CN110767311A - Auxiliary evaluation device and method for arterial calcified plaque image of lower limb of diabetic foot - Google Patents
Auxiliary evaluation device and method for arterial calcified plaque image of lower limb of diabetic foot Download PDFInfo
- Publication number
- CN110767311A CN110767311A CN201911289654.XA CN201911289654A CN110767311A CN 110767311 A CN110767311 A CN 110767311A CN 201911289654 A CN201911289654 A CN 201911289654A CN 110767311 A CN110767311 A CN 110767311A
- Authority
- CN
- China
- Prior art keywords
- artery
- lower limb
- total
- score
- dragonfly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Abstract
The invention discloses an auxiliary evaluation device and method for a lower limb artery calcification plaque image of a diabetic foot, which comprises the steps of collecting lower limb blood vessel image data of a patient, respectively obtaining total arterial calcification score and total stenosis score of the patient according to the size of the lower limb artery calcification plaque and the stenosis degree of the lower limb artery blood vessel, inputting the total arterial calcification score and the total stenosis score of the patient into an ELO algorithm model, and selecting a factor which can represent the amputation risk degree of the diabetic foot most through the scoring of the ELO algorithm model; simultaneously, selecting an amplification factor K in the ELO algorithm model by using a dragonfly algorithm, and further optimizing the ELO algorithm model; according to the method, the ELO algorithm model is beneficial to realizing auxiliary evaluation of calcification and stenosis degree on amputation risks of the diabetic foot patient, and the scoring result of the ELO algorithm model after the dragonfly algorithm is optimized is more stable.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence-related medicine and information intelligence, and particularly relates to an auxiliary evaluation device and method for a diabetic foot lower limb artery calcified plaque image.
Background
Diabetic Foot (DF) is one of the serious complications in the late stage of diabetes, and causes disability, high mortality, great treatment difficulty, long period and serious burden to patients. According to data from the international diabetes union (IDF) diabetes atlas, the number of diabetics worldwide has increased to 3.66 million people, with diabetic feet at a rate of up to 25%; chinese diabetes diagnosis and treatment guidelines also show that by 2013, the prevalence rate of diabetes of people aged 18 and over in China is 10.4%, wherein the prevalence rate of foot ulcer is 4% -10%. The major clinical manifestations of DF are peripheral arterial disease (inadequate blood supply due to large and medium-sized vasculopathies in the legs), and/or neuropathy (nerve damage or degeneration). IDF data show that up to half of all patients with diabetic foot ulcers have peripheral arterial disease. The main pathogenesis of the peripheral arterial disease of diabetes is that atherosclerosis is accelerated due to long-term poor blood sugar control, vascular calcification is aggravated, and then serious lower limb blood supply insufficiency is induced.
Vascular calcification, the main manifestation of progression to the end stage of atherosclerosis, is the process of active deposition of a calcium salt on vascular tissue under various cell-mediated conditions. It can cause increased stiffness of the vessel wall, decreased compliance, plaque rupture, thrombosis, and the like. During the last two decades, extensive research has been conducted to show the important role of detecting vascular calcification in the diagnosis and treatment of cardiovascular diseases. For example, coronary calcification can be an important marker of coronary artery disease and has value in predicting future coronary events; in the research aiming at the calcification of abdominal aorta, more data indicate that the screening of the vascular calcification condition of the patient with chronic kidney disease and the timely intervention treatment can help to improve the prognosis of the patient.
The classification of the diabetic foot and the calcification index have obvious positive correlation, which shows that the calcification index has important significance for the prediction and diagnosis of the severity of the diabetic foot; in recent years, research shows that the degree of stenosis of blood vessels has a positive correlation with the degree of calcification of blood vessels of lower limbs besides the calcification index, and the importance of the stenosis in quantitative detection of the degree of calcification of blood vessels is shown. Therefore, there is an urgent need to design a device and a method for scientifically grading and evaluating the size and stenosis degree of artery calcified plaques in lower limbs so as to evaluate the recent amputation risk of a diabetic foot patient through the correlation between the degree and stenosis degree of artery calcification of lower limbs.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides an auxiliary evaluation device and method for a lower limb artery calcified plaque image of a diabetic foot.
The technical scheme adopted by the invention is as follows:
an auxiliary evaluation device for artery calcified plaque images of lower limbs of diabetic foot comprises a data processing unit, an ELO algorithm module, a database, a CT acquisition module and a wireless module;
the CT acquisition module is used for acquiring a blood vessel image of the lower limb of the patient and then sending the blood vessel image to the data processing unit to acquire the blood vessel image of the lower limb to acquire the size of artery calcified plaque of the lower limb and the blood vessel stenosis degree information at the calcified plaque;
the database comprises a scoring standard of lower limb artery calcified plaque and a scoring standard of lower limb artery stenosis degree;
the ELO algorithm module obtains total arterial calcification scores and total stenosis scores according to scoring standards of a database, and inputs the total scores into an ELO algorithm model for obtaining factors which can represent the diabetic foot amputation risk degree most;
the wireless module is used for sending the information of the diabetic foot amputation risk degree to a doctor handheld computer or a patient client.
Further, in the database, the data is stored in the database,
the scoring standard of lower limb artery calcified plaque is as follows: the disease condition is divided into four grades according to the size of calcified plaques on the front wall and the rear wall of the artery of the lower limb: i, no calcification and rating of 0; II, the length of the artery wall with the calcification range less than 1/3 is scored as 1; III, the calcification range covers the artery wall length of 1/3-2/3, and the score is 2; IV, the artery wall length with the calcification range larger than 2/3 is scored as 3 points; therefore, the blood vessel segmentation treatment is carried out, the blood vessel of the lower limb is totally divided into an upper section and a lower section by taking the middle of the shank as a boundary line, and the treatment comprises the following steps: the proximal end of the posterior tibial artery, the distal end of the posterior tibial artery, the proximal end of the anterior tibial artery, the distal end of the anterior tibial artery, the proximal fibular artery and the distal fibular artery;
the scoring standard of the lower limb arterial stenosis degree is as follows: the disease condition is divided into four grades according to the lumen area of the artery blood vessel of the lower limb: i, reducing the diameter of the tube cavity by 1-25 percent, scoring 1, reducing the diameter of the tube cavity by 25-50 percent, scoring 2, reducing the diameter of the tube cavity by 51-75 percent, scoring 3, reducing the diameter of the tube cavity by 76-100 percent, scoring 4; the acquisition method of the stenosis degree data comprises the following steps: collecting the maximum value h of the stenosis degree of the lower limb artery at the section with calcified plaquemaxAnd average value of stenosis
According toDetermining the degree of stenosis of the segment
Wherein a and b are constant coefficients.
Further, the ELO algorithm module executes the ELO algorithm model, and the total integral score input into the ELO algorithm model is: rn＝Rn-1-Kφ(αRn-1+ β) wherein Rn-1、RnRespectively scoring the total points before and after n iterations; constant number
yA0、yB0Respectively obtaining original scores of the total arterial calcification score and the total stenosis degree score, wherein sigma is a standard deviation of the total arterial calcification score and the total stenosis degree score; phi (x) represents the cumulative distribution function of a standard normal distribution; k is an amplification factor; the amplification factor K is selected through a dragonfly algorithm module, and the dragonfly algorithm module is used for executing a dragonfly algorithm program.
Further, the CT acquisition module is a Germany double-source spiral CT; the data processing unit is a DSP; the ELO algorithm module is realized by using a UML diagram design; the database runs in a win7 environment, the SQLServer 2000 database management system of Microsoft corporation is used as a development tool, the VC +6.0 of Microsoft is used as the front end of the database, and the CPU: AMDXP1800+, memory kingston 3G DDR, hard disk Dall 600G.
The invention discloses an auxiliary evaluation method of a lower limb artery calcified plaque image of a diabetic foot, which comprises the steps of collecting a lower limb blood vessel image of a patient, obtaining the size of the lower limb artery calcified plaque and the stenosis degree of a blood vessel at the calcified plaque by the lower limb blood vessel image, further obtaining the total arterial calcification score and the total stenosis degree score, inputting the total arterial calcification score and the total stenosis degree score into an ELO algorithm model, and selecting a factor which can represent the most diabetic foot amputation risk degree.
Further, the total arterial calcification score is obtained according to a scoring standard of lower limb arterial calcification plaques, wherein the scoring standard is as follows: the disease condition is divided into four grades according to the size of calcified plaques on the front wall and the rear wall of the artery of the lower limb: i, no calcification and rating of 0; II, the length of the artery wall with the calcification range less than 1/3 is scored as 1; III, the calcification range covers the artery wall length of 1/3-2/3, and the score is 2; IV, the artery wall length with the calcification range larger than 2/3 is scored as 3 points; therefore, the blood vessel segmentation treatment is carried out, the blood vessel of the lower limb is totally divided into an upper section and a lower section by taking the middle of the shank as a boundary line, and the treatment comprises the following steps: the proximal end of the posterior tibial artery, the distal end of the posterior tibial artery, the proximal end of the anterior tibial artery, the distal end of the anterior tibial artery, the proximal fibular artery and the distal fibular artery.
Further, the total score of the stenosis degree is obtained by a scoring standard of the stenosis degree of the artery of the lower limb, wherein the scoring standard is as follows: the disease condition is divided into four grades according to the lumen area of the artery blood vessel of the lower limb: i, reducing the diameter of the tube cavity by 1-25 percent, scoring 1, reducing the diameter of the tube cavity by 25-50 percent, scoring 2, reducing the diameter of the tube cavity by 51-75 percent, scoring 3, reducing the diameter of the tube cavity by 76-100 percent, scoring 4; the acquisition method of the stenosis degree data comprises the following steps: collecting the maximum value h of the stenosis degree of the lower limb artery at the section with calcified plaquemaxAnd average value of stenosis
According to
Determining the degree of stenosis of the segment
Wherein a and b are constant coefficients.
Further, the total integral score input into the ELO algorithm model is: rn＝Rn-1-Kφ(αRn-1+ β) wherein Rn-1、RnRespectively scoring the total points before and after n iterations; constant number
yA0、yB0Respectively obtaining original scores of the total arterial calcification score and the total stenosis degree score, wherein sigma is a standard deviation of the total arterial calcification score and the total stenosis degree score;phi (x) represents the cumulative distribution function of a standard normal distribution; and K is an amplification coefficient, and the amplification coefficient K is selected through a dragonfly algorithm.
Further, the specific process of selecting the amplification factor K by the dragonfly algorithm is as follows:
s1, initializing dragonfly algorithm parameters;
s2, initializing an individual position X and a step size vector delta X of the dragonfly by adopting a random generation method;
s3, making the initial value of the iteration times t equal to 1;
s4, substituting the position of the dragonfly individual into the adaptive function, and calculating the adaptive value;
s5, if t is more than or equal to 2, constructing an individual position augmentation matrix and an adaptive value augmentation matrix of the dragonfly, and then mapping the position augmentation matrix to the adaptive value augmentation matrix in sequence to obtain the Elite dragonfly individuals of the first two generations of the history and the optimal amplification factor K+The worst amplification factor K as the source position of the food-As the position of the natural enemy, the adaptive value of the current optimal elite dragonfly individual is saved;
s6, using Euclidean distance formula to determine the position X of food source+And natural enemy position X-Updating is carried out;
s7, updating the five dragonfly behaviors S, A, C, F, E using formulas;
s8, updating the field radius r, and further updating the distance between every dragonfly individual;
s9, performing a disturbing operation on the dragonfly position X;
s10, checking whether the position of each individual dragonfly is in the definition domain of the adaptive function, if not, correcting the boundary of the position of the individual dragonfly and making the position return to the boundary;
s11, making the iteration time t equal to t +1, if t is less than MIT, namely the current iteration time is less than the maximum iteration time, jumping to S4 to continue execution; otherwise, the loop is stopped.
Further, the fitness function is:
wherein KiIs the ith amplification factor, i ∈ [1, d ∈ ]]D is the number of dragonflies, and m and n are constants.
The invention has the beneficial effects that:
the auxiliary evaluation device and method for the arterial calcified plaque image of the lower limb of the diabetic foot realize scientific classification and evaluation of the size and the stenosis degree of the arterial calcified plaque of the lower limb, and are favorable for evaluating the amputation risk of a diabetic foot patient through the arterial calcification and the vascular stenosis degree of the lower limb; the system of the invention is also beneficial to providing auxiliary risk prompt and intelligent auxiliary expert suggestion in cooperation with the medical treatment of the diabetic foot by a doctor.
The device and the method provided by the invention innovatively provide that the total score of the size of the artery calcified plaque and the total score of the stenosis degree of the patient are input into an ELO algorithm module for the first time, a corresponding dividing mode of the artery calcified score and the stenosis degree score and a data obtaining mode are provided by combining a large number of case analysis and actual diabetes cases, two factors influencing the condition of the diabetic foot, namely lower limb artery calcification and vessel stenosis degree, are subjected to game playing through the ELO algorithm module, the risk of amputation of the diabetic foot patient can be most represented by evaluating the two influencing factors, and the risk of the diabetic foot patient with higher rank in the influencing factors is larger. In the invention, in the process of scoring by adopting the ELO algorithm module, in order to avoid the fluctuation in the iterative process and the accuracy of the scoring result, the dragonfly algorithm module is utilized to optimize the value of the amplification coefficient K. The dragonfly algorithm adopted by the invention fully utilizes historical excellent individuals, improves the convergence speed of the dragonfly algorithm, naturally switches between the global search process and the local opening process, and improves the optimization precision. According to the method, the evaluation on the amputation risk of the diabetic foot patient caused by calcification and stenosis degree can be quickly realized by using the ELO algorithm module, and particularly, the evaluation result of the ELO algorithm model optimized by the dragonfly algorithm is more stable, so that a solid foundation is laid for subsequent clinical auxiliary evaluation.
Drawings
FIG. 1 is a flow chart of an auxiliary evaluation method of an artery calcified plaque image of a lower limb of a diabetic foot according to the present invention;
FIG. 2 is a block diagram of a dragonfly algorithm process flow;
FIG. 3 is a schematic diagram of the degree of calcification and stenosis of an artery of a lower limb; 3a-3d are graphs of stenosis in arterial calcification of the lower extremities (obtained by CT) at different degrees (0, 10%, 30%, 80%) respectively;
FIG. 4 is a line graph of the clinical evaluation results of the severity of diabetic foot patients and the auxiliary evaluation results of the present invention.
FIG. 5 is a view showing the structure of the apparatus of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The auxiliary evaluation device for the artery calcified plaque image of the lower limb of the diabetic foot as shown in fig. 5 comprises a data processing unit, an ELO algorithm module, a database, a CT acquisition module and a wireless module;
the CT acquisition module is used for acquiring a blood vessel image of the lower limb of the patient and then sending the blood vessel image to the data processing unit to acquire the blood vessel image of the lower limb to acquire the size of artery calcified plaque of the lower limb and the blood vessel stenosis degree information at the calcified plaque;
the database comprises a scoring standard of lower limb artery calcified plaque and a scoring standard of lower limb artery stenosis degree;
the ELO algorithm module obtains total arterial calcification scores and total stenosis scores according to scoring standards of a database, and inputs the total scores into an ELO algorithm model for obtaining factors which can represent the diabetic foot amputation risk degree most;
the wireless module is used for sending the information of the diabetic foot amputation risk degree to a doctor handheld computer or a patient client.
In the database, the scoring standard of the lower limb artery calcified plaque is as follows: the disease condition is divided into four grades according to the size of calcified plaques on the front wall and the rear wall of the artery of the lower limb: i, no calcification and rating of 0; II, arterial wall length with calcification range less than 1/3, score 1(ii) a III, the calcification range covers the artery wall length of 1/3-2/3, and the score is 2; IV, the artery wall length with the calcification range larger than 2/3 is scored as 3 points; therefore, the blood vessel segmentation treatment is carried out, the blood vessel of the lower limb is totally divided into an upper section and a lower section by taking the middle of the shank as a boundary line, and the treatment comprises the following steps: the proximal end of the posterior tibial artery, the distal end of the posterior tibial artery, the proximal end of the anterior tibial artery, the distal end of the anterior tibial artery, the proximal fibular artery and the distal fibular artery; the scoring standard of the lower limb arterial stenosis degree is as follows: the disease condition is divided into four grades according to the lumen area of the artery blood vessel of the lower limb: i, reducing the diameter of the tube cavity by 1-25 percent, scoring 1, reducing the diameter of the tube cavity by 25-50 percent, scoring 2, reducing the diameter of the tube cavity by 51-75 percent, scoring 3, reducing the diameter of the tube cavity by 76-100 percent, scoring 4; the acquisition method of the stenosis degree data comprises the following steps: collecting the maximum value h of the stenosis degree of the lower limb artery at the section with calcified plaquemaxAnd average value of stenosis
According to
Determining the degree of stenosis of the segment
Wherein a and b are constant coefficients.
The CT acquisition module is a Germany double-source spiral CT; the data processing unit is a DSP; the ELO algorithm module is realized by using a UML diagram design; the database runs in a win7 environment, a SQL Server 2000 database management system of Microsoft corporation is used as a development tool, VC +6.0 of Microsoft is used as a database front end, and a CPU: AMD XP1800+, Kingston 3G DDR, hard disk Dall 600G.
The method comprises the following specific processes:
Step 1.1, image acquisition: adopting German double-source spiral CT, the scanning range is from abdominal aorta level to sole, the patient adopts supine-foot advanced scanning body position, and the feet of the patient are fixed at the inversion position during scanning. Scanning parameters are as follows: the width of the collimator is 0.6mm, the thread pitch is 0.8, the scanning speed is 0.37 s/r, and the thickness of the reconstruction layer is 1.0 mm; scanning conditions are as follows: the voltage is 120kV, the current is 50-60mAs, a non-ionic iodine contrast agent (Youyuwei display 370mgI/ml, Xianling company) is applied to inject through the median elbow vein, the injection rate is 3.5-4.0 ml/s, the total amount is 100-120 ml, and BOLUS-TRACKING scanning is adopted.
Step 1.2, image processing: and (2) transmitting the thin layer reconstructed cross section image into a Leonardoi workstation, respectively adopting post-processing technologies such as multi-planar reconstruction (MPR), Volume Reconstruction (VR), deboning and the like to reconstruct blood vessels, analyzing by combining an original image, and intercepting images of a positive angle and a lateral angle.
Step 1.3, performing blood vessel segmentation treatment, namely dividing the blood vessel of the lower limb into an upper section and a lower section by taking the middle of a shank as a boundary line, wherein the blood vessel segmentation treatment comprises the following steps: the proximal tibial artery (upper 1/2 of the lower leg), the distal tibial artery (lower 1/2 of the lower leg), the proximal tibial artery (upper 1/2), the distal tibial artery (lower 1/2), the proximal peroneal artery (upper 1/2), and the distal peroneal artery (lower 1/2).
And 1.4, deriving the lower limb blood vessel image data, as shown in figure 3.
And 2, acquiring the size of the calcified plaque of the artery of the lower limb and the stenosis degree data of the blood vessel at the calcified plaque by combining the blood vessel image data of the lower limb, wherein the stenosis degree data acquisition method comprises the following steps: collecting the maximum value h of the stenosis degree of the lower limb artery at the section with calcified plaquemaxAnd average value of stenosis
According to
Determining the degree of stenosis of the segment
Wherein a and b are constant coefficients (in the experiment, a takes a value of 0.7, and b takes a value of 0.3).
Step 3, scoring the length of the lower limb artery calcified plaque and the stenosis degree of the lower limb artery blood vessel respectively, wherein the specific process is as follows:
scoring criteria for lower limb artery calcified plaque: the disease condition is divided into four grades according to the length of calcified plaques on the front wall and the rear wall of the artery of the lower limb: i, no calcification and rating of 0; II, the length of the artery wall with the calcification range less than 1/3 is scored as 1; III, the calcification range covers the artery wall length of 1/3-2/3, and the score is 2; IV, arterial wall length with calcification range greater than 2/3, score 3.
The scoring standard of the lower limb arterial stenosis degree is as follows: the disease condition is divided into four grades according to the lumen area of the artery blood vessel of the lower limb: the diameter of the tube cavity I is reduced by 1-25 percent, the rating is 1, the diameter of the tube cavity II is reduced by 25-50 percent, the rating is 2, the diameter of the tube cavity III is reduced by 51-75 percent, the rating is 3, the diameter of the tube cavity IV is reduced by 76-100 percent, and the rating is 4.
And obtaining the total score of the artery calcification and the total score of the stenosis of the patient according to the length of the artery calcification plaque of the lower limb and the stenosis of the artery blood vessel of the lower limb respectively.
Step 4, inputting the total score of artery calcification and the total score of stenosis degree of the patient into an ELO algorithm model, and selecting the factor which can represent the diabetic foot amputation risk degree most through the score of the ELO algorithm model, wherein the processing process of the ELO algorithm model is as follows:
assuming that the total product of artery calcification and stenosis degree obeys normal distribution random variable X-N (mu, sigma)2) And the mean value mu is constant in a short period, the variance sigma of the total score of arterial calcification and the total score of stenosis degree2The same is true. On the premise, the score change of the total score of artery calcification or the total score of stenosis degree only depends on the deviation degree of the recent examination result and the mean value, so the designed linear correction is as follows:
yn＝yn-1+K(M-μ) (1)
in the formula, ynFor iteratively updated scores, yn-1For the score before the iterative update, K is an amplification factor, M is a recent examination result of the total score of the arterial calcification or the total score of stenosis degree, M ═ 1 indicates an influence, M ═ 0 indicates no influence, and μ is a mean value of the total score of the arterial calcification or the total score of stenosis degree. To distinguish the total arterial calcification score from the total stenosis score, the corresponding markers M are markedA，MB，μA，μB(ii) a Therefore, the score Q for the total score of arterial calcificationA～N(μA，σ2) Score Q for Total score of stenosisB～N(μB，σ2) The difference value of the influence of the total arterial calcification score and the total stenosis degree score is QA-QB～N(μA-μB，2σ2) (ii) a When Q isA-QBWhen the total score of artery calcification is more than 0, the total score of artery calcification is influenced to exceed the total score of stenosis degree, and is calculated by probability:
in the formula, φ (x) represents the cumulative distribution function of the standard normal distribution.
Since the total score of artery calcification or stenosis is assumed to be Q-N (mu, sigma)2) Thus μA＝E(QA)，μB＝E(QB) Score yA(n-1)Is an estimate of the total score of arterial calcification or total score of stenosis influencing the expectation; from equation (2), the probability estimate that the impact is large can be:
for total arterial calcification scores, there are:
yAn＝yA(n-1)+K(MA-μA) (4)
and:
thus, MAAre random variables that obey bernoulli distributions: mA～B(1，q)，
Due to MA+MB＝1、μA+μBWhen 1, then:
yAn+yBn＝yA(n-1)+yB(n-1)(6)
it can be seen that the sum of the score of the total score of arterial calcification and the score of the total score of stenosis remains constant. Let the original score of the total arterial calcification score and the total stenosis score be yA0、yB0The following can be obtained:
yB＝yA0+yB0-yA(7)
recording constant
The total score of artery calcification before and after the nth iteration is Rn-1、RnThen, there are:
Rn＝Rn-1-Kφ(αRn-1+β) (9)
the selection of the amplification factor K is large, so that the fluctuation of the scoring result after the ELO algorithm is iterated is large, and the selection of the amplification factor K is small, so that the scoring updating function of the characterization competition factors (namely the total arterial calcification score and the total stenosis degree score) is lost in an ELO algorithm iteration formula, and the updating process is stopped; therefore, the invention selects the amplification coefficient K through the dragonfly algorithm; the specific process is as follows:
s1, initializing algorithm parameters, and enlarging the value range [ K ] of the amplification factor K1,Kd]And taking all amplification coefficients K as individual dragonflies, setting the number of the dragonflies as D, setting the maximum iteration number as MIT, setting the dimension of an adaptive function as D and setting the domain radius r between the individual dragonflies.
And S2, initializing the dragonfly individual position X and the step vector delta X by adopting a random generation method.
S3, let the initial value of the iteration number t equal to 1.
S4, substituting the position of the dragonfly individual into the adaptive function, and calculating the adaptive value;
the fitness function is:
wherein, KiIs the ith amplification factor, i ∈ [1, d ∈ ]]And m and n are constants.
S5, if t is more than or equal to 2, constructing an individual position augmentation matrix and an adaptive value augmentation matrix of the dragonfly, and then mapping the position augmentation matrix to the adaptive value augmentation matrix in sequence to obtain the Elite dragonfly individuals of the first two generations of the history and the optimal amplification factor K+The worst amplification factor K as the source position of the food-And as the position of the natural enemy, the adaptive value of the current optimal Elite dragonfly individual is saved.
S6, using Euclidean distance formula to determine the position X of food source+And natural enemy position X-And (6) updating.
S7, the dragonfly behavior S, A, C, F, E is updated by using the formula, the updating process is as follows:
the collision avoidance behavior S is calculated by the following formula:
the formula for the formation behavior A is as follows:
the calculation formula of the aggregation behavior C is:
the foraging behavior F is calculated as:
Fi＝X+-X (14)
the calculation formula of the avoidance behavior E is as follows:
Ei＝X-+X (15)
wherein S isiThe collision avoidance position of the ith individual dragonfly, X is the position of the individual dragonfly when flyingjIs the jth adjacent dragonfly individual flyPosition in line, N represents the number of adjacent dragonflies, AiIs the position of the ith dragonfly individual team, VjIs the flight speed of the jth adjacent dragonfly individual, CiPosition of aggregation for the ith dragonfly individual, FiThe location of the ith dragonfly individual from the food source, EiIs the position of the ith individual dragonfly natural enemy.
And S8, updating the field radius r, and further updating the distance between every dragonfly individual, wherein the specific process is as follows:
s8.1, if the dragonfly individual is surrounded by adjacent individuals, changing the step vector delta X and the position vector X of the dragonfly individual, and the specific process is as follows:
ΔXt+1＝(sSi+aAi+cCi+fFi+eEi)+wΔXt(16)
Xt+1＝Xt+ΔXt+1(17)
wherein s is a collision avoidance weight, a is a pairing weight, c is an aggregation weight, f is a food factor, e is a natural enemy factor, and w is an inertia parameter of dragonfly flight; the calculation and change of the weight parameters a, c, s, f and e can be arbitrarily selected from the real number interval [0, 1 ]; the self-adaptive linear decreasing value of the flying inertia parameter w is within the interval [0.5, 0.9 ].
S8.2, if no adjacent individual exists in the current dragonfly individual field, in order to improve the randomness, the random behavior and the global search performance of the dragonfly individual, updating the position vector X of the dragonfly individual by random walk, wherein the position vector X is as follows:
Xt+1＝Xt+Le′vy(m)Xt(18)
wherein the content of the first and second substances,
r1and r2Are each [0, 1]The random number in the dragonfly group is β ═ 0.5, m is the dimension of the position vector when the dragonfly group flies,
when the position of the dragonfly changes, whether the dragonfly is adjacent or not is checked, and if the dragonfly is not adjacent, the random walk state is entered, so that the method continuously keeps excellent individuals, but the random walk state can also prevent the dragonfly from falling into a local extreme value to a certain extent.
S9, executing the operation of disturbing the dragonfly position X, the process is as follows:
wherein the content of the first and second substances,for the ith individual in the t iteration, rnIn order to iteratively optimize the parameters, the parameters are,
is an excellent individual dragonfly in the last iteration. In the evolution process, excellent dragonfly individuals can be operated during iterative computation, communication about positions of the dragonfly individuals can be carried out, the performance of global search is improved, and premature convergence of an algorithm is prevented.
S10, checking whether the position of each individual dragonfly is within the definition domain of the adaptive function, if not, correcting the boundary of the position of the individual dragonfly and making the position return to the boundary.
S11, making the iteration time t equal to t +1, if t is less than MIT, namely the current iteration time is less than the maximum iteration time, jumping to S4 to continue execution; otherwise, the loop is stopped.
Determining the optimal amplification factor K through dragonfly algorithm+The total score has small fluctuation of the scoring result, the scoring result is accurate, factors influencing the diabetic foot patient can be quickly determined, the short-term amputation risk of the patient can be predicted, and the method has important significance for predicting and diagnosing the severity of the diabetic foot.
In order to verify the evaluation effect of the auxiliary evaluation method for the arterial calcified plaque image of the lower limb of the diabetic foot, 255 cases of data of the diabetic foot are taken within 12 months of 2013 to 12 months of 2018, and are classified into 6 groups according to Wagner diagnosis standards: level 0: the risk factors of foot ulcer are present, and no ulcer exists at present; level 1: the risk factors of foot ulcer are present, and no ulcer exists at present; and 2, stage: surface ulcers, no clinical infection; and 3, level: deeper ulcers, frequently combined parenchyma inflammation, no abscess or bone infection; 4, level: deep infection with bone tissue lesions or abscesses; and 5, stage: localized gangrene (toe, heel or forefoot); and 6, level: gangrene of all feet; 30 data of 255 diabetes foot patient data are randomly extracted, clinical scoring results are given according to Wagner diagnostic criteria, then the 255 diabetes foot patient data are input into the evaluation method, and clinical judgment results are compared with the evaluation results of the invention, as shown in FIG. 4, it can be seen that the 225 evaluation results are highly consistent, the algorithm precision and stability are greatly improved, and the evaluation results of the invention meet requirements.
The above embodiments are only used for illustrating the design idea and features of the present invention, and the purpose of the present invention is to enable those skilled in the art to understand the content of the present invention and implement the present invention accordingly, and the protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes and modifications made in accordance with the principles and concepts disclosed herein are intended to be included within the scope of the present invention.
Claims (10)
1. An auxiliary evaluation device for artery calcified plaque images of lower limbs of diabetic foot is characterized by comprising a data processing unit, an ELO algorithm module, a database, a CT acquisition module and a wireless module;
the CT acquisition module is used for acquiring a blood vessel image of the lower limb of the patient and then sending the blood vessel image to the data processing unit to acquire the blood vessel image of the lower limb to acquire the size of artery calcified plaque of the lower limb and the blood vessel stenosis degree information at the calcified plaque;
the database comprises a scoring standard of lower limb artery calcified plaque and a scoring standard of lower limb artery stenosis degree;
the ELO algorithm module obtains total arterial calcification scores and total stenosis scores according to scoring standards of a database, and inputs the total scores into an ELO algorithm model for obtaining factors which can represent the diabetic foot amputation risk degree most;
the wireless module is used for sending the information of the diabetic foot amputation risk degree to a doctor handheld computer or a patient client.
2. The apparatus for assisting in evaluating an image of arterial calcified plaque of lower limbs of diabetic foot according to claim 1, wherein in said database,
the scoring standard of lower limb artery calcified plaque is as follows: the disease condition is divided into four grades according to the size of calcified plaques on the front wall and the rear wall of the artery of the lower limb: i, no calcification and rating of 0; II, the length of the artery wall with the calcification range less than 1/3 is scored as 1; III, the calcification range covers the artery wall length of 1/3-2/3, and the score is 2; IV, the artery wall length with the calcification range larger than 2/3 is scored as 3 points; therefore, the blood vessel segmentation treatment is carried out, the blood vessel of the lower limb is totally divided into an upper section and a lower section by taking the middle of the shank as a boundary line, and the treatment comprises the following steps: the proximal end of the posterior tibial artery, the distal end of the posterior tibial artery, the proximal end of the anterior tibial artery, the distal end of the anterior tibial artery, the proximal fibular artery and the distal fibular artery;
the scoring standard of the lower limb arterial stenosis degree is as follows: the disease condition is divided into four grades according to the lumen area of the artery blood vessel of the lower limb: i, reducing the diameter of the tube cavity by 1-25 percent, scoring 1, reducing the diameter of the tube cavity by 25-50 percent, scoring 2, reducing the diameter of the tube cavity by 51-75 percent, scoring 3, reducing the diameter of the tube cavity by 76-100 percent, scoring 4; the acquisition method of the stenosis degree data comprises the following steps: collecting the maximum value h of the stenosis degree of the lower limb artery at the section with calcified plaquemaxAnd average value of stenosisAccording to
Determining the degree of stenosis of the segment
Wherein a and b are constant coefficients.
3. The device of claim 1, wherein the ELO algorithm module executes an ELO algorithm model, and the total score input into the ELO algorithm model is divided into: rn＝Rn-1-Kφ(αRn-1+ β) wherein Rn-1、RnRespectively scoring the total points before and after n iterations; constant number
yA0、yB0Respectively obtaining original scores of the total arterial calcification score and the total stenosis degree score, wherein sigma is a standard deviation of the total arterial calcification score and the total stenosis degree score; phi (x) represents the cumulative distribution function of a standard normal distribution; k is an amplification factor; the amplification factor K is selected through a dragonfly algorithm module, and the dragonfly algorithm module is used for executing a dragonfly algorithm program.
4. The auxiliary evaluation device for the arterial calcified plaque of lower limbs of diabetic foot according to claim 1, wherein the CT acquisition module is a Germany dual-source spiral CT; the data processing unit is a DSP; the ELO algorithm module is realized by using a UML diagram design; the database runs in a win7 environment, a SQL Server 2000 database management system of Microsoft corporation is used as a development tool, VC +6.0 of Microsoft is used as a database front end, and a CPU: AMD XP1800+, Kingston 3G DDR, hard disk Dall 600G.
5. An auxiliary evaluation method for an artery calcified plaque image of a lower limb of a diabetic foot is characterized by comprising the following steps: the method comprises the steps of collecting a lower limb blood vessel image of a patient, obtaining the size of artery calcified plaques of the lower limb and the stenosis degree of blood vessels at the calcified plaques through the lower limb blood vessel image, further obtaining the total score of artery calcification and the total score of stenosis degree, inputting the total score into an ELO algorithm model, and selecting a factor which can represent the amputation risk degree of the diabetic foot most.
6. The method for assisting in evaluating an image of arterial calcified plaque of lower limbs of diabetic foot according to claim 5, wherein: the total arterial calcification score is obtained according to a scoring standard of lower limb arterial calcification plaques, wherein the scoring standard is as follows: the disease condition is divided into four grades according to the size of calcified plaques on the front wall and the rear wall of the artery of the lower limb: i, no calcification and rating of 0; II, the length of the artery wall with the calcification range less than 1/3 is scored as 1; III, the calcification range covers the artery wall length of 1/3-2/3, and the score is 2; IV, the artery wall length with the calcification range larger than 2/3 is scored as 3 points; therefore, the blood vessel segmentation treatment is carried out, the blood vessel of the lower limb is totally divided into an upper section and a lower section by taking the middle of the shank as a boundary line, and the treatment comprises the following steps: the proximal end of the posterior tibial artery, the distal end of the posterior tibial artery, the proximal end of the anterior tibial artery, the distal end of the anterior tibial artery, the proximal fibular artery and the distal fibular artery.
7. The method for assisting in evaluating an image of arterial calcified plaque of lower limbs of diabetic foot according to claim 5, wherein: the total integral of the stenosis degree is obtained by a scoring standard of the stenosis degree of the artery vessel of the lower limb, wherein the scoring standard is as follows: the disease condition is divided into four grades according to the lumen area of the artery blood vessel of the lower limb: i, reducing the diameter of the tube cavity by 1-25 percent, scoring 1, reducing the diameter of the tube cavity by 25-50 percent, scoring 2, reducing the diameter of the tube cavity by 51-75 percent, scoring 3, reducing the diameter of the tube cavity by 76-100 percent, scoring 4; the acquisition method of the stenosis degree data comprises the following steps: collecting the maximum value h of the stenosis degree of the lower limb artery at the section with calcified plaquemaxAnd average value of stenosis
According to
Determining the stenosis of the segmentNarrowness degreeWherein a and b are constant coefficients.
8. The method for assisting in evaluating an image of arterial calcified plaque of lower limbs of diabetic foot according to claim 5, wherein: the total integral input into the ELO algorithm model is scored as: rn＝Rn-1-Kφ(αRn-1+ β) wherein Rn-1、RnRespectively scoring the total points before and after n iterations; constant number
yA0、yB0Respectively obtaining original scores of the total arterial calcification score and the total stenosis degree score, wherein sigma is a standard deviation of the total arterial calcification score and the total stenosis degree score; phi (x) represents the cumulative distribution function of a standard normal distribution; and K is an amplification coefficient, and the amplification coefficient K is selected through a dragonfly algorithm.
9. The method for assisting in evaluating an image of arterial calcified plaque of lower limbs of diabetic foot according to claim 8, wherein: the specific process of selecting the amplification factor K by the dragonfly algorithm is as follows:
s1, initializing dragonfly algorithm parameters;
s2, initializing an individual position X and a step size vector delta X of the dragonfly by adopting a random generation method;
s3, making the initial value of the iteration times t equal to 1;
s4, substituting the position of the dragonfly individual into the adaptive function, and calculating the adaptive value;
s5, if t is more than or equal to 2, constructing an individual position augmentation matrix and an adaptive value augmentation matrix of the dragonfly, and then mapping the position augmentation matrix to the adaptive value augmentation matrix in sequence to obtain the Elite dragonfly individuals of the first two generations of the history and the optimal amplification factor K+As a food source position, the worst amplification factor K-is used as a natural enemy position, and the adaptive value of the current optimal Elite dragonfly individual is stored;
s6, using Euclidean distance formula to determine the position X of food source+And natural enemy position X-Updating is carried out;
s7, updating the five dragonfly behaviors S, A, C, F, E using formulas;
s8, updating the field radius r, and further updating the distance between every dragonfly individual;
s9, performing a disturbing operation on the dragonfly position X;
s10, checking whether the position of each individual dragonfly is in the definition domain of the adaptive function, if not, correcting the boundary of the position of the individual dragonfly and making the position return to the boundary;
s11, making the iteration time t equal to t +1, if t is less than MIT, namely the current iteration time is less than the maximum iteration time, jumping to S4 to continue execution; otherwise, the loop is stopped.
10. The method for assisting in evaluating an image of arterial calcified plaque of lower limbs of diabetic foot according to claim 9, wherein: the fitness function is:wherein KiIs the ith amplification factor, i ∈ [1, d ∈ ]]D is the number of dragonflies, and m and n are constants.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910888058.7A CN110600126A (en) | 2019-09-19 | 2019-09-19 | Auxiliary evaluation method for arterial calcified plaque image of lower limb of diabetic foot |
| CN2019108880587 | 2019-09-19 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110767311A true CN110767311A (en) | 2020-02-07 |
| CN110767311B CN110767311B (en) | 2020-12-25 |
Family
ID=68861320
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910888058.7A Pending CN110600126A (en) | 2019-09-19 | 2019-09-19 | Auxiliary evaluation method for arterial calcified plaque image of lower limb of diabetic foot |
| CN201911289654.XA Active CN110767311B (en) | 2019-09-19 | 2019-12-13 | Auxiliary evaluation device and method for arterial calcified plaque image of lower limb of diabetic foot |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910888058.7A Pending CN110600126A (en) | 2019-09-19 | 2019-09-19 | Auxiliary evaluation method for arterial calcified plaque image of lower limb of diabetic foot |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110600126A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667467A (en) * | 2020-05-28 | 2020-09-15 | 江苏大学附属医院 | Clustering algorithm-based lower limb vascular calcification index multi-parameter accumulation calculation method |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489806B (en) * | 2020-11-27 | 2022-02-15 | 南通市第一人民医院 | Intelligent management method and system for disease state information of diabetic foot patient |
| CN113077432B (en) * | 2021-03-30 | 2024-01-05 | 中国人民解放军空军军医大学 | Patient risk grading system based on coronary artery CTA image atherosclerosis plaque comprehensive characteristics |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103917166A (en) * | 2011-08-17 | 2014-07-09 | Vp诊断公司 | A method and system of characterization of carotid plaque |
| CN104436656A (en) * | 2014-12-24 | 2015-03-25 | 深圳市腾讯计算机系统有限公司 | Method and device for matching users in game application |
| CN104933593A (en) * | 2015-04-16 | 2015-09-23 | 西安交通大学 | Integration excitation system based on Elo hierarchy model and integration excitation method based on Elo hierarchy model |
| CN106447645A (en) * | 2016-04-05 | 2017-02-22 | 天津大学 | Device and method for coronary artery calcification detection and quantification in CTA image |
| CN108335744A (en) * | 2018-04-03 | 2018-07-27 | 江苏大学附属医院 | A kind of emergency cardiovascular care network system and its method for early warning of classifying |
| CN108392828A (en) * | 2018-03-16 | 2018-08-14 | 深圳冰川网络股份有限公司 | A kind of player's On-line matching method and system for the game of MOBA classes |
| TW201928863A (en) * | 2017-12-25 | 2019-07-16 | 潘宗賢 | High precision interactive care system for high blood sugar measurement |
-
2019
- 2019-09-19 CN CN201910888058.7A patent/CN110600126A/en active Pending
- 2019-12-13 CN CN201911289654.XA patent/CN110767311B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103917166A (en) * | 2011-08-17 | 2014-07-09 | Vp诊断公司 | A method and system of characterization of carotid plaque |
| CN104436656A (en) * | 2014-12-24 | 2015-03-25 | 深圳市腾讯计算机系统有限公司 | Method and device for matching users in game application |
| CN104933593A (en) * | 2015-04-16 | 2015-09-23 | 西安交通大学 | Integration excitation system based on Elo hierarchy model and integration excitation method based on Elo hierarchy model |
| CN106447645A (en) * | 2016-04-05 | 2017-02-22 | 天津大学 | Device and method for coronary artery calcification detection and quantification in CTA image |
| TW201928863A (en) * | 2017-12-25 | 2019-07-16 | 潘宗賢 | High precision interactive care system for high blood sugar measurement |
| CN108392828A (en) * | 2018-03-16 | 2018-08-14 | 深圳冰川网络股份有限公司 | A kind of player's On-line matching method and system for the game of MOBA classes |
| CN108335744A (en) * | 2018-04-03 | 2018-07-27 | 江苏大学附属医院 | A kind of emergency cardiovascular care network system and its method for early warning of classifying |
Non-Patent Citations (5)
| Title |
|---|
| 刘超: "《能谱CT冠状动脉成像与冠状动脉血管造影评价冠状动脉钙化性斑块管腔狭窄程度的对比研究》", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
| 吴汪洋: "《基于增强个体信息交流的蜻蜓算法研究与应用》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 欧阳梅生: "《基于ELO算法的竞技项目评价体系研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王中群 等: "蛋白激酶C活性与糖尿病足截肢患者胫前动脉钙化积分的相关性", 《中国动脉硬化杂志》 * |
| 蔡宏等: "《腹主动脉钙化评分可预估血液透析患者的冠状动脉钙化程度》", 《中国血液净化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667467A (en) * | 2020-05-28 | 2020-09-15 | 江苏大学附属医院 | Clustering algorithm-based lower limb vascular calcification index multi-parameter accumulation calculation method |
| CN111667467B (en) * | 2020-05-28 | 2021-01-26 | 江苏大学附属医院 | Clustering algorithm-based lower limb vascular calcification index multi-parameter accumulation calculation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110767311B (en) | 2020-12-25 |
| CN110600126A (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110767311B (en) | Auxiliary evaluation device and method for arterial calcified plaque image of lower limb of diabetic foot | |
| US20230148977A1 (en) | Systems and methods for numerically evaluating vasculature | |
| CN104837407B (en) | Blood vessel resolver, medical diagnostic imaging apparatus and blood vessel analytic method | |
| WO2020107732A1 (en) | Method and device for establishing blood vessel section function, blood vessel pressure difference and blood vessel stress | |
| JP2008503303A (en) | Method and apparatus for displaying a tracheobronchial tree | |
| CN111951277A (en) | Coronary artery segmentation method based on CTA image | |
| CN111523549B (en) | Aortic valve evaluation method, aortic valve evaluation device and computer equipment | |
| US20150348260A1 (en) | System and Method for Mapping Patient Data from One Physiological State to Another Physiological State | |
| CN109727242B (en) | Blood vessel center line extraction method, device, computer equipment and storage medium | |
| CN115564737A (en) | Method and device for segmenting coronary artery CT (computed tomography) contrast image and storage medium | |
| CN108805923B (en) | Physiological parameter acquisition method and device | |
| US20220151579A1 (en) | Method and apparatus for correcting blood flow velocity on the basis of interval time between angiogram images | |
| CN110706770B (en) | Cardiac data processing apparatus, cardiac data processing method, and computer-readable storage medium | |
| CN110444275A (en) | System and method for quickly calculating blood flow reserve score | |
| US20230222668A1 (en) | Image processing apparatus, image processing method, and recording medium | |
| CN116051544A (en) | Method and system for evaluating arterial branch occlusion by three-dimensional CT | |
| CN116309346A (en) | Medical image detection method, device, equipment, storage medium and program product | |
| LU500981B1 (en) | Image-assisted evaluation device and its application method for calcified plaque of lower limbs artery of diabetes foot | |
| US11452490B2 (en) | Methods and systems for an adaptive perfusion scan | |
| CN111754452B (en) | Detection method, medium and terminal for lower limb deep venous thrombosis based on deep learning | |
| CN113706557B (en) | Method for judging depth in three-dimensional space of pulmonary nodule by symmetrical four-partition of pulmonary parenchyma | |
| Altalhi et al. | Computation of aortic geometry using mr and ct 3d images | |
| CN115005982A (en) | System for guiding interventional operation by matching coronary function detection with intraoperative radiography in real time | |
| CN113539516A (en) | Method and device for acquiring effect after application of treatment scheme | |
| CN115761433A (en) | Deep learning algorithm for coronary arteriosclerosis prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |