Method and device for measuring hardness of venous thrombosis of lower limb
Multimodal information of lower limb thrombosis is obtained through magnetic resonance and ultrasound technology, combined with pre-trained models, the problem of poor accuracy in measuring deep vein thrombosis in the existing technology is solved, and non-invasive and highly accurate thrombosis softness and hardness evaluation is achieved .
Patent Information
- Application Number
- CN202411563018.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing method of measuring softness and hardness of deep vein thrombosis in the lower limb is an invasive detection, with poor accuracy, especially when the thrombosis is involved in a wide range, it is difficult to accurately evaluate the softness and hardness of the thrombus.
Full-length localization images and thrombosis localization images of both lower limbs were obtained through magnetic resonance imaging and ultrasound technology. Combined with multimodal thrombosis information, including thrombus type and properties, the comprehensive softness and hardness of thrombus was analyzed using a pre-trained thrombus softness evaluation model. .
Non-invasive detection of lower limb venous thrombosis is achieved, the accuracy of thrombus softness and hardness measurement is improved, and the current state of thrombus can be fully reflected from different angles.
Smart Images

Figure CN119067977A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the fields of smart medical treatment and computer technology, and in particular to a method and device for measuring the softness and hardness of lower extremity venous thrombosis. Background Art
[0002] In the field of diagnosis and treatment of deep vein thrombosis (DVT) in the lower extremities, accurate assessment of the hardness of the thrombus is crucial for choosing the appropriate treatment plan. Deep vein thrombosis in the lower extremities refers to the abnormal coagulation of blood in the deep veins of the lower extremities to form a thrombus, which may lead to serious complications such as pulmonary embolism (PE) and post-thrombotic syndrome. In clinical practice, interventional technology has become the preferred method for the treatment of central and mixed DVT, which can effectively remove thrombi, maintain venous valve function and restore venous blood flow.
[0003] At present, the method for measuring the hardness of lower extremity venous thrombosis is to extract thrombus samples from deep veins and measure the Young's modulus of thrombus in vitro. This method can reflect the hardness of thrombus. This method is invasive. At the same time, due to the wide range of deep vein thrombosis in the lower extremities, the stage of thrombus in each vein segment is different, and the method of using thrombus samples for evaluation is less accurate. Summary of the invention
[0004] The embodiments of the present application provide a method and device for measuring the hardness of lower extremity venous thrombosis. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.
[0005] In a first aspect, an embodiment of the present application provides a method for measuring the hardness of lower extremity venous thrombosis, the method comprising: Acquire historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging of deep veins of the lower limbs; Acquire a historical thrombus localization image of the target object obtained by scanning with an ultrasound device, where the thrombus localization image is captured based on the thrombus position obtained by the ultrasound device when examining the target object; Based on the full-length positioning images of the bilateral lower limbs and the historical thrombus positioning images, the multimodal thrombus information of each lower limb deep vein thrombosis of the target subject is determined, and the multimodal thrombus information includes the thrombus type and thrombus property; Based on the type and properties of thrombus, the comprehensive hardness and softness of deep vein thrombosis in the lower limbs of the target subjects were analyzed.
[0006] Optionally, based on the full-length positioning images of the bilateral lower limbs and the historical thrombus positioning images, multimodal thrombus information of each lower limb deep vein thrombosis of the target subject is determined, including: Based on the full-length positioning images of the bilateral lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target subject is generated; Generate the thrombus properties of each lower limb deep vein thrombosis of the target subject based on the historical thrombus localization images; The thrombus type and thrombus properties are used as multimodal thrombus information of each lower limb deep vein thrombosis of the target object.
[0007] Optionally, based on the full-length positioning images of the bilateral lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target object is generated, including: Displays full-length positioning images for both lower limbs; In response to a positioning instruction for the displayed bilateral lower limb full-length positioning image, marking a region of interest on the bilateral lower limb full-length positioning image; Upon receiving the image capture instruction, all marked regions of interest are acquired from the full-length positioning images of the bilateral lower limbs to obtain a sequence image corresponding to the magnetic resonance black blood thrombus imaging sequence; The sequence images are spliced longitudinally to obtain the overall image of the deep veins of both lower limbs of the target object; Based on the overall images of the deep veins of both lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target subject was determined.
[0008] Optionally, based on the overall image of the deep veins of both lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target subject is determined, including: Shows the overall image of deep veins in both lower extremities; In response to a thrombus marking instruction for the displayed overall image of the deep veins of both lower limbs, marking the thrombus area of each lower limb deep vein thrombosis present in the overall image of the deep veins of both lower limbs; According to the thrombus area of each lower limb deep vein thrombosis, the thrombus signal of each lower limb deep vein thrombosis is obtained; Responding to a movement instruction for a thrombus area of each lower limb deep vein thrombosis, acquiring adjacent muscle signals of each lower limb deep vein thrombosis; The thrombus signal of each lower limb deep vein thrombosis or the adjacent muscle signal of each lower limb deep vein thrombosis is used as the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis; Based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis, the thrombus type of each lower limb deep vein thrombosis of the target subject is determined.
[0009] Optionally, based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis, the thrombus type of each lower limb deep vein thrombosis of the target subject is determined, including: When the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset homogeneous signal, each deep vein thrombosis of the lower limb is determined to be a soft thrombus; or, when the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset high signal, each deep vein thrombosis of the lower limb is determined to be a medium thrombus; or, when the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset inhomogeneous signal, each deep vein thrombosis of the lower limb is determined to be a hard thrombus; The thrombus type of each lower limb deep vein thrombosis of the target object is a soft thrombus, a medium thrombus, or a hard thrombus.
[0010] Optionally, based on the historical thrombus localization image, the thrombus properties of each lower limb deep vein thrombosis of the target subject are generated, including: Display historical thrombus localization images; In response to a sampling frame setting instruction for a historical thrombus localization image, sampling frame information is set, the sampling frame information includes interest frames, each interest frame includes a lower extremity deep vein thrombosis; The thrombus localization images were scored for elastic imaging, and the average Young's modulus of the lower extremity deep vein thrombosis in each frame of interest was measured; The thrombus properties of each lower limb deep vein thrombosis of the target subject were determined based on the elastic imaging score and the average value of Young's modulus of the lower limb deep vein thrombosis in each frame of interest.
[0011] Optionally, based on the elastic imaging score and the average value of the Young's modulus of the deep vein thrombosis in each frame of interest, the thrombus properties of each deep vein thrombosis in the lower limb of the target subject are determined, including: When the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are respectively within the preset first threshold interval, each deep vein thrombosis of the lower limbs is determined to be a chronic thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are respectively within the preset second threshold interval, each deep vein thrombosis of the lower limbs is determined to be a subacute thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are within the preset third threshold interval, each deep vein thrombosis of the lower limbs is determined to be an acute thrombosis; The thrombotic properties of each lower extremity deep vein thrombosis are determined by taking chronic phase thrombosis, subacute phase thrombosis, or acute phase thrombosis as the target object.
[0012] Optionally, based on the type and properties of thrombus, the comprehensive hardness and softness of the target subject's lower extremity deep vein thrombosis is analyzed, including: Inputting the thrombus type and thrombus properties into a pre-trained thrombus hardness assessment model; wherein the pre-trained thrombus hardness assessment model is obtained by machine learning based on historical magnetic resonance imaging and historical ultrasound imaging data of a preset number of patients with lower extremity deep vein thrombosis; Output the comprehensive hardness and softness of the target object's lower extremity deep vein thrombosis.
[0013] Optionally, a pre-trained thrombus hardness assessment model is generated by following the steps below, including: Historical magnetic resonance imaging and historical ultrasound imaging data of a pre-specified number of patients with lower extremity deep vein thrombosis were collected and preprocessed; Determine historical multimodal thrombotic information of each lower extremity deep vein thrombosis in patients with lower extremity deep vein thrombosis based on historical magnetic resonance imaging and historical ultrasound imaging data; For each patient with lower limb deep vein thrombosis, the historical multimodal thrombosis information of each lower limb deep vein thrombosis is annotated with soft and hard labels to obtain model training samples; A neural network was used to create a thrombus hardness assessment model; The model training samples are input into the thrombus hardness assessment model for machine learning, and the model loss value is output; When the model loss value reaches the minimum, a pre-trained thrombus hardness assessment model is generated.
[0014] In a second aspect, an embodiment of the present application provides a device for measuring the hardness of lower extremity venous thrombosis, the device comprising: A magnetic resonance image acquisition module is used to acquire historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging of deep veins of the lower limbs; An ultrasound image acquisition module is used to acquire a historical thrombus localization image of a target object obtained by scanning with an ultrasound device, wherein the thrombus localization image is captured based on the thrombus position obtained by the ultrasound device when inspecting the target object; A multimodal information determination module, used to determine the multimodal thrombosis information of each lower limb deep vein thrombosis of the target subject based on the full-length positioning images of the bilateral lower limbs and the historical thrombosis positioning images, wherein the multimodal thrombosis information includes the thrombus type and thrombus property; The comprehensive hardness and softness analysis module is used to analyze the comprehensive hardness and softness of the deep vein thrombosis in the lower limbs of the target object based on the type and property of the thrombus.
[0015] The technical solution provided by the embodiments of the present application may have the following beneficial effects: In an embodiment of the present application, on the one hand, by acquiring magnetic resonance images and ultrasound images of the target object for comprehensive analysis, non-invasive detection of the hardness and softness of lower limb venous thrombosis can be achieved; on the other hand, based on the full-length positioning images of both lower limbs and the historical thrombus positioning images, the multimodal thrombus information of each lower limb deep vein thrombosis of the target object is determined, and the multimodal thrombus information includes the type of thrombus and the nature of the thrombus, thereby achieving detailed information of the thrombus from different angles. The detailed information can comprehensively reflect the current state of the thrombus, thereby improving the accuracy of the hardness and softness measurement of the lower limb venous thrombosis.
[0016] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0018] Figure 1 It is a flow chart of a method for measuring the softness and hardness of lower extremity venous thrombosis provided in an embodiment of the present application; Figure 2 It is a schematic diagram of a full-length positioning image of bilateral lower limbs provided in an embodiment of the present application; Figure 3 is a schematic diagram of a thrombus localization image provided in an embodiment of the present application; Figure 4 It is a schematic diagram of an overall image of deep veins of bilateral lower limbs provided in an embodiment of the present application; Figure 5 is a schematic diagram of a thrombus in a magnetic resonance imaging provided in an embodiment of the present application; Figure 6 This is a schematic diagram of the mapping relationship between thrombus type / property and comprehensive hardness and softness provided in an embodiment of the present application; Figure 7 It is a structural schematic diagram of a device for measuring the hardness and softness of lower extremity venous thrombosis provided by the present application; Figure 8 It is a structural schematic diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0019] The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.
[0020] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0021] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the attached claims.
[0022] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, in the description of the present invention, unless otherwise specified, "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship.
[0023] The present application provides a method and device for measuring the hardness of lower extremity venous thrombosis to solve the problems existing in the above-mentioned related technical issues. In the embodiment of the present application, on the one hand, by acquiring the magnetic resonance image and ultrasound image of the target object for comprehensive analysis, non-invasive detection of the hardness and softness measurement of lower extremity venous thrombosis can be achieved; on the other hand, based on the full-length positioning image of the bilateral lower limbs and the historical thrombus positioning image, the multimodal thrombus information of each lower extremity deep vein thrombosis of the target object is determined. The multimodal thrombus information includes the thrombus type and thrombus properties, and the detailed information of the thrombus is obtained from different angles. The detailed information can fully reflect the current state of the thrombus, thereby improving the accuracy of the hardness and softness measurement of the lower extremity venous thrombosis. The following is a detailed description using an exemplary embodiment.
[0024] The following will be combined with the attached Figure 1 -Attached Figure 6 , the method for measuring the hardness of lower extremity venous thrombosis provided in the embodiment of the present application is introduced in detail. The method can be implemented by a computer program and can be run on a device for measuring the hardness of lower extremity venous thrombosis based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.
[0025] See also Figure 1, a flow chart of a method for measuring the hardness of lower extremity venous thrombosis is provided in the embodiment of the present application. Figure 1 As shown, the method of the embodiment of the present application may include the following steps: S101, obtaining historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging of deep veins of the lower limbs; Among them, the magnetic resonance imaging device (MRI) is a medical imaging technology that uses strong magnetic fields and radio wave pulses to obtain images of the internal structures of the body. The target object refers to the patient being examined. The lower limbs refer to the two lower limbs of the human body, that is, the two legs. The bilateral iliac veins refer to the veins that start from the hip bones (ilium) on both sides. The bilateral intermuscular veins refer to the veins located between the thigh muscles on both sides. The historical image refers to the image taken and stored in advance for the target object. The full-length positioning image of the bilateral lower limbs refers to the image obtained by the magnetic resonance imaging device, which includes the entire lower limb from the hip joint to the ankle joint. The magnetic resonance black blood thrombus imaging sequence is a special magnetic resonance imaging sequence used to optimize the imaging of thrombi, so that the thrombi appear black in the image, thereby contrasting with the surrounding blood.
[0026] Specifically, magnetic resonance black blood thrombus imaging (MRBTI) technology can non-invasively identify thrombi in the venous lumen, characterize thrombus characteristics, and display compensatory dilation of blood vessels. MRIBTI technology uses the difference in methemoglobin concentration in thrombi at different stages to present different T1 signal differences, and directly observes the characteristics of the thrombus itself through signal changes, thereby distinguishing different stages and hardness of thrombi. Magnetic resonance black blood thrombus imaging technology is based on the T1 three-dimensional fast spin echo imaging (SPACE) sequence combined with the variable delay precession customized excitation (DANTE) sequence. As a 3D scanning technology, the main technical features of SPACE are to reduce the flip angle of the refocusing pulse and use non-plane selective radio frequency pulses, thereby increasing the length of the echo chain, reducing the SAR value, shortening the echo gap, and shortening the scanning time.
[0027] In some embodiments, a magnetic resonance imaging sequence suitable for deep veins of both lower limbs is set in the magnetic resonance imaging device D, such as the localize and DANTE-SPACE sequences (but not limited to the above sequences), and then the magnetic resonance imaging device D is started to scan and obtain the full-length localization images of the lower limbs of the target object. The server can obtain or receive the full-length positioning image of the target object's bilateral lower limbs from the magnetic resonance imaging device. ,For example Figure 2 shown.
[0028] For example, suppose there is a patient who needs to be evaluated for deep vein thrombosis in the lower extremities. The patient follows the instructions of the doctor or technician and takes an appropriate position, usually supine, with the legs naturally straight. The magnetic resonance imaging device is set up according to the requirements of deep vein imaging of the lower extremities, including selecting an appropriate magnetic resonance black blood thrombosis imaging sequence, such as the DANTE-SPACE sequence. The technician operates the magnetic resonance imaging device, starting from the patient's bilateral iliac veins, and gradually scans down to the bilateral intermuscular veins to obtain continuous images of the entire lower extremity. The magnetic resonance imaging device generates a series of images, which are stored as historical images waiting for the server to obtain, or actively send these images to the server.
[0029] S102, obtaining a historical thrombus localization image of the target object obtained by scanning with an ultrasound device, where the thrombus localization image is captured based on the thrombus position obtained by inspecting the target object with the ultrasound device; Ultrasound equipment is a medical imaging device that uses the echoes generated by ultrasound waves reflected in the human body to obtain images of the body's internal structures. Thrombus localization images are images obtained when examining patients with ultrasound equipment, which can show the specific location of thrombi in blood vessels.
[0030] In some embodiments, when performing lower extremity deep vein imaging on an ultrasound device, the best ultrasound device is a color Doppler ultrasound diagnostic device. A routine examination is first performed on the ultrasound device to locate the thrombus position, and a thrombus localization image can be obtained. Among them, thrombus localization images such as Figure 3 shown.
[0031] For example, suppose there is a patient suspected of having deep vein thrombosis (DVT) in the lower extremities and needs to use ultrasound equipment to determine the location of the thrombus. The patient follows the instructions of the doctor or technician and takes an appropriate position, usually supine, with the legs naturally straight. The technician sets up the ultrasound equipment and selects a suitable probe, such as a high-frequency linear array probe with a frequency between 5.0 and 10.0 MHz, which is suitable for imaging superficial blood vessels. The technician uses the ultrasound probe to examine the patient's lower extremity blood vessels, starting from the femoral vein at the root of the thigh and gradually moving down to the intermuscular veins of the calf. On the ultrasound image, the technician looks for typical features of thrombus, such as seeing high echo shadows in the blood vessels, filling defects under color Doppler ultrasound, and observing whether the blood vessels can be closed by intermittent pressure application to determine the presence of thrombus. Once a thrombus is found, the technician will perform detailed imaging of the area and save these images as historical thrombus localization images. These images are stored as historical images waiting for the server to obtain, or they are actively sent to the server.
[0032] S103, determining multimodal thrombosis information of each lower limb deep vein thrombosis of the target subject based on the bilateral lower limb full-length positioning images and the historical thrombus positioning images, the multimodal thrombosis information including thrombus type and thrombus property; In some embodiments of the present application, the specific process of determining the multimodal thrombosis information of each lower limb deep vein thrombosis of the target object based on the full-length positioning images of both lower limbs and the historical thrombosis positioning images includes: generating the thrombus type of each lower limb deep vein thrombosis of the target object based on the full-length positioning images of both lower limbs; generating the thrombus properties of each lower limb deep vein thrombosis of the target object based on the historical thrombus positioning images; and using the thrombus type and thrombus properties as the multimodal thrombus information of each lower limb deep vein thrombosis of the target object.
[0033] Among them, the types of thrombi include soft thrombi, medium thrombi and hard thrombi. The properties of thrombi include chronic thrombi, subacute thrombi and acute thrombi.
[0034] In an embodiment of the present application, by using full-length positioning images of both lower limbs and historical thrombus positioning images, detailed thrombus type and property information can be generated for each lower limb deep vein thrombosis, thereby providing comprehensive multimodal thrombus information, which helps to improve the accuracy of thrombus diagnosis.
[0035] In some embodiments of the present application, the specific process of generating the thrombus type of each lower limb deep vein thrombosis of the target object based on the full-length positioning images of both lower limbs includes: displaying the full-length positioning images of both lower limbs; marking the region of interest of the full-length positioning images of both lower limbs in response to the positioning instructions for the displayed full-length positioning images of both lower limbs; upon receiving the image capture instruction, acquiring all marked regions of interest from the full-length positioning images of both lower limbs to obtain a sequence image corresponding to the magnetic resonance black blood thrombosis imaging sequence; longitudinally splicing the sequence images to obtain an overall image of the deep veins of both lower limbs of the target object; and determining the thrombus type of each lower limb deep vein thrombosis of the target object based on the overall image of the deep veins of both lower limbs.
[0036] For example, based on the full-length positioning image of the target object's bilateral lower limbs Locate and scan three DANTE-SPACE sequence images , , , then , , After the images are stitched together, the overall image of the deep veins on both sides of the lower limbs of the target object is obtained. , overall image of the deep veins of both lower limbs of the target object For example Figure 4 shown.
[0037] In some embodiments of the present application, the specific process of determining the thrombus type of each lower limb deep vein thrombosis of the target object based on the overall image of the deep veins of both lower limbs includes: displaying the overall image of the deep veins of both lower limbs; marking the thrombus area of each lower limb deep vein thrombosis existing in the overall image of the deep veins of both lower limbs in response to the thrombus marking instruction for the displayed overall image of the deep veins of both lower limbs; acquiring the thrombus signal of each lower limb deep vein thrombosis according to the thrombus area of each lower limb deep vein thrombosis; acquiring the adjacent muscle signal of each lower limb deep vein thrombosis in response to the movement instruction for the thrombus area of each lower limb deep vein thrombosis; using the thrombus signal of each lower limb deep vein thrombosis or the adjacent muscle signal of each lower limb deep vein thrombosis as the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis; determining the thrombus type of each lower limb deep vein thrombosis of the target object based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis.
[0038] Specifically, based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis, the specific process of determining the thrombus type of each lower limb deep vein thrombosis of the target object includes: when the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis is within the preset threshold interval corresponding to the preset homogeneous signal, each lower limb deep vein thrombosis is determined to be a soft thrombus; or, when the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis is within the preset threshold interval corresponding to the preset high signal, each lower limb deep vein thrombosis is determined to be a medium thrombus; or, when the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis is within the preset threshold interval corresponding to the preset inhomogeneous signal, each lower limb deep vein thrombosis is determined to be a hard thrombus; soft thrombus, medium thrombus or hard thrombus is used as the thrombus type of each lower limb deep vein thrombosis of the target object. For example Figure 5 As shown, a is the magnetic resonance image of a soft thrombus, b is the magnetic resonance image of a medium thrombus, and c is the magnetic resonance image of a hard thrombus.
[0039] For example, the overall image of the deep veins in both lower limbs of the target object is obtained. Afterwards, based on The image can determine the relative signal ratio (RSC) of the thrombus location. RSC is defined as the thrombus signal (SI thrombus ) / adjacent muscle signal (SI muscle ).
[0040] Among them, when RSC is the preset homogeneous signal, it is judged as soft thrombus, and the homogeneous signal includes RSC=1.47 ±0.50. When RSC is a high signal, it is judged as medium thrombus, and the high signal includes RSC=1.75 ± 0.51. When RSC is an inhomogeneous signal, it is judged as a hard signal, and the inhomogeneous signal includes RSC=1.59 ± 0.52 and / or a low signal shadow of flow void inside.
[0041] In some embodiments of the present application, the specific process of generating the thrombus properties of each lower limb deep vein thrombosis of the target object based on the historical thrombus localization image includes: displaying the historical thrombus localization image; setting the sampling frame information in response to the sampling frame setting instruction for the historical thrombus localization image, the sampling frame information includes a frame of interest, each frame of interest includes a lower limb deep vein thrombosis; performing elastic imaging scoring on the thrombus localization image, and measuring the average value of Young's modulus of the lower limb deep vein thrombosis in each frame of interest; determining the thrombus properties of each lower limb deep vein thrombosis of the target object based on the elastic imaging score and the average value of Young's modulus of the lower limb deep vein thrombosis in each frame of interest.
[0042] Specifically, based on the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis in each frame of interest, the specific process of determining the thrombotic properties of each deep vein thrombosis in the lower limbs of the target object includes: when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis in each frame of interest are respectively within the preset first threshold interval, each deep vein thrombosis in the lower limbs is determined to be a chronic thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis in each frame of interest are respectively within the preset second threshold interval, each deep vein thrombosis in the lower limbs is determined to be a subacute thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis in each frame of interest are within the preset third threshold interval, each deep vein thrombosis in the lower limbs is determined to be an acute thrombosis; chronic thrombosis, subacute thrombosis or acute thrombosis is used as the thrombotic property of each deep vein thrombosis in the lower limbs of the target object. For example Figure 3 In the figure, image a is an ultrasound image of an acute thrombus, image b is an ultrasound image of a subacute thrombus, and image c is an ultrasound image of a chronic thrombus.
[0043] Among them, the image was frozen after stabilization for elastic imaging scoring, and the average value of the Young's modulus (Emean) of the thrombus in the area of interest was measured at the same time, and the same thrombus was measured more than twice to get the average value; according to the elasticity score and Emean value, the thrombus was defined from high to low as chronic thrombus, subacute thrombus and acute thrombus. Among them, the chronic thrombus elastic imaging score = 3.02 ± 0.71, Emean = 18.42 ± 6.86; the subacute thrombus elastic imaging score = 2.78 ± 0.66, Emean = 15.43 ± 5.02; the acute thrombus elastic imaging score = 1.82 ± 0.55, Emean = 8.23 ± 2.56.
[0044] S104, analyzing the comprehensive hardness and softness of the target subject's lower extremity deep vein thrombosis based on the type and properties of the thrombus.
[0045] In some embodiments of the present application, the specific process of analyzing the comprehensive hardness and softness of the target object's lower limb deep vein thrombosis based on the thrombus type and thrombus properties includes: inputting the thrombus type and thrombus properties into a pre-trained thrombus hardness and softness assessment model; wherein the pre-trained thrombus hardness and softness assessment model is obtained by machine learning based on historical magnetic resonance imaging and historical ultrasound imaging data of a preset number of patients with lower limb deep vein thrombosis; and outputting the comprehensive hardness and softness of the target object's lower limb deep vein thrombosis.
[0046] Specifically, a pre-trained thrombus hardness assessment model is generated according to the following steps, including: collecting and pre-processing a preset number of historical magnetic resonance imaging and historical ultrasound imaging data of patients with lower limb deep vein thrombosis; determining the historical multimodal thrombus information of each lower limb deep vein thrombosis of patients with lower limb deep vein thrombosis based on the historical magnetic resonance imaging and historical ultrasound imaging data; annotating the historical multimodal thrombus information of each lower limb deep vein thrombosis of patients with lower limb deep vein thrombosis with hardness labels to obtain model training samples; using a neural network to create a thrombus hardness assessment model; inputting the model training samples into the thrombus hardness assessment model for machine learning, and outputting the model loss value; when the model loss value reaches the minimum, generating a pre-trained thrombus hardness assessment model.
[0047] In an embodiment of the present application, by combining magnetic resonance imaging and ultrasound imaging data of patients with deep vein thrombosis in the lower extremities, detailed multimodal thrombus information can be generated. Using this information and annotating the hardness and softness labels, model training samples for thrombus hardness assessment can be created. By training a neural network and using machine learning technology, a model that can accurately assess the hardness and softness of thrombi can be developed. When the model loss value reaches the minimum, it indicates that the model has accurately learned the pattern in the data. At this time, the pre-trained thrombus hardness assessment model generated can be used in clinical practice, thereby improving the accuracy of thrombus detection.
[0048] In other embodiments, the thrombus can be defined as a soft / medium / hard thrombus based on the image of the magnetic resonance imaging device, i.e., the first layer of hardness and softness information; secondly, the thrombus can be further defined as a chronic thrombus, a subacute thrombus, and an acute thrombus based on the elastic imaging score and Emean value of the image obtained by the ultrasound device, i.e., the second layer of hardness and softness information; finally, the first layer of hardness and softness information is added to the second layer of hardness and softness information to obtain a result, and based on the result, the comprehensive hardness and softness of the deep vein thrombosis of the lower extremities of the target object is queried from the pre-configured data table. The pre-configured data table stores the mapping relationship between the thrombus type / property and the comprehensive hardness and softness. Among them, the pre-configured data table, for example Figure 6 shown.
[0049] In an embodiment of the present application, on the one hand, by acquiring magnetic resonance images and ultrasound images of the target object for comprehensive analysis, non-invasive detection of the hardness and softness of lower limb venous thrombosis can be achieved; on the other hand, based on the full-length positioning images of both lower limbs and the historical thrombus positioning images, the multimodal thrombus information of each lower limb deep vein thrombosis of the target object is determined, and the multimodal thrombus information includes the type of thrombus and the nature of the thrombus, thereby achieving detailed information of the thrombus from different angles. The detailed information can comprehensively reflect the current state of the thrombus, thereby improving the accuracy of the hardness and softness measurement of the lower limb venous thrombosis.
[0050] The following are embodiments of the device of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments of the present invention, please refer to the method embodiments of the present invention.
[0051] See also Figure 7 , which shows a schematic diagram of the structure of a device for measuring the hardness of lower limb venous thrombosis provided by an exemplary embodiment of the present invention. The device for measuring the hardness of lower limb venous thrombosis can be implemented as all or part of a device through software, hardware or a combination of both. The device 1 includes a magnetic resonance image acquisition module 10, an ultrasound image acquisition module 20, a multimodal information determination module 30, and a comprehensive hardness analysis module 40.
[0052] A magnetic resonance image acquisition module 10 is used to acquire historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging of deep veins of the lower limbs; An ultrasound image acquisition module 20 is used to acquire a historical thrombus localization image of a target object obtained by scanning with an ultrasound device, wherein the thrombus localization image is captured based on the thrombus position obtained by the ultrasound device when inspecting the target object; A multimodal information determination module 30, for determining multimodal thrombosis information of each lower limb deep vein thrombosis of the target subject based on the bilateral lower limb full-length positioning images and the historical thrombosis positioning images, wherein the multimodal thrombosis information includes thrombosis type and thrombosis property; The comprehensive hardness and softness analysis module 40 is used to analyze the comprehensive hardness and softness of the deep vein thrombosis of the lower limbs of the target object based on the type and property of the thrombus.
[0053] It should be noted that the hardness measuring device for lower limb venous thrombosis provided in the above embodiment only uses the division of the above functional modules as an example when executing the hardness measuring method for lower limb venous thrombosis. In actual applications, the above functional distribution can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the hardness measuring device for lower limb venous thrombosis provided in the above embodiment and the hardness measuring method for lower limb venous thrombosis belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.
[0054] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0055] In an embodiment of the present application, on the one hand, by acquiring magnetic resonance images and ultrasound images of the target object for comprehensive analysis, non-invasive detection of the hardness and softness of lower limb venous thrombosis can be achieved; on the other hand, based on the full-length positioning images of both lower limbs and the historical thrombus positioning images, the multimodal thrombus information of each lower limb deep vein thrombosis of the target object is determined, and the multimodal thrombus information includes the type of thrombus and the nature of the thrombus, thereby achieving detailed information of the thrombus from different angles. The detailed information can comprehensively reflect the current state of the thrombus, thereby improving the accuracy of the hardness and softness measurement of the lower limb venous thrombosis.
[0056] The present invention also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the method for measuring the hardness and softness of lower limb venous thrombosis provided by the above-mentioned various method embodiments.
[0057] The present invention also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method for measuring the softness and hardness of lower limb venous thrombosis in the above-mentioned various method embodiments.
[0058] See also Figure 8 , which is a schematic diagram of the structure of a device provided in the embodiment of the present application. Figure 8 As shown, the device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .
[0059] The communication bus 1002 is used to realize the connection and communication between these components.
[0060] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.
[0061] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0062] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts within the entire device 1000, and executes various functions and processes data of the device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) 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 display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.
[0063] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 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 above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage device located away from the aforementioned processor 1001. As Figure 8 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a hardness and softness measurement application for lower extremity venous thrombosis.
[0064] exist Figure 8 In the device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the softness and hardness measurement application of lower extremity venous thrombosis stored in the memory 1005, and specifically perform the following operations: Acquire historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging of deep veins of the lower limbs; Acquire a historical thrombus localization image of the target object obtained by scanning with an ultrasound device, where the thrombus localization image is captured based on the thrombus position obtained by the ultrasound device when examining the target object; Based on the full-length positioning images of the bilateral lower limbs and the historical thrombus positioning images, the multimodal thrombus information of each lower limb deep vein thrombosis of the target subject is determined, and the multimodal thrombus information includes the thrombus type and thrombus property; Based on the type and properties of thrombus, the comprehensive hardness and softness of deep vein thrombosis in the lower limbs of the target subjects were analyzed.
[0065] In one embodiment, when the processor 1001 determines the multimodal thrombus information of each lower limb deep vein thrombosis of the target object based on the bilateral lower limb full-length positioning images and the historical thrombus positioning images, the processor 1001 specifically performs the following operations: Based on the full-length positioning images of the bilateral lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target subject is generated; Generate the thrombus properties of each lower limb deep vein thrombosis of the target subject based on the historical thrombus localization images; The thrombus type and thrombus properties are used as multimodal thrombus information of each lower limb deep vein thrombosis of the target object.
[0066] In one embodiment, when the processor 1001 generates the thrombus type of each lower limb deep vein thrombosis of the target object according to the full-length positioning images of the bilateral lower limbs, the processor 1001 specifically performs the following operations: Displays full-length positioning images for both lower limbs; In response to a positioning instruction for the displayed bilateral lower limb full-length positioning image, marking a region of interest on the bilateral lower limb full-length positioning image; Upon receiving the image capture instruction, all marked regions of interest are acquired from the full-length positioning images of the bilateral lower limbs to obtain a sequence image corresponding to the magnetic resonance black blood thrombus imaging sequence; The sequence images are spliced longitudinally to obtain the overall image of the deep veins of both lower limbs of the target object; Based on the overall images of the deep veins of both lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target subject was determined.
[0067] In one embodiment, when the processor 1001 determines the thrombus type of each lower limb deep vein thrombosis of the target object based on the overall image of the bilateral lower limb deep veins, the processor 1001 specifically performs the following operations: Shows the overall image of deep veins in both lower extremities; In response to a thrombus marking instruction for the displayed overall image of the deep veins of both lower limbs, marking the thrombus area of each lower limb deep vein thrombosis present in the overall image of the deep veins of both lower limbs; According to the thrombus area of each lower limb deep vein thrombosis, the thrombus signal of each lower limb deep vein thrombosis is obtained; Responding to a movement instruction for a thrombus area of each lower limb deep vein thrombosis, acquiring adjacent muscle signals of each lower limb deep vein thrombosis; The thrombus signal of each lower limb deep vein thrombosis or the adjacent muscle signal of each lower limb deep vein thrombosis is used as the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis; Based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis, the thrombus type of each lower limb deep vein thrombosis of the target subject is determined.
[0068] In one embodiment, when the processor 1001 determines the thrombus type of each lower limb deep vein thrombosis of the target object based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis, the processor 1001 specifically performs the following operations: When the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset homogeneous signal, each deep vein thrombosis of the lower limb is determined to be a soft thrombus; or, when the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset high signal, each deep vein thrombosis of the lower limb is determined to be a medium thrombus; or, when the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset inhomogeneous signal, each deep vein thrombosis of the lower limb is determined to be a hard thrombus; The thrombus type of each lower limb deep vein thrombosis of the target object is a soft thrombus, a medium thrombus, or a hard thrombus.
[0069] In one embodiment, when the processor 1001 generates the thrombus properties of each lower limb deep vein thrombosis of the target object according to the historical thrombus localization image, the processor 1001 specifically performs the following operations: Display historical thrombus localization images; In response to a sampling frame setting instruction for a historical thrombus localization image, sampling frame information is set, the sampling frame information includes interest frames, each interest frame includes a lower extremity deep vein thrombosis; The thrombus localization images were scored for elastic imaging, and the average Young's modulus of the lower extremity deep vein thrombosis in each frame of interest was measured; The thrombus properties of each lower limb deep vein thrombosis of the target subject were determined based on the elastic imaging score and the average value of Young's modulus of the lower limb deep vein thrombosis in each frame of interest.
[0070] In one embodiment, when the processor 1001 determines the thrombus property of each lower limb deep vein thrombosis of the target object based on the elastic imaging score and the average value of the Young's modulus of the lower limb deep vein thrombosis in each frame of interest, the processor 1001 specifically performs the following operations: When the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are respectively within the preset first threshold interval, each deep vein thrombosis of the lower limbs is determined to be a chronic thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are respectively within the preset second threshold interval, each deep vein thrombosis of the lower limbs is determined to be a subacute thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are within the preset third threshold interval, each deep vein thrombosis of the lower limbs is determined to be an acute thrombosis; The thrombotic properties of each lower extremity deep vein thrombosis are determined by taking chronic phase thrombosis, subacute phase thrombosis, or acute phase thrombosis as the target object.
[0071] In one embodiment, when the processor 1001 analyzes the comprehensive hardness and softness of the target object's lower extremity deep vein thrombosis based on the thrombus type and thrombus property, the processor 1001 specifically performs the following operations: Inputting the thrombus type and thrombus properties into a pre-trained thrombus hardness assessment model; wherein the pre-trained thrombus hardness assessment model is obtained by machine learning based on historical magnetic resonance imaging and historical ultrasound imaging data of a preset number of patients with lower extremity deep vein thrombosis; Output the comprehensive hardness and softness of the target object's lower extremity deep vein thrombosis.
[0072] In one embodiment, when the processor 1001 generates a pre-trained thrombus hardness assessment model, the processor 1001 specifically performs the following operations: Historical magnetic resonance imaging and historical ultrasound imaging data of a pre-specified number of patients with lower extremity deep vein thrombosis were collected and preprocessed; Determine historical multimodal thrombotic information of each lower extremity deep vein thrombosis in patients with lower extremity deep vein thrombosis based on historical magnetic resonance imaging and historical ultrasound imaging data; For each patient with lower limb deep vein thrombosis, the historical multimodal thrombosis information of each lower limb deep vein thrombosis is annotated with soft and hard labels to obtain model training samples; A neural network was used to create a thrombus hardness assessment model; The model training samples are input into the thrombus hardness assessment model for machine learning, and the model loss value is output; When the model loss value reaches the minimum, a pre-trained thrombus hardness assessment model is generated.
[0073] In an embodiment of the present application, on the one hand, by acquiring magnetic resonance images and ultrasound images of the target object for comprehensive analysis, non-invasive detection of the hardness and softness of lower limb venous thrombosis can be achieved; on the other hand, based on the full-length positioning images of both lower limbs and the historical thrombus positioning images, the multimodal thrombus information of each lower limb deep vein thrombosis of the target object is determined, and the multimodal thrombus information includes the type of thrombus and the nature of the thrombus, thereby achieving detailed information of the thrombus from different angles. The detailed information can comprehensively reflect the current state of the thrombus, thereby improving the accuracy of the hardness and softness measurement of the lower limb venous thrombosis.
[0074] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program for measuring the hardness and softness of lower extremity venous thrombosis can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0075] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.
Claims
1. A method for measuring the hardness of lower extremity venous thrombosis, characterized in that: The method comprises: Acquire historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging the deep veins of the lower limbs; Acquire a historical thrombus localization image of the target object obtained by scanning with an ultrasound device, wherein the thrombus localization image is captured based on the thrombus position obtained by inspecting the target object with the ultrasound device; Determining multimodal thrombus information of each lower limb deep vein thrombosis of the target subject based on the bilateral lower limb full-length positioning images and the historical thrombus positioning images, wherein the multimodal thrombus information includes thrombus type and thrombus property; Based on the thrombus type and thrombus properties, the comprehensive hardness and softness of the deep vein thrombosis in the lower extremities of the target subject are analyzed.
2. The method according to claim 1, characterized in that The determining of multimodal thrombosis information of each lower limb deep vein thrombosis of the target subject based on the bilateral lower limb full-length positioning images and the historical thrombosis positioning images includes: generating a thrombus type of deep vein thrombosis in each lower limb of the target subject according to the bilateral lower limb full-length positioning images; generating the thrombus properties of each lower limb deep vein thrombosis of the target subject according to the historical thrombus localization image; The thrombus type and thrombus property are used as multimodal thrombus information of each lower limb deep vein thrombosis of the target object.
3. The method according to claim 2, characterized in that Generating the thrombus type of each lower limb deep vein thrombosis of the target object according to the bilateral lower limb full-length positioning images includes: Displaying full-length positioning images of the bilateral lower limbs; In response to a positioning instruction for the displayed full-length positioning image of the bilateral lower limbs, marking a region of interest of the full-length positioning image of the bilateral lower limbs; Upon receiving the image capture instruction, all marked regions of interest are acquired from the full-length positioning images of the bilateral lower limbs to obtain a sequence image corresponding to the magnetic resonance black blood thrombus imaging sequence; The sequence images are longitudinally spliced to obtain an overall image of the deep veins of both lower limbs of the target object; Based on the overall image of the deep veins of both lower limbs, the thrombus type of each lower limb deep vein thrombosis of the target subject is determined.
4. The method according to claim 3, characterized in that The step of determining the thrombus type of each lower limb deep vein thrombosis of the target subject based on the overall image of the bilateral lower limb deep veins comprises: Display the overall image of the deep veins of the bilateral lower limbs; In response to a thrombus marking instruction for the displayed overall image of the deep veins of both lower limbs, marking a thrombus area of each deep vein thrombosis of the lower limbs present in the overall image of the deep veins of both lower limbs; Acquiring a thrombus signal of each lower limb deep vein thrombosis according to the thrombus area of each lower limb deep vein thrombosis; In response to a movement instruction for the thrombus area of each lower limb deep vein thrombosis, acquiring a muscle signal adjacent to each lower limb deep vein thrombosis; Using the thrombus signal of each lower limb deep vein thrombosis or the adjacent muscle signal of each lower limb deep vein thrombosis as the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis; Based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis, the thrombus type of each lower limb deep vein thrombosis of the target object is determined.
5. The method according to claim 4, characterized in that The method of determining the thrombus type of each lower limb deep vein thrombosis of the target subject based on the relative signal ratio of the thrombus position of each lower limb deep vein thrombosis comprises: When the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset homogeneous signal, each deep vein thrombosis of the lower limb is determined to be a soft thrombus; or, when the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset high signal, each deep vein thrombosis of the lower limb is determined to be a medium thrombus; or, when the relative signal ratio of the thrombus position of each deep vein thrombosis of the lower limb is within the preset threshold interval corresponding to the preset inhomogeneous signal, each deep vein thrombosis of the lower limb is determined to be a hard thrombus; The soft thrombus, medium thrombus or hard thrombus is used as the thrombus type of each lower limb deep vein thrombosis of the target subject.
6. The method according to claim 2, characterized in that The generating, based on the historical thrombus localization image, the thrombus properties of each lower limb deep vein thrombosis of the target subject comprises: displaying the historical thrombus localization image; In response to a sampling frame setting instruction for the historical thrombus localization image, the sampling frame information is set, wherein the sampling frame information includes interest frames, each of which includes a lower extremity deep vein thrombosis; The thrombus localization image is scored by elastic imaging, and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest is measured; The thrombus properties of each deep vein thrombosis in the lower limbs of the target subject are determined based on the elastic imaging score and the average value of the Young's modulus of the deep vein thrombosis in the lower limbs of each frame of interest.
7. The method according to claim 6, characterized in that The determining of the thrombus properties of each lower limb deep vein thrombosis of the target subject based on the elastic imaging score and the average value of the Young's modulus of the lower limb deep vein thrombosis in each frame of interest comprises: When the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are respectively within the preset first threshold interval, each deep vein thrombosis of the lower limbs is determined to be a chronic thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are respectively within the preset second threshold interval, each deep vein thrombosis of the lower limbs is determined to be a subacute thrombosis; or, when the elastic imaging score and the average value of Young's modulus of the deep vein thrombosis of the lower limbs in each frame of interest are within the preset third threshold interval, each deep vein thrombosis of the lower limbs is determined to be an acute thrombosis; The chronic phase thrombosis, subacute phase thrombosis or acute phase thrombosis is used as the thrombotic property of each lower limb deep vein thrombosis of the target subject.
8. The method according to claim 1, characterized in that The comprehensive hardness and softness of the deep vein thrombosis of the lower extremities of the target subject is analyzed based on the thrombus type and thrombus property, including: Inputting the thrombus type and thrombus properties into a pre-trained thrombus hardness assessment model; wherein the pre-trained thrombus hardness assessment model is obtained by machine learning based on historical magnetic resonance imaging and historical ultrasound imaging data of a preset number of patients with lower extremity deep vein thrombosis; The comprehensive hardness and softness of the deep vein thrombosis in the lower extremities of the target object is output.
9. The method according to claim 8, wherein the pre-trained thrombus hardness assessment model is generated according to the following steps, comprising: Historical magnetic resonance imaging and historical ultrasound imaging data of a pre-specified number of patients with lower extremity deep vein thrombosis were collected and preprocessed; Determining historical multimodal thrombosis information of each lower limb deep vein thrombosis of the lower limb deep vein thrombosis patient based on the historical magnetic resonance imaging and historical ultrasound imaging data; For each lower limb deep vein thrombosis patient's historical multimodal thrombosis information, label the soft and hard labels to obtain a model training sample; A neural network was used to create a thrombus hardness assessment model; Inputting the model training samples into the thrombus hardness assessment model for machine learning, and outputting a model loss value; When the model loss value reaches the minimum, a pre-trained thrombus hardness assessment model is generated.
10. A device for measuring the hardness of lower extremity venous thrombosis, characterized in that: The device comprises: A magnetic resonance image acquisition module, used to acquire historical images of the target object's lower limbs from the bilateral iliac veins to the bilateral intermuscular veins obtained by scanning with a magnetic resonance imaging device as full-length positioning images of the bilateral lower limbs, wherein the magnetic resonance imaging device is provided with a magnetic resonance black blood thrombosis imaging sequence suitable for imaging of deep veins of the lower limbs; An ultrasound image acquisition module, used to acquire a historical thrombus localization image of a target object obtained by scanning with an ultrasound device, wherein the thrombus localization image is captured based on the thrombus position obtained by inspecting the target object with the ultrasound device; a multimodal information determination module, configured to determine multimodal thrombosis information of each lower limb deep vein thrombosis of the target subject based on the bilateral lower limb full-length positioning images and the historical thrombosis positioning images, wherein the multimodal thrombosis information includes thrombosis type and thrombosis property; The comprehensive hardness and softness analysis module is used to analyze the comprehensive hardness and softness of the deep vein thrombosis in the lower limbs of the target object based on the thrombus type and thrombus properties.
Citation Information
Patent Citations
Method for detecting in-vivo thrombus hardness and system for method
CN111202519A
Lower limb venous thrombosis early warning evaluation system based on multi-mode continuous monitoring signals
CN115633943A
Blood vessel image target detection method and device
CN117132837A
Vascular assessment using acoustic sensing
US20220071497A1
