CN117084654A - Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image - Google Patents
Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image Download PDFInfo
- Publication number
- CN117084654A CN117084654A CN202311353496.6A CN202311353496A CN117084654A CN 117084654 A CN117084654 A CN 117084654A CN 202311353496 A CN202311353496 A CN 202311353496A CN 117084654 A CN117084654 A CN 117084654A
- Authority
- CN
- China
- Prior art keywords
- side branch
- occlusion
- temperature difference
- unblocked
- thermal image
- 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
- 230000001815 facial effect Effects 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 73
- 210000001367 artery Anatomy 0.000 title claims abstract description 43
- 230000017531 blood circulation Effects 0.000 title description 7
- 210000004279 orbit Anatomy 0.000 claims abstract description 91
- 210000001061 forehead Anatomy 0.000 claims abstract description 87
- 238000011156 evaluation Methods 0.000 claims abstract description 57
- 206010048964 Carotid artery occlusion Diseases 0.000 claims abstract description 50
- 238000003709 image segmentation Methods 0.000 claims abstract description 29
- 238000013210 evaluation model Methods 0.000 claims abstract description 23
- 230000000004 hemodynamic effect Effects 0.000 claims description 22
- 210000001715 carotid artery Anatomy 0.000 claims description 21
- 238000007477 logistic regression Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 210000004204 blood vessel Anatomy 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000009191 jumping Effects 0.000 claims description 3
- 210000001636 ophthalmic artery Anatomy 0.000 claims 3
- 239000008280 blood Substances 0.000 abstract description 7
- 210000004369 blood Anatomy 0.000 abstract description 7
- 230000005855 radiation Effects 0.000 abstract description 4
- 230000004087 circulation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 206010069729 Collateral circulation Diseases 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000002490 cerebral effect Effects 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 206010008118 cerebral infarction Diseases 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 239000002872 contrast media Substances 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 230000000302 ischemic effect Effects 0.000 description 2
- 230000010412 perfusion Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000008733 trauma Effects 0.000 description 2
- 208000012902 Nervous system disease Diseases 0.000 description 1
- 206010060860 Neurological symptom Diseases 0.000 description 1
- 208000032109 Transient ischaemic attack Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 210000002551 anterior cerebral artery Anatomy 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000001447 compensatory effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 210000003657 middle cerebral artery Anatomy 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 201000010875 transient cerebral ischemia Diseases 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Hematology (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of identification, in particular to a method and a system for evaluating the blood dynamics of an ocular artery side branch based on a facial thermal image. The method comprises the following steps: acquiring a first facial thermal image of a carotid artery occlusion patient, and further, performing image segmentation on the first facial thermal image, and further, performing temperature comparison on the side branch passage area around the occlusion side eye socket and the side branch passage area around the unblocked side eye socket to obtain a first temperature difference; and comparing the temperatures of the occlusion side forehead side branch passage area and the unblocked side forehead side branch passage area to obtain a second temperature difference, and further obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model. By the method, when facial thermal image acquisition is carried out, the carotid artery occlusion patient has better comfort, and non-contact, non-radiation and non-wound are realized.
Description
Technical Field
The invention relates to the technical field of identification, in particular to a method and a system for evaluating the blood dynamics of an ocular artery side branch based on a facial thermal image.
Background
In the early stages of carotid occlusion, blood flow may decrease, but the extent of decrease may vary from individual to individual side branch circulation differences. In the case of chronic or incomplete occlusion, collateral circulation may gradually build up to alleviate ischemic symptoms; however, in the case of acute or total occlusion, the collateral circulation may not be established rapidly, causing significant neurological symptoms such as transient ischemic attacks or cerebral infarction, and even disability, mortality. Thus, for patients with carotid artery occlusion, it is necessary to closely monitor their hemodynamic changes and take appropriate therapeutic measures to avoid serious neurological complications.
Wherein, the ocular artery collateral circulation plays a key role in cerebral and ocular ischemic areas of patients with carotid artery occlusion, such as maintaining cerebral and ocular perfusion stable, delaying cerebral infarction growth rate and striving for a treatment time window. Currently, detection techniques for the ocular arterial side branch circulation include DSA (digital subtraction angiography ) and TCD (transcranial doppler ultrasound, transcranial doppler); DSA can clearly show the ocular artery collateral channel and the compensatory contribution to cerebral blood supply, but the DSA cannot be widely developed due to the causes of originality, large radiation, high cost and the like; TCD can detect the direction of blood flow of the ocular artery and a portion of the side branch, indirectly suggesting the formation of the ocular artery side branch circulation, but cannot determine the actual contribution of the ocular artery side branch passage to brain and ocular perfusion.
In summary, no non-invasive technique exists that can provide auxiliary information for directly assessing ocular arterial side branch hemodynamics.
Disclosure of Invention
The main objective of the present invention is to provide a method and a system for estimating the blood flow dynamics of the ocular artery side branch based on facial thermal images, so as to change the existing situation, that is, no noninvasive technology capable of providing auxiliary information for directly estimating the blood flow dynamics of the ocular artery side branch exists at present.
In order to achieve the above-mentioned object,
the invention provides a method for evaluating the hemodynamics of an ocular artery side branch based on a facial thermal image, which comprises the following steps:
acquiring a first facial thermal image of a carotid occlusion patient; the face of the carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, wherein one side of the carotid artery occlusion is used as an occlusion side, and one side of the carotid artery unblocked is used as an unblocked side;
image segmentation is carried out on the first facial thermal image, so that a side branch access area around an occlusion side eye socket and a forehead side branch access area on the occlusion side, a side branch access area around an unblocked side eye socket and a forehead side branch access area on the unblocked side are obtained;
comparing the temperature of the side branch access area around the blocked side orbit with that of the side branch access area around the unblocked side orbit to obtain a first temperature difference; comparing the temperature of the occlusion side forehead side branch passage area with that of the unblocked side forehead side branch passage area to obtain a second temperature difference;
And obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model.
Alternatively, the first temperature difference is AI 1 A representation; the step of comparing the temperature of the side branch access area around the occlusion side orbit with the temperature of the side branch access area around the unblocked side orbit to obtain a first temperature difference comprises the following steps:
based on formula AI 1 =（T 1 - T 2 ）/（T 1 + T 2 ) X 200, solve AI 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein T is 1 To average temperature, T, of the side branch access area around the occlusion side orbit 2 An average temperature for the open side orbit surrounding side branch access region;
the second temperature difference AI 2 A representation; the step of comparing the temperature of the occlusion side forehead side branch passage area with the temperature of the unblocked side forehead side branch passage area to obtain a second temperature difference comprises the following steps:
based on formula AI 2 =（T 3 - T 4 ）/（T 3 + T 4 ) X 200, solve AI 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein T is 3 T is the average temperature of the occlusion side forehead side branch passage zone 4 For the clear side forehead side branch access zoneIs used for the temperature control of the temperature sensor.
Optionally, the probability evaluation model is an alignment chart, including:
a first temperature asymmetry index, which is a continuous variable; and
a first variable line segment corresponding to the first temperature asymmetry index, a value on the first variable line segment representing the first temperature difference; and
A second temperature asymmetry index, which is a continuous variable; and
a second variable line segment corresponding to the second temperature asymmetry index, the value on the second variable line segment representing the second temperature difference; and
the score line segment is used for representing the scores of the points on the first variable line segment and the scores of the points on the second variable line segment, wherein the score corresponding to the first temperature difference on the score line segment is used as a first score, and the score corresponding to the second temperature difference on the score line segment is used as a second score; and
a total score segment, the total score of which represents the sum of the first score and the second score; and
a probability line segment, wherein the numerical value of the probability line segment represents the probability corresponding to each total score on the total score segment;
the step of obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model comprises the following steps:
based on formula S 1 =-16.666666667 * AI 1 + 58.333333333 solving for S 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein S is 1 Is the first score;
based on formula S 2 =-5.842783141 * AI 2 + 11.685566282 solving for S 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein S is 2 Is the second score;
display S 1 、S 2 And the probability evaluation model is used for a user to obtain the probability evaluation result.
Optionally, the step of obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model includes: inputting the first temperature difference and the second temperature difference into the probability assessment model;
the probability-estimating model is used for estimating the probability of the probability,
based on formula S 1 =-16.666666667 * AI 1 + 58.333333333 solving for S 1 The method comprises the steps of carrying out a first treatment on the surface of the And
based on formula S 2 =-5.842783141 * AI 2 + 11.685566282 solving for S 2 The method comprises the steps of carrying out a first treatment on the surface of the And
based on formula S 3 =S 1 +S 2 Solving S 3 The method comprises the steps of carrying out a first treatment on the surface of the And
based on the formula p= -2.1901e-5*S 3 ^3+0.004851776*S 3 ^2-0.324173844*S 3 + 6.80133679, solving for P; and
and outputting P as the probability evaluation result.
Optionally, the step of performing image segmentation on the first facial thermal image to obtain a side branch access area around the occlusion orbit and a forehead side branch access area around the occlusion orbit, and a side branch access area around the unblocked orbit and a forehead side branch access area around the unblocked orbit, which are both located on the unblocked side, includes: extracting characteristic parameters of the first facial thermal image, wherein the characteristic parameters are used for representing the morphology and density of facial blood vessels and the temperature distribution and difference of each region;
clustering the characteristic parameters to obtain a clustering result;
and performing image segmentation according to the clustering result to obtain the side branch passage area around the blocked side orbit, the side branch passage area around the blocked side forehead, the side branch passage area around the unblocked side orbit and the side branch passage area around the unblocked side forehead.
Optionally, before the step of obtaining the corresponding probability evaluation result based on the first temperature difference, the second temperature difference and the preset probability evaluation model, the method further includes: acquiring a facial thermal image set for model training; wherein, the facial thermal image set corresponds to a patient unilateral carotid occlusion and DSA detection for carotid artery has been completed; acquiring a probability evaluation set corresponding to the facial thermal image set;
image segmentation is carried out on the facial thermal image set to obtain a segmented image set; each facial thermal image in the segmented image set is segmented into an occlusion side orbit circumference side branch access area and an occlusion side forehead side branch access area which are both positioned at the occlusion side, and an unblocked side orbit circumference side branch access area and an unblocked side forehead side branch access area which are both positioned at the unblocked side;
temperature comparison is carried out on the side branch passage area around the blocked side orbit and the side branch passage area around the unblocked side orbit of each facial thermal image in the segmented image set to obtain a first temperature difference set; temperature comparison is carried out on the blocked forehead side branch passage area and the unblocked forehead side branch passage area of each facial thermal image in the segmented image set, so that a second temperature difference set is obtained;
Inputting the first temperature difference set, the second temperature difference set and the probability evaluation set into a preset Logistic regression model for training to obtain S in the Logistic regression model 1 、S 2 And P.
Optionally, the probability included in the probability evaluation set includes: 1, representing no or less than a first predetermined degree of ocular artery side-compensation; and
0.5, representing ocular artery side-branch compensation having a second preset degree, the second preset degree being higher than the first preset degree; and 0, representing ocular artery side-branch compensation above a third preset level, the third preset level being higher than the second preset level.
Optionally, the first temperature difference set, the second temperature difference set and the probability evaluation set are input into a preset Logistic regression model to be trained, so as to obtain S in the Logistic regression model 1 、S 2 After the step of calculating the formula of P, the method further comprises: judging whether a preset model optimization period is reached or not at regular time;
and if the model optimization period is reached, jumping to the step of acquiring the facial thermal image set for model training.
Optionally, the step of acquiring a first facial thermal image of a carotid artery occlusion patient includes: acquiring a second facial thermal image of the carotid occlusion patient;
And preprocessing the second facial thermal image to obtain the first facial thermal image.
The present invention also provides a system for assessing ocular artery collateral hemodynamics based on facial thermal images, comprising: an acquisition unit for acquiring a first facial thermal image of a carotid artery occlusion patient; the face of the carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, wherein one side of the carotid artery occlusion is used as an occlusion side, and one side of the carotid artery unblocked is used as an unblocked side;
the segmentation unit is used for carrying out image segmentation on the first facial thermal image to obtain a side branch passage area around an occlusion side eye socket and a forehead side branch passage area on the occlusion side, a side branch passage area around an unblocked side eye socket and a forehead side branch passage area on the unblocked side;
the comparison unit is used for comparing the temperatures of the side branch passage area around the blocked side eye orbit and the side branch passage area around the unblocked side eye orbit to obtain a first temperature difference; comparing the temperature of the occlusion side forehead side branch passage area with that of the unblocked side forehead side branch passage area to obtain a second temperature difference;
and the evaluation unit is used for obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model.
According to the evaluation method provided by the invention, a first facial thermal image of a carotid artery occlusion patient is acquired; the method comprises the steps that the face of a carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, one side with carotid artery occlusion is used as an occlusion side, one side with carotid artery unblocked is used as an unblocked side, further, image segmentation is carried out on a first facial thermal image to obtain an occlusion side orbit surrounding side branch passage area and an occlusion side forehead side branch passage area which are both positioned on the occlusion side, and an unblocked side orbit surrounding side branch passage area and an unblocked side forehead side branch passage area which are both positioned on the unblocked side, further, temperature comparison is carried out on the occlusion side orbit surrounding side branch passage area and the unblocked side orbit surrounding side branch passage area, and a first temperature difference is obtained; and comparing the temperatures of the occlusion side forehead side branch passage area and the unblocked side forehead side branch passage area to obtain a second temperature difference, and further obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model. By the method, firstly, when facial thermal image acquisition is carried out, the carotid artery occlusion patient has better comfortableness, and the non-contact, non-radiation and non-trauma carotid artery occlusion patient is more acceptable; secondly, the visibility of the facial thermal image is strong, so that the patient with carotid artery occlusion and a doctor can intuitively see the side branch circulation condition of the ocular artery; thirdly, the matched equipment (namely the thermal imager) for collecting the facial thermal images is small in size and convenient to use.
Drawings
FIG. 1 is a flow chart of a method for evaluating ocular artery side branch hemodynamics based on facial thermal images according to an embodiment of the present invention;
FIG. 2 is a block diagram illustrating image segmentation according to a first embodiment of the present invention;
FIG. 3 is a schematic view of still another set of image segmentation according to the first embodiment of the present invention;
FIG. 4 is a schematic diagram of a probability evaluation model in a third embodiment of the present invention;
fig. 5 is a schematic diagram of a system for estimating the blood dynamics of an ocular artery side branch based on facial thermal images according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
The embodiment of the invention provides a method for evaluating the blood dynamics of an ocular artery side branch based on a facial thermal image, which is shown in fig. 1 and comprises the following steps:
step S1, acquiring a first facial thermal image of a carotid artery occlusion patient; the face of the carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, and one side of the carotid artery occlusion is used as an occlusion side, and the other side of the carotid artery occlusion is used as an unblocked side.
And S2, performing image segmentation on the first facial thermal image to obtain a side branch passage area around an occlusion side eye socket and a forehead side branch passage area on the occlusion side, and a side branch passage area around an unblocked side eye socket and a forehead side branch passage area on the unblocked side.
S3, comparing the temperatures of the side branch passage area around the blocked side orbit and the side branch passage area around the unblocked side orbit to obtain a first temperature difference; and comparing the temperature of the occlusion side forehead side branch passage area with that of the unblocked side forehead side branch passage area to obtain a second temperature difference.
And S4, obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model.
In step S1, firstly, the facial thermal image can reflect the temperature and heat distribution of the carotid artery occlusion patient, can reflect the blood flow change of skin and tissues, and does not need invasive operation or invasive examination, so that the carotid artery occlusion patient has better comfort when compared with the traditional detection methods (such as DSA and TCD) for facial thermal image acquisition. And secondly, the occlusion side and the smooth side are defined in advance, so that the positions of all areas can be conveniently determined during the subsequent image segmentation. Third, a first facial thermal image is acquired to provide raw data for subsequent image segmentation.
In step S2, if the ocular artery collateral circulation is established, the heat and temperature increase of the side branch access area around the occlusion side orbit and the side branch access area on the occlusion side forehead are promoted, so that the side branch access area around the occlusion side orbit and the side branch access area on the occlusion side forehead are areas needing to be focused; in addition, since the occlusion side orbit surrounding side branch access area and the open side orbit surrounding side branch access area are symmetrical, the occlusion side forehead side branch access area and the open side forehead side branch access area are also symmetrical, and since the open side orbit surrounding side branch access area and the open side forehead side branch access area are both located on the open side, the open side orbit surrounding side branch access area and the open side forehead side branch access area can be used as reference groups to judge whether the heat and temperature conditions of the occlusion side orbit surrounding side branch access area and the occlusion side forehead side branch access area are abnormal, the open side orbit surrounding side branch access area and the open side forehead side branch access area are areas which need to be focused. It can be known that by performing image segmentation, a region needing important attention can be marked, which is beneficial to the efficiency and accuracy of subsequent evaluation.
As an example, fig. 2 is a set of image segmentation schematic diagrams, and fig. 3 is a further set of image segmentation schematic diagrams, wherein reference numeral 1 indicates an occlusion side forehead side branch access area, reference numeral 2 indicates an occlusion side orbit surrounding side branch access area, reference numeral 3 indicates an unblocked side forehead side branch access area, and reference numeral 4 indicates an unblocked side orbit surrounding side branch access area.
In step S3, a first temperature difference and a second temperature difference are obtained for probability evaluation by combining a probability evaluation model later.
In step S4, the probability of a significant temperature difference between the regions in the first facial thermal image may be estimated from the probability estimation result. The probability evaluation result can also be used for assisting doctors in evaluating the hemodynamic state of the side branch of the ocular artery.
The evaluation method provided by the embodiment is that a first facial thermal image of a carotid artery occlusion patient is acquired; the method comprises the steps that the face of a carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, one side with carotid artery occlusion is used as an occlusion side, one side with carotid artery unblocked is used as an unblocked side, further, image segmentation is carried out on a first facial thermal image to obtain an occlusion side orbit surrounding side branch passage area and an occlusion side forehead side branch passage area which are both positioned on the occlusion side, and an unblocked side orbit surrounding side branch passage area and an unblocked side forehead side branch passage area which are both positioned on the unblocked side, further, temperature comparison is carried out on the occlusion side orbit surrounding side branch passage area and the unblocked side orbit surrounding side branch passage area, and a first temperature difference is obtained; and comparing the temperatures of the occlusion side forehead side branch passage area and the unblocked side forehead side branch passage area to obtain a second temperature difference, and further obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model. By the method, firstly, when facial thermal image acquisition is carried out, the carotid artery occlusion patient has better comfortableness, and the non-contact, non-radiation and non-trauma carotid artery occlusion patient is more acceptable; secondly, the visibility of the facial thermal image is strong, so that the patient with carotid artery occlusion and a doctor can intuitively see the side branch circulation condition of the ocular artery; thirdly, the matched equipment (namely the thermal imager) for collecting the facial thermal images is small in size and convenient to use.
Example two
The embodiment of the invention also provides a method for evaluating the blood dynamics of the artery side branch of the eye based on the facial thermal image, which is the same as the embodiment and is not repeated, and the difference is that the first temperature difference is AI 1 A representation; the step of comparing the temperature of the side branch access area around the occlusion side orbit with the temperature of the side branch access area around the unblocked side orbit to obtain a first temperature difference comprises the following steps:
based on formula AI 1 =（T 1 - T 2 ）/（T 1 + T 2 ) X 200, solve AI 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein T is 1 To average temperature, T, of the side branch access area around the occlusion side orbit 2 An average temperature for the open side orbit surrounding side branch access region;
the second temperature difference AI 2 A representation; the step of comparing the temperature of the occlusion side forehead side branch passage area with the temperature of the unblocked side forehead side branch passage area to obtain a second temperature difference comprises the following steps:
based on formula AI 2 =（T 3 - T 4 ）/（T 3 + T 4 ) X 200, solve AI 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein T is 3 T is the average temperature of the occlusion side forehead side branch passage zone 4 For the open side forehead side branch access zoneAverage temperature.
In the step, the average temperature is selected as the temperature index of each region, and the main point is that firstly, the average temperature can comprehensively describe the overall condition of the temperature distribution in the region, so that the overall thermal state of the region is reflected more accurately; secondly, in the thermal image acquisition process, local temperature fluctuation or mutation may be caused by various factors, and the influence of noise and errors can be reduced to a certain extent by calculating the average temperature.
The evaluation method provided in this embodiment is based on the formula AI 1 =（T 1 - T 2 ）/（T 1 + T 2 ) X 200, solve AI 1 Wherein T is 1 To average temperature, T, of the side branch access area around the occlusion side orbit 2 For the average temperature of the side branch passage area around the open side orbit, further, based on the formula AI 2 =（T 3 - T 4 ）/（T 3 + T 4 ) X 200, solve AI 2 Wherein T is 3 T is the average temperature of the occlusion side forehead side branch passage zone 4 An average temperature for the clear side forehead side branch access region. By the method, more accurate first temperature difference and second temperature difference can be obtained, and more accurate data can be provided for subsequent probability evaluation.
Example III
The embodiment of the present invention further provides a method for estimating the hemodynamics of the ocular artery side branch based on the facial thermal image, which is the same as the second embodiment, and the differences are not repeated, as shown in fig. 4, and the probability estimation model is an alignment chart, including:
a first temperature asymmetry index, which is a continuous variable; and
a first variable line segment corresponding to the first temperature asymmetry index, a value on the first variable line segment representing the first temperature difference; and
a second temperature asymmetry index, which is a continuous variable; and
a second variable line segment corresponding to the second temperature asymmetry index, the value on the second variable line segment representing the second temperature difference; and
The score line segment is used for representing the scores of the points on the first variable line segment and the scores of the points on the second variable line segment, wherein the score corresponding to the first temperature difference on the score line segment is used as a first score, and the score corresponding to the second temperature difference on the score line segment is used as a second score; and
a total score segment, the total score of which represents the sum of the first score and the second score; and
a probability line segment, wherein the numerical value of the probability line segment represents the probability corresponding to each total score on the total score segment;
the step of obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model comprises the following steps:
based on formula S 1 =-16.666666667 * AI 1 + 58.333333333 solving for S 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein S is 1 Is the first score;
based on formula S 2 =-5.842783141 * AI 2 + 11.685566282 solving for S 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein S is 2 Is the second score;
display S 1 、S 2 And the probability evaluation model is used for a user to obtain the probability evaluation result.
The evaluation method provided in this embodiment is implemented by displaying S 1 、S 2 And the probability evaluation model has good visualization effect, a user can conveniently search the first score and the second score, and the corresponding probability can be found on the probability line segment by summing the first score and the second score to obtain the total score.
Example IV
The embodiment of the present invention further provides a method for estimating the hemodynamics of the side branch of the ocular artery based on the facial thermal image, which is the same as the second embodiment, and is not repeated, wherein the step of obtaining the corresponding probability estimation result based on the first temperature difference, the second temperature difference and the preset probability estimation model includes: inputting the first temperature difference and the second temperature difference into the probability assessment model;
the probability-estimating model is used for estimating the probability of the probability,
based on formula S 1 =-16.666666667 * AI 1 + 58.333333333 solving for S 1 The method comprises the steps of carrying out a first treatment on the surface of the And
based on formula S 2 =-5.842783141 * AI 2 + 11.685566282 solving for S 2 The method comprises the steps of carrying out a first treatment on the surface of the And
based on formula S 3 =S 1 +S 2 Solving S 3 The method comprises the steps of carrying out a first treatment on the surface of the And
based on the formula p= -2.1901e-5*S 3 ^3+0.004851776*S 3 ^2-0.324173844*S 3 + 6.80133679, solving for P; and
and outputting P as the probability evaluation result.
The evaluation method provided by the embodiment has high automation degree, does not need to be manually participated in operation, and the probability evaluation model can automatically output a probability evaluation result.
Example five
The embodiment of the present invention further provides a method for evaluating the hemodynamics of an ocular artery side branch based on a facial thermal image, which is the same as the first embodiment and is not repeated, and is different in that the step of performing image segmentation on the first facial thermal image to obtain a side branch access area around an occlusion side orbit and a side branch access area around an occlusion side forehead, which are both located on the occlusion side, and a side branch access area around an occlusion side orbit and a side branch access area around an occlusion side forehead, which are both located on the occlusion side, includes: extracting characteristic parameters of the first facial thermal image, wherein the characteristic parameters are used for representing the morphology and density of facial blood vessels and the temperature distribution and difference of each region;
Clustering the characteristic parameters to obtain a clustering result;
and performing image segmentation according to the clustering result to obtain the side branch passage area around the blocked side orbit, the side branch passage area around the blocked side forehead, the side branch passage area around the unblocked side orbit and the side branch passage area around the unblocked side forehead.
Wherein, (1) in the step of extracting the characteristic parameters of the first facial thermal image, the characteristic parameters are extracted as one of key steps, and key information such as morphology and density of facial blood vessels, temperature distribution and difference of each region can be obtained by analyzing the characteristics such as pixel value distribution, texture information and temperature change of the first facial thermal image. The characteristic parameters can objectively reflect the thermal state of biological tissues and provide basis for subsequent analysis. (2) In the step of clustering the feature parameters to obtain a clustering result, performing cluster analysis, and classifying the pixels with similar features in the facial thermal image into one category, wherein the clustering result is helpful for identifying different areas, such as a side branch passage area around an occlusion side eye orbit, a side branch passage area around an occlusion side forehead, a side branch passage area around an unblocked side eye orbit and a side branch passage area around an unblocked side forehead. By clustering, complex image information can be converted into data which is easier to analyze, thereby providing a basis for image segmentation and subsequent evaluation. (3) Based on the clustering result, image segmentation is a key step. The image is divided into different areas, so that different tissue structures can be effectively isolated, and quantitative analysis of a specific area is realized.
The evaluation method provided in this embodiment, by extracting the characteristic parameters of the first facial thermal image, the characteristic parameters are used to characterize the morphology and density of facial blood vessels, the temperature distribution and differences of each region, and further,
and clustering the characteristic parameters to obtain a clustering result, and further, performing image segmentation according to the clustering result to obtain the side branch access area around the occlusion side orbit, the side branch access area around the occlusion side forehead, the side branch access area around the unblocked side orbit and the side branch access area around the unblocked side forehead. By the method, the accuracy of subsequent evaluation is improved, and probability evaluation results with more reference significance are provided.
Example six
The embodiment of the present invention further provides a method for estimating the hemodynamics of the side branch of the ocular artery based on the facial thermal image, which is the same as the fourth embodiment and is not repeated, wherein before the step of obtaining the corresponding probability estimation result based on the first temperature difference, the second temperature difference and the preset probability estimation model, the method further includes: acquiring a facial thermal image set for model training; wherein, the facial thermal image set corresponds to a patient unilateral carotid occlusion and DSA detection for carotid artery has been completed; acquiring a probability evaluation set corresponding to the facial thermal image set;
Image segmentation is carried out on the facial thermal image set to obtain a segmented image set; each facial thermal image in the segmented image set is segmented into an occlusion side orbit circumference side branch access area and an occlusion side forehead side branch access area which are both positioned at the occlusion side, and an unblocked side orbit circumference side branch access area and an unblocked side forehead side branch access area which are both positioned at the unblocked side;
temperature comparison is carried out on the side branch passage area around the blocked side orbit and the side branch passage area around the unblocked side orbit of each facial thermal image in the segmented image set to obtain a first temperature difference set; temperature comparison is carried out on the blocked forehead side branch passage area and the unblocked forehead side branch passage area of each facial thermal image in the segmented image set, so that a second temperature difference set is obtained;
inputting the first temperature difference set, the second temperature difference set and the probability evaluation set into a preset Logistic regression model for training to obtain S in the Logistic regression model 1 、S 2 And P.
The Logistic regression model is a common statistical model, and can be used to predict the probability of an event.
The evaluation method provided in this embodiment obtains a probability evaluation set corresponding to a facial thermal image set by obtaining the facial thermal image set for model training, wherein a single-sided carotid artery of a patient corresponding to the facial thermal image set is occluded and DSA detection for the carotid artery has been completed, and further performs image segmentation on the facial thermal image set to obtain a segmented image set, wherein each facial thermal image in the segmented image set is segmented into an occlusion side orbit surrounding side branch access area and an occlusion side forehead side branch access area both located on the occlusion side, an unblocked side orbit surrounding side branch access area and an unblocked side forehead side branch access area both located on the unblocked side, and a segmentation image set Performing temperature comparison on the side branch passage area around the occlusion side orbit and the side branch passage area around the unblocked side orbit of each facial thermal image in the segmented image set to obtain a first temperature difference set, performing temperature comparison on the side branch passage area around the occlusion side forehead and the side branch passage area around the unblocked side of each facial thermal image in the segmented image set to obtain a second temperature difference set, and further inputting the first temperature difference set, the second temperature difference set and the probability evaluation set into a preset Logistic regression model to perform training to obtain S in the Logistic regression model 1 、S 2 And P. By acquiring the high-quality facial thermal image set, the probability evaluation set, the segmentation image set, the first temperature difference set and the second temperature difference set, a more accurate calculation formula can be obtained through a Logistic regression model, so that a subsequent probability evaluation result is more reliable.
Example seven
The embodiment of the present invention further provides a method for estimating the hemodynamics of the ocular artery side branch based on the facial thermal image, which is the same as the sixth embodiment, and is not repeated, wherein the probability included in the probability estimation set includes: 1, representing no or less than a first predetermined degree of ocular artery side-compensation; and
0.5, representing ocular artery side-branch compensation having a second preset degree, the second preset degree being higher than the first preset degree; and 0, representing ocular artery side-branch compensation above a third preset level, the third preset level being higher than the second preset level.
In this step, when the probability is 1, no or little contrast agent in the DSA image of the carotid artery occlusion patient is visualized in the ocular artery; when the probability is 0.5, in the DSA image of the carotid artery occlusion patient, the contrast agent reverses through the ocular artery, and the carotid siphon segment is visible to develop; when the probability is 0, the carotid artery occludes the DSA image of the patient, and the anterior cerebral artery and the middle cerebral artery develop. Since the result of the determination based on DSA images is regarded as a gold standard in the industry, the probability contained in the probability evaluation set is extremely close to the actual evaluation result.
The evaluation method provided by the embodiment can ensure the authenticity and the accuracy of the training data, and is beneficial to obtaining a more accurate calculation formula.
Example eight
The embodiment of the invention also provides a method for estimating the blood dynamics of the ocular artery side branch based on the facial thermal image, which is the same as the sixth embodiment and is not repeated, wherein the difference is that the first temperature difference set, the second temperature difference set and the probability estimation set are input into a preset Logistic regression model for training, so that S in the Logistic regression model is obtained 1 、S 2 After the step of calculating the formula of P, the method further comprises: judging whether a preset model optimization period is reached or not at regular time;
and if the model optimization period is reached, jumping to the step of acquiring the facial thermal image set for model training.
The evaluation method provided in this embodiment determines, by timing, whether a preset model optimization period is reached,
if the model optimization period is reached, the step of obtaining the facial thermal image set for model training is skipped, and the calculation formula can be continuously optimized to improve the accuracy of probability evaluation.
Example nine
The embodiment of the present invention further provides a method for evaluating the hemodynamics of an ocular artery side branch based on a facial thermal image, which is the same as the first embodiment, and is not repeated, and is different in that the step of obtaining the first facial thermal image of the carotid artery occlusion patient includes: acquiring a second facial thermal image of the carotid occlusion patient;
and preprocessing the second facial thermal image to obtain the first facial thermal image.
Among them, the preprocessing methods include but are not limited to noise removal, calibration temperature, and data normalization.
According to the evaluation method provided by the embodiment, the second facial thermal image of the carotid artery occlusion patient is acquired, and then the second facial thermal image is preprocessed to obtain the first facial thermal image. Through preprocessing, the image quality can be improved, and the subsequent characteristic parameter extraction and analysis are facilitated.
Examples ten
The embodiment of the invention also provides a system for evaluating the blood dynamics of the side branch of the ocular artery based on the facial thermal image, as shown in fig. 5, comprising: an acquisition unit 10 for acquiring a first facial thermal image of a carotid artery occlusion patient; the face of the carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, wherein one side of the carotid artery occlusion is used as an occlusion side, and one side of the carotid artery unblocked is used as an unblocked side;
a segmentation unit 20, configured to perform image segmentation on the first facial thermal image, to obtain a side branch access area around the occlusion orbit and a forehead side branch access area around the occlusion, and a side branch access area around the unblocked orbit and a forehead side branch access area around the unblocked side;
a comparison unit 30, configured to compare temperatures of the side branch access area around the occlusion side orbit and the side branch access area around the unblocked side orbit, so as to obtain a first temperature difference; comparing the temperature of the occlusion side forehead side branch passage area with that of the unblocked side forehead side branch passage area to obtain a second temperature difference;
and the evaluation unit 40 is configured to obtain a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model.
In this embodiment, for specific implementation of each unit, please refer to the above method embodiment, and detailed description is omitted here.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. A method for assessing ocular artery collateral hemodynamics based on facial thermal images, comprising the steps of:
acquiring a first facial thermal image of a carotid occlusion patient; the face of the carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, wherein one side of the carotid artery occlusion is used as an occlusion side, and one side of the carotid artery unblocked is used as an unblocked side;
Image segmentation is carried out on the first facial thermal image, so that a side branch access area around an occlusion side eye socket and a forehead side branch access area on the occlusion side, a side branch access area around an unblocked side eye socket and a forehead side branch access area on the unblocked side are obtained;
comparing the temperature of the side branch access area around the blocked side orbit with that of the side branch access area around the unblocked side orbit to obtain a first temperature difference; comparing the temperature of the occlusion side forehead side branch passage area with that of the unblocked side forehead side branch passage area to obtain a second temperature difference;
and obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model.
2. The method for estimating ophthalmic artery side branch hemodynamics based on facial thermal images of claim 1, wherein the first temperature difference is AI 1 A representation; the step of comparing the temperature of the side branch access area around the occlusion side orbit with the temperature of the side branch access area around the unblocked side orbit to obtain a first temperature difference comprises the following steps:
based on formula AI 1 =（T 1 - T 2 ）/（T 1 + T 2 ) X 200, solve AI 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein T is 1 To average temperature, T, of the side branch access area around the occlusion side orbit 2 An average temperature for the open side orbit surrounding side branch access region;
the second temperature difference AI 2 A representation; the step of comparing the temperature of the occlusion side forehead side branch passage area with the temperature of the unblocked side forehead side branch passage area to obtain a second temperature difference comprises the following steps:
based on formula AI 2 =（T 3 - T 4 ）/（T 3 + T 4 ) X 200, solve AI 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein T is 3 T is the average temperature of the occlusion side forehead side branch passage zone 4 An average temperature for the clear side forehead side branch access region.
3. The method of assessing ophthalmic arterial side branch hemodynamics based on facial thermal images of claim 2, wherein the probabilistic assessment model is an alignment chart comprising:
a first temperature asymmetry index, which is a continuous variable; and
a first variable line segment corresponding to the first temperature asymmetry index, a value on the first variable line segment representing the first temperature difference; and
a second temperature asymmetry index, which is a continuous variable; and
a second variable line segment corresponding to the second temperature asymmetry index, the value on the second variable line segment representing the second temperature difference; and
the score line segment is used for representing the scores of the points on the first variable line segment and the scores of the points on the second variable line segment, wherein the score corresponding to the first temperature difference on the score line segment is used as a first score, and the score corresponding to the second temperature difference on the score line segment is used as a second score; and
A total score segment, the total score of which represents the sum of the first score and the second score; and
a probability line segment, wherein the numerical value of the probability line segment represents the probability corresponding to each total score on the total score segment;
the step of obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model comprises the following steps:
based on formula S 1 =-16.666666667 * AI 1 + 58.333333333 solving for S 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein S is 1 Is the first score;
based on formula S 2 =-5.842783141 * AI 2 + 11.685566282 solving for S 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein S is 2 Is the second score;
display S 1 、S 2 And the probability evaluation model is used for a user to obtain the probability evaluation result.
4. The method for estimating ophthalmic artery side branch hemodynamics based on facial thermal images according to claim 2, wherein the step of obtaining the corresponding probability estimation result based on the first temperature difference, the second temperature difference and a preset probability estimation model comprises: inputting the first temperature difference and the second temperature difference into the probability assessment model;
the probability-estimating model is used for estimating the probability of the probability,
based on formula S 1 =-16.666666667 * AI 1 + 58.333333333 solving for S 1 The method comprises the steps of carrying out a first treatment on the surface of the And
based on formula S 2 =-5.842783141 * AI 2 + 11.685566282 solving for S 2 The method comprises the steps of carrying out a first treatment on the surface of the And
based on formula S 3 =S 1 +S 2 Solving S 3 The method comprises the steps of carrying out a first treatment on the surface of the And
based on the formula p= -2.1901e-5*S 3 ^3+0.004851776*S 3 ^2-0.324173844*S 3 + 6.80133679, solving for P; and
and outputting P as the probability evaluation result.
5. The method of assessing ophthalmic arterial side branch hemodynamics of claim 1, wherein said step of image segmentation of said first facial thermal image results in a side branch access area around the occlusion side orbit and a side branch access area on the occlusion side, a side branch access area around the occlusion side and a side branch access area on the occlusion side, comprising: extracting characteristic parameters of the first facial thermal image, wherein the characteristic parameters are used for representing the morphology and density of facial blood vessels and the temperature distribution and difference of each region;
clustering the characteristic parameters to obtain a clustering result;
and performing image segmentation according to the clustering result to obtain the side branch passage area around the blocked side orbit, the side branch passage area around the blocked side forehead, the side branch passage area around the unblocked side orbit and the side branch passage area around the unblocked side forehead.
6. The method for evaluating ocular artery side-branch hemodynamics based on the facial thermal image of claim 4,
Before the step of obtaining the corresponding probability evaluation result based on the first temperature difference, the second temperature difference and the preset probability evaluation model, the method further comprises the following steps: acquiring a facial thermal image set for model training; wherein, the facial thermal image set corresponds to a patient unilateral carotid occlusion and DSA detection for carotid artery has been completed; acquiring a probability evaluation set corresponding to the facial thermal image set;
image segmentation is carried out on the facial thermal image set to obtain a segmented image set; each facial thermal image in the segmented image set is segmented into an occlusion side orbit circumference side branch access area and an occlusion side forehead side branch access area which are both positioned at the occlusion side, and an unblocked side orbit circumference side branch access area and an unblocked side forehead side branch access area which are both positioned at the unblocked side;
temperature comparison is carried out on the side branch passage area around the blocked side orbit and the side branch passage area around the unblocked side orbit of each facial thermal image in the segmented image set to obtain a first temperature difference set; temperature comparison is carried out on the blocked forehead side branch passage area and the unblocked forehead side branch passage area of each facial thermal image in the segmented image set, so that a second temperature difference set is obtained;
Inputting the first temperature difference set, the second temperature difference set and the probability evaluation set into a preset Logistic regression model for training to obtain S in the Logistic regression model 1 、S 2 And P.
7. The method of assessing ophthalmic arterial side branch hemodynamics based on facial thermal images of claim 6, wherein the probability contained in the probability assessment set comprises: 1, representing no or less than a first predetermined degree of ocular artery side-compensation; and
0.5, representing ocular artery side-branch compensation having a second preset degree, the second preset degree being higher than the first preset degree; and 0, representing ocular artery side-branch compensation above a third preset level, the third preset level being higher than the second preset level.
8. The method for estimating ophthalmic artery side branch hemodynamics based on facial thermal images according to claim 6, wherein the first temperature difference set, the second temperature difference set and the probability estimation set are input into a preset Logistic regression model for training to obtain S in the Logistic regression model 1 、S 2 After the step of calculating the formula of P, the method further comprises: judging whether a preset model optimization period is reached or not at regular time;
And if the model optimization period is reached, jumping to the step of acquiring the facial thermal image set for model training.
9. The method of assessing ophthalmic arterial side branch hemodynamics based on facial thermal images of claim 1, wherein the step of acquiring a first facial thermal image of a carotid occlusion patient comprises: acquiring a second facial thermal image of the carotid occlusion patient;
and preprocessing the second facial thermal image to obtain the first facial thermal image.
10. A system for assessing ocular artery collateral hemodynamics based on facial thermal images, comprising: an acquisition unit for acquiring a first facial thermal image of a carotid artery occlusion patient; the face of the carotid artery occlusion patient comprises two groups of carotid arteries distributed on the left side and the right side, wherein one side of the carotid artery occlusion is used as an occlusion side, and one side of the carotid artery unblocked is used as an unblocked side;
the segmentation unit is used for carrying out image segmentation on the first facial thermal image to obtain a side branch passage area around an occlusion side eye socket and a forehead side branch passage area on the occlusion side, a side branch passage area around an unblocked side eye socket and a forehead side branch passage area on the unblocked side;
The comparison unit is used for comparing the temperatures of the side branch passage area around the blocked side eye orbit and the side branch passage area around the unblocked side eye orbit to obtain a first temperature difference; comparing the temperature of the occlusion side forehead side branch passage area with that of the unblocked side forehead side branch passage area to obtain a second temperature difference;
and the evaluation unit is used for obtaining a corresponding probability evaluation result based on the first temperature difference, the second temperature difference and a preset probability evaluation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311353496.6A CN117084654B (en) | 2023-10-19 | 2023-10-19 | Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311353496.6A CN117084654B (en) | 2023-10-19 | 2023-10-19 | Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117084654A true CN117084654A (en) | 2023-11-21 |
| CN117084654B CN117084654B (en) | 2024-01-12 |
Family
ID=88780116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311353496.6A Active CN117084654B (en) | 2023-10-19 | 2023-10-19 | Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117084654B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020049384A1 (en) * | 2000-09-29 | 2002-04-25 | John Davidson | Systems and methods for assessing vascular health |
| US6496594B1 (en) * | 1998-10-22 | 2002-12-17 | Francine J. Prokoski | Method and apparatus for aligning and comparing images of the face and body from different imagers |
| CN103917164A (en) * | 2011-08-26 | 2014-07-09 | Ebm株式会社 | Blood-vessel bloodstream simulation system, method therefor, and computer software program |
| US20180153457A1 (en) * | 2016-12-02 | 2018-06-07 | University Of Dayton | Detection of physiological state using thermal image analysis |
| US20180199869A1 (en) * | 2017-01-19 | 2018-07-19 | General Electric Company | Pulse oximetry sensors and methods |
| US20190307388A1 (en) * | 2018-04-10 | 2019-10-10 | Cerenetex, Inc. | Systems and Methods for the Identification of Medical Conditions, and Determination of Appropriate Therapies, by Passively Detecting Acoustic Signals Generated from Cerebral Vasculature |
| CN113974580A (en) * | 2021-10-29 | 2022-01-28 | 苏州爱琴生物医疗电子有限公司 | Carotid artery stenosis degree analysis method based on NIRS technology |
| CN115299915A (en) * | 2022-08-08 | 2022-11-08 | 杭州新瀚光电科技有限公司 | Blood vessel health data acquisition method and system based on infrared thermal wave imaging |
| CN116077024A (en) * | 2023-02-20 | 2023-05-09 | 北京鹰之眼智能健康科技有限公司 | Data processing method based on head infrared image, electronic equipment and storage medium |
| CN116269247A (en) * | 2023-02-17 | 2023-06-23 | 合肥中聚源智能科技有限公司 | Method for detecting carotid artery occlusion by using facial thermal imaging data |
| CN116485810A (en) * | 2023-03-27 | 2023-07-25 | 清华大学 | Carotid artery segmentation method, device and equipment based on magnetic resonance image |
-
2023
- 2023-10-19 CN CN202311353496.6A patent/CN117084654B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6496594B1 (en) * | 1998-10-22 | 2002-12-17 | Francine J. Prokoski | Method and apparatus for aligning and comparing images of the face and body from different imagers |
| US20020049384A1 (en) * | 2000-09-29 | 2002-04-25 | John Davidson | Systems and methods for assessing vascular health |
| CN103917164A (en) * | 2011-08-26 | 2014-07-09 | Ebm株式会社 | Blood-vessel bloodstream simulation system, method therefor, and computer software program |
| US20180153457A1 (en) * | 2016-12-02 | 2018-06-07 | University Of Dayton | Detection of physiological state using thermal image analysis |
| US20180199869A1 (en) * | 2017-01-19 | 2018-07-19 | General Electric Company | Pulse oximetry sensors and methods |
| US20190307388A1 (en) * | 2018-04-10 | 2019-10-10 | Cerenetex, Inc. | Systems and Methods for the Identification of Medical Conditions, and Determination of Appropriate Therapies, by Passively Detecting Acoustic Signals Generated from Cerebral Vasculature |
| CN113974580A (en) * | 2021-10-29 | 2022-01-28 | 苏州爱琴生物医疗电子有限公司 | Carotid artery stenosis degree analysis method based on NIRS technology |
| CN115299915A (en) * | 2022-08-08 | 2022-11-08 | 杭州新瀚光电科技有限公司 | Blood vessel health data acquisition method and system based on infrared thermal wave imaging |
| CN116269247A (en) * | 2023-02-17 | 2023-06-23 | 合肥中聚源智能科技有限公司 | Method for detecting carotid artery occlusion by using facial thermal imaging data |
| CN116077024A (en) * | 2023-02-20 | 2023-05-09 | 北京鹰之眼智能健康科技有限公司 | Data processing method based on head infrared image, electronic equipment and storage medium |
| CN116485810A (en) * | 2023-03-27 | 2023-07-25 | 清华大学 | Carotid artery segmentation method, device and equipment based on magnetic resonance image |
Non-Patent Citations (3)
| Title |
|---|
| 张雄伟;张以善;牛俊英;王翠玉;张红丽;: "经颅多普勒评估颈内动脉系统动脉闭塞患者的侧支循环代偿能力", 中国动脉硬化杂志, no. 05 * |
| 程晓青;田建明;卢光明;左长京;刘嘉;徐嘉璐;: "CT灌注成像评价单侧颈动脉闭塞脑血流动力学与侧支代偿方式", 中国医学影像技术, no. 06 * |
| 范秀玉;王琳娜;范博;吴铁丽;: "颅内外动脉重度狭窄或闭塞患者的侧支循环途径", 中华老年心脑血管病杂志, no. 07 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117084654B (en) | 2024-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fraz et al. | QUARTZ: Quantitative Analysis of Retinal Vessel Topology and size–An automated system for quantification of retinal vessels morphology | |
| Koreen et al. | Evaluation of a computer-based system for plus disease diagnosis in retinopathy of prematurity | |
| WO2021208739A1 (en) | Method and apparatus for evaluating blood vessel in fundus color image, and computer device and medium | |
| JP2002534144A (en) | Method and apparatus for performing a visual field test and computer program for processing the result | |
| CN112716446A (en) | Method and system for measuring pathological change characteristics of hypertensive retinopathy | |
| US20230277151A1 (en) | System and Methods of Prediction of Ischemic Brain Tissue Fate from Multi-Phase CT-Angiography in Patients with Acute Ischemic Stroke using Machine Learning | |
| Vázquez et al. | Improvements in retinal vessel clustering techniques: towards the automatic computation of the arterio venous ratio | |
| CN111340087A (en) | Image recognition method, image recognition device, computer-readable storage medium and computer equipment | |
| Morgan et al. | Objective detection of retinal vessel pulsation | |
| Shoba et al. | Detection of glaucoma disease in fundus images based on morphological operation and finite element method | |
| Aslam et al. | Digital image analysis of plus disease in retinopathy of prematurity | |
| Ţălu et al. | Analysis of normal human retinal vascular network architecture using multifractal geometry | |
| CN115222674A (en) | Detection device for intracranial aneurysm rupture risk based on multi-dimensional feature fusion | |
| CN117084654B (en) | Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image | |
| WO2021046418A1 (en) | Systems and methods for detection and grading of diabetic retinopathy | |
| Huang et al. | Computer-aided detection of retinopathy of prematurity severity in preterm infants via measurement of temporal vessel width and angle | |
| Sedai et al. | Forecasting retinal nerve fiber layer thickness from multimodal temporal data incorporating OCT volumes | |
| CN111971751A (en) | System and method for evaluating dynamic data | |
| US11903742B2 (en) | Non-invasive non-contact system and method for measuring dyslipidemia condition using thermal imaging | |
| CA3211800A1 (en) | System and method for non-invasive determination of intracranial pressure | |
| Díaz et al. | Automatic extraction of vascularity measurements using OCT-A images | |
| Jung et al. | Evaluating a deep-learning system for automatically calculating the stroke ASPECT score | |
| Carmona et al. | Modeling, localization, and segmentation of the foveal avascular zone on retinal OCT-angiography images | |
| Hassanin et al. | Automatic localization of Common Carotid Artery in ultrasound images using Deep Learning | |
| Archana et al. | Classification of plaque in carotid artery using intravascular ultrasound images (IVUS) by machine learning techniques |
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 |