Method, system and device for measuring and classifying CT-FFR and storage medium

Abstract

A method, system, device and storage medium for measuring and classifying CT-FFR, dividing lesions into different types according to coronary artery computed tomography angiography (CCTA) images, determining lesion lengths at lesion positions according to different lesion types, and determining the lesion lengths at the lesion positions according to different lesion types. Then, the measurement range of computed tomography fractional flow reserve is determined according to the focus lengths of different lesion types, a statistical matrix is established to calculate the numerical values of all computed tomography fractional flow reserve CT-FFR in the measurement range, and finally, hemodynamic classification is conducted on calculation results. According to the CT-FFR evaluation method, the accuracy and the stability of CT-FFR evaluation are enhanced by carrying out pathological change specificity classification on the pathological change in the haemodynamics sense, interference is reduced, and a more reliable solution is provided for clinicians and patients.

Description

Technical Field

[0001] This invention relates to a method, system, apparatus, and storage medium for measuring and classifying CT-FFR. Background Technology

[0002] CT-FFR (Computed Tomography Fractional Flow Reserve), as a non-invasive technique for assessing functional stenosis in coronary arteries, shows good correlation with invasive FFR (Fractional Flow Reserve) in diagnostic performance, but it has some drawbacks. First, the manually selected measurement location may introduce subjectivity, affecting the consistency of results. Second, CT-FFR values ​​within 2-3 cm distal to the stenosis may vary depending on the centerline point and luminal contour, leading to uncertainty in the measurement results. Furthermore, CT-FFR values ​​in the "grey area" between 0.75 and 0.8 have low diagnostic value and may lead to misdiagnosis.

[0003] The statements herein provide only background information in relation to this invention and do not necessarily constitute prior art. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, device, and storage medium for measuring and classifying CT-FFR, which improves the accuracy of measurement, enhances the accuracy and stability of assessment, reduces interference, and provides a more reliable solution for clinicians and patients.

[0005] To achieve the above objectives, the present invention provides a method for measuring and classifying fractional flow reserve in computed tomography scans, comprising:

[0006] Based on the length, calcification, and branch involvement of the lesions shown in coronary computed tomography (CCTA) images, the lesions are classified into different lesion types.

[0007] The length of the lesion at different locations is determined based on the type of lesion.

[0008] The measurement range of fractional flow reserve in computed tomography is determined based on the lesion length for different lesion types.

[0009] Obtain the values ​​of fractional flow reserve (CT-FFR) from all computed tomography scans within the measurement range. Perform statistical calculations on all CT-FFR values ​​and classify the calculation results into lesion-specific categories based on the cutoff values ​​from hemodynamic classification to obtain lesion-specific classification results.

[0010] This solution includes a lesion type classification function, which can identify different types of lesions and select appropriate lesion length measurement strategies according to different lesion types. This determines the measurement range of CT-FFR values ​​for specific lesions, thereby improving measurement accuracy. By classifying lesions in a hemodynamic sense, the accuracy and stability of CT-FFR assessment are enhanced, interference is reduced, and a more reliable solution is provided for clinicians and patients.

[0011] Optionally, the method for automatically classifying lesion types includes:

[0012] If the length of the lesion is less than or equal to 10 mm, with mild or no calcification, and no major branches are involved, it is determined to be a unifocal lesion.

[0013] If the length of the lesion is greater than or equal to 20 mm, the main branches are involved, and the proximal end is excessively tortuous, it is determined to be a diffuse lesion.

[0014] If the length of the entire lesion is greater than 10 mm and less than 20 mm, with moderate or severe calcification and an irregular outline, it is identified as a tandem lesion; if the interval between lesions is less than 10 mm, it is identified as a continuous tandem lesion; if the interval between lesions is greater than or equal to 10 mm, it is identified as a discontinuous tandem lesion.

[0015] In this approach, by identifying different types of lesions such as unifocal lesions, diffuse lesions, and tandem lesions, appropriate lesion length measurement strategies can be selected based on different lesion types to determine the measurement range of CT-FFR values ​​for specific lesions, thereby improving measurement accuracy.

[0016] Optionally, the method for determining the lesion length at the lesion location includes:

[0017] For unifocal lesions, the proximal centerline point (LP) of the lesion was recorded separately. pro and the distal center line point LP of the lesion dis ;

[0018] For diffuse lesions, the proximal centerline point (LP) of the lesion was recorded. pro and the distal center line point LP of the lesion dis ;

[0019] For tandem lesions, first determine the proximal centerline point LP of the entire lesion. pro and the distal center line point LP of the lesion dis Then, the continuity of the entire lesion is measured to determine whether the tandem lesion is a continuous tandem lesion or a discontinuous tandem lesion.

[0020] For consecutive tandem lesions, the proximal centerline point (LP) of each lesion was recorded. pro and the distal center line point LP of the lesiondis ;

[0021] For discontinuous tandem lesions, first record the proximal centerline point LP of the entire lesion. pro and the distal center line point LP of the lesion dis Then, record the proximal centerline point LP of each lesion. pro ′ and the distal center line point LP of the lesion dis ′.

[0022] In this approach, a matching method is selected based on different lesion types to determine the proximal and distal centerline points of the lesion. This allows for the determination of the measurement range of the CT-FFR value for a specific lesion based on its length, thereby improving measurement accuracy.

[0023] Optionally, for unifocal lesions, diffuse lesions, and continuous tandem lesions, the method for determining the measurement range of computed tomography fractional flow reserve includes:

[0024] Calculate the starting measurement centerline point MP beg and the end of the measurement centerline point MP end :

[0025] MP beg =LP dis +2cm

[0026] Among them, the center line point MP is measured first. beg At the distal center line point LP of the lesion dis Extend longitudinally along the coronary artery 2 cm towards the distal end of the lesion;

[0027] MP end =LP dis +3cm

[0028] Among them, the measurement centerline point MP ends end At the distal center line point LP of the lesion dis Based on this, extend longitudinally along the coronary artery 3cm towards the distal end of the lesion.

[0029] In this protocol, the starting point for measuring the centerline (MP) is determined based on different lesion types and lengths. beg and the end of the measurement centerline point MP end This reduces interference, improves accuracy, and helps doctors understand the exact length and location of lesions.

[0030] Optionally, for discontinuous tandem lesions, the method for determining the measurement range of computed tomography fractional flow reserve includes:

[0031] Calculate the starting measurement centerline point MPbeg and the end of the measurement centerline point MP end :

[0032]

[0033] Among them, the center line point MP is measured first. end It is the position where the blood vessel diameter returns to the center line point from the previous lesion;

[0034] MP end =MP beg +(0.5~1)mm

[0035] Among them, the measurement centerline point MP ends end At the beginning of the measurement of the center line point MP beg Based on this, extend longitudinally along the coronary artery 0.5mm to 1mm towards the distal end of the lesion.

[0036] In this protocol, the starting point for measuring the centerline (MP) is determined based on different lesion types and lengths. beg and the end of the measurement centerline point MP end This reduces interference, improves accuracy, and helps doctors understand the exact length and location of lesions.

[0037] Optionally, if the distal end of the lesion is close to the distal end of the coronary artery, the centerline point at a lumen diameter of 1.5 mm is used as the distal centerline point when determining the lesion length; and the centerline point at a lumen diameter of 1.5 mm is used as the end-of-measure centerline point (MP) when determining the measurement range of the fractional flow reserve (FLR) on computed tomography. end MP end =Centerline point of 1.5mm lumen diameter.

[0038] In this protocol, the typical or average diameter of the distal end of the lesion is usually 1.5 mm. Choosing this point as a reference can help doctors more accurately assess the length and severity of the lesion.

[0039] Optionally, the method for performing lesion-specific classification includes:

[0040] When the maximum value of all CT-FFR values ​​within the measurement range is less than or equal to the cutoff value of 0.7, the average value of all CT-FFR values ​​within the measurement range is used as the CT-FFR value of the lesion, and the lesion is marked as positive.

[0041] When the minimum value of all CT-FFR values ​​within the measurement range is greater than or equal to the cutoff value of 0.85, the average value of all CT-FFR values ​​within the measurement range is used as the CT-FFR value of the lesion, and the lesion is marked as negative.

[0042] When CT-FFR values ​​within the measurement range are distributed between 0.7 and 0.85, a histogram is constructed based on all CT-FFR values. The category with the highest frequency in the histogram is determined, and the average CT-FFR value in that category is calculated. The average value is compared with the cutoff value: if the average value is less than or equal to 0.7, it is judged as a positive lesion and marked as positive; if the average value is greater than or equal to 0.85, it is judged as a negative lesion and marked as negative; if the average value is greater than 0.7 and less than 0.85, it is judged as a gray area.

[0043] In this approach, histogram statistics are used to classify lesions in a hemodynamic sense, which intuitively and effectively displays the distribution characteristics of CT-FFR values, enhances the accuracy and stability of CT-FFR assessment, reduces interference, and provides a more reliable solution for clinicians and patients.

[0044] Another technical solution of the present invention is to provide a system for measuring and classifying fractional flow reserve in computed tomography scans, for implementing the method for measuring and classifying fractional flow reserve in computed tomography scans, the system comprising:

[0045] The lesion type classification module is used to classify lesions into different types based on the lesion length, calcification, and branch involvement shown in coronary computed tomography (CCTA) images.

[0046] The lesion length determination module is used to determine the length of the lesion based on different lesion types.

[0047] The measurement range determination module is used to determine the measurement range of fractional flow reserve in computed tomography scans based on the lesion length for different lesion types.

[0048] The CT-FFR value calculation module is used to calculate the CT-FFR values ​​for all computed tomography scans within the measurement range.

[0049] The statistical analysis module is used to statistically analyze the values ​​of fractional flow reserve in computed tomography scans based on the measurement range, and obtain lesion-specific classification results.

[0050] This solution incorporates a lesion type classification function, which can identify different types of lesions and select appropriate lesion length measurement strategies based on different lesion types. This determines the measurement range of CT-FFR values ​​for specific lesions, thereby improving measurement accuracy. By classifying lesions in a hemodynamically specific manner, the accuracy and stability of CT-FFR assessment are enhanced, interference is reduced, and a more reliable solution is provided for clinicians and patients.

[0051] Another technical solution of the present invention is to provide an apparatus for measuring and classifying fractional flow reserve in computed tomography scans, comprising: a memory, a processor, and a program stored in the memory and executable on the processor, the program being configured to implement the method for measuring and classifying fractional flow reserve in computed tomography scans.

[0052] Another technical solution of the present invention is to provide a storage medium on which a program is stored, and when the program is executed by a processor, it implements the method for measuring and classifying fractional flow reserve in computed tomography scans.

[0053] In summary, this invention incorporates a lesion type classification function, enabling the identification of different lesion types such as unifocal lesions, diffuse lesions, and tandem lesions. It selects appropriate lesion length measurement strategies based on different lesion types to determine the measurement range of CT-FFR values ​​for specific lesions, thereby improving measurement accuracy. By classifying lesions specifically in a hemodynamic sense, the accuracy and stability of CT-FFR assessment are enhanced, interference is reduced, and a more reliable solution is provided for clinicians and patients. Attached Figure Description

[0054] Figure 1 This is a flowchart of a method for measuring and classifying fractional flow reserve in computed tomography scans, provided by an embodiment of the present invention.

[0055] Figure 2 It is a schematic diagram for determining the lesion length and measurement range of single-focal lesions, diffuse lesions, and continuous tandem lesions.

[0056] Figure 3 This is a schematic diagram for determining the length and measurement range of discontinuous tandem lesions.

[0057] Figure 4 This is a framework diagram of a system for measuring and classifying fractional blood flow reserve in computed tomography scans, provided by one embodiment of the present invention.

[0058] Figure label:

[0059] S1-S4: Steps of a method for measuring and classifying fractional flow reserve in computed tomography scans provided in one embodiment;

[0060] LP pro : The proximal centerline point of the entire lesion;

[0061] LP dis : The distal center line point of the entire lesion;

[0062] LP pro′: The proximal centerline point of each lesion in a discontinuous tandem lesion;

[0063] LP dis ′: The distal centerline point of each lesion in a discontinuous tandem lesion;

[0064] MP beg Begin measuring the centerline point;

[0065] MP end : End measurement of the center line point;

[0066] 101: Lesion type classification module;

[0067] 102: Lesion length determination module;

[0068] 103: Measurement range determination module;

[0069] 104: CT-FFR value calculation module;

[0070] 105: Statistical Analysis Module. Detailed Implementation

[0071] The following is based on Figures 1-4 The preferred embodiments of the present invention will be described in detail below.

[0072] Fractional Flow Reserve (FFR) is an important clinical reference standard for evaluating functional stenosis in coronary artery disease (CAD). FFR is calculated by measuring the ratio of distal coronary pressure (Pd) to aortic pressure (Pa) under maximal coronary congestion, with a value ranging from 0.0 to 1.0. FFR measurement is typically performed under the guidance of percutaneous coronary intervention (PCI), requiring the use of a pressure guidewire and ensuring the pressure sensor is placed at least 2 to 3 cm distal to the stenosis being evaluated. Generally, lesions with an FFR value ≤ 0.8 are considered to cause lesion-specific ischemia, while lesions with an FFR value > 0.8 are less associated with myocardial ischemia. FFR values ​​between 0.75 and 0.8 are considered a "grey area" with low diagnostic value.

[0073] When measuring fractional flow reserve (FFR), close monitoring of the patient's blood pressure and congestion is necessary. After calibrating the pressure system, balancing the distal coronary artery pressure (Pd) and aortic pressure (Pa), and injecting adenosine, the measurement is performed when the lowest point of the Pd / Pa tracer remains stable for 20 seconds. In cases of multiple continuous stenosis or diffuse atherosclerotic disease, the pressure sensor needs to be slowly pulled back under stable congestion to assess the distribution of abnormal epicardial resistance, examining the entire length of the artery over approximately 15 to 20 seconds.

[0074] Computed Tomography Fractional Flow Reserve (CT-FFR) is a non-invasive assessment technique based on coronary computed tomography angiography (CCTA) data, combined with advanced computational analysis methods such as computational fluid dynamics (CFD) or machine learning (ML). CT-FFR aims to simulate the physiological state of the coronary arteries, providing simulated values ​​similar to invasive FFR, thereby assessing the hemodynamic significance of coronary artery lesions. CT-FFR shows good correlation with invasive FFR in diagnostic performance and, compared to CCTA alone, demonstrates potential in optimizing patient management, improving risk stratification, and enhancing prognosis.

[0075] The calculation process of CT-FFR includes: reconstructing the coronary anatomy model using CCTA data, extracting the coronary artery centerline and lumen contour, then inputting the extracted coronary artery centerline tree, performing corresponding lumen segmentation at each centerline point, and using machine learning algorithms to predict the CT-FFR value of each centerline point along the centerline tree. Finally, a color-coded grid is generated to display the CT-FFR value corresponding to each centerline point.

[0076] The recommended measurement location for CT-FFR is typically 2 to 3 cm distal to the stenosis for better correlation with invasive FFR. However, since the CT-FFR measurement location is manually selected, and CT-FFR values ​​within the 2 to 3 cm distal range of the stenosis may vary depending on different centerline points and lumen profiles, this can lead to measurement uncertainty or inconsistency, especially when the CT-FFR value is in a gray area, and may even result in misjudgment.

[0077] When using software algorithms for automated detection and measurement, a fixed centerline point (e.g., 2 cm distal to the lesion) is typically chosen as the measurement point for CT-FFR values. While this method is simple and quick, providing a rapid reference value, fixed centerline measurements may overlook subtle changes in blood flow within the lesion area. Simply fixing the centerline may not accurately reflect the CT-FFR value of the entire lesion region, failing to fully account for the complexity and diversity of lesions, thus reducing the precision and accuracy of the measurement. Therefore, when selecting the measurement location for CT-FFR, different types of lesions should be comprehensively considered, and the measurement location should be chosen as precisely as possible to ensure the clinical relevance and accuracy of the measurement results.

[0078] In clinical practice, there are clear guidelines for selecting CT-FFR measurement locations based on the type and distribution of the lesion: For single focal lesions, the measurement point is usually manually selected 2 to 3 cm distal to the stenosis; for diffuse lesions ≥3 cm in length or tandem lesions with consecutive intervals ≤1 cm, the measurement is performed 2 cm distal to the lesion; for intermittent tandem lesions with intervals ≥1 cm, it is recommended to perform measurements distal to each lesion. For most stenotic lesions, the measurement location for distal epigenetically normal coronary arteries should extend from the distal end of the stenosis to 2 cm along the entire lesion.

[0079] Based on this, the present invention provides a method for automatically measuring and classifying fractional flow reserve in computed tomography scans, such as... Figure 1 As shown, the method includes the following steps:

[0080] Step S1: Based on the length, calcification, and branch involvement of the lesions shown in the coronary computed tomography angiography (CCTA) images, classify the lesions into different lesion types.

[0081] Step S2: Determine the lesion length based on the different lesion types.

[0082] Step S3: Determine the measurement range of fractional flow reserve in computed tomography based on the lesion length of different lesion types.

[0083] Step S4: Obtain the values ​​of CT-FFR (fractional flow reserve) for all computed tomography scans within the measurement range, perform statistical calculations on all CT-FFR values, and classify the calculation results into lesion-specific categories based on the cutoff values ​​from hemodynamic classification to obtain lesion-specific classification results.

[0084] This invention features a lesion type classification function, which can identify different types of lesions and select appropriate lesion length measurement strategies based on different lesion types. This allows for the determination of the measurement range of CT-FFR values ​​for specific lesions, thereby improving measurement accuracy. By classifying lesions in a hemodynamically specific manner, the accuracy and stability of CT-FFR assessment are enhanced, interference is reduced, and a more reliable solution is provided for clinicians and patients.

[0085] In step S1, the lesion types include: unifocal lesions, diffuse lesions, and tandem lesions, wherein tandem lesions are further divided into continuous tandem lesions and discontinuous tandem lesions.

[0086] In step S1, the method for classifying lesion types includes:

[0087] Measure the length of lesions in CCTA images and analyze the degree of calcification and branch involvement in the lesions in CCTA images;

[0088] The Agatston score is commonly used in clinical practice to assess the severity of coronary artery calcification. Typically, a coronary artery calcification score of 0, 1-100, 101-400, and greater than 400 correspond to four categories: no calcification, mild calcification, moderate calcification, and severe calcification, respectively.

[0089] Single-focal lesions: If the length of the lesion is less than or equal to 10 mm, with mild or no calcification, and no major branches are involved, it is determined to be a single-focal lesion. Single-focal lesions also have other characteristics, such as incomplete occlusion (meaning that the blood vessel is not completely blocked and some blood flow still passes through), location not at the opening (the lesion is not located at the opening of the blood vessel, that is, the starting point of the blood vessel branch), no thrombus (no thrombus has formed in the blood vessel), and smooth outline. According to the classification of coronary artery lesions by the American College of Cardiology (ACC) and the American Heart Association (AHA), single-focal lesions are usually classified as typical type A lesions (simple lesions).

[0090] Diffuse lesions: If the length of the lesion is greater than or equal to 20 mm, the major branches are involved, and the proximal end is excessively tortuous (meaning that the proximal part of the blood vessel, i.e., the part close to the heart, has abnormal bending or twisting), it is determined to be a diffuse lesion. According to the classification of coronary artery lesions by the American College of Cardiology (ACC) and the American Heart Association (AHA), diffuse lesions are usually classified as typical type C lesions (complex lesions).

[0091] Tandem lesions: If the length of the entire lesion is greater than 10 mm and less than 20 mm, with moderate or severe calcification and irregular outline, it is identified as a tandem lesion; further, if the interval between lesions is less than 10 mm, it is identified as a continuous tandem lesion, and if the interval between lesions is greater than or equal to 10 mm, it is identified as a discontinuous tandem lesion; according to the classification of coronary artery lesions by the American College of Cardiology (ACC) and the American Heart Association (AHA), tandem lesions are usually classified as typical type B lesions (moderately complex lesions).

[0092] By identifying different types of lesions, such as unifocal lesions, diffuse lesions, and tandem lesions, appropriate lesion length measurement strategies can be selected based on different lesion types, and the measurement range of CT-FFR values ​​for specific lesions can be automatically determined to improve measurement accuracy.

[0093] In step S2, the method for determining the lesion length at the lesion location includes:

[0094] like Figure 2 As shown, for unifocal lesions, the proximal centerline point LP of the lesion was recorded. proand the distal center line point LP of the lesion dis If the lesion is close to the distal end of the coronary artery, the centerline point at a location with a lumen diameter of 1.5 mm is taken as the distal centerline point LP of the lesion. dis The typical or average diameter of the distal end of the lesion is usually 1.5 mm. Choosing this point as a reference can help doctors more accurately assess the length and severity of the lesion.

[0095] like Figure 2 As shown, for diffuse lesions, the proximal centerline point LP of the lesion was recorded respectively. pro and the distal center line point LP of the lesion dis If the lesion is close to the distal end of the coronary artery, the centerline point at a location with a lumen diameter of 1.5 mm can be used as the distal centerline point (LP) of the lesion. dis .

[0096] For tandem lesions, first measure the LP of the entire lesion. pro and LP dis Then, a continuity test is performed, which includes: if the rate of change of the radius of the lesion changes suddenly, that is, the diameter is greater than the proximal end of the lesion and the length exceeds 1 cm, it is classified as a discontinuous tandem lesion.

[0097] like Figure 2 As shown, for consecutive tandem lesions, the proximal centerline point LP of the lesion is recorded respectively. pro and the distal center line point LP of the lesion dis If the lesion is close to the distal end of the coronary artery, the centerline point at a location with a lumen diameter of 1.5 mm can be used as the distal centerline point (LP) of the lesion. dis .

[0098] like Figure 3 As shown, for discontinuous tandem lesions, the proximal centerline point LP of the entire lesion is first recorded. pro and the distal center line point LP of the lesion dis Then, record the proximal centerline point LP of each lesion. pro ′ and the distal center line point LP of the lesion dis If the lesion is close to the distal end of the coronary artery, the centerline point at a location with a lumen diameter of 1.5 mm can be used as the distal centerline point of the lesion.

[0099] By selecting a matching method based on different lesion types, the proximal and distal centerline points of the lesion can be determined. This allows for the determination of the measurement range of CT-FFR values ​​for specific lesions based on their length, thereby improving measurement accuracy.

[0100] In step S3, the method for determining the measurement range of fractional flow reserve in computed tomography includes:

[0101] like Figure 2 As shown, for unifocal lesions, diffuse lesions, and continuous tandem lesions, the starting measurement centerline point MP is calculated. beg and the end of the measurement centerline point MP end :

[0102] MP beg =LP dis +2cm(1)

[0103] Among them, the center line point MP is measured first. beg At the distal center line point LP of the lesion dis Extend longitudinally along the coronary artery 2 cm towards the distal end of the lesion;

[0104] MP end =LP dis +3cm(2)

[0105] Among them, the measurement centerline point MP ends end At the distal center line point LP of the lesion dis Based on this, extend longitudinally along the coronary artery 3cm towards the distal end of the lesion.

[0106] Determine the starting point for measuring the centerline, MP. beg and the end of the measurement centerline point MP end It helps doctors understand the exact length and location of the lesion.

[0107] or,

[0108] If the lesion is close to the distal end of the coronary artery, the centerline point at a location with a lumen diameter of 1.5 mm is taken as the end point of the measurement (MP). end MP end =1.5mm lumen diameter centerline point (3), choosing this point as a reference can help doctors more accurately assess the length and severity of the lesion.

[0109] like Figure 3 As shown, for discontinuous tandem lesions, the starting measurement centerline point MP is calculated. beg and the end of the measurement centerline point MP end :

[0110] MP beg =CLP normal fr om LPdis (4)

[0111] Among them, the center line point MP is measured first. beg It is the position where the blood vessel diameter returns to the center line point from the previous lesion;

[0112] MP end =MP beg +(0.5~1)mm(5)

[0113] Among them, the measurement centerline point MP ends end At the beginning of the measurement of the center line point MP beg Based on this, extend longitudinally along the coronary artery 0.5mm to 1mm towards the distal end of the lesion.

[0114] Determine the starting point for measuring the centerline, MP. beg and the end of the measurement centerline point MP end It helps doctors understand the exact length and location of the lesion.

[0115] Alternatively, if the lesion is close to the distal end of the coronary artery, the centerline point at a location with a lumen diameter of 1.5 mm can be used as the end point of measurement (MP). end MP end =1.5mm lumen diameter centerline point (6), choosing this point as a reference can help doctors more accurately assess the length and severity of the lesion.

[0116] In step S4, the values ​​of fractional flow reserve from computed tomography scans are statistically analyzed based on the measurement range to obtain lesion-specific classification results.

[0117] The fractional flow reserve (CT-FFR) values ​​for all computed tomographic scans within the measurement range are obtained. A statistical matrix is ​​established to calculate all values, and the calculation results are classified according to cutoff values ​​from hemodynamic classification. The sampling interval and sampling frequency of CT-FFR are usually related to the parameter settings of the CT scan, and the specific values ​​may vary depending on different CT equipment and scanning protocols.

[0118] The statistical matrix includes: minimum value, maximum value, average value, and histogram.

[0119] The cutoff values ​​are 0.7 and 0.85. If the CT-FFR value is ≤0.7, it is considered a positive lesion; if the CT-FFR value is ≥0.85, it is considered a negative lesion; and if the CT-FFR value is between the two, it will be considered a gray area, indicating that other clinical evidence is needed for classification.

[0120] When the maximum value of all CT-FFR values ​​within the measurement range is less than or equal to 0.7, the average value of all CT-FFR values ​​within the measurement range is used as the CT-FFR value of the lesion, and the lesion is marked as positive, for example, marked in red.

[0121] When the minimum value of all CT-FFR values ​​within the measurement range is greater than or equal to 0.85, the average value of all CT-FFR values ​​within the measurement range is used as the CT-FFR value of the lesion, and the lesion is marked as negative, for example, marked in blue.

[0122] When CT-FFR values ​​within the measurement range are distributed between 0.7 and 0.85, a histogram is constructed based on all CT-FFR values. The category with the highest frequency in the histogram is determined, and the average CT-FFR value in that category is calculated. The average value is compared with the cutoff value. If it is less than or equal to 0.7, it is judged as a positive lesion and marked as positive. If it is greater than or equal to 0.85, it is judged as a negative lesion and marked as negative. If it is greater than 0.7 and less than 0.85, it is judged as a gray area and marked as gray area, for example, marked as gray.

[0123] Histogram analysis of CT-FFR values ​​provides an intuitive and effective data visualization tool. It clearly displays the distribution characteristics of CT-FFR values, including central tendency, dispersion, and data density, and helps to quickly identify outliers and anomalies. Histograms allow physicians to compare the distribution of CT-FFR values ​​across different patient groups, aiding diagnostic decisions and determining whether the data falls within the normal range. The adjustability of histograms allows physicians to adjust the number of groups to obtain more detailed or generalized data views, thereby better evaluating and interpreting CT-FFR data.

[0124] This invention classifies lesions into different types based on coronary computed tomography angiography (CCTA) images, determines the lesion length at the lesion location according to different lesion types, then determines the measurement range of computed tomography fractional flow reserve (CT-FFR) based on the lesion length of different lesion types, establishes a statistical matrix to calculate the CT-FFR values ​​of all computed tomography scans within the measurement range, and finally performs hemodynamic classification on the calculation results.

[0125] This invention adds a lesion type classification function, which can automatically identify different types of lesions such as single-focal lesions, diffuse lesions, and tandem lesions. It selects an appropriate lesion length measurement strategy based on different lesion types, thereby determining the measurement range of CT-FFR values ​​for specific lesions and improving measurement accuracy. This invention performs hemodynamically specific lesion classification, enhancing the accuracy and stability of CT-FFR assessment, reducing interference, and providing a more reliable solution for clinicians and patients.

[0126] like Figure 4 As shown, the present invention also provides a system for measuring and classifying fractional flow reserve in computed tomography scans, comprising:

[0127] The lesion type classification module 101 is used to classify lesions into different types based on the lesion length, calcification and branch involvement shown in coronary computed tomography angiography (CCTA) images.

[0128] The lesion length determination module 102 is used to determine the lesion length at the lesion location based on different lesion types.

[0129] Measurement range determination module 103 is used to determine the measurement range of fractional flow reserve in computed tomography scans based on the lesion length of different lesion types.

[0130] CT-FFR value calculation module 104 is used to calculate the CT-FFR values ​​for all computed tomography scans within the measurement range;

[0131] The statistical analysis module 105 is used to statistically analyze the values ​​of fractional flow reserve in computed tomography scans based on the measurement range, and obtain lesion-specific classification results.

[0132] This invention adds a lesion type classification function, enabling it to identify different types of lesions such as single-focal lesions, diffuse lesions, and tandem lesions. It selects an appropriate lesion length measurement strategy based on different lesion types, thereby determining the measurement range of CT-FFR values ​​for specific lesions and improving measurement accuracy. This invention performs hemodynamically specific lesion classification, enhancing the accuracy and stability of CT-FFR assessment, reducing interference, and providing a more reliable solution for clinicians and patients.

[0133] The present invention also provides an apparatus for measuring and classifying fractional flow reserve in computed tomography scans, comprising: a memory, a processor, and a program stored in the memory and executable on the processor, the program being configured to implement the method for measuring and classifying fractional flow reserve in computed tomography scans.

[0134] The present invention also provides a storage medium storing a program that, when executed by a processor, implements the method for measuring and classifying fractional flow reserve in computed tomography scans.

[0135] This invention adds a lesion type classification function, enabling it to identify different types of lesions such as single-focal lesions, diffuse lesions, and tandem lesions. It selects an appropriate lesion length measurement strategy based on different lesion types, thereby determining the measurement range of CT-FFR values ​​for specific lesions and improving measurement accuracy. This invention performs hemodynamically specific lesion classification, enhancing the accuracy and stability of CT-FFR assessment, reducing interference, and providing a more reliable solution for clinicians and patients.

[0136] It should be noted that, in the embodiments of the present invention, the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing the embodiments. They 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, and therefore should not be construed as a limitation of the present 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.

[0137] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; 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; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0138] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described feature, integral, step, operation, element and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0139] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0140] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0141] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0142] Although the present invention has been described in detail through the preferred embodiments above, it should be understood that the above description should not be considered as a limitation of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present invention. After reading the above content, various modifications and substitutions to the present invention will be obvious to those skilled in the art. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. A method of measuring and classifying computed tomography blood flow reserve fraction, characterized by, The method comprises the following steps: According to the length and calcification and branch involvement of the lesion shown in the CCTA image, the lesion is divided into different lesion types; According to the length of the lesion at the lesion site, the length of the lesion at the lesion site is determined according to different lesion types; According to the length of the lesion of different lesion types, the measurement range of CT-FFR is determined; All CT-FFR values in the measurement range are obtained, and statistical calculation is performed on all CT-FFR values. According to the cutoff value from the hemodynamic classification, the calculation result is classified according to the lesion specificity, and the lesion specificity classification result is obtained.

2. The method of measuring and classifying computed tomography flow reserve as defined in claim 1, wherein, The method for classifying lesion types comprises: If the length of the lesion is less than or equal to 10 mm, there is mild or no calcification, and there is no main branch involvement, it is determined as a single lesion; If the length of the lesion is greater than or equal to 20 mm, there is main branch involvement, and the proximal end is excessively twisted, it is determined as a diffuse lesion; If the length of the entire lesion is greater than 10 mm and less than 20 mm, there is moderate or severe calcification, and the outline is irregular, it is determined as a tandem lesion; if the interval between lesions is less than 10 mm, it is determined as a continuous tandem lesion, and if the interval between lesions is greater than or equal to 10 mm, it is determined as a discontinuous tandem lesion.

3. The method of measuring and classifying computed tomography flow reserve as defined in claim 2, wherein, The method for determining the length of the lesion at the lesion site comprises: For single lesion, record the proximal centerline point LP pro and the distal centerline point LP dis of the lesion, respectively. For diffuse lesions, record the proximal centerline point LP pro and the distal centerline point LP dis of the lesion, respectively. For tandem lesions, first measure the proximal centerline point LP of the entire lesion pro and the distal centerline point LP of the lesion dis Then measure the continuity of the entire lesion to determine whether the tandem lesions are continuous tandem lesions or discontinuous tandem lesions; For consecutive series of lesions, record the proximal centerline point LP pro and the distal centerline point LP dis of the lesions, respectively. For discontinuous series lesions, first record the lesion proximal centerline point LP pro and the lesion distal centerline point LP dis , and then record the lesion proximal centerline point LP pro ′ and the lesion distal centerline point LP dis ′ of each lesion, respectively.

4. The method of measuring and classifying computed tomography flow reserve of claim 3, wherein, For single lesion, diffuse lesion and continuous tandem lesion, the method for determining the measurement range of CT-FFR comprises: The calculation starts with the measurement centerline point MP beg and the end measurement centerline point MP end : MP beg = LP dis + 2 cm wherein the measurement of the centerline point MP beg is based on the centerline point LP dis which is 2 cm distal to the lesion in the longitudinal direction of the coronary artery. MP end = LP dis + 3 cm wherein the end measurement centerline point MP end is 3 cm longitudinally along the coronary artery in the distal direction from the lesion distal centerline point LP dis .

5. The method of measuring and classifying computed tomography flow reserve of claim 3, wherein, For discontinuous tandem lesion, the method for determining the measurement range of CT-FFR comprises: The calculation starts with the measurement centerline point MP beg and the end measurement centerline point MP end : wherein the start measurement centerline point MP beg is the location of the centerline point from which the previous lesion returned to normal vessel diameter; MP end = MP beg + (0.5-1) mm wherein the end measurement centerline point MP end is 0.5mm-1mm longitudinally along the coronary artery in the distal direction of the lesion based on the start measurement centerline point MP beg .

6. The method of measuring and classifying computed tomography flow reserve fraction of claim 4 or 5, wherein, If the lesion distal end is close to the distal end of the coronary artery, the center line point at the position of the lumen diameter of 1.5 mm is taken as the lesion distal end center line point in determining the lesion length at the lesion position, and the center line point at the position of the lumen diameter of 1.5 mm is taken as the end measurement center line point MP in determining the measurement range of the computed tomography flow reserve fraction end : MP end = center line point of 1.5 mm lumen diameter.

7. The method of measuring and classifying computed tomography flow reserve as defined in claim 6, wherein, The method for classifying lesion specificity comprises: When the maximum value of all CT-FFR values in the measurement range is less than or equal to the cutoff value 0.7, the average value of all CT-FFR values in the measurement range is used as the CT-FFR value of the lesion, and the lesion is marked as positive; When the minimum value of all CT-FFR values in the measurement range is greater than or equal to the cutoff value 0.85, the average value of all CT-FFR values in the measurement range is used as the CT-FFR value of the lesion, and the lesion is marked as negative; When the CT-FFR values in the measurement range are distributed between 0.7 and 0.85, a histogram is established according to all CT-FFR values, the category with the highest frequency in the histogram is determined, the average value of the CT-FFR values in the category is calculated, and the average value is compared with the cutoff value: if the average value is less than or equal to 0.7, it is determined as a positive lesion and marked as positive; if the average value is greater than or equal to 0.85, it is determined as a negative lesion and marked as negative; If the average value is greater than 0.7 and less than 0.85, it is determined as a gray area.

8. A system for measuring and classifying computed tomography flow reserve, for implementing the method of measuring and classifying computed tomography flow reserve according to any one of claims 1-7, characterized in that, The system comprises: A lesion type classification module (101) is used to divide the lesion into different types according to the length and calcification and branch involvement of the lesion shown in the CCTA image; A lesion length determination module (102) is used to determine the length of the lesion at the lesion site according to different lesion types; A measurement range determining module (103) is configured to determine a measurement range of CT-FFR according to the lesion length of different lesion types; A CT-FFR value calculating module (104) is configured to calculate the numerical value of CT-FFR within the measurement range; A statistical analysis module (105) is configured to statistically analyze the numerical value of CT-FFR according to the measurement range, and obtain a lesion-specific classification result.

9. An apparatus for measuring and classifying computed tomography flow reserve, characterized by, A computer readable storage medium, having stored therein a program, which, when executed by a processor, implements the method for measuring and classifying CT-FFR according to any one of claims 1-7.

10. A storage medium, characterized by The storage medium has stored therein a program, which, when executed by a processor, implements the method for measuring and classifying CT-FFR according to any one of claims 1-7.

Images