering result to obtain an intermediate image; Extracting adjacent regions of low and high pixels of the intermediate image, and dilating a first preset number of pixels in a cross section to obtain abnormal pixels; The abnormal pixels are re-assigned to obtain a tumor phase image after artifact removal.

3. The method according to claim 1, wherein Delineating the lesion region in the tumor phase image to generate a lesion delineated region includes: Obtain a doctor's instruction, and perform closed-loop delineation on the lesion area in the tumor phase image according to the doctor's instruction to generate the lesion delineation area.

4. The method according to claim 3, wherein The step of performing closed-loop delineation on the lesion region in the tumor phase image to generate the lesion delineation region includes: Delineate the lesion in each layer within the image range covered by the lesion. When outlining each layer, obtain the control points of the lesion contour, and use spline curves to automatically connect the control points to form a closed curve. Fine-tune the contour line to make it fit the lesion boundary.

5. The method according to claim 1, wherein The step of generating a three-dimensional region of interest based on the lesion delineation area includes: Calculating a distance map on the labeled layer, wherein the values ​​within the range of the region of interest are positive, and the values ​​outside the range are negative; Create an empty three-dimensional array covering all layers that the region of interest passes through; among them, the annotated layers are filled with distance maps; Spline interpolation is performed along a preset direction to fill in the pixel values ​​of the unlabeled layer to generate the three-dimensional region of interest.

6. The method according to claim 1, wherein Obtaining a ratio of magnetic susceptibility signals within the tumor volume based on the three-dimensional region of interest includes: The ratio of the magnetic susceptibility signal within the tumor volume is obtained based on the ratio of the number of low-signal pixels displayed in the three-dimensional region of interest to the total number of pixels in the three-dimensional region of interest.

7. The method according to claim 1, wherein The method further comprises: Based on the three-dimensional region of interest, obtaining a ratio of the area of ​​the magnetic susceptibility signal in the tumor to the area of ​​the region of interest on the layer with the largest magnetic susceptibility signal area in the tumor; and / or, Based on the three-dimensional region of interest, the position of the layer with the largest ratio of the magnetic susceptibility signal area in the tumor to the area of ​​the region of interest on each layer is obtained.

8. A tumor magnetic susceptibility signal extraction device based on ESWAN sequence, characterized in that: The device comprises: An image acquisition module, configured to acquire a phase image of a tumor at a target site; wherein the phase image is a susceptibility-weighted imaging image; a lesion delineation module, configured to input the tumor phase image into a preset medical image processing model, delineate the lesion region in the tumor phase image, and generate a lesion delineation region; A three-dimensional image generation module, configured to generate a three-dimensional region of interest based on the lesion outline area; The result output module is used to obtain the ratio of magnetic susceptibility signals within the tumor volume based on the three-dimensional region of interest.

9. A computing device, characterized in that The computing device includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer readable medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is executed.

Images