Evaluation method and device applied to maxillofacial region pain caused by cold and hot stimulation and medium

Abstract

The invention discloses a maxillofacial region cold and hot stimulation pain evaluation method and device and a medium. Acquiring image data of the experimental animal in a normal state, and extracting a first facial feature from the image data of the experimental animal in the normal state; acquiring image data of the experimental animal after cold and hot stimulation, and extracting a second facial feature from the image data of the experimental animal after cold and hot stimulation; and comparing the second facial feature with the first facial feature to determine the maxillofacial region cold and hot stimulation pain degree. According to the invention, unsupervised learning is carried out by using a large amount of image data before and after cold and hot stimulation to establish a classification model to predict the pain degree, and based on the classification model, the pain degree can be accurately identified only by acquiring the image data before and after cold and hot stimulation subsequently. The method has advantages in evaluating the analgesic effect and postoperative pain degree of weak opioid drugs.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer image processing, and more specifically, relates to a method, device and medium for evaluating pain caused by cold and hot stimulation of the maxillofacial region. Background Art

[0002] Experimental mice have made an indelible contribution to helping us understand molecular biology. In the study of pain mechanisms and analgesics, the prediction and accurate measurement of pain models is one of the important ways to avoid high costs and improve translational results.

[0003] The facial pain score is a new method for evaluating spontaneous pain behavior, which is applicable to both rat and mouse experiments. This method uses a high-definition electronic camera to capture and analyze the facial expression characteristics of the test animals, such as the size of the eye sockets, the protrusion of the eyes and nose, the position of the ears and the changes in the whiskers, the contraction of the facial muscles, etc., so as to accurately judge the pain level of the experimental animals. However, the current method is still based on manual recognition after the corresponding images are collected. Especially in the case of a large number of experiments, the efficiency of manual recognition is slow and the work intensity is high. In the prior art, there is a lack of a method that can quickly identify stimulating pain. Summary of the invention

[0004] The present invention is provided to solve the above problems existing in the prior art. Therefore, a method, device and medium for evaluating the pain of cold and hot stimulation in the maxillofacial region are needed to quickly and accurately identify the pain degree of experimental animals after being subjected to cold and hot stimulation and give corresponding pain grading results.

[0005] According to a first embodiment of the present invention, a method for evaluating pain caused by hot and cold stimulation in the maxillofacial region is provided, the method comprising:

[0006] Acquire image data of the experimental animal in a normal state, and extract a first facial feature from the image data of the experimental animal in the normal state;

[0007] Acquire image data of the experimental animal after cold and hot stimulation, and extract a second facial feature from the image data of the experimental animal after cold and hot stimulation;

[0008] The second facial feature is compared with the first facial feature to determine the pain degree of cold and hot stimulation of the maxillofacial region.

[0009] Furthermore, the first facial feature includes a first eye feature, a first head feature, a first mouth feature, a first beard feature and a first ear feature, the first eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data of the experimental animal in a normal state, the first head feature is the projection size of the head of the experimental animal in the image data of the experimental animal in a normal state, the first mouth feature is the size of the mouth of the experimental animal in the image data of the experimental animal in a normal state, the first beard feature is the length of the beard of the experimental animal in the image data of the experimental animal in a normal state, and the first ear feature is the size of the ear of the experimental animal in the image data of the experimental animal in a normal state.

[0010] Furthermore, the second facial feature includes a second eye feature, a second head feature, a second mouth feature, a second beard feature and a second ear feature, the second eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation, the second head feature is the projection size of the head of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation, the second mouth feature is the size of the mouth of the experimental animal in the image data of the experimental animal in a normal state, the second beard feature is the length of the beard of the experimental animal in the image data of the experimental animal in a normal state, and the second ear feature is the size of the ear of the experimental animal in the image data of the experimental animal in a normal state.

[0011] Furthermore, comparing the second facial feature with the first facial feature to determine the degree of pain of cold and hot stimulation of the maxillofacial region includes:

[0012] The pain level of hot or cold stimulation to the maxillofacial region is determined based on the difference between the first eye feature and the second eye feature, the difference between the first head feature and the second head feature, the difference between the first mouth feature and the second mouth feature, the difference between the first beard feature and the second beard feature, and / or the difference between the first ear feature and the second ear feature.

[0013] Further, determining the pain degree of the maxillofacial region cold and hot stimulation according to the difference between the first eye feature and the second eye feature includes:

[0014] Using differences between a plurality of first eye features and a second eye feature as data, and randomly dividing the data into K groups;

[0015] Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters.

[0016] When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

[0017] Further, determining the degree of pain of cold and hot stimulation of the maxillofacial region according to the difference between the first facial feature and the second facial feature includes:

[0018] Using differences between a plurality of first head features and a second head feature as data, and randomly dividing the data into K groups;

[0019] Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters.

[0020] When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

[0021] Further, the degree of pain of the maxillofacial cold and hot stimulation is determined according to the difference between the first eye feature and the second eye feature, the difference between the first head feature and the second head feature, the difference between the first mouth feature and the second mouth feature, the difference between the first beard feature and the second beard feature, and the difference between the first ear feature and the second ear feature, including:

[0022] The pain characteristic value is calculated by the following formula:

[0023] X=w1x1+w2x2+w3x3+w4x4+w5x5

[0024] Wherein, X represents the feature value, w1, w2, w3, w4 and w5 represent weight factors, x1 represents the difference between the first eye feature and the second eye feature, x2 represents the difference between the first head feature and the second head feature, x3 represents the difference between the first mouth feature and the second mouth feature, x4 represents the difference between the first beard feature and the second beard feature, and x5 represents the difference between the first ear feature and the second ear feature;

[0025] Using multiple pain characteristic values ​​as data, and randomly dividing the data into K groups;

[0026] Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters.

[0027] When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

[0028] According to the second technical solution of the present invention, a device for evaluating cold and hot stimulation pain in the maxillofacial region is provided, the device comprising:

[0029] A first acquisition module is configured to acquire image data of the experimental animal in a normal state, and extract a first facial feature from the image data of the experimental animal in the normal state;

[0030] A second acquisition module is configured to acquire image data of the experimental animal after the cold and hot stimulation, and extract a second facial feature from the image data of the experimental animal after the cold and hot stimulation;

[0031] The pain determination module is configured to compare the second facial feature with the first facial feature to determine the pain level of cold and hot stimulation of the maxillofacial region.

[0032] Furthermore, the pain determination module is further configured to:

[0033] The pain degree of the maxillofacial region cold or hot stimulation is determined according to the difference between the first eye feature and the second eye feature and / or according to the difference between the first facial feature and the second facial feature.

[0034] According to a third technical solution of the present invention, a readable storage medium is provided, wherein the readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method as described above.

[0035] The present invention has at least the following beneficial effects:

[0036] The present invention uses a large amount of image data before and after cold and hot stimulation for unsupervised learning to establish a classification model that can predict the degree of pain. Based on this classification model, it is only necessary to obtain the image data before and after cold and hot stimulation to accurately identify the degree of pain. This has advantages in evaluating the analgesic effect of weak opioids and the degree of postoperative pain. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It shows an overall flow chart of a method for evaluating cold and hot stimulation pain in the maxillofacial region according to an embodiment of the present invention;

[0038] Figure 2 A device for collecting image data according to an embodiment of the present invention is shown;

[0039] Figure 3Shown is a mouse facial feature diagram according to an embodiment of the present invention;

[0040] Figure 4 A flow chart of clustering based on eye features according to an embodiment of the present invention is shown;

[0041] Figure 5 A flow chart of clustering based on facial features according to an embodiment of the present invention is shown;

[0042] Figure 6 A flow chart of clustering based on eye features and facial features according to an embodiment of the present invention is shown;

[0043] Figure 7 A cat facial feature diagram according to an embodiment of the present invention is shown;

[0044] Figure 8 A structural diagram of a device for evaluating cold and hot stimulation pain in the maxillofacial region according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and specific embodiments, but are not intended to limit the present invention. For the various steps described herein, if there is no necessity for a causal relationship between each other, the order in which they are described as examples herein should not be regarded as a limitation, and those skilled in the art should know that they can be adjusted in order, as long as the logic between them is not destroyed, resulting in the inability to implement the entire process.

[0046] Figure 1 FIG. 4 shows an overall flow chart of a method for evaluating cold and hot stimulation pain in the maxillofacial region according to an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a method for evaluating pain caused by cold or hot stimulation in the maxillofacial region, the method comprising steps S100-S300.

[0047] The method begins at step S100, obtaining image data of an experimental animal in a normal state, and extracting a first facial feature from the image data of the experimental animal in the normal state.

[0048] Step S200, acquiring image data of the experimental animal after the cold and hot stimulation, and extracting a second facial feature from the image data of the experimental animal after the cold and hot stimulation.

[0049] Exemplarily, this embodiment provides a device for collecting image data, such as Figure 2As shown, the device includes an experimental box 201, a drinking trough 202 is arranged in the experimental box 201, and an experimental animal 204 is placed in the experimental box 201. The entire interior of the experimental box 201 is monitored by real-time photography through an image acquisition device 203. For example, the image acquisition device 203 can be three cameras, according to Figure 2 Of course, the image acquisition device 203 can also be set to one, as long as it can achieve global monitoring in the experimental box 201.

[0050] It is understandable that the drinking trough 202 can also be replaced by two water bottles with automatic temperature control function. The two water bottles are respectively provided with temperature sensors, and a controller is uniformly configured. One water bottle has a heating component, and the other water bottle has a cooling component. The water bottle with a heating component controls the heating component to work through the controller under the temperature feedback of the temperature sensor, so that the water temperature is maintained at 55-70°C, and the water bottle with a cooling component controls the cooling component to work through the controller under the temperature feedback of the temperature sensor, so that the water temperature is maintained at 0-4°C. When the mouse drinks, a sensor is added to the drinking spouts of cold water and hot water respectively (automatically identifying whether the mouse is drinking hot water or ice water). After the mouse drinks the water, the automatic facial recognition system of the mouse is immediately started to recognize it.

[0051] The first facial feature is the facial feature of the experimental animals without hot / cold water feeding, please refer to Figure 3 shown.

[0052] The second facial feature is the facial feature of the experimental animals collected after being artificially fed at 55-70°C or ice water.

[0053] It should be noted that since the first facial feature and the second facial feature need to be compared later, the image data collected before and after the cold and hot stimulation should be kept as the data collected when the experimental animal is at substantially the same distance from the image acquisition device 203.

[0054] As an example only, the image acquisition device 203 collects two video stream data, which are respectively the reaction videos of the experimental animals before and after the cold and hot stimulation, and performs frame-by-frame analysis from the two video stream data, and selects the image data of the experimental animals before and after the cold and hot stimulation at the same position to extract the first facial features and the second facial features, so as to ensure the accuracy of the subsequent difference calculation. In addition, it should be noted that the experimental animals, such as mice, after the cold and hot stimulation will run around in the experimental box 201 after being subjected to the emergency, therefore, as long as the position of the mouse in the image data before the cold and hot stimulation is determined, the image data of the mouse passing through the position can be extracted from the video stream, and the corresponding second facial features can be extracted.

[0055] In this embodiment, the first facial feature includes a first eye feature, a first head feature, a first mouth feature, a first beard feature and a first ear feature, the first eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data of the experimental animal in the normal state, the first head feature is the projection size of the head of the experimental animal in the image data of the experimental animal in the normal state, the first mouth feature is the size of the mouth of the experimental animal in the image data of the experimental animal in the normal state, the first beard feature is the length of the beard of the experimental animal in the image data of the experimental animal in the normal state, and the first ear feature is the size of the ear of the experimental animal in the image data of the experimental animal in the normal state.

[0056] In this embodiment, the second facial feature includes a second eye feature, a second head feature, a second mouth feature, a second beard feature and a second ear feature. The second eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation. The second head feature is the projection size of the head of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation. The second mouth feature is the size of the mouth of the experimental animal in the image data of the experimental animal in a normal state. The second beard feature is the length of the beard of the experimental animal in the image data of the experimental animal in a normal state. The second ear feature is the size of the ear of the experimental animal in the image data of the experimental animal in a normal state.

[0057] Finally, in step S300, the second facial feature is compared with the first facial feature to determine the pain level of cold and hot stimulation of the maxillofacial region.

[0058] In this embodiment, the K clustering algorithm is used to process the second facial features and the first facial features collected in multiple pairs of experiments to obtain a classification model. Based on the classification model, in subsequent experiments, only the corresponding second facial features and the first facial features need to be collected to predict the pain level.

[0059] Here, the classification model may have certain differences in the classification process due to different selection of facial features. In simple terms, the pain level of maxillofacial cold and hot stimulation is determined based on the difference between the first eye feature and the second eye feature and / or based on the difference between the first facial feature and the second facial feature.

[0060] In detail, Figure 4 As shown, the degree of pain of cold and hot stimulation of the maxillofacial region is determined according to the difference between the first eye feature and the second eye feature, including:

[0061] Step S401, taking the differences between the first eye features and the second eye features as data, and randomly dividing the data into K groups;

[0062] Step S402, randomly selecting k objects from the data as initial cluster centers, assigning objects in K groups to the cluster center closest to the object, and when a group of data is assigned, the cluster center and the objects assigned to the cluster center are a cluster, and the cluster center of the cluster is updated according to the mean of all objects in the cluster;

[0063] Step S403: when the cluster center does not change or no object is reallocated to a different cluster, a label is allocated to each cluster, and the label is used to distinguish the pain level of maxillofacial cold and heat stimulation.

[0064] like Figure 5 As shown, the degree of pain of cold and hot stimulation of the maxillofacial region is determined according to the difference between the first facial feature and the second facial feature, including:

[0065] Step S501, taking the differences between a plurality of first head features and a second head feature as data, and randomly dividing the data into K groups;

[0066] Step S502, randomly selecting k objects from the data as initial cluster centers, assigning objects in K groups to the cluster center closest to the object, and when a group of data is assigned, the cluster center and the objects assigned to the cluster center are a cluster, and the cluster center of the cluster is updated according to the mean of all objects in the cluster;

[0067] Step S503: when the cluster center does not change or no object is reallocated to a different cluster, a label is allocated to each cluster, and the label is used to distinguish the pain level of maxillofacial cold and heat stimulation.

[0068] The above examples are examples of using only one of the facial features as a pain judgment factor. In the following embodiment, multiple facial features are used as pain judgment factors to more accurately identify the pain of experimental animals after being subjected to cold or hot stimulation.

[0069] like Figure 6 As shown, the degree of cold and hot stimulation pain in the maxillofacial region is determined according to the difference between the first eye feature and the second eye feature, the difference between the first head feature and the second head feature, the difference between the first mouth feature and the second mouth feature, the difference between the first beard feature and the second beard feature, and the difference between the first ear feature and the second ear feature, including:

[0070] Step S601, calculate the pain feature value by X=w1x1+w2x2+w3x3+w4x4+w5x5:

[0071] Among them, X represents the pain feature value, w1, w2, w3, w4 and w5 represent weight factors, x1 represents the difference between the first eye feature and the second eye feature, x2 represents the difference between the first head feature and the second head feature, x3 represents the difference between the first mouth feature and the second mouth feature, x4 represents the difference between the first beard feature and the second beard feature, and x5 represents the difference between the first ear feature and the second ear feature.

[0072] It should be noted that the weight factors are set according to actual conditions to satisfy w1+w2+w3+w4+w5=1. For example, w1, w2, w3, w4 and w5 can all be set to 0.2.

[0073] Step S602, using a plurality of pain characteristic values ​​as data, and randomly dividing the data into K groups;

[0074] Step S603, randomly selecting k objects from the data as initial cluster centers, assigning objects in the K groups to the cluster center closest to the object, and when a group of data is assigned, the cluster center and the objects assigned to the cluster center are a cluster, and the cluster center of the cluster is updated according to the mean of all objects in the cluster;

[0075] Step S604: when the cluster center does not change or no object is reallocated to a different cluster, a label is allocated to each cluster, and the label is used to distinguish the degree of pain caused by hot and cold stimulation of the maxillofacial region.

[0076] It should be noted that step S603 is an iterative process, and step S604 is an iterative termination condition. After the iterative termination condition is reached, the classification model is formed. When a new first facial feature and a new second facial feature appear, after calculating the pain feature value, the distance between the pain feature value and each cluster center is determined, and the label corresponding to the nearest cluster center corresponds to the first facial feature and the second facial feature. The value of k can be 3, 5, 8, etc., which is not specifically limited in this embodiment.

[0077] For example, Figure 7 As shown, the experimental animals were cats. Figure 7 (a) to (c) in the figure respectively show the facial features of the experimental animals in different states, including eye features, head features, mouth features, beard features and ear features, where Figure 7 (a) represents the facial features in a normal state, i.e., the first facial features. Figure 7 (b) and (c) are the facial features collected under the stimulation state, namely the second facial features. By comparing different facial features, the judgment of pain can be achieved.

[0078] In this embodiment, another method for classifying pain is given. First, a preset data set is given, which includes various pain feature values ​​and their corresponding classification labels. Specifically, by obtaining pictures of experimental animals under certain different stimuli, a pain score is given according to the existing scoring method, and then the pain feature value corresponding to the current experimental animal is calculated based on the method described above. The pain score is used as the label of the corresponding pain feature value, thereby obtaining a data set. In the case of a new pain feature value, the k points closest to the pain feature value in the preset data set are calculated, and the category of the new pain feature value is determined according to the category of the k points and the principle of minority obeys majority. The principle of minority obeys majority means that among the k points, the category of the points that belong to the same category the most is used as the category of the new pain feature value, and the k value is generally selected as an odd number.

[0079] It should be noted that the pain scoring method can use an existing method to score pain, which is not elaborated in detail in this embodiment.

[0080] in addition, Figures 4 to 6 The steps shown in are based on the same technical idea. The difference lies in the different input features when building the classification model, such as Figure 4 The difference between the first eye features and the second eye features is used as input, such as Figure 5 Taking the difference between a plurality of first head features and a second head feature as input, Figure 6 The difference of the five features is taken as the input.

[0081] The embodiment of the present invention provides a device for evaluating pain caused by cold and hot stimulation in the maxillofacial region, such as Figure 8 As shown, the device 800 includes:

[0082] The first acquisition module 801 is configured to acquire image data of the experimental animal in a normal state, and extract a first facial feature from the image data of the experimental animal in the normal state;

[0083] The second acquisition module 802 is configured to acquire image data of the experimental animal after the cold and hot stimulation, and extract the second facial feature from the image data of the experimental animal after the cold and hot stimulation;

[0084] The pain determination module 803 is configured to compare the second facial feature with the first facial feature to determine the pain level of cold and hot stimulation of the maxillofacial region.

[0085] In some embodiments, the first facial feature includes a first eye feature and a first facial feature, the first eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data of the experimental animal in a normal state, and the first facial feature is the projection size of the face of the experimental animal in the image data of the experimental animal in a normal state.

[0086] In some embodiments, the second facial feature includes a second eye feature and a second facial feature, the second eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation, and the second facial feature is the projection size of the face of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation.

[0087] In some embodiments, the pain determination module is further configured to:

[0088] The pain degree of the maxillofacial region cold or hot stimulation is determined according to the difference between the first eye feature and the second eye feature and / or according to the difference between the first facial feature and the second facial feature.

[0089] In some embodiments, the pain determination module is further configured to:

[0090] Using differences between a plurality of first eye features and a second eye feature as data, and randomly dividing the data into K groups;

[0091] Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters.

[0092] When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

[0093] In some embodiments, the pain determination module is further configured to:

[0094] Using differences between a plurality of first facial features and a second facial feature as data, and randomly dividing the data into K groups;

[0095] Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters.

[0096] When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

[0097] In some embodiments, the pain determination module is further configured to:

[0098] The pain characteristic value is calculated by the following formula:

[0099] X=w1x1+w2x2

[0100] Wherein, X represents the feature value, w1 and w2 represent weight factors, x1 represents the difference between the first eye feature and the second eye feature, and x2 represents the difference between the first facial feature and the second facial feature;

[0101] Using multiple pain characteristic values ​​as data, and randomly dividing the data into K groups;

[0102] Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters.

[0103] When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

[0104] It should be noted that the device described in this embodiment belongs to the same technical concept as the method described previously, and can achieve the same technical effect, which will not be repeated here.

[0105] An embodiment of the present invention provides a readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the methods described in the above embodiments.

[0106] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art can use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features can be grouped together to simplify the present invention. This should not be interpreted as a feature of an invention that is not claimed for protection being necessary for any claim. On the contrary, the subject matter of the present invention may be less than all the features of the embodiments of a specific invention. Thus, the following claims are incorporated into the specific embodiments as examples or embodiments, wherein each claim is independently used as a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or arrangements. The scope of the present invention should be determined with reference to the full scope of the equivalent forms of the attached claims and these claims.

Claims

1. A method for evaluating pain caused by hot and cold stimulation in the maxillofacial region, characterized in that: The method comprises: Acquire image data of the experimental animal in a normal state, and extract a first facial feature from the image data of the experimental animal in the normal state; Acquire image data of the experimental animal after cold and hot stimulation, and extract a second facial feature from the image data of the experimental animal after cold and hot stimulation; The second facial feature is compared with the first facial feature to determine the pain degree of cold and hot stimulation of the maxillofacial region.

2. The method according to claim 1, characterized in that The first facial feature includes a first eye feature, a first head feature, a first mouth feature, a first beard feature and a first ear feature. The first eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data of the experimental animal in the normal state. The first head feature is the projection size of the head of the experimental animal in the image data of the experimental animal in the normal state. The first mouth feature is the size of the mouth of the experimental animal in the image data of the experimental animal in the normal state. The first beard feature is the length of the beard of the experimental animal in the image data of the experimental animal in the normal state. The first ear feature is the size of the ear of the experimental animal in the image data of the experimental animal in the normal state.

3. The method according to claim 2, characterized in that The second facial feature includes a second eye feature, a second head feature, a second mouth feature, a second beard feature and a second ear feature. The second eye feature is the projection area size of the left eye and the right eye of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation. The second head feature is the projection size of the head of the experimental animal in the image data after the experimental animal is subjected to cold and hot stimulation. The second mouth feature is the size of the mouth of the experimental animal in the image data of the experimental animal in a normal state. The second beard feature is the length of the beard of the experimental animal in the image data of the experimental animal in a normal state. The second ear feature is the size of the ear of the experimental animal in the image data of the experimental animal in a normal state.

4. The method according to claim 3, characterized in that Comparing the second facial feature with the first facial feature to determine the degree of pain of cold and hot stimulation in the maxillofacial region includes: The pain level of hot or cold stimulation to the maxillofacial region is determined based on the difference between the first eye feature and the second eye feature, the difference between the first head feature and the second head feature, the difference between the first mouth feature and the second mouth feature, the difference between the first beard feature and the second beard feature, and / or the difference between the first ear feature and the second ear feature.

5. The method according to claim 4, characterized in that The pain degree of cold and hot stimulation of the maxillofacial region is determined according to the difference between the first eye feature and the second eye feature, including: Using differences between a plurality of first eye features and a second eye feature as data, and randomly dividing the data into K groups; Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters. When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

6. The method according to claim 4, characterized in that The pain degree of cold and hot stimulation of the maxillofacial region is determined according to the difference between the first head feature and the second head feature, including: Using differences between a plurality of first head features and a second head feature as data, and randomly dividing the data into K groups; Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters. When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

7. The method according to claim 4, characterized in that Determining the degree of cold and hot stimulation pain in the maxillofacial region according to the difference between the first eye feature and the second eye feature, the difference between the first head feature and the second head feature, the difference between the first mouth feature and the second mouth feature, the difference between the first beard feature and the second beard feature, and the difference between the first ear feature and the second ear feature, including: The pain characteristic value is calculated by the following formula: X=w1x1+w2x2+w3x3+w4x4+w5x5 Wherein, X represents the feature value, w1, w2, w3, w4 and w5 represent weight factors, x1 represents the difference between the first eye feature and the second eye feature, x2 represents the difference between the first head feature and the second head feature, x3 represents the difference between the first mouth feature and the second mouth feature, x4 represents the difference between the first beard feature and the second beard feature, and x5 represents the difference between the first ear feature and the second ear feature; Using multiple pain characteristic values ​​as data, and randomly dividing the data into K groups; Randomly select k objects from the data as initial cluster centers, and assign objects in the K groups to the cluster centers closest to the objects. When a group of data is assigned, the cluster centers and the objects assigned to the cluster centers are a cluster, and the cluster centers of the clusters are updated according to the mean of all objects in the clusters. When the cluster center does not change or no object is reallocated to a different cluster, a label is assigned to each cluster, and the label is used to distinguish the pain levels of maxillofacial cold and heat stimulation.

8. A device for evaluating pain caused by hot and cold stimulation in the maxillofacial region, characterized in that: The device comprises: A first acquisition module is configured to acquire image data of the experimental animal in a normal state, and extract a first facial feature from the image data of the experimental animal in the normal state; A second acquisition module is configured to acquire image data of the experimental animal after the cold and hot stimulation, and extract a second facial feature from the image data of the experimental animal after the cold and hot stimulation; The pain determination module is configured to compare the second facial feature with the first facial feature to determine the pain level of cold and hot stimulation of the maxillofacial region.

9. The device according to claim 8, characterized in that The pain determination module is further configured to: The pain degree of the maxillofacial region cold or hot stimulation is determined according to the difference between the first eye feature and the second eye feature and / or according to the difference between the first facial feature and the second facial feature.

10. A readable storage medium, characterized in that: The readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method according to any one of claims 1 to 7.

Images