Method, device, apparatus and readable storage medium for measuring intima-media thickness of blood vessel

Abstract

The application discloses a method for measuring the intima-media thickness of a blood vessel, comprising: collecting multiple OCT images of a certain part of the blood vessel changing over time; processing the images to separate the intima-media region in each image; calculating and determining the centroid of the intima-media according to the inner boundary and / or outer boundary of the intima-media region; taking the centroid as the center of the intima-media to perform circumferential equiangular division on the intima-media; calculating the thickness of each divided intima-media section at a specific time; and averaging the thickness of part or all of the intima-media sections as the thickness of the intima-media at the certain part; wherein the OCT images are processed by a deep learning method based on a u-net algorithm to segment the intima-media region in the OCT images.

Description

Technical Field

[0001] This application relates to the field of vascular detection technology, and in particular, to a method, apparatus, device, and readable storage medium for measuring the intima-media thickness of blood vessels. Background Technology

[0002] Arterial intima-media thickness (IMT) and elasticity are important factors in the diagnosis and mechanistic study of vascular diseases. Increased IMT is closely related to the occurrence of myocardial infarction and stroke. Atherosclerotic plaques are usually caused by thickening and hardening of blood vessels, and arteriosclerosis can also lead to systemic hypertension, ultimately damaging organs and tissues. Advanced vascular imaging techniques, such as intravascular optical coherence tomography (IVOCT, also referred to as OCT in this application), can image and display the structure of the vessel wall, but cannot provide information on the elasticity or stiffness of the vessel wall.

[0003] Traditional methods for measuring vascular elasticity are primarily based on pulse wave theory. Studies have shown that blood pressure and arteriosclerosis are mutually influential; therefore, traditional pulse wave methods struggle to distinguish the effects of blood pressure and vascular stiffness on propagation velocity, resulting in low accuracy in vascular elasticity measurements. Intravascular ultrasound (IVUS) has also been used to assess vascular anatomical dimensions and wall thickness, evaluating vascular compliance at different blood pressure levels through changes in vessel diameter. However, diameter changes do not reflect local vascular compliance, especially in cases of disease progression where perivascular compliance may differ. Therefore, high-resolution imaging techniques are needed to detect circumferential intravascular thickness (IMT) and vascular compliance. Summary of the Invention

[0004] The embodiments of this application aim to partially solve the above-mentioned technical problems, thereby providing a method for rapidly detecting the thickness of the intima-media of blood vessels without consuming excessive computing power.

[0005] According to a first aspect of the present invention, this application discloses a method for measuring the thickness of the intima-media layer of a blood vessel, characterized by comprising: acquiring multiple OCT images of a certain location of the blood vessel over time; processing the images to separate the intima-media region in each image; calculating and determining the centroid of the intima-media layer based on the inner boundary and / or outer boundary of the intima-media region; using the centroid as the center of the intima-media layer to divide the intima-media layer circumferentially at equal angles; calculating the thickness of each segment of the intima-media layer at a specific time; taking the average thickness of part or all of the segments of the intima-media layer as the thickness of the intima-media layer at that location; wherein, the OCT images are processed by a deep learning method based on the u-net algorithm to segment them and thereby separate the intima-media region therein.

[0006] Furthermore, the centroid is used as the origin of polar coordinates to perform coordinate transformation on the image of the inner membrane region, and the thickness of each segment of the inner membrane at a specific time is calculated in polar coordinates.

[0007] Furthermore, this method can also obtain the radial strain and / or strain rate of the intima-media of blood vessels to assess the health of the blood vessels.

[0008] Furthermore, the strain is defined with reference to any frame of the image, assuming the deformation of the intima-media layer of the blood vessel is zero at that moment, and is the ratio of the change in wall thickness over a random time t to the wall thickness at that moment; and the radial strain rate between adjacent images is calculated by the following formula:

[0009]

[0010] In the formula, i represents the i-th image, and t i For instantaneous time, T(t) i ) for t i The thickness of the blood vessel wall at that location; Δt is the time difference between adjacent OCT images.

[0011] Furthermore, the strain of the blood vessel is obtained by taking the first frame of the image as a reference, i.e. assuming that the deformation at that moment is zero.

[0012] According to some embodiments of the present invention, this application also discloses a vascular assessment method, which assesses the health status and / or disease risk of blood vessels based on at least one of the intima-media thickness, strain, and strain rate obtained by the intima-media thickness measurement method described above, and generates assessment results.

[0013] According to some embodiments of the present invention, this application also discloses a device for measuring parameters of the intima-media of a blood vessel, comprising: an image acquisition device for acquiring OCT images of the blood vessel at a specific location at different times; an image processing module for processing the images to separate the intima-media region in each image; and a calculation module for calculating the thickness, strain, and / or strain rate of the intima-media region at that location based on the images of the intima-media region at different times.

[0014] According to some embodiments of the present invention, this application also discloses a vascular assessment device, comprising: a measuring device for the parameters of the intima-media of the vascular vessel as described above, and a generation module, the generation module being used to assess the health status and / or disease risk of the vascular vessel based on at least one of the thickness, strain, and / or strain rate of the intima-media of the vascular vessel and to generate assessment results.

[0015] According to some embodiments of the present invention, this application also discloses a device for measuring the parameters of the intima-media of blood vessels, characterized in that it includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for measuring the parameters of the intima-media of blood vessels as described above.

[0016] According to some embodiments of the present invention, this application also discloses a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the method for measuring the thickness of the intima-media of blood vessels and the steps of the method for vascular assessment as described above.

[0017] The method, apparatus, device, and readable storage medium for measuring the intima-media thickness of blood vessels according to embodiments of the present invention can not only quickly obtain the intima-media thickness of blood vessels but also assess the health of blood vessels. Attached Figure Description

[0018] The advantages of the present invention will become clearer and easier to understand through the following detailed description in conjunction with the accompanying drawings, which are merely illustrative and do not limit the scope of protection of the present invention, wherein:

[0019] Figure 1 The method for measuring the intima-media thickness of blood vessels and its related steps are shown in a non-limiting manner according to embodiments of the present invention;

[0020] Figure 2 The OCT images and histological images of blood vessels according to embodiments of the invention are shown in a non-limiting manner.

[0021] Figure 3 A model diagram based on the u-net algorithm according to an embodiment of the invention is shown in a non-limiting manner;

[0022] Figure 4 The images shown are non-limiting OCT images of blood vessels in polar and Cartesian coordinate systems, as well as images processed by artificial intelligence models and GT images, according to embodiments of the present invention.

[0023] Figure 5 The images shown are non-limiting examples of OCT images of blood vessels after segmentation using a CNN model and after coordinate transformation, according to embodiments of the present invention.

[0024] Figure 6 The thickness variation of different segments of the intima-media of a blood vessel over time is shown in a non-limiting manner according to an embodiment of the present invention.

[0025] Figure 7The strain rate changes of different segments of the intima-media of a blood vessel over time are shown in a non-limiting manner according to an embodiment of the present invention.

[0026] Figure 8 The strain changes of different segments of the intima-media of a blood vessel over time are shown in a non-limiting manner according to an embodiment of the present invention.

[0027] Figure 9 The vascular assessment method and steps according to embodiments of the present invention are shown in a non-limiting manner.

[0028] Figure 10 The method and steps for determining mutations in different segments of a blood vessel according to embodiments of the present invention are shown in a non-limiting manner.

[0029] Figure 11 A schematic diagram of a device for measuring the intima-media of blood vessels according to an embodiment of the present invention is shown in a non-limiting manner.

[0030] Figure 12 A schematic diagram of a vascular assessment device according to an embodiment of the present invention is shown in a non-limiting manner;

[0031] Figure 13 A schematic diagram of a measuring device for the intima-media of blood vessels according to an embodiment of the present invention is shown in a non-limiting manner. Detailed Implementation

[0032] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0034] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0035] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0036] In a non-limiting sense, the embodiments of this application are described below using examples of vascular measurement, wherein the equipment used is commonly used in the art and will not be described in detail in this application. The testing system can simultaneously measure the expansion, cross-sectional deformation, and pressure of blood vessels. In a non-limiting sense, the testing system in this application can be of other forms, as long as it can obtain the same measurement images and parameters, it falls within the protection scope of this invention.

[0037] An intravascular OCT (Optical Coherence Tomography) system (HS-100, China Horizontal Medical) is used for imaging. In embodiments of the present invention, the axial resolution of the OCT system is 2-200 μm, preferably 20 μm. In the method according to embodiments of this application, only an image of a cross-section at a specific location on the blood vessel is needed; therefore, the OCT catheter does not need to be retracted.

[0038] It should be understood that a blood vessel includes the lumen (also called the inner membrane or lumen), the intima-media (also called the media or "intima-media"), and the adventitia. Although the expressions may differ, in the embodiments according to this application, "intima-media", "media", "intima-media", "media-intima", etc. are abstractly referred to as the intima-media.

[0039] Non-restrictive, such as Figure 1As shown, this invention provides a method for automatically quantifying changes in vascular intima-media thickness (IMT) and strain distribution, namely, a method for measuring the intima-media thickness of blood vessels, comprising the following steps: Step 101, acquiring multiple OCT images of a certain location of the blood vessel over time; Step 102, processing the images to separate the intima-media region in each image; Step 103, calculating and determining the centroid of the intima-media based on the inner and / or outer boundaries of the intima-media region; Step 104, using the centroid as the center of the intima-media to divide the intima-media into circumferential segments at equal angles; Step 105, calculating the thickness of each segment of the intima-media at a specific time; Step 106, taking the average thickness of part or all of the segments of the intima-media as the thickness of the intima-media at that location, wherein, in Step 102, the OCT images are processed using a deep learning method based on the u-net algorithm to segment them and thus separate the intima-media region.

[0040] Specifically, and without limitation, a dataset is created by acquiring images of one or more pulsating cycles of the carotid or coronary artery cross-section using an OCT system; the acquired images are processed to obtain the intima-media thickness (IMT) and strain and strain rate in various directions around the vessel. In the above steps, the acquired IVOCT images are segmented into the intima and media using a deep learning method based on a U-Net convolutional neural network (CNN). The loss function of the CNN model uses a binary cross-entropy function.

[0041]

[0042] In the formula, the loss function is the average of the binary cross-entropy between the output of all pixels and the ground truth; N is the number of predicted points, which is the total number of pixels in the output image; i th Let be the i-th pixel in the image, y be the true label value (1 for positive class, 0 for negative class), and p(yi) be the predicted probability value, representing the difference between the true sample label and the predicted probability. The CNN network is trained using the Adam optimizer with a learning rate of 1e-4. Training is complete when the loss function reaches 0.0178 and the accuracy reaches 99.22%. The trained model is then used to achieve rapid and accurate segmentation of intima-media images.

[0043] Assuming the intima-media region is approximately a ring-shaped region, the centroid of the vascular lumen can be calculated using the following formula as the center;

[0044]

[0045] In the formula, A is the area of ​​the inner-middle membrane; x and y are the distances from dA to the origin at the top left corner of the image; x c y c D represents the coordinates of the centroid; D is the endothelial region predicted by the CNN.

[0046] The radial strain rate between adjacent IVOCT images is calculated by the following formula:

[0047]

[0048] In the formula, i represents the i-th image, and t i For instantaneous time, T(t) i ) for t i The vessel wall thickness at that location; Δt is the time difference between adjacent IVOCT images.

[0049] Taking the first frame of the image sequence as a reference, i.e., assuming the deformation is zero at that moment, the total strain over a random time t is calculated by the following formula:

[0050]

[0051] In the formula, ε(t) is the radial strain of the blood vessel wall. T(t) is the wall thickness at point t;

[0052] Based on the CNN segmentation results, the full-field distribution, radial strain rate, and strain of the IMT are obtained through center detection and coordinate transformation. The advantages of the above-mentioned machine learning-based arterial IVOCT segmentation and strain quantification method are that it requires less data, has high prediction accuracy, and can identify local changes in stiffness or compliance by observing the strain distribution around the entire vessel wall.

[0053] Non-restrictive, such as Figure 2 As shown, in vivo imaging of the porcine carotid artery was performed using an IVOCT system. The IVOCT system has an axial resolution of 15 μm and a frame rate of 100 frames per second. Images were captured with and without catheter retraction; this embodiment only processes non-retracted images. The images in Cartesian coordinates are shown below. Figure 2 As shown in (b), the graph is converted to polar coordinates and displayed as follows. Figure 2 As shown in (a), it displays approximately seven cardiac cycles. The histology of the imaging vessels is as follows. Figure 2 As shown in (c). Figure 2 Correlating (b) with (c), it can be seen that the IVOCT images clearly show the intima-media and external elastic layer.

[0054] like Figure 3As shown, the CNN model can be divided into downsampling and upsampling modules. Downsampling consists of sequential convolutional blocks composed of 3×3 convolutions, batch normalization, and 2×2 max pooling, with a Rectified Linear Unit (ReLU) activation function, which allows for fast computation of the CNN model. Dropout layers are introduced in the 4th and 5th convolutional layers to avoid overfitting and improve the model's generalization ability. The upsampling process includes 2×2 unpooling and 3×3 convolutions. In this study, each convolutional step is padded with one pixel, so the image size does not change during all convolutional operations; both the network input and output are 256×256 pixel images. In the last layer, a sigmoid function is applied to normalize the pixel values ​​of the network's last layer output image to the interval (0,1) to independently generate the class probability for each pixel.

[0055] Non-limiting, the following is a specific embodiment of the automatic measurement of IMT full field distribution, radial strain rate and strain of porcine carotid artery, which further describes the method provided by the present invention in detail so that those skilled in the art can clearly and accurately understand the technical solution of the present invention.

[0056] The model was trained over 300 batches and 2 epochs with a batch size of 3, taking a total of 286 seconds. A single frame of IVOCT image 4(a) with good contrast is shown, illustrating the structure of the blood vessel wall. Images segmented in Cartesian and polar coordinates by the U-Net-based CNN model are shown below. Figure 4 As shown in (c) and (b).

[0057] from Figure 4 (c) It can be seen that the gap caused by the guidewire has been restored (indicated by the arrow). Figure 4 (d) is one of the GT images in the Cartesian coordinate system (Ground Truth image, which is an ideal image drawn by experts by hand. To avoid randomness and reduce errors, multiple experts can be selected to obtain multiple GT segmentation results, and the average value of each evaluation parameter is taken). Figure 4 (e), (g), and (i) are contrast ratios relative to... Figure 4 (a) Lower image, Figure 4 (f), (h) and (j) are the corresponding segmentation images of the CNN.

[0058] It can be seen that, apart from the small area at the tip and the guidewire blockage area, Figure 4 (f) and (h) can correctly detect the intima-media membrane. Figure 4(j) The ductal obstruction area was not segmented due to low signal. Of the 600 images, 71 were not well segmented due to poor quality and were excluded from the IMT calculation. Due to insufficient saline flushing during imaging leading to feature loss, 36 images without detectable good boundaries during imaging were used to replace adjacent images for IMT and strain assessment, such as... Figure 4 (e), (g), (i). The well-trained CNN model took a total of 36 seconds to segment 600 images, with an average time of 59ms per image.

[0059] To evaluate the segmentation performance of the trained CNN, a validation dataset containing 20 CNN-segmented images and their corresponding ground truth (GT) images was input into the formula. In this study, the overall average Dice coefficient was calculated to be 0.968.

[0060] A segmented image after binarization and connected component extraction is as follows: Figure 5 As shown in (a), the centroid C is obtained through the formula Sure. Figure 5 (b) shows the image after removing redundant pixels, moved to point C as the center. For ease of data analysis, the inner membrane-middle layer was divided into 12 regions, each 30°, and the image was converted to polar coordinates, as shown below. Figure 5 As shown in (c).

[0061] Calculate the IMT, strain rate, and strain along each line in the r-direction during imaging in polar coordinates, and then... Figure 6 , Figure 7 and Figure 8 Plot a curve that changes over time.

[0062] Calculate the average IMT for each region, then smooth the data using a 10-fold average kernel size, and plot it on... Figure 6 In the middle, the IMT curves of the three regions are as follows: Figure 6 As shown

[0063] It can be seen that the thickness in most areas is ~0.3mm, except for areas 6 and 7, where the IMT is relatively high. Figure 6 As shown in (b) and (c), the IMT pulsation is not uniform. In the first 150 ms, the thickness variation in regions 1 and 3 is small, while other regions are relatively stable. In regions 6-9, the IMT shows almost no change. Figure 6 As shown in (d), the appearance of the four larger peaks corresponds to the instant of insufficient brine flushing. It can be concluded that, from... Figure 6 In region 10-12 of (d), seven periodic variations can be observed, and these curves change periodically over time. Figure 5In (b), the peak between 300 and 400 ms is unclear because some images were replaced due to poor quality. In this study, from Figure 6 In (d), the maximum wall thickness observed at time 4.01s for curve 12 is 0.355mm; the minimum IMT value for curve 2 is 0.251mm at time 1.79s; the average IMT is calculated to be 0.298mm.

[0064] Through formula Calculate the radial strain rate of 12 regions as follows Figure 7 The data was smoothed using a point-by-point moving average method. The curve shows that the maximum instantaneous radial strain rate is 2.8e-3 / ms. Figure 7 (d) The minimum value is -2.7e-3 / ms at 4.02s of curve 12; the minimum value is -2.7e-3 / ms at 4.14s of curve 12.

[0065] Through formula The calculated radial strain of the vessel wall is as follows Figure 7 As shown, its trend is the same as that of IMT.

[0066] Region 2 exhibits a larger negative strain than other regions, possibly due to inaccurate boundary identification. This is primarily because Region 2 is furthest from the IVOCT catheter, where the boundary between the medium and the outer elastic layer is unclear. It can be seen that, except for curve 2, the maximum strain value of 0.227 appears... Figure 8 (d) is at 4.05s in curve 12; the minimum value is -0.008, as shown at 5.02s in curve 7.

[0067] The full-field distribution of IMT, radial strain rate, and strain were obtained through center detection and coordinate transformation. We found that these parameters are non-uniform in the circumferential direction, and their values ​​over time reflect the pulsating characteristics of the blood vessel. The average wall thickness of the porcine carotid artery was calculated to be 0.298 mm. This study provides an automated and accurate method for measuring vascular wall IMT, strain rate, and strain, laying the foundation for the development of functional in vivo endovascular computed tomography (IVOCT) technology and the analysis of in vivo vascular biomechanical properties.

[0068] Non-restrictive, such as Figure 9 As shown in the embodiment of this application, a device 1000 for measuring the parameters of the intima-media of a blood vessel is also provided, including an image acquisition module 1100 for acquiring OCT images of the blood vessel at a specific location at different times; an image processing module 1200 for processing the images to separate the intima-media region in each image; and a calculation module 1300 for calculating the thickness, strain, and / or strain rate of the intima-media at that location based on the images of the intima-media region at different times.

[0069] Non-restrictive, such as Figure 10As shown, this application embodiment also provides a method 200 for evaluating blood vessels, including step 210, acquiring the circumferential thickness distribution, strain rate distribution, and strain distribution curves of the intima-media at a specific location of the blood vessel over time; step 220, acquiring regions of abrupt changes in any parameter among the above three distribution curves; step 230, confirming whether any of the other two parameters in the abrupt region also exhibits abrupt changes; if it is determined that at least one of the other two parameters also exhibits abrupt changes, then step 240 is executed to indicate and / or mark the risk at that location, and adjust the sampling frequency and / or catheter travel rate near that location; otherwise, step 250 is executed to allow the catheter to continue evaluating other locations of the blood vessel at the original rate and sampling rate; wherein, the method of step 210 can be referred to according to the embodiments of the present invention. Figure 1 The method 100 shown in the figure for obtaining the thickness of the intima-media of a blood vessel is implemented, and the method for obtaining the strain rate and strain of the intima-media can also be implemented with reference to the description of the embodiments of this application. It is readily understood that steps 210 and 250 are essentially the same operation performed, except that the detected location changes over time and with the movement of the catheter.

[0070] Furthermore, regarding how to determine whether a parameter mutation exists at a certain location in the intima-media of a blood vessel, please refer to... Figure 11 The method 300 is implemented as follows, including step 310, removing the maximum and minimum values ​​of the thickness of each segment of the intima-media at a certain location of the blood vessel, and taking the arithmetic mean of the remaining values, where the number of segments n∈(4,96); step 320, comparing the maximum and / or minimum values ​​of each segment with the arithmetic mean obtained above, and determining that there is a mutation when the difference exceeds x% of the average value, where x∈(3,30); and similarly, the other two parameters can also be determined using this approach and method.

[0071] Preferably, in order to reduce the amount of computation, increase the efficiency of operation, and improve the detection speed, the thickness of the inner membrane is usually analyzed first to determine whether there is a sudden change.

[0072] Preferably, when it is determined that there is a mutation in at least two of the parameters of intima-media thickness, strain rate, and strain at a certain location, the catheter movement speed after confirming the mutation should be reduced and / or the image sampling frequency / sampling time should be increased to obtain more detailed assessment information of the surrounding area to further confirm the lesion risk at and near that location; if the intima-media tissue detected after reducing the catheter movement speed and / or increasing the image sampling frequency / sampling time still shows mutations, then continuous sampling should be performed with the current reduced and / or increased parameters until no mutations are observed in the three parameters, and then the original initial detection parameters should be restored.

[0073] Figure 12Further illustrated is a vascular assessment device 2000 according to an embodiment of this application, including an image acquisition module 2100, an image processing module 2200, a calculation module 2300, and an assessment module 2400; wherein the first three modules are integrated together to form a vascular intima-media thickness measuring device 1000 according to an embodiment of the present invention.

[0074] Figure 13 A measuring device and an evaluation device for the thickness of the intima-media layer of a blood vessel according to an embodiment of this application are illustrated. In this embodiment, the control device includes a processor, a memory, and an application program stored in the memory and executable on the processor. When the processor executes the application program, it implements the steps in the embodiments of the methods for measuring the thickness of the intima-media layer of a blood vessel and the methods for evaluating blood vessels. Alternatively, when the processor executes the application program, it implements the functions of each module / unit as described in the embodiments of the system embodiments above.

[0075] A processor can be a single processing unit or multiple processing units, and all processing units may include single or multiple computing units or multiple cores. A processor can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. Among other capabilities, a processor can be configured to fetch and execute computer-readable instructions, such as application program code, program code of other programs, etc., stored in memory, mass storage devices, or other computer-readable media.

[0076] Memory and mass storage devices are examples of computer-readable storage media used to store instructions that are executed by a processor to perform the various functions described above. For example, memory can generally include both volatile and non-volatile memory (e.g., RAM, ROM, etc.). Furthermore, mass storage devices can generally include hard disk drives, solid-state drives, removable media (including external and removable drives), memory cards, flash memory, floppy disks, optical disks (e.g., CDs, DVDs), storage arrays, network-attached storage, storage area networks, etc. Both memory and mass storage devices can be collectively referred to as memory or computer-readable storage media, and can be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer program code, which can be executed by a processor as a specific machine configured to perform the operations and functions described in the examples herein.

[0077] Multiple programs can be stored on a mass storage device. These programs include one or more applications, other programs, and program data, and they can be loaded into memory for execution. Examples of such applications or program modules may include, for example, computer program logic (e.g., computer program code or instructions) for implementing components / functions.

[0078] This invention also provides a computer-readable storage medium storing an application program that, when executed by a processor, implements... Figure 1 , Figure 2 , Figure 9 and / or Figure 10 The method steps are shown. The application program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0079] Furthermore, the application includes application code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the application code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0080] Figure 13 In this system, one or more communication interfaces are used to exchange data with other devices, such as via a network, direct connection, etc. Such communication interfaces can be one or more of the following: any type of network interface (e.g., a network interface card (NIC)), wired or wireless (such as IEEE 802.11 Wireless LAN (WLAN)) wireless interface, Wi-MAX interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, Bluetooth™ interface, Near Field Communication (NFC) interface, etc. Communication interfaces can facilitate communication across various network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. Communication interfaces can also provide communication with external storage devices (not shown), such as storage arrays, network-attached storage, storage area networks, etc.

[0081] As used in this invention, "computer-readable medium" includes at least two types of computer-readable media, namely computer-readable storage media and communication media.

[0082] Computer-readable storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD, or other optical storage devices, magnetic cassettes, magnetic tapes, disk storage devices or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by electronic devices. In contrast, communication media can embody computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms. The computer-readable storage media as defined in this invention do not include communication media.

[0083] Furthermore, the memory can include both internal storage units and external storage devices within the control device. The memory is used to store application programs and other programs and data required by the control device. The memory can also be used to temporarily store data that has been output or will be output.

[0084] In some examples, control devices may include display devices such as monitors for displaying information and images to the user. Other I / O devices may be devices that receive various inputs from the user and provide various outputs to the user, and may include touch input devices, gesture input devices, cameras, keyboards, remote controls, mice, printers, audio input / output devices, etc.

[0085] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0086] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method of measuring the intima-media thickness of a blood vessel, characterized by, The method comprises: acquiring a plurality of OCT images of a blood vessel at a certain location over time; processing the images to separate the intima-media region in each image; calculating the centroid of the intima-media according to the inner boundary and / or outer boundary of the intima-media region; using the centroid as the center of the intima-media to perform equiangular circumferential division of the intima-media; calculating the thickness of each divided segment of the intima-media at a certain time; averaging the thickness of all or part of the segments of the intima-media to obtain the thickness of the intima-media at the acquired blood vessel location; wherein the OCT images are processed by a deep learning method based on a u-net algorithm to segment the intima-media region.

2. The method of measuring the intima-media thickness of a blood vessel according to claim 1, wherein, The centroid is used as the origin of the polar coordinate to perform coordinate transformation on the image of the intima-media region, and the thickness of each segmented segment of the intima-media at a certain time is calculated in the polar coordinate system.

3. The method of measuring the intima-media thickness of a blood vessel according to Claim 1, wherein, The method can also obtain the radial strain and / or strain rate of the intima-media of the blood vessel.

4. The method of measuring the intima-media thickness of a blood vessel according to claim 3, wherein, The strain is calculated with respect to any frame of the image, assuming that the deformation of the intima-media of the blood vessel at the time corresponding to the first frame image is 0, and the ratio of the change in wall thickness in a random time t to the wall thickness at the time corresponding to the first frame image; and the radial strain rate between adjacent images is calculated by the following formula: ， wherein i is the first i image, t i is the instantaneous time, T t i is the t i the blood vessel wall thickness at the location; Δ t is the time difference between adjacent OCT images.​ 5. The method of measuring the intima-media thickness of a blood vessel according to claim 4, wherein, The strain of the blood vessel is obtained with respect to the first frame of the image, i.e., assuming that the deformation at this time is zero.

6. An apparatus for measuring a parameter of an intima of a blood vessel, characterized by, A method for measuring the thickness of the intima-media of a blood vessel according to any one of claims 1 to 5, comprising: an image acquisition module for acquiring OCT images of the blood vessel at a certain location at different times; an image processing module for processing the images to separate the intima-media region in each image; a calculation module for calculating the thickness, strain and / or strain rate of the intima-media at the location according to the images of the intima-media region at different times.

7. An assessment device of a blood vessel, characterized in that The method comprises: The device for measuring the parameters of the intima-media of a blood vessel according to claim 6, and an evaluation module for evaluating the health degree and / or lesion risk of the blood vessel according to at least one of the thickness, strain and / or strain rate of the intima-media of the blood vessel and generating an evaluation result.

8. An apparatus for measuring a parameter of the intima-media of a blood vessel, characterized by The method comprises: a memory, a processor and a computer program stored on the memory and executable on the processor, which, when executed by the processor, implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images