Aortic dissection rupture risk early warning method based on CTA image

Abstract

The invention relates to the technical field of medical data processing, in particular to an aortic dissection rupture risk early warning method based on a CTA image, and the method comprises the steps: determining the blood pressure abnormity trend representation degree corresponding to a target patient according to the systolic pressure distribution condition of the target patient in a preset historical time period, and predicting a possible high pressure time interval; obtaining a CTA image of a target patient, and determining a precursor rupture early warning index, a new rupture spread degree and a blood pressure image correlation degree; and on the basis of the systolic pressure, the overall correlation coefficient and the current CTA image of the target patient in the current period, aortic dissection rupture risk early warning is realized through a pre-trained aortic dissection rupture risk early warning network. When the network is used, the systolic pressure, the overall correlation coefficient and the current CTA image in the current period are combined, so that the richness of network input data is enriched, and the accuracy of aortic dissection rupture risk early warning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a CTA image-based aortic dissection rupture risk warning method. Background Art

[0002] With the development of technology, neural networks are being used more and more widely. For example, they can be used to warn patients about the risk of aortic dissection rupture. Specifically, neural networks are often used to provide early warnings of aortic dissection rupture risk based on CTA (Computed Tomography Angiography) images collected from patients with aortic dissection at the current moment.

[0003] However, when only considering the CTA images of patients with aortic dissection acquired at the current moment and implementing aortic dissection rupture risk warning through neural networks, the following technical problems often arise: The CTA images of patients with aortic dissection collected at the current moment can often only show the appearance of the aortic dissection of the patient at the current moment. However, the risk of aortic dissection rupture is not only related to the appearance of the aortic dissection. Therefore, when performing aortic dissection rupture risk warning, if only the CTA images of patients with aortic dissection collected at the current moment are considered, it often leads to poor richness of the data input into the neural network, thereby resulting in poor accuracy of the aortic dissection rupture risk warning. Summary of the Invention

[0004] In order to solve the technical problem of poor accuracy of aortic dissection rupture risk warning due to poor richness of data input into the neural network, the present invention proposes an aortic dissection rupture risk warning method based on CTA images.

[0005] In a first aspect, the present invention provides a method for early warning of aortic dissection rupture risk based on CTA images, the method comprising: Based on the distribution of systolic blood pressure of the target patient within a preset historical time period, determine the abnormal blood pressure trend expression corresponding to the target patient and predict the possible high blood pressure time interval corresponding to the target patient; Obtain all historical CTA images of the target patient, acquire the current CTA image corresponding to the target patient based on the possible high-pressure time interval in the current cycle, and determine the corresponding precursory rupture warning indicator for the target patient based on the aortic diameter in the current CTA image; Determine the extent of the new rupture corresponding to the target patient based on the difference between the rupture in the current CTA image and the previous CTA image; Based on the precursory rupture warning index, the spread of the new rupture, and the expression of abnormal blood pressure trends, the correlation degree of the blood pressure image corresponding to the current CTA image is determined. Similarly, the correlation degree of the blood pressure image corresponding to the CTA images collected in the past of the target patient is determined. According to the correlation of all blood pressure images, the overall correlation coefficient corresponding to the target patient is determined. Based on the systolic blood pressure, overall correlation coefficient and current CTA image of the target patient in the current cycle period, the aortic dissection rupture risk warning network completed in advance is used to realize the aortic dissection rupture risk warning.

[0006] In conjunction with the first aspect above, in one possible implementation, determining the abnormal blood pressure trend expression level corresponding to the target patient based on the distribution of the target patient's systolic blood pressure within a preset historical time period includes: If the systolic blood pressure of the target patient collected within the preset historical time period is greater than or equal to the preset systolic blood pressure threshold, the collection moment corresponding to the systolic blood pressure is determined as the high pressure moment; Perform period division on the preset historical time period to obtain historical periodic periods, and combine the continuous high-voltage moments within the historical periodic periods into historical high-voltage periods, and obtain a historical high-voltage period set corresponding to each historical periodic period; The total number of all high-pressure moments in the historical period is determined as the representative value of the high-pressure duration corresponding to the historical period, and the average of the representative values of the high-pressure duration corresponding to all historical periods is determined as the stage high-pressure duration value corresponding to the target patient; Determine the recent persistent high-pressure manifestation degree of the target patient corresponding to the historical high-pressure period set corresponding to all historical periodic periods; Determine the persistent high pressure manifestation degree corresponding to the target patient according to the stage high pressure duration value corresponding to the target patient and the recent persistent high pressure manifestation degree during the same period; Determine the high-pressure short-term fluctuation corresponding to the target patient based on a set of historical high-pressure periods corresponding to all historical cycle periods; The abnormal blood pressure trend expression degree corresponding to the target patient is determined based on the persistent high pressure expression degree and the high pressure short-term fluctuation degree corresponding to the target patient.

[0007] In combination with the first aspect above, in a possible implementation, determining the recent persistent high pressure manifestation degree of the target patient in the same period according to the set of historical high pressure periods corresponding to all historical periodic periods includes: Determine the stage corresponding to each historical high-pressure period in the set of historical high-pressure periods corresponding to each historical cycle period as the target stage, and obtain the target stage set corresponding to each historical cycle period; The intersection of the target stage sets corresponding to all historical cycle periods is determined as the recent sustained high-pressure time interval corresponding to the target patient; The union of the target stage sets corresponding to all historical cycle periods is determined as the recent high-pressure occurrence time interval corresponding to the target patient; The recent continuous high pressure manifestation degree of the target patient in the same period is determined according to the duration corresponding to the recent continuous high pressure time interval and the duration corresponding to the recent high pressure occurrence time interval.

[0008] In combination with the first aspect above, in a possible implementation, determining the high-pressure short-term fluctuation corresponding to the target patient based on the set of historical high-pressure periods corresponding to all historical cycle periods includes: All historical high-pressure periods in the historical high-pressure period set corresponding to all historical cycle periods constitute a historical high-pressure period sequence; The mean of all systolic blood pressure values of the target patient collected during each historical high-pressure period is determined as the representative systolic blood pressure value corresponding to each historical high-pressure period; The high pressure short-term fluctuation corresponding to the target patient is determined based on the ratio between the systolic pressure representative values corresponding to adjacent historical high pressure periods in the historical high pressure period sequence and the duration between adjacent historical high pressure periods.

[0009] In conjunction with the first aspect above, in a possible implementation, predicting the possible high-pressure time interval corresponding to the target patient includes: The recent continuous high-pressure time interval corresponding to the target patient is determined as the possible high-pressure time interval corresponding to the target patient.

[0010] In conjunction with the first aspect above, in a possible implementation, acquiring a current CTA image corresponding to the target patient according to a possible high-pressure time interval within the current cycle period includes: If the possible high-pressure time interval is not empty, the CTA image of the target patient acquired at a random moment in the possible high-pressure time interval within the current cycle period is determined as the current CTA image corresponding to the target patient; If the possible high-pressure time interval is empty, the CTA image of the target patient acquired at a random time within the current cycle period is determined as the current CTA image corresponding to the target patient.

[0011] In conjunction with the first aspect above, in one possible implementation, determining the precursory rupture warning indicator corresponding to the target patient based on the aortic diameter in the current CTA image includes: Obtain the aortic diameters corresponding to all historical patients under the preset aortic dissection category to which the target patient belongs; Determine the mean aortic diameter of all historical patients with a preset aortic dissection category as a reference diameter index for the target patient; The precursory rupture warning index corresponding to the target patient is determined based on the aortic diameter in the current CTA image, the reference diameter index corresponding to the target patient, and the preset abnormal aortic diameter threshold.

[0012] In conjunction with the first aspect above, in one possible implementation, determining the extent of the new lesion corresponding to the target patient based on the difference between the lesions in the current CTA image and the lesions in the previously acquired CTA image includes: determining the maximum diameter of each rupture in the current CTA image as a rupture diameter index, and obtaining a rupture diameter index set corresponding to the current CTA image; Determine the cumulative value of all rupture diameter indices in the rupture diameter indicator set corresponding to the current CTA image as the rupture representative diameter corresponding to the current CTA image. Similarly, determine the rupture representative diameter corresponding to the CTA image acquired once before the current CTA image. The extension degree of the new rupture corresponding to the target patient is determined according to the difference between the rupture representative diameter corresponding to the current CTA image and the rupture representative diameter corresponding to the CTA image acquired previously.

[0013] In conjunction with the first aspect above, in one possible implementation, determining the blood pressure image correlation corresponding to the current CTA image based on the precursory rupture warning indicator, the new rupture spread, and the abnormal blood pressure trend expression includes: determining a false lumen expansion index corresponding to the target patient based on a difference between a false lumen cross-sectional area corresponding to the current CTA image and a false lumen cross-sectional area corresponding to a previously acquired CTA image; If a CTA image of the target patient has been acquired before the current CTA image, determining the static risk of acute rupture corresponding to the target patient according to the new rupture spread and false lumen expansion index corresponding to the target patient; If no CTA image of the target patient has been acquired before the current CTA image, the static risk of acute rupture corresponding to the target patient is set to a constant of 0; determining an aortic rupture warning level corresponding to the target patient based on the acute rupture static risk level and precursory rupture warning index corresponding to the target patient; The blood pressure image correlation degree corresponding to the current CTA image is determined according to the aortic rupture warning degree and the blood pressure abnormality trend expression degree corresponding to the target patient.

[0014] In combination with the first aspect above, in a possible implementation, determining the overall correlation coefficient corresponding to the target patient based on the correlation degrees of all blood pressure images includes: If the correlation degree of the blood pressure image corresponding to the acquired CTA image of the target patient is greater than or equal to a preset correlation threshold, the CTA image is determined as the reference CTA image; Determine the total number of all CTA images acquired for the target patient as the representative number of images corresponding to the target patient; The ratio of the number of reference CTA images to the number of representative images is determined as the high correlation coefficient corresponding to the target patient; The overall correlation coefficient corresponding to the target patient is determined according to the blood pressure image correlation degree corresponding to the current CTA image and the high correlation ratio coefficient corresponding to the target patient.

[0015] In a second aspect, the present invention provides a CTA-based aortic dissection rupture risk warning system, the system comprising: The determination and prediction module is used to determine the abnormal blood pressure trend expression corresponding to the target patient based on the distribution of the target patient's systolic blood pressure within a preset historical time period, and predict the possible high blood pressure time interval corresponding to the target patient; An acquisition and determination module is used to acquire all CTA images of the target patient acquired in the past, acquire the current CTA image corresponding to the target patient based on the possible high-pressure time interval in the current cycle, and determine the corresponding precursory rupture warning indicator of the target patient based on the aortic diameter in the current CTA image; A new rupture spread determination module is used to determine the new rupture spread corresponding to the target patient based on the difference between the rupture in the current CTA image and the rupture in the previous CTA image; The blood pressure image correlation determination module is used to determine the blood pressure image correlation corresponding to the current CTA image based on the precursory rupture warning index, the spread of the new rupture, and the expression of the abnormal blood pressure trend. Similarly, it determines the blood pressure image correlation corresponding to the target patient's historical CTA images; The determination and warning module is used to determine the overall correlation coefficient corresponding to the target patient based on the correlation of all blood pressure images, and based on the systolic blood pressure, overall correlation coefficient and current CTA image of the target patient in the current cycle period, realize the aortic dissection rupture risk warning through the pre-trained aortic dissection rupture risk warning network.

[0016] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and execute the executable program code from the memory, so that the device executes the method of the first aspect or any possible implementation of the first aspect.

[0017] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0018] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0019] The present invention has the following beneficial effects: The present invention's aortic dissection rupture risk warning method based on CTA images combines the systolic blood pressure, the overall correlation coefficient, and the current CTA image within the current cycle period when using the network, solving the technical problem of poor accuracy of aortic dissection rupture risk warning due to poor richness of data input to the neural network, thereby enriching the richness of network input data, and further improving the accuracy of aortic dissection rupture risk warning. Specifically, when performing aortic dissection rupture risk warning through a neural network, the present invention not only considers the CTA image, but also considers the patient's systolic blood pressure distribution, and quantifies the overall correlation coefficient that characterizes the overall correlation between the CTA image and the patient's systolic blood pressure, enriching the input data of the aortic dissection rupture risk warning network to a certain extent, thereby improving the risk warning effect of the aortic dissection rupture risk warning network, and further improving the accuracy of the aortic dissection rupture risk warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of a CTA image-based aortic dissection rupture risk warning method of the present invention; Figure 2 This is a schematic diagram of the structure of a CTA-based aortic dissection rupture risk warning system of the present invention; Figure 3 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0022] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0024] Aortic dissection is an extremely serious medical emergency that often poses a serious threat to life. When rupture occurs, patients often experience rapid and severe blood circulation problems, such as acute hemorrhagic shock and multiple organ failure. This condition often occurs quickly and is fatal. Without timely intervention, the mortality rate is extremely high. In recent years, with the development of medical imaging technology, especially computed tomography (CTA) technology, it can provide high-resolution vascular images, which helps to accurately identify the location, size, morphology of aortic dissection and its potential risk of rupture, which has significantly improved the diagnosis and risk assessment methods of aortic dissection.

[0025] When patients have risk factors such as hypertension, the aortic wall will be under continuous pressure, causing damage to the intima and further increasing the risk of aortic dissection rupture. However, the current diagnosis of aortic dissection mainly relies on CTA imaging analysis. Although CTA can provide detailed static imaging information, it has certain limitations. CTA images can only reflect the vascular structure at a fixed moment and cannot perform dynamic blood flow analysis, which limits a comprehensive understanding of the progression of aortic dissection. Especially in the assessment of acute aortic dissection, changes in dynamic blood flow characteristics play a crucial role in judging the evolution of the disease, the risk of rupture, and determining the timing of surgery.

[0026] Therefore, the lack of dynamic monitoring capability makes it difficult for traditional CTA image analysis methods to accurately reflect changes in the disease, resulting in diagnostic results that can only be based on static data, thereby ignoring the complexity and rapid changes of hemodynamic characteristics, which may affect the accuracy of clinical decision-making.

[0027] In addition to considering CTA images, the present invention also considers changes in systolic blood pressure that reflect changes in dynamic blood flow characteristics, and quantifies the overall correlation coefficient that characterizes the overall correlation between CTA images and patients' systolic blood pressure, thereby enriching the richness of network input data and further improving the accuracy of aortic dissection rupture risk warning.

[0028] refer to Figure 1, shows the process of some embodiments of a method for early warning of aortic dissection rupture risk based on CTA images according to the present invention. The method for early warning of aortic dissection rupture risk based on CTA images includes the following steps: Step S1, based on the distribution of the systolic blood pressure of the target patient within a preset historical time period, determine the abnormal blood pressure trend expression corresponding to the target patient, and predict the possible high blood pressure time interval corresponding to the target patient.

[0029] The target patient may be an aortic dissection patient who is seeking an aortic dissection rupture risk warning. Aortic dissection (AD), also known as aortic dissecting aneurysm, is a serious cardiovascular emergency. Aortic dissection occurs when a rupture occurs in the intima of the arterial wall, allowing blood to enter the arterial wall through the rupture, forming a hematoma and further dissecting the intima and media of the aorta. The preset historical time period may be a pre-set historical time period, which may last for one month. The next moment after the end of the preset historical time period may be the start time of the current period. The current period may be the period during which the target patient is scheduled to undergo a CTA (Computed Tomography Angiography) examination, which may last for one day. In this embodiment of the present invention, one day is considered a period. For example, the preset historical time period may be May 2025, and the current period may be June 1, 2025. Systolic blood pressure reflects the contractile function of the left ventricle and the elasticity of the aorta and other large blood vessels. The potentially high-pressure time period may be the time period during which the target patient frequently experiences abnormal blood pressure.

[0030] It should be noted that aortic dissection is often caused by structural abnormalities and hemodynamic abnormalities in the aortic media itself, and patients with hypertension are often at high risk for aortic dissection. When monitoring and analyzing patients' hypertension, systolic blood pressure is the core measurement target. This is because during cardiac contraction, the shear stress on the aortic wall is positively correlated with systolic blood pressure, and fluctuations in systolic blood pressure can cause fatigue damage to the aortic wall, a key factor in inducing acute rupture.

[0031] The risk of aortic dissection rupture is closely related to blood pressure levels. Long-term hypertension can cause continuous pressure on the aortic wall, damage the endothelium and increase the risk of rupture. Therefore, it is possible to consider performing dynamic hemodynamic analysis based on blood for patients with aortic dissection, so as to dynamically collect CTA images based on their performance and conduct further comparative analysis.

[0032] The impact of hypertension on aortic dissection rupture is not only persistent but also fluctuating. This is because persistent high-pressure load often leads to collagen fiber rupture and elastic fiber degeneration in the aortic wall, accelerates atherosclerosis, and makes the endothelium more easily torn. Blood pressure volatility, especially short-term fluctuations, is closely related to the risk of dissection rupture. When blood pressure fluctuates sharply, the shear force changes on the aortic wall are often more significant, which may induce secondary endothelial tearing or false lumen expansion.

[0033] As an example, this step may include the following steps: In the first step, if the systolic blood pressure of the target patient collected within a preset historical time period is greater than or equal to a preset systolic blood pressure threshold, the collection moment corresponding to the systolic blood pressure is determined as the high pressure moment.

[0034] The preset systolic blood pressure threshold may be a pre-set threshold, which may be 140 mmHg.

[0035] It should be noted that the patient's systolic blood pressure can be obtained through a wearable device, such as a smart bracelet.

[0036] The second step is to divide the preset historical time period into periods to obtain historical cycle periods, and to form historical high-pressure periods from the continuous high-pressure moments within the historical cycle periods, and to obtain a set of historical high-pressure periods corresponding to each historical cycle period.

[0037] The historical period can be a period whose duration is equal to the duration of the current period. For example, if the preset historical time period is May 2025, then every day in May 2025 can be recorded as a historical period.

[0038] For example, if there are 10 systolic blood pressure collection moments in a historical cycle period, and these 10 systolic blood pressure collection moments are the first moment, the second moment, the third moment, the fourth moment, the fifth moment, the sixth moment, the seventh moment, the eighth moment, the ninth moment and the tenth moment, and the third moment, the fourth moment, the fifth moment, the seventh moment, the eighth moment, the ninth moment and the tenth moment are high-pressure moments, then there can be two historical high-pressure periods in the historical high-pressure period set corresponding to the historical cycle period, and these two historical high-pressure periods are {the third moment, the fourth moment, the fifth moment} and {the seventh moment, the eighth moment, the ninth moment, the tenth moment}.

[0039] The third step is to determine the total number of all high-pressure moments in the historical cycle period as the representative value of the high-pressure duration corresponding to the historical cycle period, and to determine the average of the representative values of the high-pressure duration corresponding to all historical cycle periods as the stage high-pressure duration value corresponding to the above-mentioned target patient.

[0040] The fourth step is to determine the recent persistent high-pressure manifestation degree of the target patient according to the set of historical high-pressure periods corresponding to all historical periodic periods, which may include the following sub-steps: In the first sub-step, the stage corresponding to each historical high-pressure period in the set of historical high-pressure periods corresponding to each historical cycle period is determined as the target stage, thereby obtaining the target stage set corresponding to each historical cycle period.

[0041] The stage corresponding to the historical high-pressure period can be a stage within the cycle period, which represents a time period within the cycle period. For example, if the start time of a historical high-pressure period is 11:12:02 on May 2, 2025, and the end time of the historical high-pressure period is 11:12:16 on May 2, 2025, then the start time of the stage corresponding to the historical high-pressure period can be 11:12:02, and the start time of the stage corresponding to the historical high-pressure period can be 11:12:16. The number of target stages in the target stage set corresponding to the historical cycle period can be equal to the number of historical high-pressure periods in the historical high-pressure period set corresponding to the historical cycle period.

[0042] In the second sub-step, the intersection of the target stage sets corresponding to all historical cycle periods is determined as the recent continuous high-pressure time interval corresponding to the target patient.

[0043] It should be noted that the recent continuous high-pressure time interval may represent the time when the target patient frequently experiences high pressure in each historical cycle period within a preset historical time period.

[0044] In the third sub-step, the union of the target stage sets corresponding to all historical cycle periods is determined as the recent high-pressure occurrence time interval corresponding to the target patient.

[0045] It should be noted that the recent high-pressure time interval can represent the high-pressure time that the target patient has experienced in different historical cycle periods within a preset historical time period.

[0046] The fourth sub-step is to determine the recent continuous high pressure manifestation degree of the target patient according to the duration corresponding to the recent continuous high pressure time interval and the duration corresponding to the recent high pressure occurrence time interval.

[0047] The fifth step is to determine the persistent high pressure manifestation degree corresponding to the above target patient based on the stage high pressure duration value corresponding to the above target patient and the recent persistent high pressure manifestation degree in the same period.

[0048] For example, the formula for determining the persistent high pressure manifestation corresponding to the target patient can be: ; Among them, xA is the corresponding sustained high pressure manifestation of the target patient. is a normalization function. xB is the high-pressure duration value corresponding to the target patient, that is, the mean of the high-pressure duration representative values corresponding to all historical cycle periods within the preset historical time period. It is the duration of the recent sustained high-pressure time interval corresponding to the target patient. It is the duration of the recent high-pressure time interval corresponding to the target patient. It is a pre-set factor greater than 0, mainly used to prevent the denominator from being 0, which can be 0.0001. It is the recent persistent high pressure manifestation of the target patient in the same period.

[0049] It should be noted that when xB is larger, it often means that the high pressure duration in different historical periods is relatively longer, which often means that there is a greater possibility of sustained high pressure in different historical periods. A larger value indicates that high blood pressure is more likely to occur frequently at the same time in different historical periods, and that high blood pressure is more likely to persist in different historical periods. Therefore, a larger value for xA indicates that the target patient is more likely to have relatively persistent high blood pressure in the preset historical period.

[0050] The sixth step, based on the set of historical high-pressure periods corresponding to all historical cycle periods, determines the high-pressure short-term fluctuation corresponding to the target patient, which may include the following sub-steps: In the first sub-step, all historical high-pressure periods in the historical high-pressure period set corresponding to all historical cycle periods constitute a historical high-pressure period sequence.

[0051] Among them, the historical high-pressure period series can be a time series.

[0052] In the second sub-step, the average of all systolic blood pressures of the target patient collected during each historical high-pressure period is determined as the systolic blood pressure representative value corresponding to each historical high-pressure period.

[0053] The third sub-step is to determine the short-term fluctuation of high pressure corresponding to the target patient based on the ratio between the systolic pressure representative values corresponding to adjacent historical high pressure periods in the historical high pressure period sequence and the duration between adjacent historical high pressure periods.

[0054] For example, the formula for determining the high-pressure short-term fluctuation corresponding to the target patient can be: ; Where D is the short-term fluctuation of high blood pressure corresponding to the target patient. N is the number of historical high blood pressure periods in the historical high blood pressure period sequence. i is the sequence number of the historical high blood pressure period in the historical high blood pressure period sequence. It is the representative value of systolic blood pressure corresponding to the i-th historical high-pressure period in the historical high-pressure period sequence. It is the representative value of systolic blood pressure corresponding to the i+1th historical high pressure period in the historical high pressure period sequence. It is the duration between the i-th historical high-pressure period and the i+1-th historical high-pressure period in the historical high-pressure period sequence, which can be equal to the duration between the latest moment of the i-th historical high-pressure period and the earliest moment of the i+1-th historical high-pressure period. It is a pre-set factor greater than 0, mainly used to prevent the denominator from being 0, which can be 0.0001.

[0055] It should be noted that for adjacent historical high-pressure periods, if the latter is in a higher systolic blood pressure state than the former, it often indicates that a more severe fluctuation growth trend may be present. The larger it is, the more likely the systolic pressure in the i+1th historical high pressure period is to be higher than the systolic pressure in the ith historical high pressure period, which often indicates that the systolic pressure is more likely to show an upward trend. For patients with frequent short-term fluctuations, they often show obvious discontinuity in the patient's historical high pressure period, that is, the smaller the time interval between adjacent historical high pressure periods, the more frequent the short-term fluctuations between adjacent historical high pressure periods. The smaller the value, the more frequent the short-term fluctuations between the i-th historical high pressure period and the i+1-th historical high pressure period. Therefore, when D is larger, it often means that the target patient's systolic blood pressure is more consistent with the short-term frequent fluctuations.

[0056] Step 7: Determine the abnormal blood pressure trend expression degree corresponding to the target patient based on the persistent high pressure expression degree and high pressure short-term fluctuation degree corresponding to the target patient.

[0057] For example, the formula for determining the abnormal blood pressure trend expression degree corresponding to the target patient can be: ; Among them, F is the expression degree of abnormal blood pressure trend corresponding to the target patient. is a normalized function. xA is the sustained high pressure expression corresponding to the target patient. D is the short-term fluctuation of high pressure corresponding to the target patient.

[0058] It should be noted that a larger xA value indicates that the target patient is more likely to have had relatively persistent high blood pressure over the preset historical time period. A larger D value indicates that the target patient's systolic blood pressure is more consistent with short-term, frequent fluctuations. Therefore, a larger F value indicates that the target patient's systolic blood pressure distribution is relatively abnormal.

[0059] In the eighth step, the recent continuous high-pressure time interval corresponding to the target patient is determined as the possible high-pressure time interval corresponding to the target patient.

[0060] Step S2: Obtain all CTA images of the target patient collected historically, collect the current CTA image corresponding to the target patient according to the possible high-pressure time interval in the current cycle period, and determine the precursory rupture warning indicator corresponding to the target patient based on the aortic diameter in the current CTA image.

[0061] It should be noted that the CTA image in the embodiment of the present invention may be a CTA image of aortic dissection.

[0062] As an example, this step may include the following steps: In the first step, if the possible high-pressure time interval is not empty, a CTA image of the target patient acquired at a random moment in the possible high-pressure time interval within the current cycle period is determined as the current CTA image corresponding to the target patient.

[0063] In the second step, if the possible high-pressure time interval is empty, the CTA image of the target patient acquired at a random time within the current cycle period is determined as the current CTA image corresponding to the target patient.

[0064] The third step is to obtain the aortic diameters corresponding to all historical patients under the preset aortic dissection category to which the target patient belongs.

[0065] It should be noted that aortic dissection is primarily classified into two systems: the Stanford and DeBakey classifications, based on the site and extent of involvement. The Stanford classification is further divided into types A and B, while the DeBakey classification is further subdivided into types I, II, and III. Different types of aortic dissection require different treatment strategies. In particular, Stanford types A, DeBakey types I, and II, which involve the ascending aorta, share a common treatment principle of high surgical urgency. Stanford types B and DeBakey types III, however, lack surgical involvement, so their treatment urgency is relatively low. Therefore, aortic dissection can be categorized into two types based on surgical urgency: urgent and less urgent. Urgent types include Stanford types A, DeBakey types I, and II. Less urgent types include Stanford types B and DeBakey types III. Patients with a history of aortic dissection can be considered to have a history of aortic dissection. The historical patients under the preset aortic dissection category may be patients suffering from aortic dissection symptoms of the preset aortic dissection category. The aorta often includes different parts such as a false lumen, an intimal sheet, a true lumen, and a rupture. The method for obtaining the aortic diameter corresponding to the historical patient may be: collecting CTA images of the historical patient, and segmenting the aortic intimal sheet, true and false lumen, and rupture areas of the historical patient by image segmentation technology, so as to obtain segmented images of different parts of the aorta of the historical patient; based on the segmented images of various parts of the aorta of the historical patient, a NURBS surface model may be constructed, and a meshed surface may be generated by the Marching Cubes algorithm, so as to obtain the morphological parameters corresponding to various parts of the aorta of the historical patient, i.e., the aortic diameter (maximum diameter), the false lumen cross-sectional area, etc.

[0066] In the fourth step, the average aortic diameter corresponding to all historical patients under the preset aortic dissection category to which the target patient belongs is determined as the reference diameter index corresponding to the above target patient.

[0067] The fifth step is to determine the precursory rupture warning index corresponding to the target patient based on the aortic diameter in the current CTA image, the reference diameter index corresponding to the target patient, and the preset abnormal aortic diameter threshold.

[0068] The preset abnormal aorta diameter threshold may be a pre-set threshold, which may be 5.5 cm.

[0069] It should be noted that in medicine, an aortic diameter of 5.5 cm is generally regarded as an abnormal standard, so this value is recorded here as the preset abnormal aortic diameter threshold.

[0070] For example, the formula for determining the precursory rupture warning indicator corresponding to the target patient can be: ; Among them, G is the precursory rupture warning indicator corresponding to the target patient. is the normalization function. is the aorta diameter in the current CTA image. is the preset abnormal aortic diameter threshold. H is the reference diameter index corresponding to the target patient.

[0071] It should be noted that when A larger H value indicates a larger aortic diameter at the time of examination, which in turn indicates a higher risk of premonitory rupture. A larger H value indicates a higher likelihood of an emergency-type patient. Therefore, a larger G value indicates a higher risk of premonitory rupture.

[0072] Step S3: determining the extension of the new lesion corresponding to the target patient based on the difference between the lesions in the current CTA image and the lesions in the previously acquired CTA image.

[0073] It should be noted that the CTA image acquired the previous time before the current CTA image may be the CTA image of the target patient acquired the previous time before the current CTA image.

[0074] As an example, this step may include the following steps: In the first step, the maximum diameter of each rupture in the current CTA image is determined as a rupture diameter index, and a set of rupture diameter indices corresponding to the current CTA image is obtained.

[0075] In the second step, the cumulative value of all the rupture diameter indices in the rupture diameter indicator set corresponding to the current CTA image is determined as the rupture representative diameter corresponding to the current CTA image. Similarly, the rupture representative diameter corresponding to the CTA image acquired the previous time is determined.

[0076] It should be noted that the method for obtaining the representative diameter of the rupture corresponding to the CTA image acquired the previous time before the current CTA image may be the same as the method for obtaining the representative diameter of the rupture corresponding to the current CTA image, which will not be described in detail here.

[0077] The third step is to determine the extent of the new rupture corresponding to the target patient based on the difference between the rupture representative diameter corresponding to the current CTA image and the rupture representative diameter corresponding to the previously acquired CTA image.

[0078] For example, the formula for determining the spread of the new rupture corresponding to the target patient can be: ; in, It is the spread of new rupture corresponding to the target patient. is the normalization function. It is the representative diameter of the rupture corresponding to the current CTA image. It is the representative diameter of the rupture corresponding to the CTA image acquired before the current CTA image.

[0079] It should be noted that when The larger it is, the more likely the rupture area of the target patient is to expand, that is, it may spread on the basis of the original rupture, or a new rupture may appear at a different location of the original rupture.

[0080] Step S4: Based on the precursory rupture warning index, the new rupture spread, and the abnormal blood pressure trend expression, the blood pressure image correlation degree corresponding to the current CTA image is determined. Similarly, the blood pressure image correlation degree corresponding to the target patient's historically collected CTA images is determined.

[0081] As an example, this step may include the following steps: In the first step, the false lumen expansion index corresponding to the target patient is determined based on the difference between the false lumen cross-sectional area corresponding to the current CTA image and the false lumen cross-sectional area corresponding to the previously acquired CTA image.

[0082] For example, the formula for determining the false lumen expansion index corresponding to the target patient can be: ; Where h is the false lumen expansion index corresponding to the target patient. is the normalization function. is the false lumen cross-sectional area corresponding to the current CTA image. It is the false lumen cross-sectional area corresponding to the CTA image acquired before the current CTA image.

[0083] It should be noted that, when h is larger, it often indicates that the false lumen area of the target patient is more likely to be expanded.

[0084] In the second step, if a CTA image of the target patient has been acquired before the current CTA image, the formula for determining the static risk of acute rupture of the target patient can be obtained based on the new rupture extension and false lumen expansion index of the target patient: ; Where k is the static risk of acute rupture corresponding to the target patient. is the normalization function. is the new rupture extension corresponding to the target patient. h is the false lumen expansion index corresponding to the target patient.

[0085] It should be noted that when the false lumen of an aortic dissection expands, it is usually accompanied by changes in blood flow pressure, which may lead to uneven stress on the aortic wall, causing the existing tear to further increase, or a new tear to form at the dissection site. At the same time, false lumen expansion may slow blood flow, thereby prompting blood to form thrombi within the false lumen. Thrombosis may also increase false lumen pressure, leading to continuous stress on the false lumen wall, thereby exacerbating the expansion of the tear and worsening the condition. Therefore, increased false lumen expansion and tear propagation often reflect, to a certain extent, the instability of the patient's disease progression. Conversely, if these changes are relatively slow or limited, the condition may be relatively stable and mean that the patient's clinical manifestations are mild, with a lower chance of acute complications. Therefore, when k is larger, it often indicates that the tear area and false lumen area of the target patient are more likely to have expanded, which often indicates that the target patient has a relatively greater risk of acute rupture.

[0086] In the third step, if no CTA image of the target patient has been acquired before the current CTA image, the static risk of acute rupture corresponding to the target patient is set to a constant of 0.

[0087] The fourth step is to determine the aortic rupture warning level corresponding to the target patient according to the acute rupture static risk level and precursory rupture warning index corresponding to the target patient.

[0088] For example, the formula for determining the aortic rupture warning level corresponding to the target patient can be: ; Wherein, Y is the aortic rupture warning level corresponding to the target patient. is a normalized function. G is the precursory rupture warning indicator corresponding to the target patient. k is the static risk of acute rupture corresponding to the target patient.

[0089] It should be noted that a larger G often indicates a higher risk of precursory rupture. A larger k often indicates a higher likelihood of dilation in the target patient's rupture and false lumen areas, which often indicates a higher risk of acute rupture. Therefore, a larger Y often indicates a higher risk of aortic rupture in the target patient.

[0090] The fifth step is to determine the blood pressure image correlation degree corresponding to the current CTA image based on the aortic rupture warning degree and blood pressure abnormality trend expression degree corresponding to the target patient.

[0091] For example, the formula for determining the correlation degree of the blood pressure image corresponding to the current CTA image can be: ; Wherein, P is the correlation degree of the blood pressure image corresponding to the current CTA image. It is an exponential function with a natural constant as its base. is the absolute value function. F is the abnormal blood pressure trend expression level corresponding to the target patient. Y is the aortic rupture warning level corresponding to the target patient.

[0092] It should be noted that a larger F value indicates a more abnormal systolic blood pressure distribution in the target patient. A larger Y value indicates a greater risk of aortic rupture in the target patient. Therefore, a larger P value indicates a closer resemblance between the target patient's abnormal systolic blood pressure and the aortic rupture risk profile shown on the current CTA image. This, to a certain extent, indicates that the current CTA image may have better clarity and, to a certain extent, that the target patient's systolic blood pressure distribution is more valuable for analysis.

[0093] In the sixth step, similarly, the correlation between the target patient's blood pressure images and the CTA images collected historically is determined.

[0094] It should be noted that the method for obtaining the blood pressure image correlation degree corresponding to the historically acquired CTA image of the target patient can be the same as the method for obtaining the blood pressure image correlation degree corresponding to the current CTA image, and will not be repeated here.

[0095] In step S5, the overall correlation coefficient corresponding to the target patient is determined according to the correlation degree of all blood pressure images, and based on the systolic blood pressure, overall correlation coefficient and current CTA image of the target patient in the current cycle period, the aortic dissection rupture risk warning network that has been pre-trained is used to implement the aortic dissection rupture risk warning.

[0096] As an example, this step may include the following steps: In the first step, if the blood pressure image correlation degree corresponding to the CTA image of the target patient is greater than or equal to a preset correlation threshold, the CTA image is determined as the reference CTA image.

[0097] The preset correlation threshold may be a pre-set threshold, which may be 0.6.

[0098] In the second step, the total number of all CTA images collected for the target patient is determined as the representative number of images corresponding to the target patient.

[0099] In the third step, the ratio of the number of reference CTA images to the number of representative images mentioned above is determined as the high correlation coefficient corresponding to the target patients mentioned above.

[0100] The fourth step is to determine the overall correlation coefficient corresponding to the target patient based on the blood pressure image correlation corresponding to the current CTA image and the high correlation ratio coefficient corresponding to the target patient.

[0101] For example, the formula for determining the overall correlation coefficient corresponding to the target patient can be: ; Where W is the overall correlation coefficient corresponding to the target patient. is a normalization function. m is the number of reference CTA images. M is the number of representative images corresponding to the target patient. P is the correlation degree of the blood pressure image corresponding to the current CTA image.

[0102] It should be noted that when P is larger, it often indicates that the abnormal systolic blood pressure of the target patient is more similar to the aortic rupture risk shown by the current CTA image. To a certain extent, it often indicates that the clarity of the current CTA image may be better, and to a certain extent, it indicates that the systolic blood pressure distribution of the target patient is more valuable for analysis. A larger value indicates that more of the target patient's CTA images have a high correlation with the systolic blood pressure distribution. Therefore, a larger value for W indicates that the target patient's systolic blood pressure abnormality is more similar to the aortic rupture risk profile shown on the CTA images. This suggests that the clarity of the target patient's CTA images may be better, and that the target patient's systolic blood pressure distribution is more valuable for analysis.

[0103] The fifth step is to realize aortic dissection rupture risk warning through the pre-trained aortic dissection rupture risk warning network based on the systolic blood pressure of the target patient in the current cycle period, the overall correlation coefficient corresponding to the target patient and the current CTA image.

[0104] Among them, the aortic dissection rupture risk warning network can be a CNN (Convolutional Neural Networks) used for aortic dissection rupture risk warning.

[0105] For example, the training process of an aortic dissection rupture risk warning network may include the following sub-steps: In the first sub-step, a CNN is constructed as a pre-trained aortic dissection rupture risk warning network.

[0106] The second sub-step is to obtain the preset cycle time periods, overall correlation coefficients and current CTA images corresponding to different aortic dissection patients.

[0107] The preset period of time corresponding to the aortic dissection patient may be the period of time during which the aortic dissection patient plans to undergo a CTA examination. For example, the current period of time recorded above is the preset period of time corresponding to the target patient.

[0108] It should be noted that the method for obtaining the overall correlation coefficient and the current CTA image corresponding to the aortic dissection patient can be the same as the method for obtaining the overall correlation coefficient and the current CTA image corresponding to the target patient, and will not be repeated here.

[0109] In the third sub-step, the systolic blood pressure of different aortic dissection patients in their corresponding preset cycle time periods, as well as the overall correlation coefficient and current CTA images corresponding to different aortic dissection patients, are used as training samples of the aortic dissection rupture risk warning network; the aortic dissection rupture risk levels corresponding to different aortic dissection patients are used as training labels of the aortic dissection rupture risk warning network; the aortic dissection rupture risk warning network is trained using the training samples and training labels of the aortic dissection rupture risk warning network to obtain a trained aortic dissection rupture risk warning network.

[0110] It should be noted that the aortic dissection rupture risk level corresponding to a patient with aortic dissection can be the aortic dissection rupture risk level of the patient assessed by a physician. A larger value indicates that the patient is more likely to experience aortic dissection rupture. Furthermore, the aortic dissection rupture risk level output by the trained aortic dissection rupture risk warning network can, to a certain extent, assist physicians in assessing aortic dissection rupture.

[0111] refer to Figure 2 Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a CTA-based aortic dissection rupture risk warning system. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of a CTA-based aortic dissection rupture risk warning method may include: The determination and prediction module 201 is used to determine the abnormal blood pressure trend expression degree corresponding to the target patient based on the distribution of the systolic blood pressure of the target patient within a preset historical time period, and predict the possible high blood pressure time interval corresponding to the target patient; The acquisition and determination module 202 is configured to acquire all historical CTA images of the target patient, acquire a current CTA image corresponding to the target patient based on a possible high-pressure time interval within a current cycle, and determine a precursory rupture warning indicator corresponding to the target patient based on the aortic diameter in the current CTA image; A new lesion extension determination module 203 is configured to determine the new lesion extension corresponding to the target patient based on the difference between the lesions in the current CTA image and the lesions in the previous CTA image; The blood pressure image correlation determination module 204 is configured to determine the blood pressure image correlation corresponding to the current CTA image based on the precursory rupture warning indicator, the new rupture spread, and the abnormal blood pressure trend expression. Similarly, the blood pressure image correlation corresponding to the target patient's historically acquired CTA images is determined. The determination and warning module 205 is used to determine the overall correlation coefficient corresponding to the target patient based on the correlation degree of all blood pressure images, and based on the systolic blood pressure, overall correlation coefficient and current CTA image of the target patient in the current cycle period, realize the aortic dissection rupture risk warning through the pre-trained aortic dissection rupture risk warning network.

[0112] Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the CTA image-based aortic dissection rupture risk warning methods introduced above.

[0113] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, thereby enabling the device to perform any of the above-described CTA-based aortic dissection rupture risk warning methods.

[0114] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, which, when executed on a computer, enables the computer to execute any one of the above-mentioned CTA image-based aortic dissection rupture risk warning methods.

[0115] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned CTA image-based aortic dissection rupture risk warning methods.

[0116] In summary, when performing aortic dissection rupture risk warning through a neural network, the present invention not only considers CTA images, but also considers the patient's systolic blood pressure distribution, and quantifies the overall correlation coefficient that characterizes the overall correlation between CTA images and the patient's systolic blood pressure, which enriches the input data of the aortic dissection rupture risk warning network to a certain extent, thereby improving the risk warning effect of the aortic dissection rupture risk warning network, and further improving the accuracy of the aortic dissection rupture risk warning.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A CTA-based aortic dissection rupture risk warning method, characterized in that: The following steps are involved: Based on the distribution of systolic blood pressure of the target patient within a preset historical time period, determine the abnormal blood pressure trend expression corresponding to the target patient and predict the possible high blood pressure time interval corresponding to the target patient; Obtain all historical CTA images of the target patient, acquire the current CTA image corresponding to the target patient based on the possible high-pressure time interval in the current cycle, and determine the corresponding precursory rupture warning indicator for the target patient based on the aortic diameter in the current CTA image; Determine the extent of the new rupture corresponding to the target patient based on the difference between the rupture in the current CTA image and the previous CTA image; Based on the precursory rupture warning index, the spread of the new rupture, and the expression of abnormal blood pressure trends, the correlation degree of the blood pressure image corresponding to the current CTA image is determined. Similarly, the correlation degree of the blood pressure image corresponding to the CTA images collected in the past of the target patient is determined. According to the correlation of all blood pressure images, the overall correlation coefficient corresponding to the target patient is determined. Based on the systolic blood pressure, overall correlation coefficient and current CTA image of the target patient in the current cycle period, the aortic dissection rupture risk warning network completed in advance is used to realize the aortic dissection rupture risk warning.

2. The CTA-based aortic dissection rupture risk warning method according to claim 1, characterized in that: Determining the abnormal blood pressure trend expression level corresponding to the target patient based on the distribution of the target patient's systolic blood pressure within a preset historical time period includes: If the systolic blood pressure of the target patient collected within the preset historical time period is greater than or equal to the preset systolic blood pressure threshold, the collection moment corresponding to the systolic blood pressure is determined as the high pressure moment; Perform period division on the preset historical time period to obtain historical periodic periods, and combine the continuous high-voltage moments within the historical periodic periods into historical high-voltage periods, and obtain a historical high-voltage period set corresponding to each historical periodic period; The total number of all high-pressure moments in the historical period is determined as the representative value of the high-pressure duration corresponding to the historical period, and the average of the representative values of the high-pressure duration corresponding to all historical periods is determined as the stage high-pressure duration value corresponding to the target patient; Determine the recent persistent high-pressure manifestation degree of the target patient corresponding to the historical high-pressure period set corresponding to all historical periodic periods; Determine the persistent high pressure manifestation degree corresponding to the target patient according to the stage high pressure duration value corresponding to the target patient and the recent persistent high pressure manifestation degree during the same period; Determine the high-pressure short-term fluctuation corresponding to the target patient based on a set of historical high-pressure periods corresponding to all historical cycle periods; The abnormal blood pressure trend expression degree corresponding to the target patient is determined based on the persistent high pressure expression degree and the high pressure short-term fluctuation degree corresponding to the target patient.

3. The CTA-based aortic dissection rupture risk warning method according to claim 2, characterized in that: Determining the recent persistent high-pressure manifestation degree of the target patient corresponding to the historical high-pressure period set corresponding to all historical periodic periods includes: Determine the stage corresponding to each historical high-pressure period in the set of historical high-pressure periods corresponding to each historical cycle period as the target stage, and obtain the target stage set corresponding to each historical cycle period; The intersection of the target stage sets corresponding to all historical cycle periods is determined as the recent sustained high-pressure time interval corresponding to the target patient; The union of the target stage sets corresponding to all historical cycle periods is determined as the recent high-pressure occurrence time interval corresponding to the target patient; The recent continuous high pressure manifestation degree of the target patient in the same period is determined according to the duration corresponding to the recent continuous high pressure time interval and the duration corresponding to the recent high pressure occurrence time interval.

4. The CTA-based aortic dissection rupture risk warning method according to claim 2, characterized in that: Determining the high-pressure short-term fluctuation corresponding to the target patient based on the set of historical high-pressure periods corresponding to all historical cycle periods includes: All historical high-pressure periods in the historical high-pressure period set corresponding to all historical cycle periods constitute a historical high-pressure period sequence; The mean of all systolic blood pressure values of the target patient collected during each historical high-pressure period is determined as the representative systolic blood pressure value corresponding to each historical high-pressure period; The high pressure short-term fluctuation corresponding to the target patient is determined based on the ratio between the systolic pressure representative values corresponding to adjacent historical high pressure periods in the historical high pressure period sequence and the duration between adjacent historical high pressure periods.

5. The CTA-based aortic dissection rupture risk warning method according to claim 3, characterized in that: The predicted possible high-pressure time interval corresponding to the target patient includes: The recent continuous high-pressure time interval corresponding to the target patient is determined as the possible high-pressure time interval corresponding to the target patient.

6. The CTA-based aortic dissection rupture risk warning method according to claim 1, characterized in that: The acquiring of the current CTA image corresponding to the target patient according to the possible high-pressure time interval within the current cycle period includes: If the possible high-pressure time interval is not empty, the CTA image of the target patient acquired at a random moment in the possible high-pressure time interval within the current cycle period is determined as the current CTA image corresponding to the target patient; If the possible high-pressure time interval is empty, the CTA image of the target patient acquired at a random time within the current cycle period is determined as the current CTA image corresponding to the target patient.

7. The CTA-based aortic dissection rupture risk warning method according to claim 1, characterized in that: Determining the precursory rupture warning indicator corresponding to the target patient based on the aortic diameter in the current CTA image includes: Obtain the aortic diameters corresponding to all historical patients under the preset aortic dissection category to which the target patient belongs; Determine the mean aortic diameter of all historical patients with a preset aortic dissection category as a reference diameter index for the target patient; The precursory rupture warning index corresponding to the target patient is determined based on the aortic diameter in the current CTA image, the reference diameter index corresponding to the target patient, and the preset abnormal aortic diameter threshold.

8. The CTA-based aortic dissection rupture risk warning method according to claim 1, characterized in that: Determining the extent of the new rupture corresponding to the target patient based on the difference between the rupture in the current CTA image and the rupture in the previously acquired CTA image includes: determining the maximum diameter of each rupture in the current CTA image as a rupture diameter index, and obtaining a rupture diameter index set corresponding to the current CTA image; Determine the cumulative value of all rupture diameter indices in the rupture diameter indicator set corresponding to the current CTA image as the rupture representative diameter corresponding to the current CTA image. Similarly, determine the rupture representative diameter corresponding to the CTA image acquired once before the current CTA image. The extension degree of the new rupture corresponding to the target patient is determined according to the difference between the rupture representative diameter corresponding to the current CTA image and the rupture representative diameter corresponding to the CTA image acquired previously.

9. The CTA-based aortic dissection rupture risk warning method according to claim 1, characterized in that: Determining the blood pressure image correlation degree corresponding to the current CTA image based on the precursory rupture warning index, the new rupture spread, and the abnormal blood pressure trend expression degree includes: determining a false lumen expansion index corresponding to the target patient based on a difference between a false lumen cross-sectional area corresponding to the current CTA image and a false lumen cross-sectional area corresponding to a previously acquired CTA image; If a CTA image of the target patient has been acquired before the current CTA image, determining the static risk of acute rupture corresponding to the target patient according to the new rupture spread and false lumen expansion index corresponding to the target patient; If no CTA image of the target patient has been acquired before the current CTA image, the static risk of acute rupture corresponding to the target patient is set to a constant of 0; determining an aortic rupture warning level corresponding to the target patient based on the acute rupture static risk level and precursory rupture warning index corresponding to the target patient; The blood pressure image correlation degree corresponding to the current CTA image is determined according to the aortic rupture warning degree and the blood pressure abnormality trend expression degree corresponding to the target patient.

10. The CTA-based aortic dissection rupture risk warning method according to claim 1, characterized in that: Determining the overall correlation coefficient corresponding to the target patient based on the correlation of all blood pressure images includes: If the correlation degree of the blood pressure image corresponding to the acquired CTA image of the target patient is greater than or equal to a preset correlation threshold, the CTA image is determined as the reference CTA image; Determine the total number of all CTA images acquired for the target patient as the representative number of images corresponding to the target patient; The ratio of the number of reference CTA images to the number of representative images is determined as the high correlation coefficient corresponding to the target patient; The overall correlation coefficient corresponding to the target patient is determined according to the blood pressure image correlation degree corresponding to the current CTA image and the high correlation ratio coefficient corresponding to the target patient.

Images