Carotid atherosclerosis image analysis method, system, device and medium based on medical infrared thermal imaging

Abstract

The present invention relates to the field of medical data processing technology, and discloses a method, system, device and medium for analyzing carotid atherosclerosis images based on medical infrared thermal imaging, including: obtaining infrared thermal imaging images of a target population; segmenting the infrared thermal imaging images of the target population into regions of interest, obtaining multiple regions of interest and temperature index data corresponding to the multiple regions of interest; preprocessing the temperature index data corresponding to the multiple regions of interest; based on the preprocessed temperature index data, using the minimum absolute shrinkage and selection operator regression method, screening to obtain the optimal temperature index, which is used to establish a regression analysis model of the optimal temperature index to measure the probability of carotid atherosclerosis of the subject to be tested. The present invention can identify the physiological and pathological state of the carotid artery through the temperature data characteristics of infrared thermal imaging, is stable, efficient, safe, economical, and contactless, and has broad application prospects in the field of carotid atherosclerosis research.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a method, system, device and medium for analyzing carotid atherosclerosis images based on medical infrared thermal imaging. Background Art

[0002] Carotid atherosclerosis (CAS) is the pathological stage of atherosclerosis involving one or both carotid arteries, which is mainly manifested by thickening of the carotid intima-media layer, plaque formation, stenosis or occlusion, which poses a great threat to the blood supply to the brain and may lead to ischemic stroke. Studies have shown that about one-third of the population in my country has carotid atherosclerotic plaques, but they are often not discovered until there are clinical symptoms or sudden cardiovascular and cerebrovascular events. Therefore, early detection of abnormal signals of the carotid artery and identification of the pathological state of the carotid artery are of great significance for the prevention and treatment of cardiovascular and cerebrovascular diseases.

[0003] At present, the detection methods of carotid atherosclerosis are mainly based on imaging technology, including transcranial Doppler (TCD), computed tomography angiography (CTA), magnetic resonance angiography (MRA), digital subtraction angiography (DSA), carotid Doppler ultrasound, etc. However, these methods often have the risk of trauma and complications, or produce artifacts that lead to poor component display and inaccurate test results. Carotid color Doppler ultrasound is the most commonly used method for clinical examination of carotid atherosclerosis, which is relatively safe and reliable, but ultrasound examination is contact-based, depends on the level of the examiner, and has poor display of intracranial blood vessels. Therefore, how to perform early identification and screening of carotid atherosclerosis through safe, reliable, simple, fast, non-invasive and non-contact intuitive signs is a problem that needs to be solved in clinical practice.

[0004] Therefore, a new method for analyzing carotid atherosclerosis is urgently needed to assist in timely detection of abnormalities in the carotid artery. Summary of the invention

[0005] The present invention provides a method, system, device and medium for analyzing carotid atherosclerosis images based on medical infrared thermal imaging, so as to solve the defects of existing carotid atherosclerosis detection methods, such as the risk of trauma and complications, or the generation of artifacts leading to poor component display and inaccurate detection results.

[0006] The present invention provides a method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging, comprising:

[0007] Acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0008] Perform region of interest segmentation on the infrared thermal imaging image of the target population to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0009] Preprocessing the temperature index data corresponding to multiple areas of interest;

[0010] According to the preprocessed temperature index data, the optimal temperature index is screened and obtained by using the least absolute shrinkage and selection operator (LASSO) regression method, which is used to establish a regression analysis model for the optimal temperature index.

[0011] In one embodiment, the segmentation of the infrared thermal imaging image of the target population into regions of interest to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest includes:

[0012] In the infrared thermal imaging images of the target population, the anterior axillary ridge head, acromioclavicular joint, neck-shoulder intersection, neck-cheek intersection, sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour are obtained according to the calibrated image local anatomical sites;

[0013] According to the obtained axillary ridge head, acromioclavicular joint, neck-shoulder intersection, neck-cheek intersection, sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour, the infrared thermal imaging image is segmented into regions of interest, and the neck of the target population is segmented into three regions, recorded as region I, region II, and region III; the chest of the target population is segmented into five regions, recorded as region α, region β, region γ, region δ, and region ε, and the overall region of region Ⅰ, region Ⅱ, region Ⅲ, region α, region β, region γ, region δ, and region ε is segmented from the infrared thermal imaging image and recorded as region 9;

[0014] Acquire temperature index data of area I, area II, area III, area α, area β, area γ, area δ, area ε, and area 9 from the infrared thermal imaging image, wherein the temperature index data includes the maximum temperature value, the minimum temperature value, and the average temperature value of the area;

[0015] The area formed by the anterior axillary ridge head and the acromioclavicular joint in the infrared thermal imaging image is taken as the temperature reference area, and the regional temperature average value data of the temperature reference area is obtained from the infrared thermal imaging image.

[0016] In one embodiment, the preprocessing of the temperature index data corresponding to the multiple regions of interest includes:

[0017] According to the regional temperature maximum value data and regional temperature minimum value data of each region of interest in a plurality of regions of interest (including region I, region II, region III, region α, region β, region γ, region δ, region ε, and region 9), the temperature span index data of each region of interest is obtained;

[0018] According to the regional temperature average data of each area of ​​interest and the regional temperature average data of the temperature reference area, the corrected average temperature index data of each area of ​​interest is obtained;

[0019] According to the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone I and the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone III, the left and right neck temperature span index data are obtained.

[0020] In one embodiment, obtaining the temperature span index data of each region of interest according to the regional temperature maximum value data and the regional temperature minimum value data of each region of interest among the multiple regions of interest includes:

[0021] According to the regional temperature maximum value data and the regional temperature minimum value data of each region of interest among the multiple regions of interest, the temperature span index data of each region of interest is obtained by using the first expression, wherein the first expression is:

[0022] ΔT=T max -T min

[0023] In the first expression, ΔT represents the temperature span index data of the area of ​​interest, T max Represents the regional temperature maximum data of the area of ​​interest, T min Represents regional temperature minimum data for the area of ​​interest.

[0024] In one embodiment, obtaining the corrected average temperature index data of each region of interest based on the regional temperature average data of each region of interest and the regional temperature average data of the temperature reference region includes:

[0025] According to the regional temperature average data of each region of interest and the regional temperature average data of the temperature reference region, the corrected average temperature index data of each region of interest is obtained using the second expression, wherein the second expression is:

[0026] aveΔT=T ave -T stdave

[0027] In the second expression, aveΔT represents the corrected average temperature index data of the region of interest, T ave Represents the regional temperature average data of the area of ​​interest, T stdave Indicates the regional temperature average data for the temperature reference area.

[0028] In one embodiment, the left and right neck temperature span index data include maximum left and right neck temperature span index data, minimum left and right neck temperature span index data, and average left and right neck temperature span index data;

[0029] The temperature span index data of the left and right necks are obtained according to the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone I and the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone III, including:

[0030] According to the regional temperature maximum value data of zone I and the regional temperature maximum value data of zone III, the maximum left and right neck temperature span index data is obtained by using the third expression;

[0031] According to the regional temperature minimum value data of zone I and the regional temperature minimum value data of zone III, the minimum left and right neck temperature span index data is obtained by using the fourth expression;

[0032] According to the regional temperature average value data of zone I and the regional temperature average value data of zone III, the average left and right neck temperature span index data is obtained by using the fifth expression;

[0033] Among them, the third expression is:

[0034] ΔT max =|T max IT max III|

[0035] In the third expression, ΔT max Indicates the maximum left and right neck temperature span index data, T max I represents the maximum temperature data of the area in zone I, T max III represents the regional temperature maximum value data of zone III;

[0036] The fourth expression is:

[0037] ΔT min =|T min IT min III|

[0038] In the fourth expression, ΔT min Indicates the minimum left and right neck temperature span index data, T min I represents the minimum temperature data of zone I, Tmin III represents the regional temperature minimum data of zone III;

[0039] The fifth expression is:

[0040] ΔT ave =|T ave IT ave III|

[0041] In the fifth expression, ΔT ave Indicates the average left and right neck temperature span index data, T ave I represents the average temperature data of the region I, T ave III represents the regional temperature average data of Zone III.

[0042] In this way, the temperature index data of 9 areas of interest can be obtained.

[0043] In one embodiment, the preprocessing of the temperature index data corresponding to the multiple regions of interest further includes:

[0044] The temperature span index data and corrected mean temperature index data of each region of interest and the temperature span index data of the left and right necks were subjected to Z-score standardization.

[0045] In one embodiment, the method of screening out the optimal temperature index based on the preprocessed temperature index data by using the minimum absolute shrinkage and selection operator regression method to establish a regression analysis model of the optimal temperature index includes:

[0046] According to the temperature span index data and corrected average temperature index data of each region of interest and the temperature span index data of the left and right necks, the optimal temperature index is screened out using the minimum absolute shrinkage and selection operator regression method, where the optimal temperature index includes the minimum regional temperature value of region 9 and the average regional temperature value of region III.

[0047] In one embodiment, it also includes:

[0048] The temperature span index data and corrected average temperature index data of each region of interest and the temperature span index data of the left and right necks were subjected to the Shapiro-Wilk test for normality, the data that conformed to the normal distribution were subjected to the Student's t test, and the data that did not conform to the normal distribution were subjected to the Mann-Whitney U test to obtain the temperature index data.

[0049] The present invention also provides a carotid atherosclerosis image analysis system based on medical infrared thermal imaging, comprising:

[0050] An image acquisition module is used to: acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0051] The region of interest segmentation module is used to segment the infrared thermal imaging image of the target population into regions of interest to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0052] A data preprocessing module is used to: preprocess the temperature index data corresponding to multiple areas of interest;

[0053] The regression analysis module is used to: screen out the optimal temperature index based on the pre-processed temperature index data by using the minimum absolute shrinkage and selection operator regression method, and to establish a regression analysis model for the optimal temperature index.

[0054] The present invention also provides a carotid atherosclerosis probability prediction model based on medical infrared thermal imaging, which is established by performing multi-factor Logistic regression analysis based on the optimal temperature index obtained by any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging.

[0055] Furthermore, a nomogram can be drawn based on the carotid atherosclerosis probability prediction model based on medical infrared thermal imaging to assist in the diagnosis of carotid atherosclerosis. The nomogram is a concrete embodiment of the carotid atherosclerosis probability prediction model based on medical infrared thermal imaging. The optimal temperature index data of the subject to be tested can be put into the nomogram to obtain the probability of carotid atherosclerosis of the subject to be tested.

[0056] The present invention also provides a carotid atherosclerosis probability prediction system based on medical infrared thermal imaging, comprising:

[0057] A data receiving module, used to: receive optimal temperature index data of a subject to be tested, wherein the optimal temperature index data is data corresponding to the optimal temperature index obtained according to any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging;

[0058] The prediction module is used to obtain the probability of carotid atherosclerosis of the subject according to the optimal temperature index data of the subject, through a regression analysis model constructed based on the optimal temperature index obtained by any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging.

[0059] In the present invention, the subject may be an individual suspected of having carotid atherosclerosis or a healthy individual who needs to monitor the formation of carotid atherosclerosis.

[0060] The present invention also provides an electronic device, comprising a processor and a memory storing a computer program, wherein the processor implements any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging when executing the computer program.

[0061] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging.

[0062] The present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging.

[0063] The present invention provides a method, system, device and medium for analyzing carotid atherosclerosis images based on medical infrared thermal imaging. The method performs region of interest segmentation on infrared thermal imaging images of a group of patients with carotid atherosclerosis, pre-processes temperature index data corresponding to multiple regions of interest, and uses the minimum absolute shrinkage and selection operator regression method to screen out the optimal temperature index, which is used to establish a regression analysis model for the optimal temperature index. The present invention can identify the physiological and pathological state of the carotid artery through the temperature data characteristics of infrared thermal imaging. The method is stable, efficient, safe, economical and contactless, and has broad application prospects in the field of carotid atherosclerosis research. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic flow chart of a method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging provided by the present invention.

[0066] Figure 2 Schematic diagram of human infrared thermal imaging image segmentation of carotid atherosclerosis based on medical infrared thermal imaging.

[0067] Figure 3 Convergence plot of coefficients for LASSO regression screening variables, Figure 3The horizontal axis of the left figure is logλ, and the vertical axis is the coefficient. The horizontal axis of the right figure is Iogλ, and the vertical axis is the binomial anomaly. Select the λ value corresponding to the coefficient that converges to 0 the latest and the smallest feature and error.

[0068] Figure 4 The middle left picture is the nomogram of the Logistic regression analysis model. Figure 4 The middle right figure is a schematic diagram of the ROC curve (ROC Curve), with the horizontal axis being 1-specificity (1-Specificity) and the vertical axis being sensitivity (Sensitivity).

[0069] Figure 5 A structural schematic diagram of a carotid atherosclerosis image analysis system based on medical infrared thermal imaging provided by the present invention.

[0070] Figure 6 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments, and they should not be understood as limitations on the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0072] Combine the following Figure 1-Figure 6 The present invention describes a method, system, device and medium for analyzing carotid atherosclerosis images based on medical infrared thermal imaging.

[0073] Figure 1 The figure is a flow chart of the method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging provided by the present invention. Figure 1 The present invention provides a method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging, which may include:

[0074] Step S110, obtaining an infrared thermal imaging image of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0075] Step S120, performing region of interest segmentation on the infrared thermal imaging image of the target population to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0076] Step S130, preprocessing the temperature index data corresponding to the multiple regions of interest;

[0077] Step S140: According to the preprocessed temperature index data, the optimal temperature index is screened and obtained by using the minimum absolute shrinkage and selection operator regression method, and used to establish a regression analysis model of the optimal temperature index.

[0078] Infrared thermography (IRT) is a technology that receives infrared thermal signals and outputs visual temperature images after calculation. Its application in the medical field is becoming more and more profound due to its non-contact, high stability, and convenient and safe operability. Infrared thermal imaging uses high-precision temperature and image spatial resolution to sensitively capture infrared radiation emitted by various parts of the human body, locate areas with abnormal temperatures, and thus infer the energy metabolism state of subcutaneous tissue, blood circulation, and internal organs. It can provide support and reference ideas for auxiliary screening diagnosis and efficacy evaluation of various diseases. Infrared thermal imaging is increasingly widely used in the blood circulation system. By capturing and analyzing the thermal data characteristics of body surface temperature, it has great potential in identifying the physiological and pathological states of the circulatory system.

[0079] In one embodiment, medical staff can take infrared thermal imaging images of the target population. The specific shooting conditions are: using the HIR-2000A infrared thermal imaging diagnostic system produced by Beijing Yuetian Optoelectronics Technology Co., Ltd., with a temperature resolution of 0.025°C, a temperature measurement range of 0 to 100°C, a temperature in the detection cabin of 22°C, and a relative humidity of 55. The target population enters the detection cabin 15 minutes before the detection and waits to adapt to the environment. During the detection, a standing posture is taken, and the measurement distance is 2.5 meters. Each person takes a frontal full-body image to obtain an infrared thermal imaging image of the target population. Alternatively, step S110 can also obtain infrared thermal imaging images of the target population that meet the requirements from an open source medical database.

[0080] Specifically, this example recruited subjects at the Health Management Center of the International Department of Dongzhimen Hospital of Beijing University of Chinese Medicine and the Beijing Traditional Chinese Medicine Visualization Joint Innovation Center. This example included 30 patients with carotid atherosclerosis and 45 healthy volunteers, and all patients and healthy volunteers signed informed consent forms.

[0081] Inclusion criteria for patients with carotid atherosclerosis: carotid ultrasound meets the diagnostic criteria for carotid atherosclerosis; can stand alone and cooperate with the examination requirements; 18 years old ≤ age ≤ 80 years old. Inclusion criteria for healthy volunteers: healthy physical examination subjects with no history of chronic diseases; can stand alone and cooperate with the examination requirements; 18 years old ≤ age ≤ 80 years old. Exclusion criteria for subjects: pregnant or lactating women; patients with serious cardiovascular, pulmonary, liver, kidney and hematopoietic system diseases or severe organic epilepsy and mental illness; alcoholics and (or) psychoactive substances, drug abusers and addicts; those who cannot stand alone and cooperate with the examination requirements; those with acute furuncle, acne or large-area trauma and surgical scars on the head and neck.

[0082] Infrared thermal imaging images were collected for each subject. The HIR-2000A infrared thermal imaging diagnostic system produced by Beijing Yuetian Optoelectronics Technology Co., Ltd. was used, with a temperature resolution of 0.025°C, a temperature measurement range of 0-100°C, a temperature in the test chamber of 22°C, and a relative humidity of 55. The subjects entered the test chamber 15 minutes before the test and waited to adapt to the environment. The test was performed in a standing position with a measurement distance of 2.5 meters. Each patient had a full-body frontal image taken, and temperature data was extracted from the infrared thermal imaging images obtained.

[0083] By comparing the temperature index data of healthy volunteers with that of patients with carotid atherosclerosis, statistical differences can be obtained, which proves the rationality and effectiveness of the segmentation of the neck region of interest.

[0084] In one embodiment, step S120 includes:

[0085] In the infrared thermal imaging images of the target population, according to the calibrated image local anatomical sites, the anterior axillary ridge head (A, B), acromioclavicular joint (C, D), neck-shoulder intersection (E, F), neck-cheek intersection (G, H), sternoclavicular joint (J, K), and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour (L, M) are obtained. For details, refer to Figure 2 In this embodiment, the infrared thermal imaging image of each subject is segmented by the nine-point method, that is, the region of interest is segmented by mapping the carotid artery and related blood vessels;

[0086] According to the obtained axillary ridge head, acromioclavicular joint, neck-shoulder intersection, neck-cheek intersection, sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour, the infrared thermal imaging image is segmented into regions of interest, and the neck of the target population is segmented into three regions, which are recorded as region I, region II, and region III from right to left according to the anatomical position; the chest of the target population is segmented into five regions, which are recorded as region α, region β, region γ, region δ, and region ε from right to left according to the anatomical position, and the general region of region I, region II, region III, region α, region β, region γ, region δ, and region ε is segmented from the infrared thermal imaging image and recorded as region 9;

[0087] Acquire temperature index data of area I, area II, area III, area α, area β, area γ, area δ, area ε, and area 9 from the infrared thermal imaging image, wherein the temperature index data includes the maximum temperature value, the minimum temperature value, and the average temperature value of the area;

[0088] Considering the temperature differences due to seasons and individuals, the chest area of ​​interest of the target group is taken as the temperature reference area. Specifically, the area formed by the axillary ridge head and the acromioclavicular joint in the infrared thermal imaging image is taken as the temperature reference area, and the regional temperature average value data of the temperature reference area is obtained from the infrared thermal imaging image.

[0089] The human physiological and pathological basis for the nine-point division of the region of interest is as follows: In the neck, the common carotid artery is the main artery of the head and neck, one on each side. The left common carotid artery originates from the aortic arch, and the right common carotid artery originates from the brachiocephalic trunk. Both pass behind the sternoclavicular joint, rise along the esophagus, trachea, and both sides of the larynx, and divide into the internal carotid artery and the external carotid artery at the level of the upper edge of the thyroid cartilage. The internal carotid artery has no branches in the neck, and enters the cranial cavity through the carotid canal at the base of the skull, and its branches are distributed in the brain and visual organs. After the external carotid artery is issued from the common carotid artery, it first passes to the inside of the internal carotid artery, then crosses from the front to the outside, and ascends through the parotid gland to the mandibular neck. The projection of the common carotid artery and the external carotid artery on the body surface is: the midpoint of the line connecting the mandibular angle and the mastoid to the line connecting the sternoclavicular joint. With the upper edge of the thyroid cartilage as the boundary, the common carotid artery is below and the external carotid artery is above. Therefore, Zone I and Zone III accurately include the flow range of the carotid artery, and can timely and accurately reflect the state of carotid artery lesions through the temperature of the skin surface after the common carotid artery lesions. Zone II includes a variety of tissues and organs such as the trachea, larynx, esophagus, and thyroid gland, which greatly interfere with the diagnosis of the carotid artery. In the chest, the upper left point of the heart is projected on the surface of the body as the lower edge of the second costal cartilage on the left, 1.2 cm from the left edge of the sternum; the upper right point is projected on the surface of the body as the upper edge of the third costal cartilage on the right, 1.0 cm from the right edge of the sternum. Its projection falls within the γ zone; the left common carotid artery and the left subclavian artery both originate from the aortic arch, and the right common carotid artery and the right subclavian artery both originate from the brachiocephalic trunk. The left subclavian artery and the right subclavian artery, respectively, pass through the back of the sternoclavicular joint obliquely outward to the root of the neck, and pass through the front of the pleural top in an arched shape. Its projection on the surface is a convex upward arc from the sternoclavicular joint to the midpoint of the clavicle, with the highest point at 1.2 cm above the upper edge of the clavicle. Zone δ and zone β respectively include the areas where the left and right subclavian arteries flow through the surface of the body; the subclavian artery passes through the scalene muscle gap and changes to the axillary artery at the outer edge of the first rib. The axillary artery descends deep in the axilla, and the α and ε zones include the axillary artery's flow path.

[0090] In one embodiment, step S130 includes:

[0091] According to the regional temperature maximum value data and the regional temperature minimum value data of each region of interest among the multiple regions of interest, the temperature span index data of each region of interest is obtained by using the first expression, wherein the first expression is:

[0092] ΔT=T max -T min

[0093] In the first expression, ΔT represents the temperature span index data of the area of ​​interest, T max Represents the regional temperature maximum data of the area of ​​interest, T min Represents the regional temperature minimum data of the area of ​​interest;

[0094] According to the regional temperature average data of each region of interest and the regional temperature average data of the temperature reference region, the corrected average temperature index data of each region of interest is obtained using the second expression, wherein the second expression is:

[0095] aveΔT=T ave -T stdave

[0096] In the second expression, aveΔT represents the corrected average temperature index data of the region of interest, T ave Represents the regional temperature average data of the area of ​​interest, T stdave Represents the regional temperature average data of the temperature reference area;

[0097] According to the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone I and the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone III, the left and right neck temperature span index data are obtained by using the third expression, the fourth expression, and the fifth expression, wherein the left and right neck temperature span index data include the maximum left and right neck temperature span index data, the minimum left and right neck temperature span index data, and the average left and right neck temperature span index data, wherein the third expression is:

[0098] ΔT max =|T max IT max III|

[0099] In the third expression, ΔT max Indicates the maximum left and right neck temperature span index data, T max I represents the maximum temperature data of the area in zone I, T max III represents the maximum temperature data of the region III,

[0100] The fourth expression is:

[0101] ΔT min =|T min IT min III|

[0102] In the fourth expression, ΔT min Indicates the minimum left and right neck temperature span index data, T min I represents the minimum temperature data of zone I, T min III represents the regional temperature minimum data of zone III,

[0103] The fifth expression is:

[0104] ΔT ave =|T ave IT ave III|

[0105] In the fifth expression, ΔT ave Indicates the average left and right neck temperature span index data, T ave I represents the average temperature data of the region I, T ave III represents the regional temperature average data of Zone III.

[0106] In this way, the temperature index data of 9 areas of interest can be obtained, and then the temperature index screening is performed based on the temperature index data of the 9 areas of interest.

[0107] In one embodiment, step S130 further includes:

[0108] The temperature span index data and corrected average temperature index data of each region of interest and the temperature span index data of the left and right necks are subjected to Z-score standardization processing, wherein the expression of Z-score standardization processing is:

[0109] New data = (original data - mean) / standard deviation.

[0110] In one embodiment, step S140 includes:

[0111] According to the temperature span index data and corrected average temperature index data of each region of interest and the temperature span index data of the left and right necks, the optimal temperature index is screened out using the minimum absolute shrinkage and selection operator regression method, where the optimal temperature index includes the minimum regional temperature value of region 9 and the average regional temperature value of region III.

[0112] Furthermore, a multi-factor Logistic regression analysis can be performed based on the optimal temperature index, a regression analysis model of the optimal temperature index can be established, and a nomogram can be drawn to assist in the diagnosis of carotid atherosclerosis.

[0113] For details, see Figure 3-4In step S140, LASSO regression can be performed using the glmnet package in R 4.3.1 software, with the parameters set to alpha = 1, nlambda = 1000, to screen the optimal temperature index. The convergence diagram of the LASSO regression screening variable coefficient is shown in Figure 3 Finally, the optimal temperature index is selected as: the minimum temperature of area 9 and the average temperature of area III. Then, multi-factor Logistic regression analysis is performed on the optimal temperature index, and a regression analysis model based on the optimal temperature index is established. The nomogram is drawn as follows: Figure 4 As shown in the figure, the corresponding points (Points) correspond to the selected indicator values, and the points are added up to get the total points (Total points). The probability value corresponding to the total points is the probability value of carotid atherosclerosis obtained in the Logistic regression analysis model, and the ROC curve is drawn to evaluate the effectiveness of the model.

[0114] LASSO regression is a variable screening method used to deal with overfitting and multicollinearity problems. It screens variables by continuously reducing coefficients, obtains more concise model variable references, and improves the generalization ability of the model. The parameter setting alpha = 1, the penalty strength nlambda = 1000, and the coefficient convergence diagram of the variable is obtained. Each curve represents the coefficient change trend of each variable. As the lambda value changes, the variables whose coefficients are compressed to 0 later are considered to be preferred variables. Select lambda.1se to obtain the simplest model variable within the minimum target parameter mean variance range, and screen the optimal temperature index.

[0115] A multi-factor Logistic regression analysis was performed for the optimal temperature index. Logistic regression analysis is used to analyze binary variables, form a nonlinear statistical model through the Logistic function, estimate the probability P of an event, and finally establish a regression analysis model based on the optimal temperature index, draw a nomogram, and obtain the regression analysis model formula as follows:

[0116]

[0117] When the regression analysis model is used to predict the probability of carotid atherosclerosis, the minimum regional temperature value of area 9 and the average regional temperature value of area III of the subject are directly input into the regression analysis model to obtain the probability of carotid atherosclerosis of the subject.

[0118] According to the data of the corresponding optimal temperature index of 30 patients with carotid atherosclerosis and 45 healthy volunteers in the embodiment and the probability of carotid atherosclerosis predicted by the regression analysis model, the ROC curve is drawn as shown in Figure 4As shown in the figure, the ROC curve is used to show the evaluation effect of the binary classifier and evaluate the formed Logistic regression analysis model. The sensitivity of the regression analysis model is 83.3%, the specificity is 86.7%, and the area under the ROC curve AUC value is 0.853 (95% CI: 0.758-0.949). It can be concluded that the model has a good evaluation effect for the infrared thermal imaging evaluation of carotid atherosclerosis.

[0119] In one embodiment, the method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging provided by the present invention further includes step S150:

[0120] The Shapiro-Wilk normality test was performed on the temperature span index data and the corrected average temperature index data of each area of ​​interest, as well as the temperature span index data of the left and right necks. The t test was performed on the data that conformed to the normal distribution, and the Mann-Whitney U test was performed on the data that did not conform to the normal distribution to obtain the temperature index data.

[0121] In this embodiment, the temperature span index data after standardization, the corrected average temperature index data, and the temperature span index data of the left and right necks are subjected to a Shapiro-Wilk normality test, the data that conform to the normal distribution are subjected to a t test, and the data that do not conform to the normal distribution are subjected to a Mann-Whitney U test. The obtained temperature index data are shown in Table 1 below, wherein the data format in the table is mean ± standard deviation, and the "*" indicator indicates that there is a significant difference between the data of patients with carotid atherosclerosis and healthy volunteers (P < 0.05), indicating that the carotid atherosclerosis image analysis method based on medical infrared thermal imaging provided by the present invention has good interpretability, and the method can be used for technology promotion and data verification in the field.

[0122] Table 1 Standardized temperature index data

[0123]

[0124]

[0125] The carotid atherosclerosis image analysis method based on medical infrared thermal imaging provided by the present invention performs region of interest segmentation on infrared thermal imaging images of a group of carotid atherosclerosis patients, pre-processes temperature index data corresponding to multiple regions of interest, and uses the minimum absolute shrinkage and selection operator regression method to screen out the optimal temperature index for establishing a regression analysis model of the optimal temperature index. The present invention can identify the physiological and pathological state of the carotid artery through the temperature data characteristics of infrared thermal imaging, and the established regression analysis model of the optimal temperature index can be used to assist in the diagnosis of carotid atherosclerosis patients. The method is stable, efficient, safe, economical, and contactless, and has broad application prospects in the field of carotid atherosclerosis research.

[0126] The following is a description of the carotid atherosclerosis image analysis system based on medical infrared thermal imaging provided by the present invention. The carotid atherosclerosis image analysis system based on medical infrared thermal imaging described below and the carotid atherosclerosis image analysis method based on medical infrared thermal imaging described above can be referenced to each other.

[0127] Reference Figure 5 The present invention provides a carotid atherosclerosis image analysis system based on medical infrared thermal imaging, which may include:

[0128] An image acquisition module is used to: acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0129] The region of interest segmentation module is used to segment the infrared thermal imaging image of the target population into regions of interest to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0130] A data preprocessing module is used to: preprocess the temperature index data corresponding to multiple areas of interest;

[0131] The regression analysis module is used to: screen out the optimal temperature index based on the pre-processed temperature index data by using the minimum absolute shrinkage and selection operator regression method, and to establish a regression analysis model for the optimal temperature index.

[0132] In one embodiment, the region of interest partitioning module includes:

[0133] The positioning submodule is used to obtain the intersection of the axillary crest, the acromioclavicular joint, the neck-shoulder intersection, the neck-cheek intersection, the sternoclavicular joint, and the vertical line in the sternoclavicular joint plane with the facial contour in the infrared thermal imaging image of the target population according to the calibrated image local anatomical sites;

[0134] The segmentation submodule is used to: segment the infrared thermal imaging image into regions of interest according to the identified axillary crest, acromioclavicular joint, neck-shoulder intersection, neck-cheek intersection, sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour, and segment the neck of the target population into three regions, recorded as region I, region II, and region III; segment the chest of the target population into five regions, recorded as region α, region β, region γ, region δ, and region ε; segment the overall region of region Ⅰ, region Ⅱ, region Ⅲ, region α, region β, region γ, region δ, and region ε from the infrared thermal imaging image, recorded as region 9;

[0135] The data acquisition submodule is used to obtain the temperature index data of area I, area II, area III, area α, area β, area γ, area δ, area ε, and area 9 from the infrared thermal imaging image, wherein the temperature index data includes the maximum temperature of the area, the minimum temperature of the area, and the average temperature of the area;

[0136] The reference extraction submodule is used to: take the area formed by the axillary anterior ridge head and the acromioclavicular joint in the infrared thermal imaging image as the temperature reference area, and obtain the regional temperature average value data of the temperature reference area from the infrared thermal imaging image.

[0137] In one embodiment, the data preprocessing module includes:

[0138] The first preprocessing submodule is used to obtain temperature span index data of each region of interest according to the regional temperature maximum value data and the regional temperature minimum value data of each region of interest among the multiple regions of interest;

[0139] The second preprocessing submodule is used to obtain corrected average temperature index data of each region of interest based on the regional temperature average data of each region of interest and the regional temperature average data of the temperature reference region;

[0140] The third preprocessing submodule is used to obtain the left and right neck temperature span index data according to the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone I and the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone III;

[0141] The fourth preprocessing submodule is used to perform Z-score standardization processing on the temperature span index data and the corrected average temperature index data of each region of interest and the temperature span index data of the left and right necks.

[0142] In one embodiment, the regression analysis module includes:

[0143] The LASSO regression analysis submodule is used to: screen the optimal temperature index based on the temperature span index data and corrected average temperature index data of each area of ​​interest and the temperature span index data of the left and right necks using the minimum absolute shrinkage and selection operator regression method, where the optimal temperature index includes the minimum regional temperature value of area 9 and the average regional temperature value of area III.

[0144] In one embodiment, it also includes:

[0145] The test module is used to: perform Shapiro-Wilk normality test on the temperature span index data and corrected average temperature index data of each area of ​​interest and the temperature span index data of the left and right necks, perform t test on the data that conforms to the normal distribution, and perform Mann-Whitney U test on the data that does not conform to the normal distribution, to obtain the temperature index data situation.

[0146] The present invention also provides a carotid atherosclerosis probability prediction system based on medical infrared thermal imaging, comprising:

[0147] A data receiving module is used to: receive optimal temperature index data of a subject to be tested, wherein the subject to be tested is a healthy individual or an individual suspected of having carotid atherosclerosis, and the optimal temperature index data is data corresponding to the optimal temperature index obtained according to any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging;

[0148] The prediction module is used to obtain the probability of carotid atherosclerosis of the subject according to the optimal temperature index data of the subject, through a regression analysis model constructed based on the optimal temperature index obtained by any of the above-mentioned carotid atherosclerosis image analysis methods based on medical infrared thermal imaging.

[0149] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the carotid atherosclerosis image analysis method based on medical infrared thermal imaging, and the method includes:

[0150] Acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0151] Perform region of interest segmentation on the infrared thermal imaging image of the target population to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0152] Preprocessing the temperature index data corresponding to multiple areas of interest;

[0153] According to the preprocessed temperature index data, the optimal temperature index is screened and obtained by using the minimum absolute shrinkage and selection operator regression method, which is used to establish the regression analysis model of the optimal temperature index.

[0154] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0155] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the carotid atherosclerosis image analysis method based on medical infrared thermal imaging provided by the above methods, the method comprising:

[0156] Acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0157] Perform region of interest segmentation on the infrared thermal imaging image of the target population to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0158] Preprocessing the temperature index data corresponding to multiple areas of interest;

[0159] According to the preprocessed temperature index data, the optimal temperature index is screened and obtained by using the minimum absolute shrinkage and selection operator regression method, which is used to establish the regression analysis model of the optimal temperature index.

[0160] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the carotid atherosclerosis image analysis method based on medical infrared thermal imaging provided by the above methods, the method comprising:

[0161] Acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis;

[0162] Perform region of interest segmentation on the infrared thermal imaging image of the target population to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest;

[0163] Preprocessing the temperature index data corresponding to multiple areas of interest;

[0164] According to the preprocessed temperature index data, the optimal temperature index is screened and obtained by using the minimum absolute shrinkage and selection operator regression method, which is used to establish the regression analysis model of the optimal temperature index.

[0165] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0166] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. 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. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging, characterized in that: include: Acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis; Perform region of interest segmentation on the infrared thermal imaging image of the target population to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest; Preprocessing the temperature index data corresponding to multiple areas of interest; According to the pre-processed temperature index data, the optimal temperature index is screened and obtained by using the minimum absolute shrinkage and selection operator regression method, which is used to establish a regression analysis model for the optimal temperature index; The step of segmenting the infrared thermal imaging image of the target population into regions of interest to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest includes: Identify local anatomical sites in the infrared thermal imaging images of the target population, and obtain the anterior axillary crease head, acromioclavicular joint, neck-shoulder intersection, neck-cheek intersection, sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour; According to the identified axillary ridges, acromioclavicular joints, neck-shoulder intersections, neck-cheek intersections, sternoclavicular joints, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour, the infrared thermal imaging image is segmented into regions of interest, and the neck of the target population is segmented into three regions, recorded as Region I, Region II, and Region III; the chest of the target population is segmented into five regions, recorded as Region α, Region β, Region γ, Region δ, and Region ε; the overall region of Region Ⅰ, Region Ⅱ, Region Ⅲ, Region α, Region β, Region γ, Region δ, and Region ε is segmented from the infrared thermal imaging image and recorded as Region 9; Acquire temperature index data of area I, area II, area III, area α, area β, area γ, area δ, area ε, and area 9 from the infrared thermal imaging image, wherein the temperature index data includes the maximum temperature value, the minimum temperature value, and the average temperature value of the area; The area formed by the anterior axillary ridge head and the acromioclavicular joint in the infrared thermal imaging image is taken as the temperature reference area, and the regional temperature average value data of the temperature reference area is obtained from the infrared thermal imaging image; Among them, in the neck, zone I and zone III include the flow range of the carotid artery, zone II includes multiple tissues and organs such as the trachea, larynx, esophagus, and thyroid gland; in the chest, zone γ includes the area where the aortic arch and the starting parts of its branches flow on the surface of the body, zone δ includes the area where the left subclavian artery flows on the surface of the body, zone β includes the area where the right subclavian artery flows on the surface of the body, zone ε includes the area where the left axillary artery flows, and zone α includes the area where the right axillary artery flows.

2. The method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging according to claim 1, characterized in that: The preprocessing of the temperature index data corresponding to the multiple regions of interest includes: According to the regional temperature maximum value data and the regional temperature minimum value data of each of the multiple regions of interest, the temperature span index data of each region of interest is obtained; According to the regional temperature average data of each area of ​​interest and the regional temperature average data of the temperature reference area, the corrected average temperature index data of each area of ​​interest is obtained; According to the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone I and the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone III, the left and right neck temperature span index data are obtained.

3. The method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging according to claim 2, characterized in that: The step of obtaining the temperature span index data of each region of interest according to the regional temperature maximum value data and the regional temperature minimum value data of each region of interest among the multiple regions of interest includes: According to the regional temperature maximum value data and the regional temperature minimum value data of each region of interest among the multiple regions of interest, the temperature span index data of each region of interest is obtained by using the first expression, wherein the first expression is: In the first expression, Represents the temperature span indicator data of the area of ​​interest, Represents the regional temperature maximum data of the area of ​​interest, Represents regional temperature minimum data for the area of ​​interest.

4. The method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging according to claim 2, characterized in that: The corrected average temperature index data of each region of interest is obtained according to the regional temperature average data of each region of interest and the regional temperature average data of the temperature reference region, including: According to the regional temperature average data of each region of interest and the regional temperature average data of the temperature reference region, the corrected average temperature index data of each region of interest is obtained using the second expression, wherein the second expression is: In the second expression, Represents the corrected mean temperature index data for the region of interest, Represents the regional temperature average data for the area of ​​interest, Indicates the regional temperature average data for the temperature reference area.

5. The method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging according to claim 2, characterized in that: The left and right neck temperature span index data include the maximum left and right neck temperature span index data, the minimum left and right neck temperature span index data, and the average left and right neck temperature span index data; The left and right neck temperature span index data are obtained based on the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone I and the regional temperature maximum value data, regional temperature minimum value data, regional temperature average value data of zone III, including: According to the regional temperature maximum value data of zone I and the regional temperature maximum value data of zone III, the maximum left and right neck temperature span index data is obtained by using the third expression; According to the regional temperature minimum value data of zone I and the regional temperature minimum value data of zone III, the minimum left and right neck temperature span index data is obtained by using the fourth expression; According to the regional temperature average value data of zone I and the regional temperature average value data of zone III, the average left and right neck temperature span index data is obtained by using the fifth expression; Among them, the third expression is: In the third expression, Indicates the maximum left and right neck temperature span index data, Indicates the maximum regional temperature data of Zone I. It represents the regional temperature maximum value data of Zone III; The fourth expression is: In the fourth expression, Indicates the minimum left and right neck temperature span index data, Indicates the minimum temperature data of zone I. Indicates the regional temperature minimum data of Zone III; The fifth expression is: In the fifth expression, Indicates the average left and right neck temperature span index data, Indicates the average temperature data of the region I, Represents the regional temperature average data of Zone III.

6. The method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging according to any one of claims 1 to 5, characterized in that: The optimal temperature index includes the minimum regional temperature value of region 9 and the average regional temperature value of region III. The carotid atherosclerosis image analysis method based on medical infrared thermal imaging also includes the steps of: The Shapiro-Wilk normality test was performed on the temperature span index data and the corrected average temperature index data of each area of ​​interest, as well as the temperature span index data of the left and right necks. The t test was performed on the data that conformed to the normal distribution, and the Mann-Whitney U test was performed on the data that did not conform to the normal distribution to obtain the temperature index data.

7. A carotid atherosclerosis image analysis system based on medical infrared thermal imaging, characterized in that: include: An image acquisition module is used to: acquire infrared thermal imaging images of a target population, wherein the target population is a group of patients with carotid atherosclerosis; The region of interest segmentation module is used to segment the infrared thermal imaging image of the target population into regions of interest to obtain multiple regions of interest and temperature index data corresponding to the multiple regions of interest; A data preprocessing module is used to: preprocess the temperature index data corresponding to multiple areas of interest; The regression analysis module is used to: screen out the optimal temperature index based on the pre-processed temperature index data by using the minimum absolute shrinkage and selection operator regression method, and to establish a regression analysis model for the optimal temperature index; Among them, the region of interest division module includes: The positioning submodule is used to: identify the local anatomical sites of the image in the infrared thermal imaging images of the target population, and obtain the anterior axillary ridge head, the acromioclavicular joint, the neck-shoulder intersection, the neck-cheek intersection, the sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour; The segmentation submodule is used to: segment the infrared thermal imaging image into regions of interest according to the identified axillary crest, acromioclavicular joint, neck-shoulder intersection, neck-cheek intersection, sternoclavicular joint, and the intersection of the vertical line in the sternoclavicular joint plane and the facial contour, and segment the neck of the target population into three regions, recorded as region I, region II, and region III; segment the chest of the target population into five regions, recorded as region α, region β, region γ, region δ, and region ε; segment the overall region of region Ⅰ, region Ⅱ, region Ⅲ, region α, region β, region γ, region δ, and region ε from the infrared thermal imaging image, recorded as region 9; The data acquisition submodule is used to obtain the temperature index data of area I, area II, area III, area α, area β, area γ, area δ, area ε, and area 9 from the infrared thermal imaging image, wherein the temperature index data includes the maximum temperature of the area, the minimum temperature of the area, and the average temperature of the area; The reference extraction submodule is used to: take the area formed by the axillary anterior ridge head and the acromioclavicular joint in the infrared thermal imaging image as the temperature reference area, and obtain the regional temperature average value data of the temperature reference area from the infrared thermal imaging image; Among them, in the neck, zone I and zone III include the flow range of the carotid artery, zone II includes multiple tissues and organs such as the trachea, larynx, esophagus, and thyroid gland; in the chest, zone γ includes the area where the aortic arch and the starting parts of its branches flow on the surface of the body, zone δ includes the area where the left subclavian artery flows on the surface of the body, zone β includes the area where the right subclavian artery flows on the surface of the body, zone ε includes the area where the left axillary artery flows, and zone α includes the area where the right axillary artery flows.

8. A method for constructing a carotid atherosclerosis probability prediction model based on medical infrared thermal imaging, characterized in that: Based on the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging as described in any one of claims 1 to 5, a carotid atherosclerosis probability prediction model based on medical infrared thermal imaging is constructed using multi-factor logistic regression analysis.

9. A carotid atherosclerosis probability prediction system based on medical infrared thermal imaging, characterized in that: include: A data receiving module, used to: receive optimal temperature index data of a subject to be tested, wherein the subject to be tested is a healthy individual or an individual suspected of having carotid atherosclerosis, and the optimal temperature index data is data corresponding to the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging according to any one of claims 1 to 6; The prediction module is used to obtain the probability of carotid atherosclerosis of the subject according to the optimal temperature index data of the subject, through a regression analysis model constructed based on the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging as described in any one of claims 1-6.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the carotid atherosclerosis image analysis method based on medical infrared thermal imaging as described in any one of claims 1 to 6 is implemented.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the following steps are also implemented: Receiving optimal temperature index data of a subject to be tested, wherein the subject to be tested is a healthy individual or an individual suspected of having carotid atherosclerosis, and the optimal temperature index data is data corresponding to the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging according to any one of claims 1 to 6; According to the optimal temperature index data of the subject, the probability of carotid atherosclerosis of the subject is obtained by constructing a regression analysis model based on the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging as described in any one of claims 1-6.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing carotid atherosclerosis images based on medical infrared thermal imaging as described in any one of claims 1 to 6 is implemented.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the following steps are also implemented: Receiving optimal temperature index data of a subject to be tested, wherein the subject to be tested is a healthy individual or an individual suspected of having carotid atherosclerosis, and the optimal temperature index data is data corresponding to the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging according to any one of claims 1 to 6; According to the optimal temperature index data of the subject, the probability of carotid atherosclerosis of the subject is obtained by constructing a regression analysis model based on the optimal temperature index obtained by the carotid atherosclerosis image analysis method based on medical infrared thermal imaging as described in any one of claims 1-6.

Images