Tumor heterogeneity analysis method and device based on super-resolution microscopic imaging

Abstract

The invention discloses a tumor heterogeneity analysis method and equipment based on super-resolution microscopic imaging, and relates to the field of medical image analysis. The method comprises the steps that a tumor imaging result is obtained, the tumor imaging result is generated through a super-resolution microscopic imaging technology, and the tumor imaging result comprises a tumor image; determining a target area of the tumor image; based on the tumor imaging result, quantitative analysis parameters are determined, and the quantitative analysis parameters are used for quantifying capillary features of at least two dimensions of tumor capillaries in the target area; on the basis of the quantitative analysis parameters, tumor heterogeneity analysis is conducted on different target areas, heterogeneity analysis results are obtained, and different target areas belong to the same tumor or different tumors. By adopting the scheme provided by the invention, the quantitative analysis parameters are generated based on the tumor imaging result, and quantitative analysis of tumor microvessel characteristics is realized, so that the accuracy of tumor heterogeneity analysis is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image analysis, and in particular to a tumor heterogeneity analysis method and device based on super-resolution microscopy. Background Art

[0002] Tumor heterogeneity is the spatial and temporal heterogeneity of tumors in molecular biology, gene expression, and microenvironmental characteristics, which directly affects tumor growth, metastasis, drug sensitivity, and prognosis.

[0003] In related technologies, super-resolution microscopy can be used to image microvascular morphology and micro-hemodynamics in tissues by tracking the trajectory of contrast agent microbubbles moving with blood flow. The imaging process of this technology can be divided into four steps: separation and extraction of moving microbubble signals, sub-pixel localization of extracted microbubble signals, localization of moving microbubble tracking, and cumulative mapping imaging of the tracking trajectory.

[0004] However, super-resolution microscopy imaging schemes lack quantitative methods that can quantify microblood flow characteristics, resulting in a single analysis dimension, making it difficult to comprehensively and accurately evaluate tumor biological characteristics, and leading to insufficient accuracy in heterogeneity assessment. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and device for tumor heterogeneity analysis based on super-resolution microscopy to solve the problems of insufficient comprehensiveness and accuracy of tumor heterogeneity analysis.

[0006] To achieve the above-mentioned object of the invention, in one aspect, the present application provides a method for analyzing tumor heterogeneity based on super-resolution microscopy, the method comprising: obtaining a tumor imaging result, the tumor imaging result being generated by super-resolution microscopy technology, and the tumor imaging result including a tumor image; Determining a target region of a tumor image; determining quantitative analysis parameters based on the tumor imaging results, wherein the quantitative analysis parameters are used to quantify microvascular characteristics of tumor microvessels in at least two dimensions in the target region; and performing tumor heterogeneity analysis on different target regions based on the quantitative analysis parameters to obtain heterogeneity analysis results, wherein the different target regions belong to the same tumor or the different target regions belong to different tumors.

[0007] As a further improvement of the present application, the tumor imaging results include a density map and a velocity map, wherein the density map is used to reflect the distribution of tumor microvessels, and the velocity map is used to reflect the blood flow velocity in the tumor microvessels; the method also includes: determining the quantitative analysis parameters in at least two dimensions based on the density map and the velocity map; wherein the quantitative analysis parameters in different dimensions are used to characterize the microvascular characteristics in different dimensions.

[0008] As a further improvement of the present application, the quantitative analysis parameters of at least two dimensions are determined based on the density map, including: based on the density map, determining the microvascular density distribution parameters, microvascular geometric state parameters and microvascular perfusion parameters; wherein the microvascular density distribution parameters are used to quantify the microvascular density and distribution characteristics, the microvascular geometric state parameters are used to characterize the microvascular morphology and spatial structure characteristics, and the microvascular perfusion parameters are used to characterize the dynamic characteristics of blood perfusion in the microvessels.

[0009] As a further improvement of the present application, the quantitative analysis parameters of at least two dimensions are determined based on the velocity map, including: based on the velocity map, determining blood flow velocity parameters, blood flow direction parameters and hemodynamic parameters, and the hemodynamic parameters are at least used to characterize the pulsation characteristics of the microvessels.

[0010] As a further improvement of the present application, the tumor heterogeneity analysis is performed on different target areas based on the quantitative analysis parameters, including: performing a histogram analysis on the target area based on the quantitative analysis parameters to obtain a first heterogeneity analysis result; or performing a principal component analysis on the target area based on the quantitative analysis parameters to obtain a second heterogeneity analysis result.

[0011] As a further improvement of the present application, the tumor heterogeneity analysis is performed on different target areas based on the quantitative analysis parameters, including: inputting the first heterogeneity analysis results and the second heterogeneity analysis results corresponding to different target areas into a heterogeneity analysis model; performing tumor heterogeneity analysis through the heterogeneity analysis model to obtain third heterogeneity analysis results for different target areas.

[0012] As a further improvement of the present application, determining the target area of ​​the tumor image includes: obtaining a grayscale tissue image containing the tumor site; performing tumor edge identification based on the grayscale tissue image to obtain a tumor edge identification result; and determining the target area based on the tumor edge identification result, wherein the target area contains at least a portion of the tumor.

[0013] As a further improvement of the present application, when different target areas belong to the same tumor, determining the target area based on the tumor edge recognition result includes: determining the geometric center of the target area based on the tumor edge recognition result; generating concentric annular sub-areas through morphological corrosion operation with the geometric center as the origin, wherein each concentric annular sub-area is one of the target areas; or determining the tumor circumscribed rectangle based on the tumor edge recognition result; dividing the tumor circumscribed rectangle into equal parts in the horizontal and axial directions to obtain equally divided grid areas, each of which is one of the target areas.

[0014] As a further improvement of the present application, the method also includes: expanding the target area to the tumor surrounding area through morphological dilation operation, or expanding based on equal distance; dividing the tumor surrounding area into concentric rings or grids to obtain a target area including the tumor surrounding area.

[0015] As a further improvement of the present application, the heterogeneity analysis results include at least one of the following forms: a pseudo-color mapping image, used to display the differences in vascular distribution density or blood flow velocity in each sub-region; a three-dimensional heat map, superimposed on the grayscale tissue image of the tumor, and marking the high heterogeneity areas; statistical charts, including bar charts or line charts, used to compare the quantitative results of microvascular characteristics of different sub-regions.

[0016] As a further improvement of the present application, the obtaining of tumor imaging results includes: tracking the movement trajectory of contrast agent microbubbles in the tumor microvessels, separating and extracting high-frequency motion microbubble signals; performing sub-pixel positioning on the high-frequency motion microbubble signals, and tracking the microbubble movement based on the positioning results to obtain a tracking trajectory; accumulating information such as the density and speed of the motion microbubbles reflected by the tracking trajectory, and mapping the accumulated results to the corresponding spatial position to obtain the tumor imaging results.

[0017] On the other hand, the present application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the tumor heterogeneity analysis method based on super-resolution microscopy as described in any of the above aspects.

[0018] On the other hand, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the tumor heterogeneity analysis method based on super-resolution microscopy as described in any of the above aspects.

[0019] On the other hand, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the tumor heterogeneity analysis method based on super-resolution microscopy as described in any one of the above aspects.

[0020] Compared with the related art, the solution provided by this application has the following beneficial effects.

[0021] In the embodiments of the present application, based on super-resolution microscopic imaging technology, tumor imaging results with micron-level resolution are obtained, and multi-dimensional quantitative analysis parameters are generated through density maps and velocity maps to achieve high-precision quantitative analysis of tumor microvascular characteristics, effectively improving the accuracy, comprehensiveness, safety and analysis efficiency of tumor heterogeneity analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of a tumor heterogeneity analysis method based on super-resolution microscopy provided in an exemplary embodiment of the present application is shown; Figure 2 A schematic diagram of obtaining tumor imaging results provided by an exemplary embodiment of the present application is shown; Figure 3 A schematic diagram of a density map and a velocity map provided by an exemplary embodiment of the present application is shown; Figure 4 A schematic diagram of determining quantitative analysis parameters in at least two dimensions based on a density map according to an exemplary embodiment of the present application is shown; Figure 5 FIG2 shows a schematic diagram of determining quantitative analysis parameters based on a velocity map according to an exemplary embodiment of the present application; Figure 6 A schematic diagram showing quantitative analysis parameters provided by an exemplary embodiment of the present application is shown; Figure 7 A schematic diagram of a process for determining heterogeneity of different tumors provided by an exemplary embodiment of the present application is shown; Figure 8 A schematic diagram of a process for determining tumor heterogeneity in different target regions within the same tumor according to an exemplary embodiment of the present application is shown; Figure 9 A comparison diagram showing target areas obtained by concentric ring subdivision and grid subdivision provided in an exemplary embodiment of the present application is shown; Figure 10 A schematic diagram of an expanded target area provided by an exemplary embodiment of the present application is shown.

[0023] Figure 11 A structural block diagram of an electronic device provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] The present invention will be described in detail below with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by those skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0025] It should be noted that the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In addition, the terms "first," "second," etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0026] Please refer to Figure 1 , which shows a flowchart of a tumor heterogeneity analysis method based on super-resolution microscopy provided in an exemplary embodiment of the present application, the method includes the following steps.

[0027] Step 101: Obtain tumor imaging results.

[0028] The tumor imaging results are generated by super-resolution microscopy technology, and the tumor imaging results include tumor images.

[0029] Super-resolution microscopy is an imaging method that breaks through the diffraction limits of traditional ultrasound, achieving resolution down to the micron level and providing spatial resolution for tumor heterogeneity analysis. Super-resolution microscopy precisely images the micron-scale characteristics of microvessels in tumor tissue by tracking moving microbubbles within these vessels.

[0030] This embodiment uses a tumor heterogeneity analysis method based on super-resolution microscopy technology. Ultrasound-resolution microscopy is used to obtain multi-dimensional feature data of tumor microvessels. Combined with a quantitative algorithm, the heterogeneity differences between different regions are quantified. This method can solve the problems of feature omission and quantification bias caused by insufficient resolution of traditional pathology or ordinary microscopy technology.

[0031] Step 102: Determine the target area of ​​the tumor image.

[0032] Step 103: Determine quantitative analysis parameters based on the tumor imaging results.

[0033] The quantitative analysis parameters are used to quantify the microvascular characteristics of tumor microvessels in at least two dimensions in the target area.

[0034] Step 104 : Based on the quantitative analysis parameters, tumor heterogeneity analysis is performed on different target regions to obtain heterogeneity analysis results.

[0035] The different target regions belong to the same tumor, or the different target regions belong to different tumors.

[0036] In summary, in the embodiments of the present application, based on super-resolution microscopy technology, tumor imaging results with micron-level resolution are obtained, and multi-dimensional quantitative analysis parameters are generated through density maps and velocity maps to achieve high-precision quantitative analysis of tumor microvascular characteristics, effectively improving the accuracy, comprehensiveness, safety and analysis efficiency of tumor heterogeneity analysis.

[0037] The following describes the process of obtaining tumor imaging results based on super-resolution microscopy technology.

[0038] Please refer to Figure 2 , which shows a schematic diagram of obtaining tumor imaging results provided by an exemplary embodiment of the present application.

[0039] After contrast agent microbubbles are injected into the patient's veins by bolus injection or drip, the microbubbles quickly enter the tumor microvessels through blood circulation.

[0040] Since contrast agent microbubbles cannot penetrate the blood vessel walls and only move with the blood inside the blood vessels, high-precision imaging results reflecting the microvascular structure and blood flow dynamics inside the tumor can be obtained by accurately tracking and imaging the movement trajectory of the microbubbles.

[0041] Specifically, the high-frequency moving microbubble signal is separated and extracted from the ultrasound echo signal. Sub-pixel localization is performed on the high-frequency moving microbubble signal, and based on the localization results, the microbubble motion is tracked to obtain a tracking trajectory. Information such as the density and velocity of the moving microbubbles reflected in the tracking trajectory is accumulated and mapped to the corresponding spatial location to obtain the tumor imaging result.

[0042] Indicative, such as Figure 2 , which includes the following four steps.

[0043] Step 1: Use singular value decomposition filtering, frequency domain filtering and other spatiotemporal filtering techniques to effectively separate and extract high-frequency motion microbubble signals with obvious fluctuations from the tumor echo signal. The high-frequency motion microbubble signals here refer to ultrasound signals with obvious fluctuations in the time dimension due to the flow of contrast agent microbubbles.

[0044] Step 2: Sub-pixel positioning of the extracted high-frequency motion microbubble signal. Sub-pixel positioning refers to the use of centroid weighted averaging and gradient feature optimization methods to break through the diffraction limit of traditional ultrasound imaging and accurately determine the center position of a single microbubble signal.

[0045] Step 3: Based on the positioning results, a microbubble tracking algorithm such as Kalman filtering with motion model constraints is used to accurately track the movement trajectory of each microbubble in the tumor microvessels to obtain its movement speed and direction information.

[0046] Step 4: Accumulate the microbubble density, velocity and other information reflected by the tracking trajectory, and accurately map the accumulated results to the corresponding spatial position to form a tumor imaging result with micron-level resolution.

[0047] Based on the tumor imaging results obtained above, a density map and a velocity map can be further generated. The density map is used to reflect the distribution of tumor microvessels and is obtained by counting the number of contrast agent microbubbles passing through each pixel position during the imaging process. The velocity map is used to reflect the blood flow velocity in the tumor microvessels and is obtained by statistically calculating the velocity of contrast agent microbubbles passing through each pixel position during the imaging process.

[0048] The density map and velocity map respectively display the structural characteristics and dynamic blood flow characteristics of tumor microvessels from different dimensions, thereby providing an accurate and reliable data basis for the next step of target area determination and multi-dimensional quantitative analysis parameter construction.

[0049] Based on the density map and the velocity map, quantitative analysis parameters of at least two dimensions are determined, wherein the quantitative analysis parameters of different dimensions are used to characterize microvascular characteristics of different dimensions.

[0050] Please refer to Figure 3 , which shows a schematic diagram of a density map and a velocity map provided by an illustrative embodiment of the present application. The density map is determined based on the microvascular morphology in the tumor imaging results, and its pixel amplitude represents the microbubble density. The velocity map is determined based on the microblood flow velocity in the tumor imaging results, and its pixel amplitude represents the movement speed of microbubbles in the blood vessels.

[0051] Please refer to Figure 4 , which shows a schematic diagram of determining quantitative analysis parameters of at least two dimensions based on a density map provided by an exemplary embodiment of the present application.

[0052] In one possible implementation, microvascular density distribution parameters, microvascular geometric state parameters, and microvascular perfusion parameters are determined based on the density map.

[0053] Optional, such as Figure 4 , the microvascular density distribution parameters are determined based on the amplitude information of each pixel point in the density map, the microvascular geometric distribution parameters are determined based on the pixel distribution on the density map, and the microvascular perfusion parameters are determined based on the time dimension change state of the density map.

[0054] Microvascular density distribution parameters are used to quantify microvascular density and distribution characteristics, including but not limited to the maximum, minimum, mean, standard deviation, entropy, and relative blood volume. The amplitude of a single pixel on the density map reflects the number of contrast agent microbubbles that passed through the corresponding spatial location during the acquisition period. Statistical analysis of pixel amplitudes allows for the precise calculation of these density distribution characteristic parameters.

[0055] Microvascular geometric state parameters are used to characterize the morphological and spatial structural characteristics of microvessels. After image segmentation, the pixel distribution on the density map is converted into a binary image through binarization technology to obtain the microvascular geometric distribution information. By performing geometric and topological analysis on the binary image, the area, area ratio, and microvascular complexity, tortuosity and other indicators of the geometric figure can be quantitatively calculated.

[0056] Microvascular perfusion parameters are used to characterize the dynamic characteristics of blood perfusion in microvessels. By analyzing the changes in the density map in the time dimension, dynamic characteristic parameters such as microvascular perfusion rate are calculated.

[0057] Please refer to Figure 5 , which shows a schematic diagram of determining quantitative analysis parameters based on a velocity map provided by an exemplary embodiment of the present application.

[0058] In a possible implementation, blood flow velocity parameters, blood flow direction parameters, and hemodynamic parameters are determined based on the velocity map, wherein the hemodynamic parameters are used to characterize characteristics such as microvascular pulsation.

[0059] Among them, blood flow velocity parameters are used to quantitatively characterize the magnitude and changing pattern of blood flow velocity in microvessels, specifically including the maximum value, minimum value, average value, standard deviation and entropy of velocity distribution; blood flow direction parameters are used to characterize the spatial distribution direction characteristics of blood flow in microvessels; and hemodynamic parameters are used to characterize the pulsation characteristics of microvessels. The pulsation index is obtained by analyzing and calculating the changing trend of the velocity of each pixel point on the velocity map with the time dimension, so as to more deeply reflect the hemodynamic characteristics of microvessels.

[0060] Based on the above, the present invention also specifically proposes a perfusion index based on the comprehensive calculation of density map and velocity map. The perfusion index is a parameter calculated by combining the product of microbubble density and average velocity. It can effectively reflect the perfusion status in the microvasculature and further improve the accuracy of tumor heterogeneity analysis and its clinical guidance significance.

[0061] Please refer to Figure 6 , which shows a schematic diagram of quantitative analysis parameters provided in an illustrative embodiment of the present application. Microvascular density distribution parameters, microvascular geometry distribution parameters, and microvascular perfusion characteristic parameters are derived from super-resolution microscopic imaging density maps. Microvascular velocity distribution parameters, microvascular direction distribution parameters, and microvascular dynamics parameters are derived from super-resolution microscopic imaging velocity maps. Furthermore, the microvascular perfusion index is obtained based on both the density map and the velocity map.

[0062] By constructing the above-mentioned quantitative analysis parameter package, this embodiment comprehensively quantifies the characteristics of tumor microvessels from multiple dimensions, including microvessel density, spatial structure, blood flow velocity, direction, and dynamic characteristics, thereby achieving a high-precision, quantitative, and multidimensional assessment of tumor heterogeneity.

[0063] Based on the construction of the above-mentioned multi-dimensional quantitative analysis parameter package, this application further performs tumor heterogeneity analysis on different target areas based on the quantitative analysis parameters to obtain heterogeneity analysis results.

[0064] In one possible implementation, tumor heterogeneity analysis can be achieved using histogram analysis, principal component analysis, and deep learning model analysis.

[0065] Optionally, a histogram analysis is performed based on the quantitative analysis parameters to obtain a first heterogeneity analysis result.

[0066] Histogram analysis can intuitively display the distribution of various characteristic parameters of tumor tissue microvessels, helping to identify key biological characteristics and potential heterogeneous subpopulations.

[0067] Optionally, based on the quantitative analysis parameters, principal component analysis is performed on the target region to obtain a second heterogeneity analysis result.

[0068] Principal component analysis reduces the dimensionality of high-dimensional data and extracts the key features that contribute most to heterogeneity assessment, thereby effectively reducing data complexity and accurately reflecting the main variation directions of tumor heterogeneity.

[0069] Optionally, tumor heterogeneity analysis can be performed based on deep learning model analysis. First, a first heterogeneity analysis result and a second heterogeneity analysis result are obtained through histogram analysis and principal component analysis. Subsequently, the first and second heterogeneity analysis results corresponding to different target regions are input into the heterogeneity analysis model, and tumor heterogeneity analysis is performed using the heterogeneity analysis model to obtain third heterogeneity analysis results for different target regions.

[0070] Heterogeneity analysis models preferably utilize data-driven methods such as deep learning and machine learning, which can automatically mine complex patterns and associated features from large amounts of parameter data, thereby improving the accuracy and reliability of heterogeneity analysis. Using features extracted from histograms and principal component analysis as input to deep learning models further optimizes the accuracy of tumor classification and prediction.

[0071] In a possible implementation, the heterogeneity analysis results obtained based on the above implementation also include pseudo-color mapping images, three-dimensional heat maps, statistical charts, and other forms.

[0072] Pseudo-color mapping images are used to intuitively display the differences in vascular distribution density or blood flow velocity in each sub-region, clearly presenting the heterogeneous spatial distribution characteristics within the tumor with different colors; three-dimensional heat maps are superimposed on the grayscale tissue image of the tumor and mark the high heterogeneity areas, revealing the key biologically active areas in the tumor in a spatially visualized manner; statistical charts, including bar charts or line charts, are used to quantitatively compare the quantitative results of microvascular characteristics in different sub-regions, enabling doctors to quickly identify and evaluate the differences in pathological characteristics of different regions.

[0073] In the embodiments of the present application, based on the combination of histogram analysis, principal component analysis and heterogeneity analysis model, the present invention can accurately explore the heterogeneity of tumor areas.

[0074] After obtaining the tumor imaging results, it is necessary to further determine the target area of ​​the tumor image to achieve subsequent accurate heterogeneity analysis.

[0075] Optionally, a grayscale tissue image containing the tumor is first acquired. This grayscale tissue image visually demonstrates significant differences in acoustic impedance within different regions of the scanned tissue. Tumor margin identification is then performed based on the grayscale tissue image to obtain a tumor margin identification result. Finally, based on the tumor margin identification result, a target region containing part or all of the tumor is determined.

[0076] Among them, tumor edge recognition specifically adopts image difference maximization, edge detection algorithm or automatic recognition method based on deep learning to significantly improve the accuracy and stability of tumor boundary recognition.

[0077] In the embodiment of the present application, the target areas may belong to the same tumor or different tumors.

[0078] In the case that different target regions belong to different tumors, the target region may contain the entire tumor, and determining the tumor heterogeneity of different target regions is to determine the heterogeneity of different tumors.

[0079] Please refer to Figure 7 , which shows a schematic diagram of the process of determining the heterogeneity of different tumors provided by an illustrative embodiment of the present application. First, the super-resolution microscopic imaging results of multiple tumors are obtained, and then the target area is determined based on the tumor imaging results. The target area can include all parts of the tumor. Subsequently, different tumors are quantitatively analyzed based on quantitative analysis parameters, and then histogram analysis or principal component analysis is performed based on the quantitative analysis results corresponding to different tumors. In addition, tumor heterogeneity analysis can also be implemented based on deep learning. After performing histogram analysis and principal component analysis, the first heterogeneity analysis result and the second heterogeneity analysis result are input into the heterogeneity analysis model to obtain the tumor heterogeneity analysis result.

[0080] Please refer to Figure 8 , which shows a schematic diagram of the process of determining tumor heterogeneity of different target areas in the same tumor provided by an exemplary embodiment of the present application. First, a single tumor imaging result is obtained, and the tumor edge recognition result is determined therefrom. Subsequently, the tumor region is segmented based on the tumor edge recognition result to obtain multiple target areas. Then, a quantitative analysis is performed on the multiple target areas based on the quantitative analysis parameters, and the quantitative analysis results of the multiple target areas are subjected to histogram analysis, principal component analysis or deep learning for tumor heterogeneity analysis to obtain tumor heterogeneity analysis results.

[0081] In the process of segmenting the tumor region based on the edge recognition result to obtain the target region, concentric ring segmentation or grid segmentation can be used.

[0082] In the process of obtaining the target area based on concentric annular subdivision, the geometric center of the target area is first determined based on the tumor edge recognition result. Then, with the geometric center as the origin, concentric annular sub-areas are generated through morphological corrosion operation.

[0083] When calculating the geometric center, the sum of the distances from each pixel point in a certain area to the non-zero pixel points on the edge is calculated, and the position with the minimum sum of the distances is defined as the geometric center.

[0084] During the morphological erosion operation, the edge formed in the image after each erosion is defined as a new concentric annular sub-region. Through the above step-by-step erosion process, the target area is gradually refined until it is divided into multiple concentric annular sub-regions. Each concentric annular sub-region corresponds to a target area, thereby realizing the spatial heterogeneity analysis of the tumor area from the periphery to the center.

[0085] Optionally, in the process of obtaining the target region through grid-like subdivision, first, based on the tumor edge recognition result, a tumor bounding rectangle is determined. Then, the tumor bounding rectangle is equally divided in the horizontal and axial directions to obtain equally divided grid regions, each of which is a target region.

[0086] The circumscribed rectangle is the smallest rectangle that tightly surrounds the tumor edge identification area.

[0087] Please refer to Figure 9 , which shows a comparison diagram of target areas obtained by concentric annular subdivision and grid subdivision provided by an exemplary embodiment of the present application. The different target areas obtained by concentric annular subdivision have the same geometric center, and the different target areas obtained by grid subdivision are equally divided grid areas.

[0088] In another possible implementation, considering the relationship between tumor invasiveness and microvascular characteristics in the surrounding area, a morphological dilation operation or an equal-distance expansion method is further used to effectively expand the target region to the surrounding area. The surrounding area is then divided into concentric rings or grids to obtain a target region that includes the surrounding area. This fully reveals the heterogeneous characteristics of the tumor and its surrounding areas, providing more complete information support for clinical tumor invasiveness assessment and prognosis prediction.

[0089] Please refer to Figure 10 , which shows a schematic diagram of an expanded target area provided by an exemplary embodiment of the present application.

[0090] In the embodiments of the present application, the above-mentioned method for determining the target area achieves high-precision and automated division of the tumor area, ensuring the efficiency, accuracy and stability of tumor heterogeneity analysis, and significantly improving the clinical reference value of the analysis results.

[0091] Please refer to Figure 11 , which shows a structural block diagram of an electronic device provided by an exemplary embodiment of the present application. The electronic device in the present application may include one or more of the following components: a processor 1110 and a memory 1120.

[0092] Optionally, the processor 1110 executes the steps of the tumor heterogeneity analysis method based on super-resolution microscopy provided in any of the above embodiments by running or executing instructions, programs, code sets or instruction sets stored in the memory 1120, and calling data stored in the memory 1120.

[0093] In addition, the processor can also perform various functions of the device and process data. Optionally, the processor 1110 can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 1110 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a neural network processing unit (NPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the touch screen; the NPU is used to implement artificial intelligence (AI) functions; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 1110 and may be implemented separately through a chip.

[0094] The memory 1120 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 1120 includes a non-transitory computer-readable storage medium. The memory 1120 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc.; the data storage area may store data created according to the use of the device (such as audio data, a phone book), etc.

[0095] The device in the embodiment of the present application further includes a communication component 1130 and a display component 1140. The communication component 1130 may be a Bluetooth component, a WiFi (WIREless-Fidelity) component, an NFC (Near Field Communication) component, etc., and is used to communicate with an external device (server or other device) via a wired or wireless network; the display component 1140 is used to display a graphical user interface and / or receive user interaction operations.

[0096] In addition, those skilled in the art will understand that the structures of the devices shown in the above figures do not limit the devices. The devices may include more or fewer components than shown, or may combine certain components or arrange the components differently. For example, the devices may also include radio frequency circuits, input units, sensors, audio circuits, speakers, power supplies, and other components, which will not be described in detail here.

[0097] An embodiment of the present application also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the storage medium stores at least one program code, and the program code is loaded and executed by a processor to implement the tumor heterogeneity analysis method based on super-resolution microscopy as described in any of the above embodiments.

[0098] The present application provides a computer program product comprising computer instructions stored in a computer-readable storage medium. When executed by a processor, the computer program implements the method for analyzing tumor heterogeneity based on super-resolution microscopy as described in any of the above embodiments.

Claims

1. A method for analyzing tumor heterogeneity based on super-resolution microscopy, characterized in that: The method comprises: Obtaining a tumor imaging result, wherein the tumor imaging result is generated by super-resolution microscopy technology and includes a tumor image; determining target regions of tumor images; determining quantitative analysis parameters based on the tumor imaging results, wherein the quantitative analysis parameters are used to quantify microvascular characteristics of tumor microvessels in at least two dimensions in the target area; Based on the quantitative analysis parameters, tumor heterogeneity analysis is performed on different target areas to obtain heterogeneity analysis results, wherein the different target areas belong to the same tumor, or the different target areas belong to different tumors.

2. The method according to claim 1, characterized in that The tumor imaging results include a density map and a velocity map, wherein the density map is used to reflect the distribution of tumor microvessels, and the velocity map is used to reflect the blood flow velocity in the tumor microvessels; The method further comprises: Determining the quantitative analysis parameters in at least two dimensions based on the density map and the velocity map; The quantitative analysis parameters in different dimensions are used to characterize microvascular characteristics in different dimensions.

3. The method according to claim 2, characterized in that Determining the quantitative analysis parameters in at least two dimensions based on the density map includes: determining microvascular density distribution parameters, microvascular geometric state parameters, and microvascular perfusion parameters based on the density map; Among them, the microvascular density distribution parameter is used to quantify the microvascular density and distribution characteristics, the microvascular geometric state parameter is used to characterize the microvascular morphology and spatial structure characteristics, and the microvascular perfusion parameter is used to characterize the dynamic characteristics of blood perfusion in the microvessels.

4. The method according to claim 3, characterized in that Determining the quantitative analysis parameters in at least two dimensions based on the velocity map includes: Based on the velocity map, a blood flow velocity parameter, a blood flow direction parameter and a hemodynamic parameter are determined. The hemodynamic parameter is at least used to characterize the pulsation characteristics of the microvessels.

5. The method according to claim 2, characterized in that The step of performing tumor heterogeneity analysis on different target areas based on the quantitative analysis parameters includes: Based on the quantitative analysis parameters, performing a histogram analysis on the target area to obtain a first heterogeneity analysis result; or, Based on the quantitative analysis parameters, principal component analysis is performed on the target region to obtain a second heterogeneity analysis result.

6. The method according to claim 5, characterized in that The step of performing tumor heterogeneity analysis on different target areas based on the quantitative analysis parameters includes: Inputting the first heterogeneity analysis results and the second heterogeneity analysis results corresponding to different target regions into a heterogeneity analysis model; Tumor heterogeneity analysis is performed using the heterogeneity analysis model to obtain third heterogeneity analysis results for different target regions.

7. The method according to claim 1, characterized in that Determining the target area of ​​the tumor image includes: Acquire a grayscale tissue image containing the tumor site; performing tumor edge recognition based on the grayscale tissue image to obtain a tumor edge recognition result; Based on the tumor edge recognition result, the target area is determined, and the target area at least includes a part of the tumor.

8. The method according to claim 7, characterized in that In cases where different target areas belong to the same tumor, The determining of the target area based on the tumor edge recognition result includes: Based on the tumor edge recognition result, determining the geometric center of the target area; using the geometric center as the origin, generating concentric annular sub-areas through morphological erosion operation, wherein each concentric annular sub-area is one of the target areas; or, Based on the tumor edge recognition result, a tumor circumscribed rectangle is determined; the tumor circumscribed rectangle is equally divided in the horizontal and axial directions to obtain equally divided grid areas, each equally divided grid area being one of the target areas.

9. The method according to claim 8, characterized in that The method further comprises: The target area is expanded to the surrounding area of ​​the tumor through morphological dilation operation or expansion based on equal distance; The tumor peripheral area is divided into concentric rings or grids to obtain a target area including the tumor peripheral area.

10. The method according to claim 1, characterized in that The heterogeneity analysis results include at least one of the following forms: Pseudo-color mapping images are used to show differences in vascular distribution density or blood flow velocity in each sub-region; A three-dimensional heat map is superimposed on the grayscale tissue image of the tumor, with areas of high heterogeneity marked; Statistical charts, including bar charts or line charts, are used to compare the quantitative results of microvascular characteristics in different sub-regions.

11. The method according to claim 1, wherein The obtaining of tumor imaging results includes: tracking the movement trajectory of contrast agent microbubbles in the tumor microvessels, and separating and extracting high-frequency moving microbubble signals; performing sub-pixel positioning on the high-frequency motion microbubble signal, and tracking the microbubble motion based on the positioning result to obtain a tracking trajectory; The information such as the density and speed of the moving microbubbles reflected by the tracking trajectory is accumulated, and the accumulated result is mapped to the corresponding spatial position to obtain the tumor imaging result.

12. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the tumor heterogeneity analysis method based on super-resolution microscopy according to any one of claims 1 to 11.

13. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the tumor heterogeneity analysis method based on super-resolution microscopy according to any one of claims 1 to 11.

14. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the tumor heterogeneity analysis method based on super-resolution microscopy according to any one of claims 1 to 11.

Images