WO2021175039A1 - 冠状动脉的血流速度的计算方法、装置及电子设备 - Google Patents

冠状动脉的血流速度的计算方法、装置及电子设备 Download PDF

Info

Publication number
WO2021175039A1
WO2021175039A1 PCT/CN2021/073277 CN2021073277W WO2021175039A1 WO 2021175039 A1 WO2021175039 A1 WO 2021175039A1 CN 2021073277 W CN2021073277 W CN 2021073277W WO 2021175039 A1 WO2021175039 A1 WO 2021175039A1
Authority
WO
WIPO (PCT)
Prior art keywords
main branch
blood flow
vessel
length
image
Prior art date
Application number
PCT/CN2021/073277
Other languages
English (en)
French (fr)
Inventor
涂圣贤
赵秋阳
胡易斯
陈树湛
Original Assignee
博动医学影像科技(上海)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 博动医学影像科技(上海)有限公司 filed Critical 博动医学影像科技(上海)有限公司
Priority to JP2022551789A priority Critical patent/JP7445779B2/ja
Priority to EP21765234.6A priority patent/EP4104766A4/en
Priority to US17/802,838 priority patent/US20230108647A1/en
Publication of WO2021175039A1 publication Critical patent/WO2021175039A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • G06T7/0014Biomedical image inspection using an image reference approach
    • G06T7/0016Biomedical image inspection using an image reference approach involving temporal comparison
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/48Diagnostic techniques
    • A61B6/481Diagnostic techniques involving the use of contrast agents
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/48Diagnostic techniques
    • A61B6/486Diagnostic techniques involving generating temporal series of image data
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/50Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/503Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of the heart
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/50Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/504Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of blood vessels, e.g. by angiography
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/50Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/507Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for determination of haemodynamic parameters, e.g. perfusion CT
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • A61B6/5217Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/48Diagnostic techniques
    • A61B6/486Diagnostic techniques involving generating temporal series of image data
    • A61B6/487Diagnostic techniques involving generating temporal series of image data involving fluoroscopy
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10016Video; Image sequence
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10116X-ray image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20021Dividing image into blocks, subimages or windows
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20081Training; Learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20084Artificial neural networks [ANN]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20092Interactive image processing based on input by user
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30048Heart; Cardiac
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30101Blood vessel; Artery; Vein; Vascular
    • G06T2207/30104Vascular flow; Blood flow; Perfusion

Definitions

  • the present invention relates to the field of computer technology, in particular to a method, device, electronic equipment and computer storage medium for calculating the blood flow velocity of coronary arteries.
  • an object of the present invention is to provide a method for calculating the blood flow velocity of the coronary arteries, which realizes the automation of the calculation of the blood flow velocity of the coronary arteries, and the calculated blood flow velocity of the coronary arteries It is more accurate, and the calculation method is relatively simple.
  • Another object of the present invention is to provide a method for calculating the blood flow reserve of a coronary artery including the above-mentioned method for calculating the blood flow velocity of the coronary artery.
  • Another object of the present invention is to provide a coronary blood flow velocity calculation device that realizes the above-mentioned method for calculating the coronary blood flow velocity.
  • Step S1 acquiring an angiographic image of the coronary artery, and segmenting the angiographic image of the coronary artery using deep learning to obtain a segmented image of the main branch vessel;
  • Step S2 Calculate the length of the main branch blood vessel in each frame of the divided image based on the segmented image of the main branch blood vessel;
  • step S3 the blood flow velocity of the main branch vessel is obtained based on the calculated changes in the length of the main branch vessel over time.
  • the step S1 specifically includes: acquiring an angiographic image of the coronary artery, displaying the selection of the type of the main branch of the coronary artery, and using deep learning to image the coronary artery based on the type of the main branch selected by the user The image is segmented to obtain a segmented image of the main branch vessel.
  • the step S1 further includes: judging whether the projection angle of the angiographic image of the coronary artery is within the required angle range of the main branch blood vessel based on the type of the main branch blood vessel selected by the user;
  • the projection angle of the angiographic image of the coronary artery is within the required angle range of this type of main branch vessel, then using deep learning to segment the angiographic image of the coronary artery to obtain a segmented image of the main branch vessel;
  • the segmentation of the angiographic image of the coronary artery by using deep learning to obtain the segmented image of the main branch vessel specifically includes:
  • the step S2 specifically includes:
  • Step S21 extracting the segmented image of the main branch blood vessel to obtain a contrast image of the blood vessel skeleton
  • step S22 the length of the blood vessel skeleton in the angiographic image of the blood vessel skeleton is calculated to obtain the length of the main branch blood vessel in pixels, and the actual physical length of the main branch blood vessel is calculated in combination with the scaling factor of the image.
  • the step S3 specifically includes:
  • Step S31 taking time as the abscissa, and taking the length of the main branch blood vessel in the segmented image of the main branch blood vessel as the ordinate to obtain a curve of the length of the main branch blood vessel over time;
  • step S32 a predetermined section of the curve of the length of the main branch vessel with time is taken, and the slope of the predetermined section is calculated to obtain the blood flow velocity of the main branch vessel.
  • the step S31 specifically includes:
  • Step S311 taking the frame number of the segmented image of the main branch blood vessel as the abscissa and the actual length of the main branch blood vessel as the ordinate to obtain a curve of the length of the main branch blood vessel with the number of frames;
  • Step S312 Convert the abscissa in the change curve of the length of the main branch vessel with the number of frames into time based on the frame rate information, to obtain the change curve of the length of the main branch vessel with time.
  • the step S32 specifically includes:
  • the pre-selected segment Judging whether the pre-selected segment includes a cardiac cycle according to the electrocardiographic information of the coronary artery corresponding to the pre-selected segment, and if the pre-selected segment does not include a cardiac cycle, the pre-selected segment is the predetermined segment;
  • a straight line is fitted to the predetermined segment, and the slope of the straight line obtained by the fitting is calculated to obtain the blood flow velocity of the main branch vessel.
  • the predetermined segment is obtained by extending the length of half a cardiac cycle to both ends of the pre-selected segment with the center of the pre-selected segment as the starting point.
  • the time-varying curve of the length of the main branch vessel and the angiographic image of the coronary artery and the electrocardiographic information of the coronary artery corresponding to the angiographic image of the coronary artery are displayed, and the user views the corresponding predetermined segment
  • the angiographic images of the coronary arteries and the ECG information of the coronary arteries verify the selection of the predetermined segment. If the selection of the predetermined segment is unreasonable, manually adjust the selection of the predetermined segment.
  • the blood flow velocity of the main branch vessel in the resting state and the blood flow velocity in the congested state are respectively calculated.
  • the blood flow velocity of the main branch vessel in the resting state and the blood flow velocity in the congested state are used to obtain the blood flow reserve of the coronary artery.
  • the resting state of the main branch blood vessels is calculated respectively.
  • Blood flow velocity and blood flow velocity in a hyperemic state wherein the acquisition time of the contrast image of the coronary artery with the main branch vessel in a resting state and the acquisition time of the contrast image of the coronary artery with the main branch vessel in a hyperemic state The time difference between the times is not greater than the first time threshold.
  • the coronary angiography image segmentation module is used to obtain the angiography image of the coronary artery, and use deep learning to segment the angiography image of the coronary artery to obtain the segmented image of the main branch vessel;
  • a length calculation module for calculating the length of the main branch blood vessel in each frame of the divided image based on the segmented image of the main branch blood vessel;
  • a blood flow velocity calculation module for obtaining the blood flow velocity of the main branch blood vessel based on the calculated changes in the length of the main branch blood vessel over time.
  • the device for calculating the blood flow velocity of the coronary artery further includes a display device, and the display device is used to display the type selection of the main branch of the coronary artery for the user;
  • the coronary angiography image segmentation module is used to obtain the angiography image of the coronary artery, and based on the type of the main branch vessel selected by the user, use deep learning to segment the angiography image of the coronary artery to obtain the segmentation of the main branch vessel image.
  • the coronary angiography image segmentation module is used for judging whether the projection angle of the coronary angiography image is within the required angle range of the main branch blood vessel based on the type of the main branch blood vessel selected by the user;
  • the projection angle of the angiographic image of the coronary artery is within the required angle range of this type of main branch vessel, then using deep learning to segment the angiographic image of the coronary artery to obtain a segmented image of the main branch vessel;
  • the display device is used to display prompt information for the user.
  • the coronary angiography image segmentation module is used to obtain feature maps of multiple different resolutions of the coronary artery angiography image through the encoder structure of the U-Net model, and then use the RefineNet module to divide the multiple Feature maps of different resolutions are refined and combined to obtain segmented images of main branch vessels.
  • the length calculation module is configured to extract the segmented image of the main branch blood vessel to obtain a contrast image of the blood vessel skeleton, and calculate the length of the blood vessel skeleton in the contrast image of the blood vessel skeleton to obtain a pixel
  • the unit is the length of the main branch vessel, combined with the scaling factor of the image, the actual physical length of the main branch vessel is calculated.
  • the blood flow velocity calculation module is configured to use time as the abscissa and the length of the main branch blood vessel in the segmented image of the main branch blood vessel as the ordinate to obtain the change curve of the length of the main branch blood vessel over time , Taking a predetermined segment of the curve of the length of the main branch vessel over time, calculating the slope of the predetermined section, and obtaining the blood flow velocity of the main branch vessel.
  • the blood flow velocity calculation module is configured to use the frame number of the segmented image of the main branch blood vessel as the abscissa and the actual length of the main branch blood vessel as the ordinate to obtain the length of the main branch blood vessel versus the number of frames.
  • the abscissa in the change curve of the length of the main branch vessel with the number of frames is converted into time based on the frame rate information to obtain the change curve of the length of the main branch vessel with time.
  • the blood flow velocity calculation module is used to smoothly process the change curve of the length of the main branch vessel with time to obtain a smooth curve of the change curve of the length of the main branch vessel with time, and obtain the The maximum value of the length of the main branch blood vessel on the smooth curve is taken as a predetermined segment area where the length of the main branch blood vessel on the smooth curve is a predetermined value of the maximum length of the main branch blood vessel; the smooth curve A segment of the curve of the length of the main branch vessel relative to the time of the predetermined segment area is a preselected segment.
  • the preselected segment includes a cardiac cycle, If the pre-selected segment does not include a cardiac cycle, the pre-selected segment is the predetermined segment;
  • a straight line is fitted to the predetermined segment, and the slope of the straight line obtained by the fitting is calculated to obtain the blood flow velocity of the main branch vessel.
  • the predetermined segment is obtained by extending the length of half a cardiac cycle to both ends of the pre-selected segment with the center of the pre-selected segment as the starting point.
  • the device for calculating the blood flow velocity of the coronary arteries further includes a display device, the display device is used to display the length of the main branch vessel with time and the angiographic image of the coronary artery for the user, and The electrocardiographic information of the coronary artery corresponding to the angiographic image of the coronary artery, the user views the angiographic image of the coronary artery corresponding to a predetermined segment and the electrocardiographic information of the coronary artery, and verifies the selection of the predetermined segment, if The selection of the predetermined segment is unreasonable. Manually adjust the selection of the predetermined segment.
  • One or more processors are One or more processors;
  • One or more memories in which computer-readable codes are stored, and the computer-readable codes, when executed by the one or more processors, perform the method for calculating the blood flow velocity of the coronary arteries according to any one of the above embodiments .
  • a computer storage medium stores therein computer readable codes, which when executed by one or more processors perform the coronary blood flow described in any of the above embodiments.
  • the calculation method of flow velocity is described in any of the above embodiments.
  • this calculation method realizes the automation of the calculation of the coronary blood flow velocity, the calculated coronary blood flow velocity is more accurate, and the calculation method is relatively simple.
  • FIG. 1 is a flowchart of a method for calculating the blood flow velocity of coronary arteries according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of segmenting an angiographic image of a coronary artery to obtain a segmented image of a main branch vessel;
  • Figure 3 is a schematic diagram of the structure of the existing U-Net model
  • Figure 4 is a schematic diagram of the structure of the existing RefineNet model
  • FIG. 5 is a schematic structural diagram of Refine-UNet used for segmentation of an angiographic image of a coronary artery according to an embodiment of the present invention
  • FIG. 6 is an angiographic image of a blood vessel skeleton with a single pixel width obtained by extracting a segmented image of a main branch blood vessel according to an embodiment of the present invention
  • FIG. 7 is a schematic diagram of a change curve and a smooth curve of the length of the main branch vessel with time according to an embodiment of the present invention.
  • Figure 8 is an electrocardiogram in a cardiac cycle
  • FIG. 9 is a schematic diagram of a first display interface displayed by a display device according to an embodiment of the present invention.
  • FIG. 10 is a schematic diagram of a second display interface displayed by the display device according to the embodiment of the present invention.
  • FIG. 11 is a schematic diagram of a third display interface displayed by the display device according to the embodiment of the present invention.
  • FIG. 12 is a schematic diagram of a fourth display interface displayed by the display device according to the embodiment of the present invention.
  • FIG. 13 is a schematic diagram of a fifth display interface displayed by the display device according to the embodiment of the present invention.
  • FIG. 14 is a schematic structural diagram of a device for calculating coronary blood flow velocity according to an embodiment of the present invention.
  • FIG. 15 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
  • module can refer to or include an application specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) that executes one or more software or firmware programs. Group) and/or memory, combinational logic circuit, and/or other suitable hardware components that provide the described functions, or may be part of these hardware components.
  • ASIC application specific integrated circuit
  • processor shared, dedicated, or group
  • memory shared, dedicated, or group
  • combinational logic circuit and/or other suitable hardware components that provide the described functions, or may be part of these hardware components.
  • the processor may be a microprocessor, a digital signal processor, a microcontroller, etc., and/or any combination thereof.
  • the processor may be a single-core processor, a multi-core processor, etc., and/or any combination thereof.
  • the method for calculating the blood flow velocity of the coronary arteries includes the following steps:
  • Step S1 Obtain an angiographic image of the coronary artery, and segment the angiographic image of the coronary artery using deep learning to obtain a segmented image of the main branch vessel.
  • the deep neural network outputs a segmented image of the main branch vessel with the same size as the original image.
  • the segmentation of the main branch vessel The pixel value of the position corresponding to the position of the main branch of the image on the original image is 1 (shown as white in Figure 2), and the pixel value of the other positions of the segmented image of the main branch of the image is 0 (in Figure 2 Displayed in black).
  • step S1 specifically includes: acquiring an angiographic image of the coronary artery, displaying the selection of the type of the main branch of the coronary artery, and segmenting the angiographic image of the coronary artery by deep learning based on the type of the main branch selected by the user, Obtain the segmented image of the main branch vessel.
  • the main branches of the coronary arteries include the anterior descending artery, the circumflex artery, and the right coronary artery.
  • the display device can be used to show the user the specific selection of the anterior descending artery, circumflex artery, and right coronary artery.
  • a main branch vessel uses deep learning to segment the angiographic image of the coronary artery to obtain a segmented image of a certain main branch vessel.
  • the type of the main branch vessel can be automatically identified based on the angiographic image of the coronary artery, and then deep learning is used to segment the angiographic image of the coronary artery to obtain the image of a certain main branch vessel. Split the image.
  • the step S1 further includes: judging whether the projection angle of the angiographic image of the coronary artery is within the required angle range of the main branch blood vessel based on the type of the main branch blood vessel selected by the user;
  • the projection angle of the angiographic image of the coronary artery is within the required angle range of this type of main branch vessel, then using deep learning to segment the angiographic image of the coronary artery to obtain a segmented image of the main branch vessel;
  • the display device can be used to display the type selection of the main branch of the coronary artery for the user, and the angiographic image of the coronary artery can be determined based on the type of the main branch selected by the user. If the projection angle of the coronary artery is within the required angle range of this type of main branch vessel, if the projection angle of the coronary angiographic image is not within the required angle range of this type of main branch vessel, the display device will display a prompt message for the user to It is suggested that the projection angle of the angiographic image of the coronary artery is not within the acceptable angle range of this type of main branch vessel.
  • the accuracy of the calculated blood flow velocity of the main branch vessel can be ensured.
  • the segmentation of the angiographic image of the coronary artery by using deep learning to obtain the segmented image of the main branch vessel specifically includes:
  • the existing U-Net model uses an encoder-decoder structure, as shown in Figure 3, the original image is convolved twice to obtain a 64-channel feature map, which has the same resolution as the original image , The 64-channel feature map is reduced to half of the original resolution through the maximum pooling operation, and the feature is further extracted through convolution, that is, the second-level 128-channel feature map is obtained. Repeat the above process to obtain five different resolutions This is the encoding process. The purpose of this process is to extract high-level semantic information (low-resolution feature maps) and low-level structural information (high-resolution feature maps), and then enter the decoding process.
  • the existing RefineNet model is similar to the U-Net model. As shown in Figure 4, it can receive the input of feature maps of different scales and merge and refine the feature maps of different scales, so that the feature maps are convenient for subsequent processing.
  • the difference between the existing RefineNet model and the U-Net model is mainly reflected in two aspects: the encoder of the RefineNet model uses the popular ResNet structure in the field of semantic segmentation, while the encoder of the U-Net model uses only convolution to extract features; RefineNet The model uses the original RefineNet module in the decoder, which can better refine the information of low-resolution feature maps and high-resolution feature maps.
  • the structure diagram of Refine-UNet used for segmentation of coronary angiographic images in the present invention is shown in Figure 5.
  • the different resolutions of coronary angiographic images obtained through the encoder structure of the U-Net model The type of the feature map depends on actual needs, for example, it can be 5 types, 3 types, 7 types, etc.
  • Step S2 Calculate the length of the main branch blood vessel in each frame of the divided image based on the segmented image of the main branch blood vessel.
  • the step S2 specifically includes:
  • step S21 the segmented image of the main branch blood vessel is extracted to obtain a contrast image of the blood vessel skeleton.
  • the segmented image of the main branch blood vessel obtained above can be extracted to obtain a contrast image of the blood vessel skeleton with a single pixel width.
  • step S22 the length of the blood vessel skeleton in the angiographic image of the blood vessel skeleton is calculated to obtain the length of the main branch blood vessel in pixels, and the actual physical length of the main branch blood vessel is calculated in combination with the scaling factor of the image.
  • the Fast Marching algorithm may be used to calculate the length of the blood vessel skeleton in the angiographic image of the blood vessel skeleton.
  • the accuracy of the calculated length of the main branch vessel is improved, and the calculated result is improved.
  • step S3 the blood flow velocity of the main branch vessel is obtained based on the calculated changes in the length of the main branch vessel over time.
  • the step S3 specifically includes:
  • Step S31 taking time as the abscissa, and taking the length of the main branch blood vessel in the segmented image of the main branch blood vessel as the ordinate to obtain a curve of the length of the main branch blood vessel over time;
  • the length of the main branch blood vessel changes with time, generally showing a gentle-rising-smooth "S" shape. If the coronary artery is not injected, the main branch vessel is not visible under X-rays. At this time, the calculated length of the main branch vessel is generally 0. In the latter part of the coronary angiography image sequence, the filling of the contrast agent in the coronary artery ends. The length of the main branch vessel calculated at the time is the full length of the main branch vessel and will not change.
  • the step S31 specifically includes:
  • Step S311 taking the frame number of the segmented image of the main branch blood vessel as the abscissa and the actual length of the main branch blood vessel as the ordinate to obtain a curve of the length of the main branch blood vessel with the number of frames;
  • Step S312 Convert the abscissa in the change curve of the length of the main branch vessel with the number of frames into time based on the frame rate information, to obtain the change curve of the length of the main branch vessel with time.
  • step S32 a predetermined section of the curve of the length of the main branch vessel with time is taken, and the slope of the predetermined section is calculated to obtain the blood flow velocity of the main branch vessel.
  • the step S32 specifically includes:
  • step S321 smoothing is performed on the change curve of the length of the main branch vessel with time to obtain a smooth curve of the change curve of the length of the main branch vessel with time.
  • the change curve of the length of the main branch vessel over time can be smoothed, which can be used
  • the K-order Bezier curve smoothes the change curve of the length of the main branch vessel over time.
  • Step S322 Obtain the maximum value of the length of the main branch blood vessel on the smooth curve, and take a segment of the length of the main branch blood vessel on the smooth curve as the predetermined value of the maximum length of the main branch blood vessel as a predetermined segment Area, a segment of the curve of the length of the main branch vessel versus time relative to the predetermined segment area on the smooth curve is a preselected segment.
  • the lowest value of the predetermined value may be 0-20%, and the highest value of the predetermined value may be 80-90%.
  • Step S323 Determine whether the pre-selected segment includes a cardiac cycle according to the electrocardiographic information of the coronary artery corresponding to the pre-selected segment. If the pre-selected segment does not include a cardiac cycle, the pre-selected segment is the predetermined segment. .
  • the electrocardiogram in a normal cardiac cycle is shown in Figure 8.
  • the fluctuation of QRS wave is significantly higher than other waves.
  • the peak of QRS wave can be quickly detected.
  • the time interval between can get the time of a cardiac cycle.
  • step S324 a straight line is fitted to the predetermined segment, and the slope of the straight line obtained by the fitting is calculated to obtain the blood flow velocity of the main branch vessel.
  • the linear least squares method is used to fit a straight line to a predetermined segment, and the slope of the straight line obtained by the fitting is the blood flow velocity of the main branch vessel.
  • the predetermined segment of the change curve of the length of the main branch vessel with time is obtained by the above method, and the blood flow velocity of the main branch vessel is further obtained, so that the calculated blood flow velocity of the main branch vessel is more accurate.
  • the predetermined segment is obtained by extending the length of half a cardiac cycle to both ends of the preselected segment with the center of the preselected segment as the starting point.
  • the blood flow velocity of the main branch vessel generally differs at different stages of the cardiac cycle
  • a section of the curve of the length of the main branch vessel corresponding to a cardiac cycle with time is used as the predetermined section, so that the calculated main vessel
  • the blood flow velocity of branch vessels is more accurate.
  • this calculation method realizes the automation of the calculation of the coronary blood flow velocity, the calculated coronary blood flow velocity is more accurate, and the calculation method is relatively simple.
  • the time-varying curve of the length of the main branch vessel and the angiographic image of the coronary artery and the electrocardiographic information of the coronary artery corresponding to the angiographic image of the coronary artery are displayed, and the user views the corresponding predetermined segment
  • the angiographic images of the coronary arteries and the ECG information of the coronary arteries verify the selection of the predetermined segment. If the selection of the predetermined segment is unreasonable, manually adjust the selection of the predetermined segment.
  • the display device can be used to display the change curve of the length of the main branch vessel over time and the electrocardiogram information of the coronary artery corresponding to the change curve, and display the straight line for the predetermined segment.
  • the blood flow velocity of the main branch vessel obtained by fitting is shown in Figure 10.
  • the user can scroll the mouse wheel or click any position on the change curve in the image window on the right side of the display interface to view the angiography of the coronary arteries in different frames
  • the image can also be used to switch the image window on the right side of the display interface to the multi-window mode by clicking a certain function icon with the mouse to view the angiographic image of the coronary artery corresponding to the predetermined segment, and to verify the selection of the predetermined segment If the selection of the predetermined segment is unreasonable, manually adjust the selection of the predetermined segment, and the blood flow velocity of the main blood vessel displayed on the display interface is updated in real time according to the selection of the predetermined segment.
  • the selection of the predetermined segment can be manually adjusted to ensure the rationality of the selection of the predetermined segment, thereby ensuring that the coronary blood flow velocity is more accurate.
  • the method for calculating the blood flow reserve of the coronary artery includes the following steps:
  • the blood flow velocity of the main branch vessel in the resting state and the blood flow velocity in the congested state are respectively calculated.
  • the blood flow velocity of the main branch vessel in the resting state and the blood flow velocity in the congested state are used to obtain the blood flow reserve of the coronary artery.
  • a sequence of angiographic images of the coronary arteries is selected, and the blood flow velocity of the main branch vessel in one state is calculated using the above-mentioned method of calculating the blood flow velocity of the coronary arteries, as shown in Figure 12, click on the display of the display device
  • the icon for calculating the blood flow reserve of the coronary artery (CFR icon) on the interface and then select another sequence of coronary angiography images, where the state of the main branch vessels in the angiography image of the other sequence of coronary arteries and all
  • the state of the main branch vessel in the coronary artery angiography image of the one sequence is opposite, and the display device displays the type selection (resting state or congestion) of the state of the main branch vessel in the coronary artery angiography image of the other sequence for the user.
  • the blood flow velocity of the blood vessel in the resting state and the blood flow velocity in the congested state obtain the blood flow reserve of the coronary artery, and as shown in FIG. 13, the blood flow reserve of the coronary artery is displayed.
  • the resting state of the main branch blood vessels is calculated respectively.
  • Blood flow velocity and blood flow velocity in a hyperemic state wherein the acquisition time of the contrast image of the coronary artery with the main branch vessel in a resting state and the acquisition time of the contrast image of the coronary artery with the main branch vessel in a hyperemic state The time difference between the times is not greater than the first time threshold.
  • the first time threshold may be 7 days, or 15 days, etc., depending on the actual situation.
  • the acquisition time of the angiographic image of the coronary artery with the main branch vessel in a resting state is related to the time when the main branch vessel is in congestion.
  • the time difference between the acquisition times of the angiographic images of the coronary arteries in the state is not greater than the first time threshold, thereby ensuring the accuracy of the calculated coronary blood flow reserve.
  • the method for calculating the blood flow reserve of the coronary arteries realizes the automation of the calculation of the blood flow reserve of the coronary arteries, the calculated blood flow reserve of the coronary arteries is more accurate, and the calculation method is relatively simple.
  • the device for calculating the blood flow velocity of the coronary artery according to the embodiment of the present invention which implements the method for calculating the blood flow velocity of the coronary artery according to the embodiment of the present invention, includes a coronary angiography image segmentation module 20 and a length calculation Module 30 and blood flow velocity calculation module 40.
  • the coronary angiography image segmentation module 20 is used to obtain an angiography image of the coronary artery, and use deep learning to segment the angiography image of the coronary artery to obtain a segmented image of the main branch vessel.
  • the length calculation module 30 is configured to calculate the length of the main branch blood vessel in each frame of the divided image based on the segmented image of the main branch blood vessel.
  • the blood flow velocity calculation module 40 is configured to obtain the blood flow velocity of the main branch blood vessel based on the calculated changes in the length of the main branch blood vessel over time.
  • the device for calculating the blood flow velocity of the coronary artery further includes a display device, and the display device is used to display the type selection of the main branch of the coronary artery for the user;
  • the coronary angiography image segmentation module 20 is used to obtain the angiography image of the coronary artery, and based on the type of the main branch blood vessel selected by the user, use deep learning to segment the angiography image of the coronary artery to obtain the main branch blood vessel Split the image.
  • the coronary angiography image segmentation module 20 is used to determine whether the projection angle of the coronary angiography image is within the required angle range of the type of the main branch vessel based on the type of the main branch vessel selected by the user ;
  • the projection angle of the angiographic image of the coronary artery is within the required angle range of this type of main branch vessel, then using deep learning to segment the angiographic image of the coronary artery to obtain a segmented image of the main branch vessel;
  • the display device is used to display prompt information for the user.
  • the coronary angiography image segmentation module 20 is used to obtain feature maps of various resolutions of the coronary artery angiography image through the encoder structure of the U-Net model, and then use the RefineNet module to divide the multiple Feature maps with different resolutions are refined and combined to obtain segmented images of main branch vessels.
  • the length calculation module 30 is configured to extract the segmented image of the main branch blood vessel to obtain a contrast image of the blood vessel skeleton, and calculate the length of the blood vessel skeleton in the contrast image of the blood vessel skeleton to obtain The length of the main branch vessel in pixels is combined with the image scaling factor to calculate the actual physical length of the main branch vessel.
  • the blood flow velocity calculation module 40 is configured to use time as the abscissa and the length of the main branch vessel in the segmented image of the main branch vessel as the ordinate to obtain the change in the length of the main branch vessel over time. Curve, taking a predetermined section of the curve of the length of the main branch vessel over time, calculating the slope of the predetermined section, and obtaining the blood flow velocity of the main branch vessel.
  • the blood flow velocity calculation module 40 is configured to use the frame number of the segmented image of the main branch vessel as the abscissa and the actual length of the main branch vessel as the ordinate to obtain the length of the main branch vessel as the number of frames. Based on the frame rate information, the abscissa in the change curve of the length of the main branch vessel with the number of frames is converted into time to obtain the change curve of the length of the main branch vessel with time.
  • the blood flow velocity calculation module 40 is used to smoothly process the change curve of the length of the main branch vessel with time to obtain a smooth curve of the change curve of the length of the main branch vessel with time, and obtain The maximum value of the length of the main branch blood vessel on the smooth curve is taken as a predetermined segment area where the length of the main branch blood vessel on the smooth curve is a predetermined value of the maximum length of the main branch blood vessel; A segment of the change curve of the length of the main branch vessel with respect to the predetermined segment area on the curve is a preselected segment. According to the ECG information of the coronary artery corresponding to the preselected segment, it is determined whether the preselected segment includes a cardiac cycle , If the preselected segment does not include a cardiac cycle, the preselected segment is the predetermined segment;
  • a straight line is fitted to the predetermined segment, and the slope of the straight line obtained by the fitting is calculated to obtain the blood flow velocity of the main branch vessel.
  • the predetermined segment is obtained by extending the length of half a cardiac cycle to both ends of the pre-selected segment with the center of the pre-selected segment as the starting point.
  • the device for calculating the blood flow velocity of the coronary arteries further includes a display device for displaying the length of the main branch blood vessel and the angiographic image of the coronary artery for the user as a function of time.
  • the electrocardiographic information of the coronary artery corresponding to the angiographic image of the coronary artery the user views the angiographic image of the coronary artery corresponding to a predetermined segment and the electrocardiographic information of the coronary artery, and verifies the selection of the predetermined segment, if The selection of the predetermined segment is unreasonable. Manually adjust the selection of the predetermined segment.
  • the calculation device for the blood flow velocity of the coronary arteries realizes the automation of the calculation of the blood flow velocity of the coronary arteries, the calculated blood flow velocity of the coronary arteries is more accurate, and the calculation method is relatively simple.
  • the present application also provides an electronic device 1400.
  • the electronic device 1400 includes one or more processors 1401 and one or more The memory 1402, and computer readable codes are stored in the memory 1402,
  • the computer-readable code when executed by one or more processors 1401, performs the following processing:
  • Step S1 acquiring an angiographic image of the coronary artery, and segmenting the angiographic image of the coronary artery using deep learning to obtain a segmented image of the main branch vessel;
  • Step S2 Calculate the length of the main branch blood vessel in each frame of the divided image based on the segmented image of the main branch blood vessel;
  • step S3 the blood flow velocity of the main branch vessel is obtained based on the calculated changes in the length of the main branch vessel over time.
  • the step S1 specifically includes: acquiring an angiographic image of the coronary artery, displaying the selection of the type of the main branch of the coronary artery, and using deep learning to image the coronary artery based on the type of the main branch selected by the user The image is segmented to obtain a segmented image of the main branch vessel.
  • the step S1 further includes: judging whether the projection angle of the angiographic image of the coronary artery is within the required angle range of the main branch blood vessel based on the type of the main branch blood vessel selected by the user;
  • the projection angle of the angiographic image of the coronary artery is within the required angle range of this type of main branch vessel, then using deep learning to segment the angiographic image of the coronary artery to obtain a segmented image of the main branch vessel;
  • the segmentation of the angiographic image of the coronary artery by using deep learning to obtain the segmented image of the main branch vessel specifically includes:
  • the step S2 specifically includes:
  • Step S21 extracting the segmented image of the main branch blood vessel to obtain a contrast image of the blood vessel skeleton
  • step S22 the length of the blood vessel skeleton in the angiographic image of the blood vessel skeleton is calculated to obtain the length of the main branch blood vessel in pixels, and the actual physical length of the main branch blood vessel is calculated in combination with the scaling factor of the image.
  • the step S3 specifically includes:
  • Step S31 taking time as the abscissa, and taking the length of the main branch blood vessel in the segmented image of the main branch blood vessel as the ordinate to obtain a curve of the length of the main branch blood vessel over time;
  • step S32 a predetermined section of the curve of the length of the main branch vessel with time is taken, and the slope of the predetermined section is calculated to obtain the blood flow velocity of the main branch vessel.
  • the step S31 specifically includes:
  • Step S311 taking the frame number of the segmented image of the main branch blood vessel as the abscissa and the actual length of the main branch blood vessel as the ordinate to obtain a curve of the length of the main branch blood vessel with the number of frames;
  • Step S312 Convert the abscissa in the change curve of the length of the main branch vessel with the number of frames into time based on the frame rate information, to obtain the change curve of the length of the main branch vessel with time.
  • the step S32 specifically includes:
  • the pre-selected segment Judging whether the pre-selected segment includes a cardiac cycle according to the electrocardiographic information of the coronary artery corresponding to the pre-selected segment, and if the pre-selected segment does not include a cardiac cycle, the pre-selected segment is the predetermined segment;
  • a straight line is fitted to the predetermined segment, and the slope of the straight line obtained by the fitting is calculated to obtain the blood flow velocity of the main branch vessel.
  • the predetermined segment is obtained by extending the length of half a cardiac cycle to both ends of the pre-selected segment with the center of the pre-selected segment as the starting point.
  • the time-varying curve of the length of the main branch vessel and the angiographic image of the coronary artery and the electrocardiographic information of the coronary artery corresponding to the angiographic image of the coronary artery are displayed, and the user views the corresponding predetermined segment
  • the angiographic images of the coronary arteries and the ECG information of the coronary arteries verify the selection of the predetermined segment. If the selection of the predetermined segment is unreasonable, manually adjust the selection of the predetermined segment.
  • the electronic device 1400 further includes a network interface 1403, an input device 1404, a hard disk 1405, and a display device 1406.
  • the above-mentioned various interfaces and devices can be interconnected through a bus architecture.
  • the bus architecture can be any number of interconnected buses and bridges. Specifically, various circuits of one or more central processing units (CPU) represented by the processor 1401 and one or more memories 1402 represented by the memory 1402 are connected together.
  • the bus architecture can also connect various other circuits such as peripherals, voltage regulators, and power management circuits. It can be understood that the bus architecture is used to realize the connection and communication between these components.
  • the bus architecture also includes a power bus, a control bus, and a status signal bus, which are all well-known in the art, and therefore will not be described in detail herein.
  • the network interface 1403 can be connected to a network (such as the Internet, a local area network, etc.) to obtain relevant data from the network, and can be stored in the hard disk 1405.
  • a network such as the Internet, a local area network, etc.
  • the input device 1404 can receive various instructions input by the operator and send them to the processor 1401 for execution.
  • the input device 1404 may include a keyboard or a pointing device (for example, a mouse, a trackball, a touch panel, or a touch screen, etc.).
  • the display device 1406 can display the result obtained by the processor 1401 executing the instruction.
  • the memory 1402 is used to store programs and data necessary for the operation of the operating system 14021, as well as data such as intermediate results in the calculation process of the processor 1401.
  • the memory 1402 in the embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or Flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • the memory 1402 stores the following elements, executable modules or data structures, or their subsets, or their extended sets: operating system 14021 and application programs 14014.
  • the operating system 14021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks.
  • the application program 14014 includes various application programs, such as a browser (Browser), etc., which are used to implement various application services.
  • the program for implementing the method of the embodiment of the present application may be included in the application program 14014.
  • the methods disclosed in the foregoing embodiments of the present application may be applied to the processor 1401 or implemented by the processor 1401.
  • the processor 1401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the foregoing method can be completed by an integrated logic circuit of hardware in the processor 1401 or instructions in the form of software.
  • the aforementioned processor 1401 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • the components can implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of the present application.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers.
  • the storage medium is located in the memory 1402, and the processor 1401 reads the information in the memory 1402, and completes the steps of the foregoing method in combination with its hardware.
  • the embodiments described herein can be implemented by hardware, software, firmware, middleware, microcode, or a combination thereof.
  • the processing unit can be implemented in one or more application-specific integrated circuits (ASIC), digital signal processor DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA) ), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or combinations thereof.
  • ASIC application-specific integrated circuits
  • DSP digital signal processor
  • DSPD digital signal processing device
  • PLD programmable logic device
  • FPGA field programmable gate array
  • the technology described herein can be implemented through modules (for example, procedures, functions, etc.) that perform the functions described herein.
  • the software codes can be stored in the memory and executed by the processor.
  • the memory can be implemented in the processor or external to the processor.
  • the electronic device 1400 obtains the segmented image of the main branch blood vessel by segmenting the angiographic image of the coronary arteries by using deep learning, and calculates the length of the main branch blood vessel in each frame of image, and then based on the main branch blood vessel The change of length with time obtains the blood flow velocity of the main branch vessel.
  • This electronic device for calculating the blood flow velocity of the coronary arteries realizes the automation of the calculation of the blood flow velocity of the coronary arteries, and the calculated blood flow of the coronary arteries The speed is more accurate, and the calculation method is relatively simple.
  • the embodiments of the present application also provide a computer storage medium, where the computer storage medium stores computer readable code, and the computer readable code performs the following processing when executed by one or more processors:
  • Step S1 acquiring an angiographic image of the coronary artery, and segmenting the angiographic image of the coronary artery using deep learning to obtain a segmented image of the main branch vessel;
  • Step S2 Calculate the length of the main branch blood vessel in each frame of the divided image based on the segmented image of the main branch blood vessel;
  • step S3 the blood flow velocity of the main branch vessel is obtained based on the calculated changes in the length of the main branch vessel over time.
  • the computer-readable code When the computer-readable code is executed by the processor, each process of the foregoing method for calculating the blood flow velocity of the coronary artery is realized, and the same technical effect can be achieved. In order to avoid repetition, the detailed process will not be repeated here.
  • the computer storage medium such as read-only memory (Read-Only Memory, ROM for short), random access memory (Random Access Memory, RAM for short), magnetic disk, or optical disk, etc.
  • the disclosed method and device may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may be separately physically included, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Biophysics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Optics & Photonics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Quality & Reliability (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Geometry (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Vascular Medicine (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
  • Image Analysis (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

一种冠状动脉的血流速度的计算方法、装置、电子设备及存储介质,其中,冠状动脉的血流速度的计算方法包括如下步骤:步骤S1,获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像(S1);步骤S2,基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度(S2);步骤S3,基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度(S3)。所述冠状动脉的血流速度的计算方法、装置、电子设备,实现了冠状动脉的血流速度的计算的自动化,计算所得的冠状动脉的血流速度更为准确,且该计算方法较为简单。

Description

冠状动脉的血流速度的计算方法、装置及电子设备 技术领域
本发明涉及计算机技术领域,具体涉及一种冠状动脉的血流速度的计算方法、装置和电子设备以及计算机存储介质。
背景技术
近年来,很多基于心血管影像计算冠状动脉FFR(血流储备分数)以及CFR(冠状动脉血流储备)的方法被提出,其中冠状动脉血流速度是FFR与CFR计算所需的重要条件,目前计算冠状动脉血流速度的方法主要有TIMI数帧法,但该法需要医生手动进行测量,操作繁琐。
发明内容
为解决上述技术问题,本发明的一个目的在于提供一种冠状动脉的血流速度的计算方法,该计算方法实现了冠状动脉的血流速度的计算的自动化,计算所得的冠状动脉的血流速度更为准确,且该计算方法较为简单。
本发明的另一个目的在于提供一种包括上述冠状动脉的血流速度的计算方法的冠状动脉的血流储备的计算方法。
本发明的再一个目的在于提供一种实现上述冠状动脉的血流速度的计算方法的冠状动脉的血流速度的计算装置。
为达到上述目的,本发明采用如下技术方案:
根据本发明第一方面实施例的冠状动脉的血流速度的计算方法,包括:
步骤S1,获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
步骤S2,基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度;
步骤S3,基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
优选地,所述步骤S1具体包括:获取所述冠状动脉的造影图像,显示冠状动脉的主支血管的类型选择,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
优选地,所述步骤S1还包括:基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则显示提示信息。
优选地,所述利用深度学习对所述冠状动脉的造影图像进行分割获得主支血管的分割图像,具体包括:
通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
优选地,所述步骤S2具体包括:
步骤S21,对所述主支血管的分割图像进行提取,得到血管骨架的造影图像;
步骤S22,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
优选地,所述步骤S3具体包括:
步骤S31,以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线;
步骤S32,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
优选地,所述步骤S31具体包括:
步骤S311,以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线;
步骤S312,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
优选地,所述步骤S32具体包括:
对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线;
得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域,所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段;
根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段;
对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
优选地,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
优选地,显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
根据本发明第二方面实施例的冠状动脉的血流储备的计算方法,包括:
通过上述任一实施例所述的冠状动脉的血流速度的计算方法分别计算出所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,根据计算所得的所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,得到所述冠状动脉的血流储备。
优选地,通过所述的冠状动脉的血流速度的计算方法,基于主支血管处于静息状态和充血状态的所述冠状动脉的造影图像分别计算出所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,其中,所述主支血管处于静息状态的冠状动脉的造影图像的采集时间与所述主支血管处于充血状态的冠状动脉的造影图像的采集时间之间的时间差不大于第一时间阈值。
根据本发明第三方面实施例的冠状动脉的血流速度的计算装置,包括:
冠状动脉造影图像分割模块,用于获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
长度计算模块,用于基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度;
以及血流速度计算模块,用于基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
优选地,所述冠状动脉的血流速度的计算装置还包括显示装置,所述显示装置用于为用户显示冠状动脉的主支血管的类型选择;
所述冠状动脉造影图像分割模块,用于获取所述冠状动脉的造影图像,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
优选地,所述冠状动脉造影图像分割模块,用于基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则所述显示装置用于为用户显示提示信息。
优选地,所述冠状动脉造影图像分割模块,用于通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用 RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
优选地,所述长度计算模块,用于对所述主支血管的分割图像进行提取,得到血管骨架的造影图像,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
优选地,所述血流速度计算模块,用于以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
优选地,所述血流速度计算模块,用于以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
优选地,所述血流速度计算模块,用于对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线,得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域;所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段,根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段;
对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
优选地,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
优选地,所述冠状动脉的血流速度的计算装置还包括显示装置,所述显示装置,用于为用户显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
根据本发明第四方面实施例的用于冠状动脉的血流速度的计算的电子设备,包括:
一个或多个处理器;
一个或多个存储器,其中存储了计算机可读代码,所述计算机可读代码当由所述一个或多个处理器执行时进行上述任一实施例所述的冠状动脉的血流速度的计算方法。
根据本发明第五方面实施例的计算机存储介质,其中存储了计算机可读代码,所述计算机可读代码当由一个或多个处理器执行时进行上述任一实施例所述的冠状动脉的血流速度的计算方法。
本发明的有益效果在于:
通过利用深度学习对冠状动脉的造影图像进行分割得到主支血管的分割图像,并计算每一帧图像内的主支血管的长度,进而基于主支血管的长度随时间的变化得到主支血管的血流速度,该计算方法实现了冠状动脉的血流速度的计 算的自动化,计算所得的冠状动脉的血流速度更为准确,且该计算方法较为简单。
上述说明仅是本发明技术方案的概述,为了能够更清楚了解本发明的技术手段,并可依照说明书的内容予以实施,以下以本发明的较佳实施例并配合附图详细说明如后。
附图说明
图1为本发明实施例的冠状动脉的血流速度的计算方法的流程图;
图2为对冠状动脉的造影图像进行分割获得主支血管的分割图像的示意图;
图3为现有的U-Net模型的结构示意图;
图4为现有的RefineNet模型的结构示意图;
图5为本发明实施例对冠状动脉的造影图像进行分割使用的Refine-UNet的结构示意图;
图6为本发明实施例的对主支血管的分割图像进行提取得到的单像素宽度的血管骨架的造影图像;
图7为本发明实施例的主支血管的长度随时间的变化曲线及平滑曲线的示意图;
图8为一个心动周期内的心电图;
图9为本发明实施例的显示装置显示的第一显示界面示意图;
图10为本发明实施例的显示装置显示的第二显示界面示意图;
图11为本发明实施例的显示装置显示的第三显示界面示意图;
图12为本发明实施例的显示装置显示的第四显示界面示意图;
图13为本发明实施例的显示装置显示的第五显示界面示意图;
图14为本发明实施例的冠状动脉的血流速度的计算装置的结构示意图;
图15为本发明实施例的电子设备的结构示意图。
具体实施方式
下面结合附图和实施例,对本发明的具体实施方式作进一步详细描述。以下实施例仅用于说明本发明,但不用来限制本发明的范围。
可以理解的是,如本文所使用的,术语“模块””可以指代或者包括专用集成电路(ASIC)、电子电路、执行一个或多个软件或固件程序的处理器(共享、专用、或群组)和/或存储器、组合逻辑电路、和/或提供所描述的功能的其他适当硬件组件,或者可以作为这些硬件组件的一部分。
可以理解的是,在本发明各实施例中,处理器可以是微处理器、数字信号处理器、微控制器等,和/或其任何组合。根据另一个方面,所述处理器可以是单核处理器,多核处理器等,和/或其任何组合。
如图1所示,根据本发明实施例的冠状动脉的血流速度的计算方法,包括如下步骤:
步骤S1,获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
具体地,由于在计算冠状动脉的血流速度时,我们只关心主支血管中的血流速度,所以我们只需要对冠状动脉造影图像中的主支血管进行分割以获得主支血管的分割图像。但传统的图像处理方法如Gabor滤波、Hessian矩阵等对所有血管状结构都十分敏感,对区分主支血管和边支血管无能为力。因此,我们采用深度学习的方法,利用深度神经网络强大的特征提取能力区分主支血管和边支血管,并只分割主支血管,极大地简化了后续主支血管长度的计算过程。
如图2所示,对于获取的每一帧冠状动脉的造影图像,作为深度神经网络的输入,深度神经网络输出一张与原图像大小相同的主支血管的分割图像,该主支血管的分割图像与其原图上的主支血管的位置相对应的位置的像素值为1(在图2中显示为白色),该主支血管的分割图像的其它位置的像素值为0(在图2中显示为黑色)。
优选地,步骤S1具体包括:获取冠状动脉的造影图像,显示冠状动脉的主支血管的类型选择,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
具体地,冠状动脉的主支血管包括前降支血管、回旋支血管以及右冠状动脉血管,可以使用显示装置为用户显示具体选择前降支血管、回旋支血管以及右冠状动脉血管中的具体哪一个主支血管,根据用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得某一个主支血管的分割图像。另外,在本发明的其它实施例中,可根据冠状动脉的造影图像,自动识别出主支血管的类型,然后利用深度学习对所述冠状动脉的造影图像进行分割,获得某一个主支血管的分割图像。
优选地,所述步骤S1还包括:基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则显示提示信息。
具体地,如图9所示,获取冠状动脉的造影图像后,可以使用显示装置为用户显示冠状动脉的主支血管的类型选择,基于用户选择的主支血管的类型,判断冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内,若冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则显示装置为用户显示提示信息以提示冠状动脉的造影图像的投照角度不在该类型的主支血管的可接受角度范围内。
通过判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内,可确保计算得到的主支血管的血流速度的准确性。
优选地,所述利用深度学习对所述冠状动脉的造影图像进行分割获得主支血管的分割图像,具体包括:
通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
具体地,现有的U-Net模型使用编码器-译码器的结构,如图3所示,原始图像通过两次卷积,得到64通道的特征图,该特征图分辨率与原始图像相同,将该64通道的特征图通过最大池化操作降低分辨率到原来的一半,并通过卷积进一步提取特征,即得到第二层128通道的特征图,重复上述过程,可得到五种不同分辨率的特征图,此为编码过程,该过程的目的为提取高层次的语义信息(低分辨率的特征图)与低层次的结构信息(高分辨率的特征图),随后进入译码过程,将低分辨率的特征图上采样到高分辨率,并与前一级的高分辨率特征图做拼接操作,卷积提取特征后,再进行上采样及拼接的操作,直到与最高分辨率的特征图拼接后,经过1×1的卷积调整通道数,即得到所要求的分割结 果。
现有的RefineNet模型与U-Net模型类似,如图4所示,其可以接收不同尺度的特征图输入并将不同尺度的特征图合并并进行精制,使特征图便于后续处理。
现有的RefineNet模型与U-Net模型的区别主要体现在两个方面:RefineNet模型的编码器使用在语义分割领域流行的ResNet结构,而U-Net模型的编码器单纯使用卷积提取特征;RefineNet模型在解码器中使用了独创的RefineNet模块,该模块可以更好地精制低分辨率特征图和高分辨率特征图的信息。
本发明对冠状动脉的造影图像进行分割使用的Refine-UNet的结构示意图如图5所示,另外需要说明的是,通过U-Net模型的编码器结构获取的冠状动脉的造影图像的不同分辨率的特征图的种类根据实际需要而定,比如,可以是5种,也可以是3种,还可以是7种等。
通过U-Net模型的编码器结构即仅使用卷积,获取冠状动脉的造影图像的多种不同分辨率的特征图,避免了计算资源的浪费,加快了计算速度,而采用RefineNet模块将高分辨率和低分辨率的特征图进行精制后再进行结合,可以更高效地利用高层次的语义信息与低层次的结构信息,增强分割的准确性。
步骤S2,基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度。
优选地,所述步骤S2具体包括:
步骤S21,对所述主支血管的分割图像进行提取,得到血管骨架的造影图像。
具体地,如图6所示,可以对上述得到的主支血管的分割图像进行提取,得到单像素宽度的血管骨架的造影图像。
步骤S22,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
具体地,可以使用Fast Marching算法对所述血管骨架的造影图像中的血管骨架的长度进行计算。
通过提取得到血管骨架的造影图像,并计算血管骨架的造影图像中的血管骨架的长度以得到主支血管的长度,提高了计算得到的主支血管的长度的准确度,进而提高了计算得到的冠状动脉的血流速度的准确度。
步骤S3,基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
优选地,所述步骤S3具体包括:
步骤S31,以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线;
具体地,如图7所示,该主支血管的长度随时间的变化曲线,一般呈现平缓-上升-平缓的“S”形,这是由于在冠状动脉造影图像序列的前段,由于造影剂还未注入冠状动脉,主支血管在X光下不可见,此时计算得到的主支血管的长度一般为0,在冠状动脉造影图像序列的后段,由于造影剂在冠状动脉中充盈结束,此时计算得到的主支血管长度为主支血管的完整长度,不再变化。
优选地,所述步骤S31具体包括:
步骤S311,以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线;
步骤S312,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
步骤S32,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
优选地,所述步骤S32具体包括:
步骤S321,对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线。
具体地,由于心脏跳动以及血管分割误差等原因,主支血管的长度随时间的变化曲线上一般会有一定的噪音,因此可以对主支血管的长度随时间的变化曲线进行平滑处理,可以利用K阶贝塞尔曲线对主支血管的长度随时间的变化曲线进行平滑处理。
步骤S322,得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域,所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段。
优选地,所述预定值的最低值可以为0-20%,预定值的最高值可以为80-90%。
步骤S323,根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段。
具体地,正常的一个心动周期内的心电图如图8所示,其中,QRS波的波动显著高于其它波,利用阈值等方法可以快速检测出QRS波的波峰,根据相邻的两个QRS波之间的时间间隔即可得到一个心动周期的时间。
步骤S324,对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
具体地,利用线性最小二乘法对预定段进行直线拟合,拟合得到的直线的斜率即为主支血管的血流速度。
由此,通过上述方法获取主支血管的长度随时间的变化曲线的预定段,并进一步得到主支血管的血流速度,使计算得到的主支血管的血流速度更加准确。
优选地,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
具体地,由于主支血管的血流速度在心动周期的不同阶段一般会有差异,以一个心动周期相对应的主支血管的长度随时间的变化曲线的一段为预定段,使计算得到的主支血管的血流速度更为准确。
通过利用深度学习对冠状动脉的造影图像进行分割得到主支血管的分割图像,并计算每一帧图像内的主支血管的长度,进而基于主支血管的长度随时间的变化得到主支血管的血流速度,该计算方法实现了冠状动脉的血流速度的计算的自动化,计算所得的冠状动脉的血流速度更为准确,且该计算方法较为简单。
优选地,显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
具体地,如图10和图11所示,可以使用显示装置为用户显示主支血管的长度随时间的变化曲线以及该变化曲线对应的冠状动脉的心电信息,且显示了 对预定段进行直线拟合得到的主支血管的血流速度,如图10所示,用户可在显示界面的右侧影像视窗中通过滚动鼠标滚轮或点击变化曲线上的任意位置以查看不同帧的冠状动脉的造影图像,如图11所示,也可以通过鼠标点击某个功能图标将显示界面的右侧影像视窗切换为多视窗模式以便于查看预定段对应的冠状动脉的造影图像,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取,显示界面上显示的主支血管的血流速度根据预定段的选取进行实时更新。
当用户认为自动选取的预定段选取不合理时,可手动调整预定段的选择,从而以确保预定段选取的合理性,进而确保得到冠状动脉的血流速度的较为准确。
包括上述冠状动脉的血流速度的计算方法的冠状动脉的血流储备的计算方法,包括如下步骤:
通过上述任一实施例所述的冠状动脉的血流速度的计算方法分别计算出所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,根据计算所得的所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,得到所述冠状动脉的血流储备。
具体地,选取一个序列的冠状动脉的造影图像,利用上述的冠状动脉的血流速度的计算方法计算得到主支血管在一个状态下的血流速度,如图12所示,点击显示装置的显示界面的计算冠状动脉的血流储备的图标(CFR图标),然后,选取另一个序列的冠状动脉的造影图像,其中所述另一个序列的冠状动脉的造影图像中的主支血管的状态与所述一个序列的冠状动脉的造影图像中的主支血管的状态相反,显示装置为用户显示所述另一个序列的冠状动脉的造影图像中 的主支血管的状态的种类选择(静息状态或充血状态),并根据用户的选择确定所述一个序列的冠状动脉的造影图像中的主支血管的状态,然后,计算得到主支血管在另一个状态下的血流速度,根据计算所得的主支血管在静息状态下的血流速度以及在充血状态下的血流速度,得到所述冠状动脉的血流储备,且如图13所示,对冠状动脉的血流储备进行显示。
优选地,通过所述的冠状动脉的血流速度的计算方法,基于主支血管处于静息状态和充血状态的所述冠状动脉的造影图像分别计算出所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,其中,所述主支血管处于静息状态的冠状动脉的造影图像的采集时间与所述主支血管处于充血状态的冠状动脉的造影图像的采集时间之间的时间差不大于第一时间阈值。
具体地,第一时间阈值可以是7天,也可以是15天等,具体根据实际情况而定,主支血管处于静息状态的冠状动脉的造影图像的采集时间与所述主支血管处于充血状态的冠状动脉的造影图像的采集时间之间的时间差不大于第一时间阈值,由此可确保计算得到的冠状动脉的血流储备的准确性。
该冠状动脉的血流储备的计算方法,实现了冠状动脉的血流储备的计算的自动化,计算所得的冠状动脉的血流储备更为准确,且该计算方法较为简单。
如图14所示,实现上述根据发明实施例的冠状动脉的血流速度的计算方法的根据本发明实施例的冠状动脉的血流速度的计算装置,包括冠状动脉造影图像分割模块20、长度计算模块30和血流速度计算模块40。
其中,冠状动脉造影图像分割模块20,用于获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
长度计算模块30,用于基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度。
血流速度计算模块40,用于基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
优选地,所述冠状动脉的血流速度的计算装置还包括显示装置,所述显示装置用于为用户显示冠状动脉的主支血管的类型选择;
所述冠状动脉造影图像分割模块20,用于获取所述冠状动脉的造影图像,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
优选地,所述冠状动脉造影图像分割模块20,用于基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则所述显示装置用于为用户显示提示信息。
优选地,所述冠状动脉造影图像分割模块20,用于通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
优选地,所述长度计算模块30,用于对所述主支血管的分割图像进行提取,得到血管骨架的造影图像,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
优选地,所述血流速度计算模块40,用于以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
优选地,所述血流速度计算模块40,用于以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
优选地,所述血流速度计算模块40,用于对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线,得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域;所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段,根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段;
对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
优选地,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
优选地,所述冠状动脉的血流速度的计算装置还包括显示装置,所述显示装置用于,为用户显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
通过利用深度学习对冠状动脉的造影图像进行分割得到主支血管的分割图像,并计算每一帧图像内的主支血管的长度,进而基于主支血管的长度随时间的变化得到主支血管的血流速度,该冠状动脉的血流速度的计算装置,实现了冠状动脉的血流速度的计算的自动化,计算所得的冠状动脉的血流速度更为准确,且该计算方法较为简单。
如图15所示,基于与上述冠状动脉的血流速度的计算方法相同的发明构思,本申请还提供一种电子设备1400,该电子设备1400包括一个或多个处理器1401和一个或多个存储器1402,存储器1402中存储了计算机可读代码,
其中,计算机可读代码当由一个或多个处理器1401执行时进行如下处理:
步骤S1,获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
步骤S2,基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度;
步骤S3,基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
优选地,所述步骤S1具体包括:获取所述冠状动脉的造影图像,显示冠状动脉的主支血管的类型选择,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
优选地,所述步骤S1还包括:基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则显示提示信息。
优选地,所述利用深度学习对所述冠状动脉的造影图像进行分割获得主支血管的分割图像,具体包括:
通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
优选地,所述步骤S2具体包括:
步骤S21,对所述主支血管的分割图像进行提取,得到血管骨架的造影图像;
步骤S22,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
优选地,所述步骤S3具体包括:
步骤S31,以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线;
步骤S32,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
优选地,所述步骤S31具体包括:
步骤S311,以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线;
步骤S312,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
优选地,所述步骤S32具体包括:
对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线;
得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域,所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段;
根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段;
对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
优选地,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
优选地,显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
进一步地,电子设备1400还包括网络接口1403、输入设备1404、硬盘1405、和显示设备1406。
上述各个接口和设备之间可以通过总线架构互连。总线架构可以是可以包括任意数量的互联的总线和桥。具体由处理器1401代表的一个或者多个中央处理器(CPU),以及由存储器1402代表的一个或者多个存储器1402的各种电路连接在一起。总线架构还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其它电路连接在一起。可以理解,总线架构用于实现这些组件之间的连接通信。总线架构除包括数据总线之外,还包括电源总线、控制总线和状态信号总线,这些都是本领域所公知的,因此本文不再对其进行详细描述。
网络接口1403,可以连接至网络(如因特网、局域网等),从网络中获取相关数据,并可以保存在硬盘1405中。
输入设备1404,可以接收操作人员输入的各种指令,并发送给处理器1401以供执行。输入设备1404可以包括键盘或者点击设备(例如,鼠标,轨迹球(trackball)、触感板或者触摸屏等。
显示设备1406,可以将处理器1401执行指令获得的结果进行显示。
存储器1402,用于存储操作系统14021运行所必须的程序和数据,以及处 理器1401计算过程中的中间结果等数据。
可以理解,本申请实施例中的存储器1402可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(ROM)、可编程只读存储器(PROM)、可擦除可编程只读存储器(EPROM)、电可擦除可编程只读存储器(EEPROM)或闪存。易失性存储器可以是随机存取存储器(RAM),其用作外部高速缓存。本文描述的装置和方法的存储器1402旨在包括但不限于这些和任意其它适合类型的存储器。
在一些实施方式中,存储器1402存储了如下的元素,可执行模块或者数据结构,或者他们的子集,或者他们的扩展集:操作系统14021和应用程序14014。
其中,操作系统14021,包含各种系统程序,例如框架层、核心库层、驱动层等,用于实现各种基础业务以及处理基于硬件的任务。应用程序14014,包含各种应用程序,例如浏览器(Browser)等,用于实现各种应用业务。实现本申请实施例方法的程序可以包含在应用程序14014中。
本申请上述实施例揭示的方法可以应用于处理器1401中,或者由处理器1401实现。处理器1401可能是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法的各步骤可以通过处理器1401中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器1401可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件,可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成,或者用译码处理器中的硬件及软 件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1402,处理器1401读取存储器1402中的信息,结合其硬件完成上述方法的步骤。
可以理解的是,本文描述的这些实施例可以用硬件、软件、固件、中间件、微码或其组合来实现。对于硬件实现,处理单元可以实现在一个或多个专用集成电路(ASIC)、数字信号处理器DSP)、数字信号处理设备(DSPD)、可编程逻辑设备(PLD)、现场可编程门阵列(FPGA)、通用处理器、控制器、微控制器、微处理器、用于执行本申请所述功能的其它电子单元或其组合中。
对于软件实现,可通过执行本文所述功能的模块(例如过程、函数等)来实现本文所述的技术。软件代码可存储在存储器中并通过处理器执行。存储器可以在处理器中或在处理器外部实现。
本申请实施例中,该电子设备1400通过利用深度学习对冠状动脉的造影图像进行分割得到主支血管的分割图像,并计算每一帧图像内的主支血管的长度,进而基于主支血管的长度随时间的变化得到主支血管的血流速度,该用于冠状动脉的血流速度的计算的电子设备,实现了冠状动脉的血流速度的计算的自动化,计算所得的冠状动脉的血流速度更为准确,且该计算方法较为简单。
另外,本申请实施例还提供了一种计算机存储介质,所述计算机存储介质存储了计算机可读代码,计算机可读代码当由一个或多个处理器执行时进行如下处理:
步骤S1,获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
步骤S2,基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度;
步骤S3,基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
该计算机可读代码被处理器执行时实现上述冠状动脉的血流速度的计算方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再对详细的过程进行赘述。其中,所述的计算机存储介质,如只读存储器(Read-Only Memory,简称ROM)、随机存取存储器(Random Access Memory,简称RAM)、磁碟或者光盘等。
在本申请所提供的几个实施例中,应该理解到,所揭露方法和装置,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理包括,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
以上所述实施例的各技术特征可以进行任意的组合,为使描述简洁,未对上述实施例中的各个技术特征所有可能的组合都进行描述,然而,只要这些技术特征的组合不存在矛盾,都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本发明的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对发明专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本发明构思的前提下,还可以做出若干变形和改进,这些都属于本发明的保护范围。因此,本发明专利的保护范围应以所附权利要求为准。

Claims (23)

  1. 一种冠状动脉的血流速度的计算方法,其特征在于,包括如下步骤:
    步骤S1,获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
    步骤S2,基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度;
    步骤S3,基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
  2. 根据权利要求1所述的冠状动脉的血流速度的计算方法,其特征在于,所述步骤S1具体包括:获取所述冠状动脉的造影图像,显示冠状动脉的主支血管的类型选择,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
  3. 根据权利要求2所述的冠状动脉的血流速度的计算方法,其特征在于,所述步骤S1还包括:基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
    若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
    若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则显示提示信息。
  4. 根据权利要求1所述的冠状动脉的血流速度的计算方法,其特征在于,所述利用深度学习对所述冠状动脉的造影图像进行分割获得主支血管的分割图像,具体包括:
    通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
  5. 根据权利要求1所述的冠状动脉的血流速度的计算方法,其特征在于,所述步骤S2具体包括:
    步骤S21,对所述主支血管的分割图像进行提取,得到血管骨架的造影图像;
    步骤S22,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
  6. 根据权利要求5所述的冠状动脉的血流速度的计算方法,其特征在于,所述步骤S3具体包括:
    步骤S31,以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线;
    步骤S32,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
  7. 根据权利要求6所述的冠状动脉的血流速度的计算方法,其特征在于,所述步骤S31具体包括:
    步骤S311,以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线;
    步骤S312,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
  8. 根据权利要求6所述的冠状动脉的血流速度的计算方法,其特征在于,所述步骤S32具体包括:
    对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线;
    得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域,所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段;
    根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段;
    对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
  9. 根据权利要求8所述的冠状动脉的血流速度的计算方法,其特征在于,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
  10. 根据权利要求9所述的冠状动脉的血流速度的计算方法,其特征在于,显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
  11. 一种冠状动脉的血流储备的计算方法,其特征在于,通过权利要求1至10中任一项所述的冠状动脉的血流速度的计算方法分别计算出所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,根据计算所得的所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,得到所述冠状动脉的血流储备;
    优选的,通过所述的冠状动脉的血流速度的计算方法,基于主支血管处于静息状态和充血状态的所述冠状动脉的造影图像分别计算出所述主支血管在静息状态下的血流速度以及在充血状态下的血流速度,其中,所述主支血管处于静息状态的冠状动脉的造影图像的采集时间与所述主支血管处于充血状态的冠状动脉的造影图像的采集时间之间的时间差不大于第一时间阈值。
  12. 一种冠状动脉的血流速度的计算装置,其特征在于,包括:
    冠状动脉造影图像分割模块,用于获取所述冠状动脉的造影图像,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
    长度计算模块,用于基于所述主支血管的分割图像,计算每一帧分割图像内所述主支血管的长度;
    以及血流速度计算模块,用于基于计算所得的所述主支血管的长度随时间的变化得到所述主支血管的血流速度。
  13. 根据权利要求12所述的冠状动脉的血流速度的计算装置,其特征在于,所述冠状动脉的血流速度的计算装置还包括显示装置,所述显示装置用于为用户显示冠状动脉的主支血管的类型选择;
    所述冠状动脉造影图像分割模块,用于获取所述冠状动脉的造影图像,基于用户选择的主支血管的类型,利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像。
  14. 根据权利要求13所述的冠状动脉的血流速度的计算装置,其特征在于,所述冠状动脉造影图像分割模块,用于基于用户选择的主支血管的类型,判断所述冠状动脉的造影图像的投照角度是否在该类型的主支血管的要求角度范围内;
    若所述冠状动脉的造影图像的投照角度在该类型的主支血管的要求角度范围内,则利用深度学习对所述冠状动脉的造影图像进行分割,获得主支血管的分割图像;
    若所述冠状动脉的造影图像的投照角度不在该类型的主支血管的要求角度范围内,则所述显示装置用于为用户显示提示信息。
  15. 根据权利要求12所述的冠状动脉的血流速度的计算装置,其特征在于,所述冠状动脉造影图像分割模块,用于通过U-Net模型的编码器结构获取所述冠状动脉的造影图像的多种不同分辨率的特征图,进而采用RefineNet模块将所述多种不同分辨率的特征图进行精制并进行结合,获得主支血管的分割图像。
  16. 根据权利要12所述的冠状动脉的血流速度的计算装置,其特征在于,所述长度计算模块,用于对所述主支血管的分割图像进行提取,得到血管骨架的造影图像,对所述血管骨架的造影图像中的血管骨架的长度进行计算,得到以像素为单位的主支血管的长度,结合图像的定标因子,计算获得主支血管的实际物理长度。
  17. 根据权利要求16所述的冠状动脉的血流速度的计算装置,其特征在于,所述血流速度计算模块,用于以时间为横坐标,以所述主支血管的分割图像中的主支血管的长度为纵坐标,得到主支血管的长度随时间的变化曲线,取所述主支血管的长度随时间的变化曲线的预定段,计算所述预定段的斜率,得到所述主支血管的血流速度。
  18. 根据权利要求17所述的冠状动脉的血流速度的计算装置,其特征在于,所述血流速度计算模块,用于以所述主支血管的分割图像的帧数为横坐标,以主支血管的实际长度为纵坐标,得到主支血管的长度随帧数的变化曲线,基于帧频信息将所述主支血管的长度随帧数的变化曲线中的横坐标转化为时间,得到主支血管的长度随时间的变化曲线。
  19. 根据权利要求17所述的冠状动脉的血流速度的计算装置,其特征在于,所述血流速度计算模块,用于对所述主支血管的长度随时间的变化曲线进行平滑处理,得到所述主支血管的长度随时间的变化曲线的平滑曲线,得到所述平滑曲线上的主支血管的长度的最大值,取所述平滑曲线上的主支血管的长度为所述主支血管的长度的最大值的预定值的一段为预定段区域;
    所述平滑曲线上的预定段区域相对的所述主支血管的长度随时间的变化曲线的一段为预选段,根据所述预选段对应的冠状动脉的心电信息,判断所述预选段是否包含一个心动周期,若所述预选段不包含一个心动周期,则所述预选段即为所述预定段;
    对所述预定段进行直线拟合,计算拟合得到的直线的斜率,得到所述主支血管的血流速度。
  20. 根据权利要求19所述的冠状动脉的血流速度的计算装置,其特征在于,若所述预选段包含一个心动周期,则以所述预选段的中心为起始点向所述预选段的两端分别延伸半个心动周期的长度得到预定段。
  21. 根据权利要求19所述的冠状动脉的血流速度的计算装置,其特征在于,所述冠状动脉的血流速度的计算装置还包括显示装置,所述显示装置,用于为用户显示所述主支血管的长度随时间的变化曲线及所述冠状动脉的造影图像以及与所述冠状动脉的造影图像相对应的所述冠状动脉的心电信息,用户查看预定段对应的冠状动脉的造影图像以及所述冠状动脉的心电信息,对预定段的选取进行验证,若预定段选取不合理,手动调整预定段的选取。
  22. 一种用于冠状动脉的血流速度的计算的电子设备,包括:
    一个或多个处理器;
    一个或多个存储器,其中存储了计算机可读代码,所述计算机可读代码当由所述一个或多个处理器执行时进行权利要求1-10中的血流速度的计算方法。
  23. 一种计算机存储介质,其特征在于,其中存储了计算机可读代码,所述计算机可读代码当由一个或多个处理器执行时进行权利要求1-10中的血流速度的计算方法。
PCT/CN2021/073277 2020-03-02 2021-01-22 冠状动脉的血流速度的计算方法、装置及电子设备 WO2021175039A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2022551789A JP7445779B2 (ja) 2020-03-02 2021-01-22 冠状動脈の血流速度の算出方法、装置及び電子デバイス
EP21765234.6A EP4104766A4 (en) 2020-03-02 2021-01-22 METHOD AND DEVICE FOR CALCULATION OF BLOOD FLOW IN A CORONARY ARTERY AND ELECTRONIC DEVICE
US17/802,838 US20230108647A1 (en) 2020-03-02 2021-01-22 Method and Apparatus for Calculating Blood Flow Rate in Coronary Artery, and Electronic Device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010134217.7 2020-03-02
CN202010134217.7A CN111369519B (zh) 2020-03-02 2020-03-02 冠状动脉的血流速度的计算方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2021175039A1 true WO2021175039A1 (zh) 2021-09-10

Family

ID=71206516

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/073277 WO2021175039A1 (zh) 2020-03-02 2021-01-22 冠状动脉的血流速度的计算方法、装置及电子设备

Country Status (5)

Country Link
US (1) US20230108647A1 (zh)
EP (1) EP4104766A4 (zh)
JP (1) JP7445779B2 (zh)
CN (2) CN113487588B (zh)
WO (1) WO2021175039A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113487588B (zh) * 2020-03-02 2024-03-22 上海博动医疗科技股份有限公司 冠状动脉的血流速度的计算方法、装置及电子设备
CN112309542B (zh) * 2020-07-27 2021-06-15 李星阳 心脏搭桥模式选择系统
CN112674736B (zh) * 2021-01-08 2023-07-25 上海博动医疗科技股份有限公司 一种用于自动评价血管形变的监测显示方法及系统
CN113706559A (zh) * 2021-09-13 2021-11-26 复旦大学附属中山医院 基于医学图像的血管分段提取方法和装置
US11776240B1 (en) * 2023-01-27 2023-10-03 Fudan University Squeeze-enhanced axial transformer, its layer and methods thereof
CN116205917B (zh) * 2023-04-28 2023-08-11 杭州脉流科技有限公司 获取冠脉血流储备的方法、装置、计算机设备和存储介质
CN116206162B (zh) * 2023-04-28 2023-08-01 杭州脉流科技有限公司 基于造影影像的冠脉血流储备获取方法、装置及设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105096388A (zh) * 2014-04-23 2015-11-25 北京冠生云医疗技术有限公司 基于计算流体力学的冠状动脉血流仿真系统和方法
CN109686450A (zh) * 2018-12-22 2019-04-26 北京工业大学 一种基于超声和ct成像技术的冠脉血流储备分数计算方法
CN110448319A (zh) * 2018-05-08 2019-11-15 博动医学影像科技(上海)有限公司 基于造影影像及冠状动脉的血流速度计算方法
CN111369519A (zh) * 2020-03-02 2020-07-03 博动医学影像科技(上海)有限公司 冠状动脉的血流速度的计算方法、装置及电子设备

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IN2013KO01322A (zh) 2013-11-22 2015-05-29 Siemens Medical Solutions
CN105326486B (zh) * 2015-12-08 2017-08-25 博动医学影像科技(上海)有限公司 血管压力差与血流储备分数的计算方法及系统
CN105559810B (zh) * 2015-12-10 2017-08-08 博动医学影像科技(上海)有限公司 血管单位时间血流量与血流速度的计算方法
US10206646B2 (en) 2016-03-10 2019-02-19 Siemens Healthcare Gmbh Method and system for extracting centerline representation of vascular structures in medical images via optimal paths in computational flow fields
EP3375364A4 (en) * 2017-01-23 2019-01-23 Shanghai United Imaging Healthcare Co., Ltd. SYSTEM AND METHOD FOR ANALYZING THE STATUS OF BLOOD CIRCULATION
US11534136B2 (en) * 2018-02-26 2022-12-27 Siemens Medical Solutions Usa, Inc. Three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging
CN110226923B (zh) * 2018-03-05 2021-12-14 苏州润迈德医疗科技有限公司 一种无需血管扩张剂测量血流储备分数的方法
CN109754402B (zh) * 2018-03-15 2021-11-19 京东方科技集团股份有限公司 图像处理方法、图像处理装置以及存储介质
CN109065170B (zh) 2018-06-20 2021-11-19 博动医学影像科技(上海)有限公司 获取血管压力差的方法及装置
CN109509192B (zh) * 2018-10-18 2023-05-30 天津大学 融合多尺度特征空间与语义空间的语义分割网络
CN109805949B (zh) 2019-03-19 2020-05-22 苏州润迈德医疗科技有限公司 基于压力传感器和造影图像计算血流储备分数的方法
CN109907772B (zh) * 2019-04-15 2020-11-10 博动医学影像科技(上海)有限公司 获取冠脉血流量及血流速度的方法和装置
CN110136147A (zh) * 2019-05-21 2019-08-16 湖北工业大学 一种基于U-Net模型的分割医学图像的方法、装置及存储介质
CN110335670A (zh) * 2019-06-10 2019-10-15 北京深睿博联科技有限责任公司 用于骨骺等级分级的图像数据处理方法及装置
CN110350958B (zh) * 2019-06-13 2021-03-16 东南大学 一种基于神经网络的大规模mimo的csi多倍率压缩反馈方法
CN110674824A (zh) * 2019-09-26 2020-01-10 五邑大学 基于R2U-Net的手指静脉分割方法、装置和存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105096388A (zh) * 2014-04-23 2015-11-25 北京冠生云医疗技术有限公司 基于计算流体力学的冠状动脉血流仿真系统和方法
CN110448319A (zh) * 2018-05-08 2019-11-15 博动医学影像科技(上海)有限公司 基于造影影像及冠状动脉的血流速度计算方法
CN109686450A (zh) * 2018-12-22 2019-04-26 北京工业大学 一种基于超声和ct成像技术的冠脉血流储备分数计算方法
CN111369519A (zh) * 2020-03-02 2020-07-03 博动医学影像科技(上海)有限公司 冠状动脉的血流速度的计算方法、装置及电子设备

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
BLAIECH, AHMED GHAZI ET AL.: "Impact of Enhancement for Coronary Artery Segmentation Based on Deep Learning Neural Network", PATTERN RECOGNITION AND IMAGE ANALYSIS : 9TH IBERIAN CONFERENCE, IBPRIA 2019, MADRID, SPAIN, JULY 1-4, 2019, vol. 11867, 22 September 2019 (2019-09-22), pages 260 - 272, XP047523416, ISBN: 978-3-030-31321-0 *
See also references of EP4104766A4 *

Also Published As

Publication number Publication date
JP2023516013A (ja) 2023-04-17
US20230108647A1 (en) 2023-04-06
EP4104766A4 (en) 2023-09-13
CN113487588A (zh) 2021-10-08
EP4104766A1 (en) 2022-12-21
CN113487588B (zh) 2024-03-22
JP7445779B2 (ja) 2024-03-07
CN111369519A (zh) 2020-07-03
CN111369519B (zh) 2021-09-17

Similar Documents

Publication Publication Date Title
WO2021175039A1 (zh) 冠状动脉的血流速度的计算方法、装置及电子设备
JP5336370B2 (ja) 効率的診断のための解剖構造に関係した画像コンテキスト依存のアプリケーション
CN112348861B (zh) 图像处理方法、装置、设备及存储介质
CN110378913B (zh) 图像分割方法、装置、设备及存储介质
US20220277447A1 (en) Method and apparatus for acquiring contour line of blood vessel according to centerline of blood vessel
US11605447B2 (en) Intelligent agents for patient management
US10997720B2 (en) Medical image classification method and related device
CN110675481B (zh) 影像交互联动方法、装置及可读存储介质
CN112494020B (zh) 获取感兴趣的主动脉压力曲线的方法及存储介质
JP6745623B2 (ja) ボリューム画像を表示するためのシステムおよび方法
WO2022121493A1 (en) Systems and methods for blood vessel assessment
CN111091561A (zh) 感兴趣区的神经纤维提取方法、系统、设备及存储介质
CN111476791A (zh) 图像处理方法、图像处理装置和非暂时性计算机可读介质
CN113827263A (zh) 灌注影像处理方法、系统、电子设备及存储介质
Li et al. Fully feature fusion based neural network for COVID-19 lesion segmentation in CT images
CN115439478A (zh) 基于肺灌注的肺叶灌注强度评估方法、系统、设备及介质
CN112767314B (zh) 医学图像处理方法、装置、设备及存储介质
CN112075956B (zh) 一种基于深度学习的射血分数估计方法、终端及存储介质
JP2020513923A (ja) 閉塞を有する血管構造の経路の視覚化
CN114098748A (zh) 生理信号的处理方法、装置及计算机可读存储介质
CN112446499A (zh) 改进用于自动量化冠状动脉疾病的机器学习模型的性能
CN111627002A (zh) 一种冠脉微血管阻力指数计算装置及方法
CN113706541A (zh) 一种图像处理方法及装置
Feng et al. A simplified coronary model for diagnosis of ischemia-causing coronary stenosis
US20230210473A1 (en) Clinical diagnostic and patient information systems and methods

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21765234

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022551789

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2021765234

Country of ref document: EP

Effective date: 20220831

NENP Non-entry into the national phase

Ref country code: DE