Non-contrast enhanced magnetic resonance image recognition method, system, device and storage medium

Abstract

The present invention relates to the field of medical image processing technology, and discloses a non-contrast enhanced magnetic resonance image recognition method, system, device and storage medium, including: obtaining a magnetic resonance image to be recognized; analyzing the magnetic resonance image to obtain the lumen stenosis position of the central vein and the outer wall contour of the blood vessel; measuring the thrombus diameter and the outer diameter of the blood vessel according to the lumen stenosis position and the outer wall contour of the blood vessel; calculating the absolute stenosis according to the thrombus diameter and the outer diameter of the blood vessel; recognizing the magnetic resonance image by the absolute stenosis to obtain an image recognition result. The present invention can accurately locate the thrombus position, range and imaging characteristics by analyzing the magnetic resonance image, and can accurately and objectively reflect the degree of stenosis of the central vein by calculating the absolute stenosis, thereby providing effective data support for subsequent medical research.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a non-contrast enhanced magnetic resonance image recognition method, system, device and storage medium. Background Art

[0002] Central vein catheter (CVC) is a common technology used for dialysis vascular access in hemodialysis. CVC is usually inserted from one side of the internal venous vein, and the end is located at the junction of the superior vena cava and the right atrium. It is a dialysis catheter that exchanges and purifies the patient's blood through the hole at the end of the catheter. Catheter-related thrombosis (CRT) refers to the placement of a catheter into a human vein or artery, which causes thrombosis in the human body. The serious consequences of CRT include damage to the catheter-related vein that cannot be used as a dialysis vascular access, and a significant increase in deep vein thrombosis, which leads to the occurrence of serious complications and other diseases. At the same time, CVC may also cause central vein stenoses (CVS). Since the central vein is the final circuit of all dialysis vascular access, CVS can directly affect the vascular access function of both upper limbs and even shorten the dialysis life. In addition, there are other factors that can cause thrombosis in blood vessels, so it is very necessary to effectively and accurately identify the occurrence of thrombosis.

[0003] At present, the existing examination methods for CRT imaging examination have their own limitations. On the one hand, color Doppler ultrasound is only suitable for preliminary screening, and ultrasound cannot clearly display the brachiocephalic vein and nearly 1 / 3 of the subclavian vein; although digital subtraction angiography is often used for imaging diagnosis of central vein stenosis, this method is invasive and has radiation, and is not the preferred method for examination; computed tomography angiography infers the scope and extent of the lesion by observing indirect signs such as contrast agent filling defects and morphological stenosis of the imaging lumen, so it is impossible to directly observe the morphology and imaging characteristics of the lesion; on the other hand, magnetic resonance angiography (MRA) is rarely used in central vein examinations, and in MRA technology for arteries, contrast agents need to be injected through peripheral veins to display the lumen, and the magnetic resonance contrast agents used in this method can cause nephrogenic systemic fibrosis. Therefore, there is an urgent need for an image analysis and recognition method that can directly display the imaging characteristics of the central veins to provide data support for subsequent medical research. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a non-contrast enhanced magnetic resonance image recognition method, system, device and storage medium, so as to solve the problem that the existing imaging technology is not suitable for central veins, so as to achieve the effect of accurately locating the position and range of the lesion through magnetic resonance imaging, and objectively and accurately reflecting the degree of central vein stenosis.

[0005] In order to achieve the above object, in a first aspect, the present invention provides a non-contrast enhanced magnetic resonance image recognition method, the method comprising:

[0006] acquiring a magnetic resonance image to be identified;

[0007] Analyzing the magnetic resonance image to obtain the location of the lumen stenosis of the central vein and the contour of the outer wall of the blood vessel;

[0008] According to the stenosis position of the lumen and the outer wall contour of the blood vessel, the thrombus diameter and the outer diameter of the blood vessel are measured;

[0009] The absolute stenosis is calculated according to the thrombus diameter and the blood vessel outer diameter;

[0010] The absolute stenosis is calculated using the following formula:

[0011] S=D / E×100%

[0012] In the formula, D is the diameter of thrombus, and E is the outer diameter of blood vessel;

[0013] The magnetic resonance image is identified by the absolute stenosis to obtain an image identification result.

[0014] Furthermore, the step of analyzing the magnetic resonance image to obtain the stenosis position of the central vein and the outer wall contour of the blood vessel includes:

[0015] Analyzing the water phase in the magnetic resonance image to obtain a first high-signal image, and obtaining the thrombus position and thrombus range through the first high-signal image;

[0016] Determining the location of lumen stenosis of the central vein according to the location of the thrombus and the range of the thrombus;

[0017] The lipid phase in the magnetic resonance image is analyzed to obtain a second high signal image, and the outer wall contour of the central vein is obtained through the second high signal image.

[0018] Furthermore, the step of measuring the thrombus diameter and the outer diameter of the blood vessel according to the stenosis position of the lumen and the outer wall contour of the blood vessel comprises:

[0019] Measuring the range of the thrombus at the narrow position of the lumen to obtain the thrombus diameter;

[0020] According to the stenosis position of the lumen, the outer wall contour of the blood vessel is measured to obtain the outer diameter of the blood vessel.

[0021] Furthermore, the step of obtaining the outer wall contour of the central vein by using the second high signal image includes:

[0022] determining whether the distance between the central vein and the surrounding blood vessels in the second high signal image is less than a threshold;

[0023] If yes, the second high signal image is amplified by the positive phase and the negative phase in the magnetic resonance image to obtain an amplified second high signal image, and the outer wall contour of the central vein is obtained according to the amplified second high signal image;

[0024] If not, the outer wall contour of the central vein is obtained through the second high signal image.

[0025] In a second aspect, the present invention provides a non-contrast enhanced magnetic resonance image recognition system, the system comprising:

[0026] An image acquisition module, used for acquiring a magnetic resonance image to be identified;

[0027] An image analysis module, used to analyze the magnetic resonance image to obtain the location of the lumen stenosis of the central vein and the contour of the outer wall of the blood vessel;

[0028] and, measuring the thrombus diameter and the outer diameter of the blood vessel according to the stenosis position of the lumen and the outer wall contour of the blood vessel;

[0029] A data processing module, used for calculating the absolute stenosis according to the thrombus diameter and the blood vessel outer diameter;

[0030] The absolute stenosis is calculated using the following formula:

[0031] S=D / E×100%

[0032] In the formula, D is the diameter of thrombus, and E is the outer diameter of blood vessel;

[0033] The image recognition module is used to recognize the magnetic resonance image according to the absolute stenosis to obtain an image recognition result.

[0034] Furthermore, the image analysis module includes:

[0035] A water phase analysis module, used for analyzing the water phase in the magnetic resonance image to obtain a first high signal image, and obtaining a thrombus position and thrombus range through the first high signal image;

[0036] And, judging the location of lumen stenosis of the central vein according to the thrombus location and the thrombus range;

[0037] The lipid phase analysis module is used to analyze the lipid phase in the magnetic resonance image to obtain a second high signal image, and obtain the outer wall contour of the central vein through the second high signal image.

[0038] Furthermore, the image analysis module is also used to measure the range of the thrombus at the narrow position of the lumen to obtain the thrombus diameter;

[0039] And, according to the stenosis position of the lumen, the outer wall contour of the blood vessel is measured to obtain the outer diameter of the blood vessel.

[0040] Furthermore, the image analysis module also includes:

[0041] The positive and negative phase analysis module is used to determine whether the distance between the central vein and the surrounding blood vessels in the second high signal image is less than a threshold value; if so, the second high signal image is amplified by the positive phase and the negative phase in the magnetic resonance image to obtain an amplified second high signal image, and the outer wall contour of the central vein is obtained based on the amplified second high signal image; if not, the outer wall contour of the central vein is obtained through the second high signal image.

[0042] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0044] The present invention provides a non-contrast enhanced magnetic resonance image recognition method, system, device and storage medium. The present invention applies non-enhanced magnetic resonance imaging technology to the examination of central veins. Through the analysis method of magnetic resonance images provided by the present invention, the lesion can be directly displayed in the imaging examination and the positioning is accurate. At the same time, the present invention also proposes a measurement and calculation method for the absolute stenosis of central vein stenosis, which can accurately judge the degree of stenosis, thereby providing accurate and effective data support for medical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a schematic flow chart of a non-contrast enhanced magnetic resonance image recognition method according to an embodiment of the present invention;

[0046] Figure 2 yes Figure 1Schematic diagram of the process of step S20;

[0047] Figure 3 yes Figure 1 Schematic diagram of the process of step S203;

[0048] Figure 4 yes Figure 1 Schematic diagram of the process of step S30;

[0049] Figure 5 is another flow chart of the non-contrast enhanced magnetic resonance image recognition method in an embodiment of the present invention;

[0050] Figure 6 is a schematic diagram of a magnetic resonance image identified using the identification method in an embodiment of the present invention;

[0051] Figure 7 is a schematic structural diagram of a non-contrast enhanced magnetic resonance image recognition system according to an embodiment of the present invention;

[0052] Figure 8 It is a diagram of the internal structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the 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.

[0054] Among the current examination methods for central vein stenosis, digital subtraction angiography (DSA) and computed tomography angiography (CTA) are two relatively common methods. Among them, DSA is currently the gold standard for imaging diagnosis of central vein stenosis, but this method is an invasive and radiation-induced examination method and cannot be widely used. Although CTA is a non-invasive examination method, it also has the limitation of radiation and requires injection of contrast agents, and CTA cannot directly observe the morphology and imaging characteristics of the lesions. Magnetic resonance angiography (MRA) is currently rarely used in imaging examinations of central veins, and the present invention provides a method for analyzing and identifying magnetic resonance images of central veins, which can overcome the problems existing in the prior art and provide effective data support for subsequent medical research by accurately analyzing magnetic resonance images.

[0055] See also Figure 1 The first embodiment of the present invention provides a non-contrast enhanced magnetic resonance image recognition method, comprising steps S10 to S50:

[0056] Step S10, obtaining a magnetic resonance image to be identified.

[0057] Common scanning modes in magnetic resonance imaging include 2D scanning mode and 3D scanning mode. The present invention provides a method for analyzing and identifying 3D scanning images of magnetic resonance. First, a magnetic resonance image based on a central vein is obtained from a database. The 3D scanning image is generated based on a 3D anti-motion artifact sequence. The magnetic resonance image generated by a 3D-Vane sequence is used as an example for explanation below.

[0058] Step S20, analyzing the magnetic resonance image to obtain the location of the central vein lumen stenosis and the contour of the blood vessel outer wall.

[0059] Magnetic resonance imaging includes four sets of images, namely, water phase, lipid phase, positive phase and negative phase. The present invention can obtain the stenosis position of the central vein and the outer wall contour of the blood vessel by analyzing these four sets of images. The specific analysis steps are as follows: Figure 2 As shown:

[0060] Step S201, analyzing the water phase in the magnetic resonance image to obtain a first high signal image, and obtaining the thrombus position and thrombus range through the first high signal image;

[0061] Step S202, determining the stenosis position of the lumen of the central vein according to the thrombus position and the thrombus range;

[0062] Step S203, analyzing the fat phase in the magnetic resonance image to obtain a second high signal image, and obtaining the outer wall contour of the central vein through the second high signal image.

[0063] Among them, in the 3D scanning image of magnetic resonance, the water phase shows the blood flow state and thrombus state in the lumen. When the blood flow is smooth, it will show a low signal. When there is a thrombus in the lumen, the water phase will show a high signal. Therefore, through the high-signal image in the water phase, the thrombus morphology in the lumen of the central vein can be directly displayed, including the range and location of the thrombus. Then, by comparing the size of the thrombus range and the location of the thrombus in the water phase, it is possible to determine where the narrowest position of the lumen in the central vein shown in the magnetic resonance image is, thereby determining the narrow position of the lumen of the central vein.

[0064] The fat phase in the magnetic resonance image shows adipose tissue, so the adipose tissue will appear as a high signal in the fat phase. There are fat gaps between the central vein and other blood vessels and other tissues. Therefore, the high-signal image in the fat phase, that is, the high-signal adipose tissue, can clearly outline the outer wall contour of the central vein.

[0065] Although the outer wall contour of the central vein can be obtained by lipid phase in theory, in the actual image analysis process, when the central vein is close to other tissues such as peripheral blood vessels, the fat gap between the two is relatively narrow. Therefore, the outer wall contour of the vein cannot be accurately determined by lipid phase alone. In order to solve this problem, the present invention also provides a preferred embodiment, please refer to Figure 3 In this embodiment, the step of obtaining the outer wall contour of the central vein through the second high signal image includes:

[0066] Step S2031, determining whether the distance between the central vein and the surrounding blood vessels in the second high signal image is less than a threshold;

[0067] Step S2032: If yes, the second high signal image is amplified by the positive phase and the negative phase in the magnetic resonance image to obtain an amplified second high signal image, and the outer wall contour of the central vein is obtained according to the amplified second high signal image;

[0068] Step S2033: if not, obtaining the outer wall contour of the central vein through the second high signal image.

[0069] Among them, after obtaining the second-highest signal image, it is also necessary to judge the distance between the central vein and other tissues such as the surrounding blood vessels in the second-highest signal image. When the distance between the two is too close, it is considered that the second-highest signal image cannot accurately outline the outer wall contour of the central vein. At this time, it is necessary to analyze the in-phase and opposed-phase of the magnetic resonance image.

[0070] The in-phase in the magnetic resonance image can be simply understood as that the signal intensity in the image is determined by the signal generated by the protons in water plus the signal generated by the protons in fat, that is, the signal intensity in the in-phase is represented as water + fat, while the opposed-phase is the opposite of the in-phase. The signal intensity in the opposed-phase is determined by the signal generated by the protons in water minus the signal generated by the protons in fat, that is, the signal intensity in the opposed-phase is represented as water - fat. Therefore, the in-phase and opposed-phase can actually amplify the signal of the adipose tissue, and through the amplified adipose tissue, the outer wall contour of the blood vessel with a narrow fat gap can also be clearly displayed.

[0071] That is to say, by analyzing the water phase in the magnetic resonance image, the present invention can accurately find the lumen stenosis position of the central vein, and through the comprehensive analysis of the lipid phase, in-phase and opposed-phase in the magnetic resonance image, the outer wall contour of the central vein can be clearly displayed. The analysis method of the magnetic resonance image provided by the present invention is not only simple and efficient, but also accurate in results, thus providing accurate data support for the subsequent calculation of the absolute stenosis degree.

[0072] Step S30: Measure the thrombus diameter and the outer diameter of the blood vessel according to the lumen stenosis position and the outer wall contour of the blood vessel.

[0073] After obtaining the lumen stenosis position and the outer wall contour of the central vein through the above-mentioned image analysis, the thrombus diameter and the outer diameter of the blood vessel can be obtained by measuring the lumen stenosis position and the outer wall contour. The specific steps are as Figure 4 shown:

[0074] Step S301: Measure the thrombus range at the lumen stenosis position to obtain the thrombus diameter;

[0075] Step S302: Measure the outer wall contour of the blood vessel according to the lumen stenosis position to obtain the outer diameter of the blood vessel.

[0076] Among them, when analyzing the water phase, the lumen stenosis position can be judged according to the thrombus range and thrombus position in the central vein lumen. By measuring the thrombus range at the lumen stenosis position, the thrombus diameter at the lumen stenosis position can be obtained.

[0077] After obtaining the outer wall contour of the central vein by analyzing the lipid phase and the positive and negative phases, the outer wall of the blood vessel can be measured at the position corresponding to the narrow lumen position in the outer wall contour of the blood vessel in combination with the narrow lumen position found in the water phase analysis, thereby obtaining the outer diameter of the blood vessel at the narrow lumen position of the central vein. The conventional measurement methods in image processing can be used to measure the thrombus diameter and the outer diameter of the blood vessel, which will not be described in detail here.

[0078] Step S40, calculating the absolute stenosis according to the thrombus diameter and the blood vessel outer diameter.

[0079] After measuring the thrombus diameter and the outer diameter of the blood vessel at the location of lumen stenosis, the absolute stenosis of the central vein in the magnetic resonance image can be calculated. In previous technical methods, the formula used to calculate stenosis is generally: stenosis = 100% - lumen diameter at the stenosis / adjacent normal lumen diameter × 100%. It can be seen from the stenosis calculation formula that in addition to the lesion, that is, the lumen diameter at the stenosis, the previous stenosis calculation is also affected by the adjacent normal lumen diameter.

[0080] The existing stenosis calculation is actually an ideal calculation logic, that is, the diameter of the adjacent normal blood vessel is used to replace the normal diameter of the lesion blood vessel. The limitations of this in determining the degree of vascular stenosis mainly include the following three aspects:

[0081] First, the concept of proximity. For central veins, under normal circumstances, the shape of veins is variable. Even normal veins have different diameters at different locations with a short distance between them. The subjective selection of adjacent normal blood vessels will affect the evaluation of the lesion itself, but the severity of the lesion should not be affected by the morphology of adjacent normal blood vessels.

[0082] Second, the compensatory capacity of veins is much stronger than that of arteries. Severe stenosis or occlusion of central veins can cause tortuous expansion of distal veins and the opening and significant thickening of originally small venous side branches in a relatively short period of time. This has been widely confirmed in previous studies and clinical practice. In other words, although there are no lesions in the lumen of adjacent normal veins, the blood vessels themselves may have undergone secondary changes.

[0083] Third, central venous stenosis is mostly caused by intraluminal thrombosis, which may not be small-scale and focal. When the lesion is evenly attached to the inner wall of the vein and the length of the involvement is long, it is easy to mistake the adjacent mildly narrowed vein for a normal vein, resulting in an underestimation of the degree of stenosis.

[0084] Based on the above limitations, the present invention provides a method for calculating the absolute stenosis, that is, the absolute stenosis is calculated using the following formula:

[0085] S=D / E×100%

[0086] Where D is the diameter of the thrombus and E is the outer diameter of the blood vessel.

[0087] The absolute stenosis in the present invention is: the diameter of the thrombus at the stenosis of the lumen / the outer diameter of the blood vessel at the stenosis of the lumen×100%. It can be seen that the absolute stenosis of the present invention is determined only by the high signal at the stenosis, i.e., the thrombus, and the vascular morphology at the stenosis. Since the wall of the central vein is relatively thin, the outer diameter of the blood vessel can actually be approximately equal to the lumen diameter. That is, the absolute stenosis of the present invention only focuses on the stenosis of the venous lumen, and does not need to use the diameter of the normal blood vessel. The outer diameter of the blood vessel is used instead of the lumen diameter for calculation, which overcomes the limitations of the existing stenosis calculation. The calculation of the absolute stenosis provided by the present invention and the existing stenosis calculation are two essentially different calculation methods. The calculation method of the present invention can more accurately and objectively reflect the stenosis degree of the central vein than the existing method, thereby providing more effective data support for subsequent medical research.

[0088] Step S50, identifying the magnetic resonance image by using the absolute stenosis to obtain an image recognition result.

[0089] The magnetic resonance images are classified and identified by the absolute stenosis calculated as above, so as to obtain the identification result of the magnetic resonance images. Since the absolute stenosis calculation method provided by the present invention can more accurately and objectively reflect the stenosis degree of the central vein, the identification result of the magnetic resonance images classified and identified based on the absolute stenosis is also more objective and accurate.

[0090] See also Figure 5 The magnetic resonance image analysis process of the present invention includes: extracting a magnetic resonance 3D scanning image from a database, and obtaining four groups of images, namely, a water phase, a lipid phase, a positive phase, and a negative phase; performing image analysis on the water phase to obtain a high signal image; obtaining the position and range of the thrombus in the central vein according to the high signal, namely, the thrombus; judging the narrowest position of the lumen according to the position and range of the thrombus, thereby measuring the thrombus diameter at the narrowest position of the lumen; analyzing the lipid phase and the positive and negative phases in the 3D scanning image at the same time, outlining the outer wall contour of the central vein with the help of perivascular fat tissue, and measuring the outer diameter of the blood vessel at the narrowed position according to the narrowest position of the lumen; calculating the absolute stenosis by measuring the thrombus diameter and the outer diameter of the blood vessel, and classifying the magnetic resonance image according to the absolute stenosis to obtain an image recognition result.

[0091] See also Figure 6The calculation process of the absolute stenosis of the magnetic resonance image by the recognition method provided by the present invention is illustrated by an example: in the magnetic resonance image of the central vein, A, B, C, and D represent the water phase, the lipid phase, the positive phase, and the reverse phase, respectively. The stenosis position of the lumen of the central vein is obtained by analyzing the water phase, and the thrombus diameter can be measured at this position to be approximately 8 mm. The outer wall contour of the central vein is obtained by analyzing the lipid phase, the positive phase, and the reverse phase. At the narrow part of the outer wall contour of the blood vessel, the outer diameter of the blood vessel can be measured to be approximately 14 mm. According to the measured thrombus diameter and blood vessel outer diameter, the absolute stenosis of the magnetic resonance image is calculated to be 8 mm / 14 mm×100%≈60%.

[0092] The non-contrast enhanced magnetic resonance imaging recognition method provided in this embodiment is different from the traditional method which cannot directly observe the morphology and imaging characteristics of the lesion and has difficulty in finding a suitable adjacent normal lumen. The present invention can accurately locate the position of the thrombus and accurately obtain its imaging characteristics by analyzing the magnetic resonance 3D scanning images. It also proposes a method for calculating the absolute stenosis, which can accurately and objectively reflect the degree of stenosis of the central vein, thereby providing effective data support for subsequent medical research.

[0093] See also Figure 7 Based on the same inventive concept, a non-contrast enhanced magnetic resonance image recognition system proposed in the second embodiment of the present invention comprises:

[0094] An image acquisition module 10, used to acquire a magnetic resonance image to be identified;

[0095] An image analysis module 20 is used to analyze the magnetic resonance image to obtain the location of the lumen stenosis of the central vein and the contour of the outer wall of the blood vessel;

[0096] and, measuring the thrombus diameter and the outer diameter of the blood vessel according to the stenosis position of the lumen and the outer wall contour of the blood vessel;

[0097] A data processing module 30, configured to calculate an absolute stenosis degree according to the thrombus diameter and the blood vessel outer diameter;

[0098] The absolute stenosis is calculated using the following formula:

[0099] S=D / E×100%

[0100] In the formula, D is the diameter of thrombus, and E is the outer diameter of blood vessel;

[0101] The image recognition module 40 is used to recognize the magnetic resonance image according to the absolute stenosis to obtain an image recognition result.

[0102] Furthermore, the image analysis module 20 includes:

[0103] A water phase analysis module 201 is used to analyze the water phase in the magnetic resonance image to obtain a first high signal image, and obtain a thrombus position and thrombus range through the first high signal image;

[0104] And, judging the location of lumen stenosis of the central vein according to the thrombus location and the thrombus range;

[0105] The fat phase analysis module 202 is used to analyze the fat phase in the magnetic resonance image to obtain a second high signal image, and obtain the outer wall contour of the central vein through the second high signal image.

[0106] Furthermore, the image analysis module 20 is also used to measure the range of the thrombus at the narrow position of the lumen to obtain the thrombus diameter;

[0107] And, according to the stenosis position of the lumen, the outer wall contour of the blood vessel is measured to obtain the outer diameter of the blood vessel.

[0108] Furthermore, the image analysis module 20 also includes:

[0109] The positive and negative phase analysis module 203 is used to determine whether the distance between the central vein and the surrounding blood vessels in the second high signal image is less than a threshold value; if so, the second high signal image is amplified by the positive phase and the negative phase in the magnetic resonance image to obtain an amplified second high signal image, and the outer wall contour of the central vein is obtained based on the amplified second high signal image; if not, the outer wall contour of the central vein is obtained through the second high signal image.

[0110] The technical features and technical effects of the non-contrast enhanced magnetic resonance image recognition system proposed in the embodiment of the present invention are the same as those of the method proposed in the embodiment of the present invention, and are not described in detail here. Each module in the above-mentioned non-contrast enhanced magnetic resonance image recognition system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0111] See also Figure 8, an internal structure diagram of a computer device in an embodiment, the computer device can specifically be a terminal or a server. The computer device includes a processor, a memory, a network interface, a display and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a non-contrast enhanced magnetic resonance image recognition method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0112] It can be understood by those skilled in the art that Figure 8 The structure shown in the figure is merely a block diagram of a portion of the structure related to the present application scheme, and does not constitute a limitation on the computer device to which the present application scheme is applied. The specific computing device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0113] In addition, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0114] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0115] In summary, the non-contrast enhanced magnetic resonance image recognition method, system, device and storage medium proposed in the embodiments of the present invention, the method acquires the magnetic resonance image to be identified; analyzes the magnetic resonance image to obtain the lumen stenosis position of the central vein and the outer wall contour of the blood vessel; measures the thrombus diameter and the outer diameter of the blood vessel according to the lumen stenosis position and the outer wall contour of the blood vessel; calculates the absolute stenosis according to the thrombus diameter and the outer diameter of the blood vessel; identifies the magnetic resonance image by the absolute stenosis to obtain an image recognition result. The present invention can accurately locate the position, range and imaging characteristics of the thrombus by analyzing the magnetic resonance image, and can accurately and objectively reflect the degree of stenosis of the central vein by calculating the absolute stenosis, thereby providing effective data support for subsequent medical research.

[0116] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A non-contrast enhanced magnetic resonance image recognition method, It is characterized in that include: acquiring a magnetic resonance image to be identified; Analyzing the magnetic resonance image to obtain the location of the lumen stenosis of the central vein and the contour of the outer wall of the blood vessel; According to the stenosis position of the lumen and the outer wall contour of the blood vessel, the thrombus diameter and the outer diameter of the blood vessel are measured; The absolute stenosis is calculated according to the thrombus diameter and the blood vessel outer diameter; The step of analyzing the magnetic resonance image to obtain the location of the lumen stenosis of the central vein and the contour of the outer wall of the blood vessel comprises: Analyzing the water phase in the magnetic resonance image to obtain a first high-signal image, and obtaining the thrombus position and thrombus range through the first high-signal image; Determining the location of lumen stenosis of the central vein according to the location of the thrombus and the range of the thrombus; Analyzing the lipid phase in the magnetic resonance image to obtain a second high signal image, and obtaining the outer wall contour of the central vein through the second high signal image; The absolute stenosis was calculated using the following formula: S=D / E×100% In the formula, D is the diameter of thrombus, and E is the outer diameter of blood vessel; The magnetic resonance image is identified by the absolute stenosis to obtain an image identification result.

2. The non-contrast enhanced magnetic resonance image recognition method according to claim 1, It is characterized in that The step of measuring the thrombus diameter and the outer diameter of the blood vessel according to the stenosis position of the lumen and the outer wall contour of the blood vessel comprises: Measuring the range of the thrombus at the narrow position of the lumen to obtain the thrombus diameter; According to the stenosis position of the lumen, the outer wall contour of the blood vessel is measured to obtain the outer diameter of the blood vessel.

3. The non-contrast enhanced magnetic resonance image recognition method according to claim 1, It is characterized in that The step of obtaining the outer wall contour of the central vein through the second high signal image comprises: determining whether the distance between the central vein and the surrounding blood vessels in the second high signal image is less than a threshold; If yes, the second high signal image is amplified by the positive phase and the negative phase in the magnetic resonance image to obtain an amplified second high signal image, and the outer wall contour of the central vein is obtained according to the amplified second high signal image; If not, the outer wall contour of the central vein is obtained through the second high signal image.

4. A non-contrast enhanced magnetic resonance image recognition system, It is characterized in that include: An image acquisition module, used for acquiring a magnetic resonance image to be identified; An image analysis module, used to analyze the magnetic resonance image to obtain the location of the lumen stenosis of the central vein and the contour of the outer wall of the blood vessel; and, measuring the thrombus diameter and the outer diameter of the blood vessel according to the stenosis position of the lumen and the outer wall contour of the blood vessel; A data processing module, used for calculating the absolute stenosis according to the thrombus diameter and the blood vessel outer diameter; The absolute stenosis is calculated using the following formula: S=D / E×100% In the formula, D is the diameter of thrombus, and E is the outer diameter of blood vessel; An image recognition module, used to recognize the magnetic resonance image by the absolute stenosis to obtain an image recognition result; The image analysis module includes: A water phase analysis module, used for analyzing the water phase in the magnetic resonance image to obtain a first high signal image, and obtaining a thrombus position and thrombus range through the first high signal image; And, judging the location of lumen stenosis of the central vein according to the thrombus location and the thrombus range; The lipid phase analysis module is used to analyze the lipid phase in the magnetic resonance image to obtain a second high signal image, and obtain the outer wall contour of the central vein through the second high signal image.

5. The non-contrast enhanced magnetic resonance image recognition system according to claim 4, It is characterized in that The image analysis module is also used to measure the range of the thrombus at the narrow position of the lumen to obtain the thrombus diameter; And, according to the stenosis position of the lumen, the outer wall contour of the blood vessel is measured to obtain the outer diameter of the blood vessel.

6. The non-contrast enhanced magnetic resonance image recognition system according to claim 4, It is characterized in that The image analysis module also includes: The positive and negative phase analysis module is used to determine whether the distance between the central vein and the surrounding blood vessels in the second high signal image is less than a threshold value; if so, the second high signal image is amplified by the positive phase and the negative phase in the magnetic resonance image to obtain an amplified second high signal image, and the outer wall contour of the central vein is obtained based on the amplified second high signal image; if not, the outer wall contour of the central vein is obtained through the second high signal image.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images