Ultrasound positioning microscope-based vascular biomarker analysis and disease diagnosis system, method, medium, program product and terminal

Abstract

This application provides a system, method, media, program product, and terminal for vascular biomarker analysis and disease diagnosis based on ultrasound-guided microscopy. This application utilizes a unified and optimized ULM (Ultra-Large-Scale Microscopy) workflow to reconstruct complex vascular networks with high precision and resolution. It enables longitudinal imaging of the same observation area, accurately quantifying multidimensional biomarkers and monitoring their changes over time, making it suitable for monitoring disease progression or treatment response. By identifying disease-specific multidimensional biomarkers, this application has successfully differentiated between benign and malignant diseases in clinical trials. This application can be seamlessly integrated into existing clinical ultrasound equipment workflows, enabling microvascular imaging, biomarker extraction, and analysis. The standardized operating procedures and automated analysis significantly lower the technical barrier to entry, assisting scientists and physicians in disease diagnosis and possessing direct potential for clinical application.

Description

Technical Field

[0001] This application relates to the fields of medical image analysis and biomedical engineering technology, and in particular to systems, methods, media, program products and terminals for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscopes. Background Technology

[0002] Currently, changes in the structure and function of microvessels serve as early biomarkers for many major diseases, including cardiovascular and cerebrovascular diseases, tumors, and neurodegenerative diseases. However, their clinical translation faces two major bottlenecks:

[0003] (1) Bottleneck in imaging technology: There is an inherent contradiction between spatial resolution and penetration depth in existing clinical imaging technologies. For example, CT angiography (CTA) and MR angiography (MRA) cannot distinguish capillaries; although optical coherence tomography angiography (OCTA) has high resolution, it is limited to superficial tissues.

[0004] (2) Bottlenecks in the analytical system: Although Ultrasound Localization Microscopy (ULM) technology has broken through the diffraction limit of ultrasound by tracking microbubble contrast agents and achieved micron-level resolution imaging of deep tissues, its clinical application lacks standardized image processing procedures and a validated, systematic system for the quantification and analysis of microvascular biomarkers. Therefore, the clinical translation potential of ULM remains relatively limited. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the present invention provides a system, method, medium, program product and terminal for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope, which is used to solve at least one of the technical problems in the prior art.

[0006] To achieve the above and other related objectives, the first aspect of this application provides a vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy, comprising: a standardized ULM imaging and reconstruction module for acquiring microvascular image data of a patient based on ultrasound-guided microscopy technology and performing standardized processing to generate a super-resolution hemodynamic map; a multidimensional biomarker quantification module for performing biomarker quantification evaluation based on the super-resolution hemodynamic map to obtain multidimensional biomarkers; and an artificial intelligence-assisted diagnosis module for inputting the multidimensional biomarkers into a trained disease classification model and outputting disease classification results.

[0007] In some embodiments of the first aspect of this application, the standardized ULM imaging and reconstruction module includes: a motion correction unit for performing motion correction processing on the acquired microvascular image data to obtain corrected microvascular image data; a filtering and denoising unit for using the SVD algorithm to filter the corrected microvascular image data to obtain microblood flow signal data; a microbubble localization unit for performing microbubble signal separation and localization processing on the microblood flow signal data to obtain localized microbubble signal data; and a trajectory tracking unit for tracking and trajectory superposition based on the localized microbubble signal data to finally generate a super-resolution hemodynamic map.

[0008] In some embodiments of the first aspect of this application, the multidimensional biomarkers include: vascular morphology markers and hemodynamic markers.

[0009] In some embodiments of the first aspect of this application, the vascular morphological markers include: vascular density, vascular diameter, intervascular spacing, and vascular tortuosity.

[0010] In some embodiments of the first aspect of this application, the hemodynamic markers include: blood flow velocity and blood perfusion volume.

[0011] In some embodiments of the first aspect of this application, the disease classification model is constructed using any one of support vector machine, random forest, or KNN model.

[0012] To achieve the above and other related objectives, a second aspect of this application provides a method for vascular biomarker analysis and disease diagnosis based on ultrasound-guided microscopy, applied to the vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy as described above. The method includes: acquiring microvascular image data of a patient based on ultrasound-guided microscopy technology and performing standardized processing to generate a super-resolution hemodynamic map; performing biomarker quantitative evaluation based on the super-resolution hemodynamic map to obtain multidimensional biomarkers; and inputting the multidimensional biomarkers into a trained disease classification model to output disease classification results.

[0013] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope.

[0014] To achieve the above and other related objectives, a fourth aspect of this application provides a computer program product comprising computer program code that, when executed on a computer, enables the computer to implement the method for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope.

[0015] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the method for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope.

[0016] As described above, the vascular biomarker analysis and disease diagnosis system, method, medium, program product, and terminal based on ultrasound-guided microscopy provided in this application have the following beneficial effects:

[0017] (1) This application uses a unified and optimized ULM process. Experiments have verified that it can reconstruct complex vascular networks with a resolution of 16.2 μm, with a reconstruction accuracy of over 92%, achieving the imaging accuracy at the capillary level, and possessing high precision and high resolution.

[0018] (2) This application is capable of longitudinal imaging of the same observation area, accurately quantifying multidimensional biomarkers and monitoring their changes over time, and is suitable for monitoring disease progression or treatment response. For example, it can capture a decrease in vascular density, vascular diameter and blood perfusion during periods of elevated intraocular pressure, and monitor an increase in vascular density, vascular diameter and blood perfusion after pressure recovery.

[0019] (3) This application successfully distinguishes between benign and malignant diseases in clinical trials by mining multidimensional biomarkers specific to different diseases. For example, in cervical lymph node tumors, benign hyperplasia, lymphoma and metastatic cancer were effectively identified by multidimensional biomarkers.

[0020] (4) This application can be seamlessly integrated into the existing clinical ultrasound equipment workflow, thereby enabling the imaging of microvessels and the extraction and analysis of biomarkers. The standardized operation process and automated analysis process significantly reduce the technical threshold and can assist scientists and doctors in disease diagnosis, possessing direct potential for clinical application. Attached Figure Description

[0021] Figure 1 The diagram shown is a schematic representation of a vascular biomarker analysis and disease diagnosis system based on an ultrasound positioning microscope, according to one embodiment of this application.

[0022] Figure 2 The diagram shown is a structural schematic of a standardized ULM imaging and reconstruction module according to an embodiment of this application.

[0023] Figure 3 The figure shown is a specific embodiment of a vascular biomarker analysis and disease diagnosis system based on an ultrasound positioning microscope, as described in one embodiment of this application.

[0024] Figure 4 The diagram shown is a schematic representation of a super-resolution hemodynamic map according to an embodiment of this application.

[0025] Figure 5 The figure shown is a specific embodiment of another vascular biomarker analysis and disease diagnosis system based on ultrasound positioning microscope in one embodiment of this application.

[0026] Figure 6 The diagram shown is a flowchart illustrating a method for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope in one embodiment of this application.

[0027] Figure 7 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0028] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0029] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0030] <1> Ultrasound Localization Microscopy (ULM) is a super-resolution imaging technique that breaks through the traditional ultrasound diffraction limit, acquiring high-resolution blood flow images by tracking injected microbubbles.

[0031] <2> The Kuhn-Munkres algorithm (KM) is a computer algorithm for finding the maximum weight matching in a bipartite graph with complete matching. The KM algorithm is widely used due to its simplicity and lack of limitation on data distribution.

[0032] <3> Full Width Half Maximum (FWHM): The width range corresponding to when the signal intensity reaches or exceeds half of the peak intensity. It is crucial for measuring the specific characteristic width of a signal or spectrum. In the fields of spectroscopy and signal processing, it is widely used to quantify the resolution and accuracy of signals.

[0033] The vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy provided in this application is applicable to a wide range of clinical applications, including but not limited to lymph node tumor diagnosis and cardiovascular and cerebrovascular disease diagnosis. The system provided by this invention can provide reliable imaging support in different clinical scenarios, meeting the diagnostic and treatment needs of various diseases.

[0034] To facilitate understanding of the embodiments of this application, firstly, in conjunction with Figure 1 and Figure 3 Detailed explanation. Figure 1 A schematic diagram of a vascular biomarker analysis and disease diagnosis system based on ultrasound positioning microscopy, according to an embodiment of the present invention, is shown. The system 100 includes: a standardized ULM imaging and reconstruction module 110, a multidimensional biomarker quantification module 120, and an artificial intelligence-assisted diagnosis module 130.

[0035] The standardized ULM imaging and reconstruction module 110 is used to acquire microvascular image data of patients based on ultrasound positioning microscopy technology and perform standardized processing to generate super-resolution hemodynamic maps.

[0036] It's important to explain that ultrasound-guided microscopy (ULM) is a super-resolution imaging technique that breaks through the traditional ultrasound diffraction limit. It acquires high-resolution blood flow images by tracking injected microbubbles. The microbubbles, acting as ultrasound contrast agents, flow with the blood into tiny blood vessels, serving as a localization source. The key processes of ULM imaging and reconstruction include: ultrasound data acquisition, motion correction, filtering and noise reduction, microbubble localization, trajectory tracking, and finally, the generation of a super-resolution image. Specifically, microbubble-based ultrasound-guided microscopy technology, by injecting microbubbles into the body and using ultrasound waves to locate and track them, can achieve high-resolution imaging of objects such as tiny blood vessels. This overcomes the resolution limitations of traditional ultrasound imaging, providing more detailed information on vascular anatomy.

[0037] The standardized ULM imaging and reconstruction module described in this embodiment defines a standardized ULM processing flow from ultrasound data acquisition, motion correction, filtering and denoising, microbubble localization, trajectory tracking, to the generation of super-resolution hemodynamic maps. Using the standardized ULM imaging and reconstruction module for ultrasound localization microscopy microvascular imaging can significantly improve the image signal-to-noise ratio, achieving complete visualization of complex vascular networks.

[0038] In this embodiment, the patient's microvascular image data consists of ultrasound echo signals of microvessels after the application of a microbubble contrast agent. The microvascular image data includes IQ data, which is processed to generate B-mode images.

[0039] In one embodiment of this application, as Figure 2 As shown, the standardized ULM imaging and reconstruction module 110 includes: a motion correction unit 1101, a filtering and noise reduction unit 1102, a microbubble positioning unit 1103, and a trajectory tracking unit 1104.

[0040] In this embodiment, the motion correction unit is used to perform motion correction processing on the acquired microvascular image data to obtain corrected microvascular image data.

[0041] It's important to explain that, ideally, the imaging target in super-resolution microscopy is completely stationary. However, during actual acquisition, factors such as the patient's breathing, cardiac activity, or external pressure can cause changes in the position and morphology of microvessels in the ultrasound image over time, resulting in tissue movement. Since super-resolution imaging is reconstructed by superimposing the localizations of many microbubbles accumulated over time, inter-frame motion significantly affects the visualization of microvessel images. Furthermore, the impact of motion scales in clinical scans is often greater than that of super-resolution itself, directly affecting image clarity and accuracy. Therefore, precise motion correction is necessary during acquisition of the microvessel image data to correct motion artifacts caused by physiological movements (such as breathing and cardiac activity).

[0042] In this embodiment, a two-dimensional motion correction algorithm is used to remove motion artifacts caused by respiratory movements or other physiological movements in the image data to obtain corrected microvascular image data.

[0043] In this embodiment, the filtering and denoising unit is used to filter the corrected microvascular image data using the SVD algorithm to obtain microblood flow signal data.

[0044] It should be noted that the corrected microvascular image data includes tissue signals, microbubble signals, and background noise. Furthermore, the microbubble signals within microvessels are weak and easily masked by clutter and noise. A filtering and denoising unit can separate the tissue signals, microbubble signals, and background noise, effectively filtering out most of the tissue clutter and noise signals in the microvascular image data and extracting the masked microvascular microbubble signals. In this embodiment, the SVD algorithm is preferably used to process the acquired images, removing noise and tissue clutter interference, and accurately extracting the microbubble signals from the tissue signals to obtain microblood flow signal data.

[0045] This embodiment employs Singular Value Decomposition (SVD) clutter filtering technology. Utilizing inter-frame variation differences, it separates microbubble and tissue signals based on the spatial and temporal characteristics of their acoustic responses. This filtering effectively suppresses tissue and noise signals, resulting in a significantly higher echo intensity for microbubble signals compared to other signals. This enables the extraction of microvascular microbubble signals, providing a data foundation for subsequent processing and ensuring the accuracy and reliability of subsequent analysis. The SVD algorithm offers significant advantages over traditional clutter suppression methods. Furthermore, the SVD clutter suppression algorithm has fewer related parameters, making it easier to apply in clinical practice.

[0046] It should be noted that the filtering algorithm used in this embodiment is the SVD algorithm. Other filtering algorithms can also be selected, such as PCA and NLM, which can theoretically achieve similar functions. The choice should be made according to actual needs and is not limited here.

[0047] In this embodiment, the microbubble positioning unit is used to perform microbubble signal separation and positioning processing on the microblood flow signal data to obtain the positioned microbubble signal data.

[0048] It should be noted that after extracting microbubble signals using filtering algorithms, the resulting microblood flow signal data may contain multiple superimposed microbubble signals. In order to effectively track the movement trajectory of microbubbles and provide conditions for blood flow tracking, it is necessary to separate and accurately locate the superimposed microbubble signals.

[0049] This embodiment employs a super-resolution algorithm based on the point spread function (PSF) to achieve the separation and localization of microbubble signals. Specifically, the measured PSF of each microbubble signal in the microblood flow signal data is compared with a preset PSF threshold to separate superimposed microbubble signals and obtain the centroid coordinates of each microbubble signal, thereby achieving precise localization of the microbubble signals. After localization processing, the spatial distribution of the microbubble signals presents as discrete centroid points. This distribution feature directly reflects the shape and structure of microvessels, effectively improving the spatial resolution of microvessel structures and providing a reliable data foundation for subsequent trajectory tracking.

[0050] In this embodiment, the trajectory tracking unit is used to track and overlay the trajectory based on the microbubble signal data after positioning, and finally generate a super-resolution hemodynamic map.

[0051] It should be noted that after accurately locating the centroid of each microbubble signal, tracing the flow path of each located microbubble signal within the microvessel can provide more intuitive and comprehensive blood flow information. In this embodiment, the KM algorithm is used to track and match the motion trajectory of the microbubble signal centroid, thereby obtaining a complete distribution map of the microbubble signal in the microvessel. Since the size of microbubbles is similar to that of red blood cells, they do not diffuse from the vessel wall into the surrounding tissue environment; therefore, the spatial distribution of microbubble signals can directly reflect the shape and structure of the microvessel. By cumulatively superimposing the positions of microbubble signals along the time axis, not only can the distribution of microvessels be intuitively displayed, but the inner diameter information of the vessels can also be reflected, achieving characterization of the structure and functional characteristics of microvessels, and thus realizing high-resolution imaging of microvessels, i.e., generating a super-resolution hemodynamic map. The super-resolution hemodynamic map includes a blood flow intensity distribution map and a blood flow velocity distribution map, such as... Figure 4 As shown.

[0052] Specifically, the KM algorithm is used to pair microbubbles in adjacent frames to form trajectories. To ensure data reliability, microbubble trajectories spanning at least 10 consecutive frames are retained. These retained microbubble trajectories are accumulated, and a 10x data interpolation is performed to reconstruct the blood flow intensity distribution map. The velocity of each microbubble is calculated based on the displacement changes of its trajectory between adjacent frames. The velocities of all microbubble trajectories are then averaged to generate a blood flow velocity distribution map reflecting the blood flow velocity distribution within the microvessels.

[0053] In this embodiment, the trajectory tracking algorithm is the KM algorithm. Other algorithms can also be selected, such as Gaussian fitting, interpolation positioning algorithm, Kalman filter-based tracking method, etc., depending on the actual needs. No limitation is made here.

[0054] The multidimensional biomarker quantification module 120 is used to perform biomarker quantification assessment based on the super-resolution hemodynamic map to obtain multidimensional biomarkers. The multidimensional biomarker quantification module provides a unified quantification definition and calculation method, ensuring the comparability and reproducibility of the results.

[0055] In one embodiment of this application, the multidimensional biomarkers include: vascular morphology markers and hemodynamic markers.

[0056] It is important to explain that the microvascular structures formed by pathological angiogenesis are fundamentally different from those in normal physiological conditions. For example, the main characteristics of pathological vessels include the absence of branching and hierarchical division, disordered and tortuous morphology, and leakage. Due to these structural characteristics, the blood flow velocity within pathological vessels is typically significantly higher than that under normal physiological conditions, exhibiting a marked difference. Therefore, effective characterization and monitoring of the microcirculation system are crucial for revealing disease pathogenesis, achieving early diagnosis, and guiding precision treatment.

[0057] In this embodiment, the vascular morphological markers include, but are not limited to: vascular density, vascular diameter, intervascular spacing, and vascular tortuosity.

[0058] In this embodiment, the blood vessel density is defined as the proportion of the blood vessel area to the total area of ​​the selected region, and the specific calculation formula is as follows:

[0059] ;(Formula 1)

[0060] in, Blood vessel density, The area of ​​blood vessels. This represents the total area of ​​the selected region.

[0061] In this embodiment, the blood vessel diameter is obtained by calculating the half-width at half-maximum (FWHM) value, and the formula for calculating the blood vessel diameter is as follows:

[0062] ;(Formula 2)

[0063] in, The diameter of the blood vessel. These are the normalized parameters for the blood vessel profile. It is half the height and width.

[0064] In this embodiment, the intervascular spacing represents the maximum distance between adjacent blood vessels, and the specific calculation formula is as follows:

[0065] ;(Formula 3)

[0066] in, The distance between blood vessels. Adjacent blood vessels and The Euclidean distance between them This represents the boundary of a blood vessel.

[0067] In this embodiment, the vascular tortuosity is calculated using the inflection count metric (ICM). Specifically, the ICM counts the number of inflection points on the centerline of the vessel, adds 1 to this value, multiplies it by the total path length of the vessel, and then divides it by the straight-line distance between the two endpoints. Finally, it is divided by the number of vessels to obtain the vascular tortuosity. The formula for calculating the vascular tortuosity is as follows:

[0068] ;(Formula 4)

[0069] in, This represents the total number of blood vessels. For the first The number of inflection points on the central line of the root vessels. For the first Total path length of root vessels For the first The straight-line distance between the two endpoints of the root vessel.

[0070] In this embodiment, the hemodynamic markers include, but are not limited to, blood flow velocity and blood perfusion.

[0071] In this embodiment, the formula for calculating the blood vessel flow velocity is as follows:

[0072] ;(Formula 5)

[0073] in, For blood flow velocity, The average velocity of blood vessels, This represents the maximum flow rate.

[0074] In this embodiment, the blood perfusion volume reflects the blood perfusion capacity. The formula for calculating the blood perfusion volume is as follows:

[0075] ;(Formula 6)

[0076] in, Blood perfusion The radius of the blood vessel. This represents the average velocity of the blood vessels.

[0077] It should be noted that multidimensional biomarkers, including vessel density, vessel diameter, intervascular spacing, vessel tortuosity, blood flow velocity, and blood perfusion, were calculated using blood flow intensity distribution maps and blood flow velocity distribution maps, respectively. These multidimensional biomarkers were then used for quantitative analysis of the main ocular vessels supplying the optic nerve, including the central retinal artery, posterior ciliary artery, pia mater vessels, choroidal vessels, and retinal vessels. However, vessel density and intervascular spacing were limited to retinal and choroidal analysis.

[0078] The AI-assisted diagnosis module 130 is used to input the multidimensional biomarkers into a trained disease classification model and output disease classification results.

[0079] It should be noted that a disease classification model is constructed and trained using machine learning algorithms to obtain a trained disease classification model. The machine learning algorithms include, but are not limited to, support vector machines, random forests, and KNN models. The disease classification model can automatically identify disease states (e.g., normal / damaged) or disease types (e.g., benign lymph nodes, lymphoma, metastatic cancer) based on input multidimensional biomarkers, achieving automated and high-precision assisted diagnosis. The artificial intelligence-assisted diagnosis module 130 receives multidimensional biomarker data output from the multidimensional biomarker quantification module 120, inputs it into the trained disease classification model, and outputs disease classification results to assist in distinguishing between benign and malignant diseases. For example, in cervical lymph node tumors, multidimensional biomarkers can effectively differentiate between benign hyperplasia, lymphoma, and metastatic cancer.

[0080] Specifically, to verify the effectiveness of the multidimensional biomarkers provided by this system in disease diagnosis and classification, models constructed using three machine learning algorithms—Support Vector Machine (SVM), Random Forest, and KNN—were tested. A dataset of cervical lymph node tumors from patients was collected. Biomarkers showing significant differences between any two disease states were used as model inputs, and five-fold cross-validation was employed to evaluate model performance. The stratified sampling technique was used to divide the patient cervical lymph node tumor dataset into training and testing sets at an 8:2 ratio. SVM, Random Forest, and KNN models were then trained, and each model was evaluated using stratified five-fold cross-validation. The evaluation results show that the SVM model achieved the best performance, with an average accuracy of 0.85 (±0.05), significantly outperforming the KNN model (0.80±0.10) and the Random Forest model (0.75±0.16). These results demonstrate the potential of the multidimensional biomarkers extracted by this system in disease classification, highlighting their feasibility, practicality, and effectiveness in assisting clinical differential diagnosis.

[0081] To facilitate understanding of the ultrasound-guided microscope-based vascular biomarker analysis and disease diagnosis system of this application, combined with... Figure 5 The following specific embodiments are provided for illustration.

[0082] Example 1: In vitro experiment. This example is used to verify the basic imaging accuracy and quantization accuracy of the system.

[0083] (1) Fluid Experiment: A silicone tube with an inner diameter of 300 μm was placed in a water tank to simulate a blood vessel. The flow rate was precisely controlled by an injection pump, and the flow rates were set to 10 mm / s, 20 mm / s, 40 mm / s, 60 mm / s, 80 mm / s, 100 mm / s, and 120 mm / s, respectively. Based on the ultrasound data collected by this system, the blood flow velocity distribution map was reconstructed, and the calculated average flow velocities were 9.77 mm / s, 20.23 mm / s, 41.54 mm / s, 59.23 mm / s, 80.44 mm / s, 101.13 mm / s, and 115.2 mm / s, respectively. Therefore, the relative error between the calculated average flow velocity and the preset flow velocity was less than 4%, proving the accuracy of this system in quantifying blood flow velocity. In addition, the blood vessel diameter measured by this system was 295 μm, with an error of less than 2% compared to the true value (300 μm), which also verified the high accuracy of this system in measuring vascular morphological markers.

[0084] (2) Chicken embryo chorioallantoic membrane (CAM) experiment: The vascular network reconstructed by this system was compared with the optical microscope image. The experimental results showed that the two were highly consistent in terms of vascular morphology, proving the accuracy of this system in capturing vascular morphology. At the same time, the blood flow velocity distribution map reconstructed by this system showed that the minimum vascular diameter was 16.2 μm and the maximum vascular diameter was 233.5 μm, corresponding to actual vascular diameters of 17.6 μm and 237.4 μm, respectively, with error rates of 7.95% and 1.64%, respectively, confirming the ability of this system to distinguish microvessels.

[0085] Example 2: Validation using an animal model. This example demonstrates the system's dynamic monitoring capabilities in living organisms.

[0086] A high intraocular pressure (IOP) model was induced in New Zealand white rabbits by anterior chamber injection of α-chymotrypsin. The system was used to image the fundus vessels at different time points (baseline, high IOP, and recovery). Dynamic changes were successfully tracked: during the high IOP period, retinal and choroidal vessel density, diameter, and perfusion significantly decreased; after IOP returned to normal, these indicators partially recovered. This example demonstrates that the system can be used to monitor dynamic microvascular changes related to the pathophysiological processes of diseases.

[0087] Example 3: Clinical Validation. This example demonstrates the diagnostic value of the system in a real-world clinical setting.

[0088] Experimental Procedure: Thirty-nine patients with cervical lymph node lesions of different pathological types were collected, including benign reactive hyperplasia, lymphoma, and metastatic cancer. Lymph node data from each patient were acquired using clinical ultrasound equipment and input into this system for processing. The multidimensional biomarker quantification module extracted multidimensional vascular biomarkers from each lymph node.

[0089] Diagnostic Results: Analysis of the acquired multidimensional vascular biomarkers revealed statistically significant differences among the three types of lesions in biomarkers such as vessel diameter, intervascular spacing, vascular tortuosity, and blood perfusion. These biomarkers were input into a trained disease classification model, achieving a highly accurate three-category diagnosis. This embodiment validates the practicality and effectiveness of this system in assisting clinical disease differential diagnosis.

[0090] It should be emphasized that the vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy provided in this application has the following beneficial effects:

[0091] (1) This application uses a unified and optimized ULM process. Experiments have verified that it can reconstruct complex vascular networks with a resolution of 16.2 μm, with a reconstruction accuracy of over 92%, achieving the imaging accuracy at the capillary level, and possessing high precision and high resolution.

[0092] (2) This application is capable of longitudinal imaging of the same observation area, accurately quantifying multidimensional biomarkers and monitoring their changes over time, and is suitable for monitoring disease progression or treatment response. For example, it can capture a decrease in vascular density, vascular diameter and blood perfusion during periods of elevated intraocular pressure, and monitor an increase in vascular density, vascular diameter and blood perfusion after pressure recovery.

[0093] (3) This application successfully distinguishes between benign and malignant diseases in clinical trials by mining multidimensional biomarkers specific to different diseases. For example, in cervical lymph node tumors, benign hyperplasia, lymphoma and metastatic cancer were effectively identified by multidimensional biomarkers.

[0094] (4) This application can be seamlessly integrated into the existing clinical ultrasound equipment workflow, thereby enabling the imaging of microvessels and the extraction and analysis of biomarkers. The standardized operation process and automated analysis process significantly reduce the technical threshold and can assist scientists and doctors in disease diagnosis, possessing direct potential for clinical application.

[0095] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect, without limiting their order. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0096] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0097] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0098] Figure 6 The schematic block diagram of the vascular biomarker analysis and disease diagnosis method based on ultrasound-guided microscopy provided in this application embodiment is applied to the vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy as described above. Figure 6 The method includes:

[0099] Step S61: Acquire microvascular image data of the patient based on ultrasound positioning microscopy technology and perform standardization processing to generate a super-resolution hemodynamic map;

[0100] Step S62: Quantitatively evaluate biomarkers based on the super-resolution hemodynamic map to obtain multidimensional biomarkers;

[0101] Step S63: Input the multidimensional biomarkers into the trained disease classification model and output the disease classification results.

[0102] It should be understood that the specific process of each module performing the above-mentioned steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0103] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0104] Figure 7 This is a schematic block diagram of the electronic terminal provided in an embodiment of this application. Figure 7 As shown, the electronic terminal includes at least one processor 701, a memory 702, at least one network interface 703, and a user interface 705. The various components in the device are coupled together via a bus system 704. It is understood that the bus system 704 is used to implement communication between these components. In addition to a data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 7 The general will label all buses as bus systems.

[0105] The user interface 705 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0106] It is understood that memory 702 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0107] In this embodiment of the invention, the memory 702 is used to store various types of data to support the operation of the electronic terminal 700. Examples of this data include: any executable program for operation on the electronic terminal 700, such as the operating system 7021 and application program 7022; the operating system 7021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 7022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The method for vascular biomarker analysis and disease diagnosis based on ultrasound-guided microscopy provided in this embodiment of the invention can be included in the application program 7022.

[0108] The methods disclosed in the above embodiments of the present invention can be applied to processor 701, or implemented by processor 701. Processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 701 or by instructions in software form. The processor 701 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 701 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 701 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0109] In an exemplary embodiment, the electronic terminal 700 may be used to execute the aforementioned method by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs).

[0110] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the vascular biomarker analysis and disease diagnosis method based on ultrasound positioning microscope of any of the embodiments shown.

[0111] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to execute the vascular biomarker analysis and disease diagnosis method based on ultrasound positioning microscope in any of the illustrated embodiments.

[0112] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0113] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0114] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0116] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0118] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs, etc.).

[0119] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0121] In summary, the vascular biomarker analysis and disease diagnosis system, method, medium, program product, and terminal based on ultrasound-guided microscopy provided in this application include: a standardized ULM imaging and reconstruction module for acquiring and standardizing microvascular image data of patients using ultrasound-guided microscopy to generate super-resolution hemodynamic maps; a multidimensional biomarker quantification module for quantifying and evaluating biomarkers based on the super-resolution hemodynamic maps to obtain multidimensional biomarkers; and an artificial intelligence-assisted diagnosis module for inputting the multidimensional biomarkers into a trained disease classification model and outputting disease classification results. This application, through a unified and optimized ULM workflow, can reconstruct complex vascular networks with high precision and high resolution. This application can perform longitudinal imaging of the same observation area, accurately quantify multidimensional biomarkers, and monitor their changes over time, making it suitable for monitoring disease progression or treatment response. This application has successfully distinguished between benign and malignant diseases in clinical trials by mining disease-specific multidimensional biomarkers. This application can be seamlessly integrated into existing clinical ultrasound equipment workflows, thereby realizing microvascular imaging, biomarker extraction, and analysis. The standardized operating procedures and automated analysis significantly lower the technical barrier to entry, assisting scientists and doctors in disease diagnosis and possessing direct potential for clinical application. Therefore, this application effectively overcomes the various shortcomings of existing technologies and has high industrial applicability.

[0122] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A system for vascular biomarker analysis and disease diagnosis based on ultrasound-guided microscopy, characterized in that, include: A standardized ULM imaging and reconstruction module is used to acquire microvascular image data of patients based on ultrasound-guided microscopy and perform standardized processing to generate super-resolution hemodynamic maps. The multidimensional biomarker quantification module is used to perform biomarker quantification and evaluation based on the super-resolution hemodynamic map to obtain multidimensional biomarkers. The AI-assisted diagnostic module is used to input the multidimensional biomarkers into a trained disease classification model and output disease classification results.

2. The vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy according to claim 1, characterized in that, The standardized ULM imaging and reconstruction module includes: The motion correction unit is used to perform motion correction processing on the acquired microvascular image data to obtain corrected microvascular image data. The filtering and denoising unit is used to filter the corrected microvascular image data using the SVD algorithm to obtain microblood flow signal data; The microbubble localization unit is used to perform microbubble signal separation and localization processing on microblood flow signal data to obtain localized microbubble signal data; The trajectory tracking unit is used to track and overlay trajectories based on the microbubble signal data after positioning, and finally generate a super-resolution hemodynamic map.

3. The vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy according to claim 1, characterized in that, The multidimensional biomarkers include: vascular morphology markers and hemodynamic markers.

4. The vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy according to claim 3, characterized in that, The vascular morphological markers include: vascular density, vascular diameter, intervascular spacing, and vascular tortuosity.

5. The vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy according to claim 3, characterized in that, The hemodynamic markers include: blood flow velocity and blood perfusion.

6. The vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy according to claim 1, characterized in that, The disease classification model can be constructed using any one of the following: support vector machine, random forest, or KNN model.

7. A method for vascular biomarker analysis and disease diagnosis based on ultrasound-guided microscopy, characterized in that, The method, applied to the vascular biomarker analysis and disease diagnosis system based on ultrasound-guided microscopy as described in any one of claims 1 to 6, comprises: Microvascular image data of patients are acquired using ultrasound positioning microscopy technology and standardized to generate super-resolution hemodynamic maps. Based on the super-resolution hemodynamic map, biomarkers were quantitatively evaluated to obtain multidimensional biomarkers; The multidimensional biomarkers are input into the trained disease classification model, and the disease classification results are output.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope as described in claim 7.

9. A computer program product, characterized in that, The computer program product includes computer program code, which, when run on a computer, enables the computer to implement the vascular biomarker analysis and disease diagnosis method based on ultrasound positioning microscope as described in claim 7.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method for vascular biomarker analysis and disease diagnosis based on ultrasound positioning microscope as described in claim 7.

Images