Patient post-anesthesia pain auxiliary identification method based on near-infrared technology

Abstract

The invention relates to the technical field of image recognition, in particular to a patient post-anesthesia pain auxiliary recognition method based on a near-infrared technology, and the method comprises the steps: obtaining near-infrared images of a surgical site of a patient to be detected after anesthesia at a historical moment and a current moment; determining a temperature rise coefficient, a temperature fluctuation factor and a postoperative pain factor corresponding to each pixel point in the near-infrared image; determining a pain occurrence factor corresponding to each pixel point in the current near-infrared image according to the difference among the temperature rise coefficients, the postoperative pain factors and the temperature rise coefficients corresponding to the pixel points at the same position; and determining a target pain level corresponding to each pixel point in the current near-infrared image according to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image. By analyzing the near-infrared image, the pain levels of different positions of the surgical site of the patient are quantified relatively objectively, so that the accuracy of pain recognition of the patient after anesthesia is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology. Background Art

[0002] After the patient completes the anesthesia surgery, it is often necessary to judge the patient's pain level so that the doctor can evaluate whether the patient needs to be given analgesics. At present, the method commonly used to judge the patient's pain level is to evaluate the patient's pain level through the pain self-rating scale filled out by the patient. However, due to the conceptual differences in the understanding of pain among different patients, it may be difficult for patients to accurately fill out the pain self-rating scale, making it difficult for doctors to obtain the patient's true pain level.

[0003] Currently, there is another method for judging the pain level of a patient: based on the patient's facial image, a neural network is used to determine whether the patient's facial expression is painful, so as to judge the patient's pain level.

[0004] However, when using a neural network to determine whether a patient's facial expression is painful based on the patient's post-anesthesia facial image to determine the patient's pain level, the following technical problems often occur: When judging the patient's pain level by judging whether the patient's facial expression is painful, it is often believed that the more painful the patient's facial expression is, the higher the patient's pain level is. However, different patients have different tolerance levels for pain. For example, some patients do not want to show painful expressions due to subjective psychological factors, so they tend to show a higher tolerance for pain, resulting in the patient's facial expression not being able to objectively and truly reflect the patient's pain level. Therefore, judging the patient's pain level only by judging whether the patient's facial expression is painful may lead to misjudgment of the pain level, resulting in poor accuracy in the patient's post-anesthesia pain recognition. Summary of the invention

[0005] In order to solve the technical problem of poor accuracy in pain recognition after anesthesia in patients, the present invention proposes an auxiliary pain recognition method after anesthesia in patients based on near infrared technology.

[0006] In a first aspect, the present invention provides a method for assisting in identifying pain after anesthesia in patients based on near infrared technology, the method comprising: Acquire near infrared images of the surgical site of the patient to be detected after anesthesia at a historical moment and a current moment, as the historical near infrared image and the current near infrared image respectively; Determine the temperature rise coefficient corresponding to each pixel in the near-infrared image according to the grayscale value corresponding to each pixel in the near-infrared image and the difference between the grayscale value corresponding to the pixel at the same position in the previous frame of near-infrared image; Determine the temperature fluctuation factor corresponding to each pixel point in the near-infrared image according to the distribution of the preset neighborhood maximum value pixel points in the preset surrounding area corresponding to each pixel point in the near-infrared image; Determine a postoperative pain factor corresponding to each pixel point in the near-infrared image according to a temperature rise coefficient and a temperature fluctuation factor in a preset surrounding area corresponding to each pixel point in the near-infrared image; Determine the pain occurrence factor corresponding to each pixel in the current near-infrared image according to the temperature rise coefficient and the postoperative pain factor in the current near-infrared image, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the previous preset number of frames of historical near-infrared images; According to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image, the target pain level corresponding to each pixel point in the current near-infrared image is determined.

[0007] In combination with the first aspect above, in a possible implementation, determining the temperature rise coefficient corresponding to each pixel in the near-infrared image according to the grayscale value corresponding to each pixel in the near-infrared image and the difference between the grayscale value corresponding to the pixel at the same position in the previous frame of the near-infrared image includes: Determine any pixel point in any frame of near-infrared image as a marked pixel point, and select pixels with the same position as the marked pixel point from the previous frame of near-infrared image to which the marked pixel point belongs as reference pixels; Normalizing the difference between the grayscale value corresponding to the marked pixel and the grayscale value corresponding to the reference pixel to obtain a grayscale difference index corresponding to the marked pixel; The product of the grayscale value corresponding to the marked pixel and the grayscale difference index is normalized to obtain the temperature rise coefficient corresponding to the marked pixel.

[0008] In combination with the first aspect above, in a possible implementation, determining the temperature fluctuation factor corresponding to each pixel in the near-infrared image according to the distribution of the preset neighborhood maximum value pixel in the preset surrounding area corresponding to each pixel in the near-infrared image includes: Filter out the pixel with the largest gray value from the preset neighborhood corresponding to each pixel as the pixel with the maximum value in the preset neighborhood; The temperature fluctuation factor corresponding to each pixel in the near-infrared image is determined based on the distances between different preset neighborhood maximum value pixels and their nearest preset neighborhood maximum value pixel in the preset surrounding area corresponding to each pixel in the near-infrared image, and the grayscale distribution between the preset neighborhood maximum value pixel and its nearest preset neighborhood maximum value pixel in the preset surrounding area corresponding to each pixel in the near-infrared image.

[0009] In combination with the first aspect above, in a possible implementation, the formula corresponding to the temperature fluctuation factor corresponding to the pixel point in the near-infrared image is: ;in, It is Frame near infrared image The temperature fluctuation factor corresponding to each pixel; is the serial number of the near-infrared image; is the serial number of the pixel in each frame of near-infrared image; is the hyperbolic tangent function; It is Frame near infrared image The number of pixels with a preset neighborhood maximum value in the preset surrounding area corresponding to the pixel point; It is Frame near infrared image The sequence number of the pixel point with the preset neighborhood maximum value in the preset surrounding area corresponding to the pixel point; It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The gray value corresponding to the maximum value pixel of the preset neighborhood; It is Frame near infrared image The gray value corresponding to the maximum pixel point in the target neighborhood in the preset surrounding area corresponding to the pixel point; the maximum pixel point in the target neighborhood is the gray value corresponding to the pixel point The preset neighborhood maximum value pixel point closest to the preset neighborhood maximum value pixel point; It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The mean of the grayscale values ​​corresponding to all pixels on the line between the maximum pixel point in the preset neighborhood and the maximum pixel point in the target neighborhood; is a pre-set factor greater than 0; It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The distance between the maximum pixel point in the preset neighborhood and the maximum pixel point in the target neighborhood.

[0010] In combination with the first aspect above, in a possible implementation, determining the postoperative pain factor corresponding to each pixel in the near-infrared image according to the temperature rise coefficient and the temperature fluctuation factor in the preset surrounding area corresponding to each pixel in the near-infrared image includes: The average value of the temperature fluctuation factors corresponding to all the pixels in the preset surrounding area corresponding to each pixel is determined as the temperature fluctuation representative indicator corresponding to each pixel; Normalizing the variance of the temperature rise coefficients corresponding to all pixels in the preset surrounding area corresponding to each pixel to obtain a temperature rise distribution factor corresponding to each pixel; The absolute value of the difference between the temperature fluctuation representative index and the temperature rise distribution factor corresponding to each pixel point is normalized to obtain the postoperative pain factor corresponding to each pixel point.

[0011] In combination with the first aspect above, in a possible implementation, the step of determining the pain occurrence factor corresponding to each pixel in the current near-infrared image according to the temperature rise coefficient and the postoperative pain factor in the current near-infrared image, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the previous preset number of frames of historical near-infrared images, includes: Determine the overall temperature rise coefficient corresponding to the current near infrared image according to the temperature rise coefficients and postoperative pain factors corresponding to all pixels in the current near infrared image; Determine each frame of historical near infrared images among a preset number of frames of historical near infrared images before the current near infrared image as a reference infrared image; The pain occurrence factor corresponding to each pixel in the current near-infrared image is determined based on the overall temperature rise coefficient, the grayscale value corresponding to each pixel in the current near-infrared image and the grayscale value corresponding to the pixel at the same position in the reference infrared image of a preset number of frames, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the reference infrared image of a preset number of frames.

[0012] In combination with the first aspect above, in a possible implementation, the formula corresponding to the overall temperature rise coefficient corresponding to the current near-infrared image is: ;in, is the overall temperature rise coefficient corresponding to the current near-infrared image; is the hyperbolic tangent function; is the number of pixels in each frame of near-infrared image; is the serial number of the pixel in each frame of near-infrared image; It is the first near-infrared image The temperature rise coefficient corresponding to each pixel; is a natural exponential function; It is the first near-infrared image The postoperative pain factor corresponding to each pixel.

[0013] In combination with the first aspect above, in a possible implementation, the formula corresponding to the pain occurrence factor corresponding to the pixel point in the current near-infrared image is: ; ; ; ;in, It is the first near-infrared image The pain occurrence factor corresponding to each pixel; is the serial number of the pixel in each frame of near-infrared image; is the normalization function; It is the first near-infrared image The gray value corresponding to the pixel is the same as the gray value of the reference infrared image in the preset number of frames. The accumulated value of the grayscale value corresponding to each pixel; is the overall temperature rise coefficient corresponding to the current near-infrared image; is a natural exponential function; Characterization The temperature change of each pixel location; is the preset quantity; is the serial number of the reference infrared image; It is Frame reference infrared image The difference between the temperature rise coefficient corresponding to a pixel point and the temperature rise coefficient corresponding to the pixel point at the same position in the next frame of infrared image; It is Frame reference infrared image The difference between the temperature rise coefficient corresponding to a pixel point and the temperature rise coefficient corresponding to the pixel point at the same position in the next frame of infrared image; It is Frame reference infrared image The temperature rise coefficient corresponding to each pixel; It is The first infrared image after the frame reference infrared image The temperature rise coefficient corresponding to each pixel; It is The frame reference infrared image The temperature rise coefficient corresponding to each pixel; It is The first infrared image after the frame reference infrared image The temperature rise coefficient corresponding to each pixel.

[0014] In combination with the first aspect above, in a possible implementation, determining the target pain level corresponding to each pixel in the current near-infrared image according to the pain occurrence factor and the postoperative pain factor corresponding to each pixel in the current near-infrared image includes: Normalizing the product of the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image to obtain the target pain index corresponding to each pixel point in the current near-infrared image; According to the target pain index corresponding to each pixel point in the current near infrared image, the target pain level corresponding to each pixel point in the current near infrared image is determined.

[0015] In combination with the first aspect above, in a possible implementation, determining the target pain level corresponding to each pixel in the current near infrared image according to the target pain index corresponding to each pixel in the current near infrared image includes: If the target pain index corresponding to the pixel point is greater than the preset pain threshold, the pixel point is determined as a pain pixel point; If the pixel is a pain pixel and the proportion of pain pixels in its corresponding preset neighborhood is greater than or equal to the preset proportion, the target pain level corresponding to the pixel is set to a high pain level, otherwise the target pain level corresponding to the pixel is set to a low pain level.

[0016] In a second aspect, the present invention provides a patient post-anesthesia pain auxiliary identification system based on near infrared technology, the system comprising: A near infrared image acquisition module is used to acquire near infrared images of the surgical site of the patient to be detected after anesthesia at a historical moment and a current moment, respectively as a historical near infrared image and a current near infrared image; A temperature rise coefficient determination module is used to determine the temperature rise coefficient corresponding to each pixel in the near-infrared image according to the grayscale value corresponding to each pixel in the near-infrared image and the difference between the grayscale value corresponding to the pixel at the same position in the previous frame of the near-infrared image; A temperature fluctuation factor determination module, used to determine the temperature fluctuation factor corresponding to each pixel point in the near-infrared image according to the distribution of the preset neighborhood maximum value pixel points in the preset surrounding area corresponding to each pixel point in the near-infrared image; A postoperative pain factor determination module is used to determine the postoperative pain factor corresponding to each pixel point in the near-infrared image according to the temperature rise coefficient and the temperature fluctuation factor in the preset surrounding area corresponding to each pixel point in the near-infrared image; A pain occurrence factor determination module is used to determine the pain occurrence factor corresponding to each pixel point in the current near-infrared image based on the temperature rise coefficient and the postoperative pain factor in the current near-infrared image and the difference between the temperature rise coefficient corresponding to each pixel point in the current near-infrared image and the temperature rise coefficient corresponding to the pixel point at the same position in the previous preset number of frames of historical near-infrared images; The target pain level determination module is used to determine the target pain level corresponding to each pixel point in the current near-infrared image according to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image.

[0017] In a third aspect, a server is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation of the first aspect.

[0018] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0019] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0020] The present invention has the following beneficial effects: The present invention's method for assisting in identifying pain after anesthesia for patients based on near-infrared technology analyzes near-infrared images to relatively objectively quantify the pain levels at different locations of the patient's surgical site, thereby solving the technical problem of poor accuracy in identifying pain after anesthesia for patients, and thus improving the accuracy of identifying pain after anesthesia for patients. In actual situations, the surgical site after anesthesia may have abnormal temperature distribution due to inflammation or infection, thereby aggravating the patient's pain level. The present invention quantifies multiple factors related to the temperature distribution of the surgical site, such as the temperature rise coefficient and the temperature fluctuation factor, by analyzing historical near-infrared images and current near-infrared images, thereby quantifying factors related to the degree of pain, such as the postoperative pain factor and the pain occurrence factor, and then relatively objectively quantifies the target pain level that characterizes the pain level at different locations of the surgical site, and to a certain extent reduces the influence of the patient's subjective psychological factors or subjective pain understanding factors, thereby improving the accuracy of identifying pain after anesthesia for patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A flowchart of the method for assisting in identifying pain after anesthesia in patients based on near infrared technology of the present invention; Figure 2 It is a schematic diagram of the composition structure of the patient post-anesthesia pain auxiliary identification system based on near infrared technology of the present invention; Figure 3 The figure is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION

[0023] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0024] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0025] refer to Figure 1 , shows the process of some embodiments of the method for assisting in identifying pain after anesthesia of a patient based on near infrared technology according to the present invention. The method for assisting in identifying pain after anesthesia of a patient based on near infrared technology comprises the following steps: Step S1, obtaining near infrared images of the surgical site of the patient to be detected after anesthesia at a historical moment and a current moment, as the historical near infrared image and the current near infrared image, respectively.

[0026] The patient to be detected may be a patient undergoing pain recognition after anesthesia. The surgical site may be a body site undergoing surgery. The historical moment may be a moment before the current moment.

[0027] As an example, a near-infrared imaging device can be used to collect a near-infrared image of the surgical site of the patient to be detected every 5 seconds during the current time period, and the near-infrared image collected at the end of the current time period is used as the current near-infrared image, and each near-infrared image except the current near-infrared image among all the near-infrared images collected during the current time period is used as a historical near-infrared image. The current time period can be the time period after the anesthesia surgery of the patient to be detected, and its start time can be the end time of the surgery of the patient to be detected, and its end time can be the current time. Each image acquisition moment except the end time in the current time period is a historical moment. The near-infrared imaging device can be a NIRS (Near Infrared Spectroscopy, imaging using near-infrared spectroscopy) device. Near-infrared technology (NIR) is a technology that analyzes and images by detecting radiation within the near-infrared spectrum, and is widely used in medicine, life sciences, materials research and other fields.

[0028] It should be noted that before monitoring, the NIRS device often needs to be calibrated to ensure that its measurement is accurate. According to the device manual, you can check whether the light source, probe and sensor are working properly, and select the appropriate NIRS probe according to the patient's postoperative site; use sterile detergent to clean the imaging site to remove dirt and grease to ensure a clear image; aim the near-infrared imaging probe at the target site and ensure that the probe is in good contact with the skin; start the near-infrared imaging device, start image acquisition of the postoperative area, and adjust the imaging parameters as needed, such as exposure time and light source intensity, so that a near-infrared image of the patient's surgical site can be obtained.

[0029] In actual situations, the patient may experience local temperature rise due to inflammation or infection after surgery, and during the healing process, temperature changes can reflect the state of blood circulation and metabolism. Therefore, the embodiment of the present invention subsequently performs pain assessment by analyzing the temperature increase and abnormal temperature changes at the patient's surgical site in the collected near-infrared images.

[0030] Step S2, determining the temperature rise coefficient corresponding to each pixel in the near-infrared image according to the grayscale value corresponding to each pixel in the near-infrared image and the difference between the grayscale value corresponding to the pixel at the same position in the previous frame of near-infrared image.

[0031] As an example, this step may include the following steps: In the first step, any pixel in any frame of near-infrared image is determined as a marked pixel, and pixels with the same position as the marked pixel are selected from the previous frame of near-infrared image to which the marked pixel belongs as reference pixels.

[0032] In the second step, the difference between the grayscale value corresponding to the marked pixel and the grayscale value corresponding to the reference pixel is normalized to obtain a grayscale difference index corresponding to the marked pixel.

[0033] In the third step, the product of the gray value corresponding to the above-mentioned marked pixel and the gray difference index is normalized to obtain the temperature rise coefficient corresponding to the above-mentioned marked pixel.

[0034] For example, the formula for determining the temperature rise coefficient corresponding to a pixel point in a near infrared image can be: ; ;in, It is Frame near infrared image The temperature rise coefficient corresponding to each pixel. is the sequence number of the near-infrared image. It is the serial number of the pixel in each frame of near infrared image. is the hyperbolic tangent function. It is Frame near infrared image The gray value corresponding to each pixel. It is Frame near infrared image The grayscale difference index corresponding to each pixel. is a normalization function. It is Frame near infrared image The gray value corresponding to the pixel point. Pixels can represent pixels at the same position in different near-infrared images.

[0035] It should be noted that pixels with higher grayscale values ​​in near-infrared images often reflect the location of body parts with higher temperatures, while pixels with lower grayscale values ​​often reflect the location of body parts with lower temperatures. Secondly, the temperature rise at the surgical site due to inflammation or infection is often higher than the temperature rise that occurs when the surgical site recovers normally. Therefore, when a certain part of the body experiences a high temperature rise, it often indicates that inflammation or infection is more likely to occur at that location, and the degree of pain at that location is likely to be greater. The larger the Frame near infrared image The larger the gray value corresponding to the pixel point, the larger the gray value corresponding to the pixel point. The temperature at the location represented by the pixel point may be higher. The larger the The pixel at The grayscale in the near infrared image of the first frame is more likely to be higher than that in the The grayscale in the near-infrared image of the frame often indicates the The temperature at the location represented by the pixel point is more likely to show a rising trend. The larger the The pixel represents the location of the part in The more likely the acquisition time of the near-infrared image of the frame is to show a trend of high temperature rise, it often indicates that the The pixel represents the location of the part in The frame near-infrared image corresponding to the acquisition moment is more likely to present a higher pain level.

[0036] Step S3, determining the temperature fluctuation factor corresponding to each pixel point in the near-infrared image according to the distribution of the preset neighborhood maximum value pixel points in the preset surrounding area corresponding to each pixel point in the near-infrared image.

[0037] The preset surrounding area may be a preset rectangular area. For example, the preset surrounding area may be a 7×7 area. The pixel point may be located at the center of its corresponding preset surrounding area.

[0038] As an example, this step may include the following steps: In the first step, the pixel with the largest gray value is selected from the preset neighborhood corresponding to each pixel as the pixel with the maximum value in the preset neighborhood.

[0039] The preset neighborhood may be a preset rectangular neighborhood whose size is smaller than the size of the preset surrounding area. For example, the preset neighborhood may be a 3×3 neighborhood. The pixel point may be located at the center of its corresponding preset neighborhood. A pixel point in the near-infrared image may correspond to a preset neighborhood maximum value pixel point, and therefore, the near-infrared image may contain multiple preset neighborhood maximum value pixels.

[0040] In the second step, the temperature fluctuation factor corresponding to each pixel in the near-infrared image is determined based on the distances between different preset neighborhood maximum value pixels and their nearest preset neighborhood maximum value pixels in the preset surrounding areas corresponding to each pixel in the near-infrared image, and the grayscale distribution between the preset neighborhood maximum value pixels and their nearest preset neighborhood maximum value pixels in the preset surrounding areas corresponding to each pixel in the near-infrared image.

[0041] For example, the formula for determining the temperature fluctuation factor corresponding to a pixel point in a near-infrared image may be: ;in, It is Frame near infrared image The temperature fluctuation factor corresponding to each pixel. is the sequence number of the near-infrared image. It is the serial number of the pixel in each frame of near infrared image. is the hyperbolic tangent function. It is Frame near infrared image The number of pixels with a preset neighborhood maximum value in the preset surrounding area corresponding to the pixel point. It is Frame near infrared image The sequence number of the pixel point with the preset neighborhood maximum value in the preset surrounding area corresponding to the pixel point. It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The gray value corresponding to the maximum value pixel in the preset neighborhood. It is Frame near infrared image The grayscale value corresponding to the maximum pixel point in the target neighborhood in the preset surrounding area corresponding to the pixel point. The maximum pixel point in the target neighborhood is the pixel point closest to the first pixel point. The preset neighborhood maximum value pixel closest to the preset neighborhood maximum value pixel. It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The average of the grayscale values ​​corresponding to all pixels on the line between the preset neighborhood maximum pixel point and the target neighborhood maximum pixel point. It is a pre-set factor greater than 0, mainly used to prevent the denominator from being 0, for example, It can be 0.001. It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The distance between the maximum pixel point in the preset neighborhood and the maximum pixel point in the target neighborhood.

[0042] It should be noted that inflammation and faster or slower blood flow may occur at the surgical site after surgery, which may cause the temperature change at the surgical site to be significantly different from the normal human body temperature change. Since human tissues are evenly distributed, the change in normal body surface temperature is often smoother. However, after surgery, the sutured wound may become inflamed and infected, and the blood flow at the postoperative site may increase or decrease, which may cause a more obvious temperature change at the surgical site. In other words, the more obvious the temperature change is, the more likely it is that inflammation or infection will occur, and the greater the pain. yes When The smaller the time, the more likely it is that The smaller the distance between the preset neighborhood maximum value pixel and its nearest preset neighborhood maximum value pixel. The larger the The greater the grayscale difference between the two pixels of the preset neighborhood maximum value pixel and its nearest preset neighborhood maximum value pixel and their surrounding pixels, the greater the grayscale difference between the two pixels of the preset neighborhood maximum value pixel and its surrounding pixels. The greater the grayscale change between the maximum value pixel of the first preset neighborhood and its nearest maximum value pixel of the first preset neighborhood, the greater the grayscale change between the maximum value pixel of the first preset neighborhood. The greater the temperature change between the position represented by the preset neighborhood maximum pixel point and the position represented by the nearest preset neighborhood maximum pixel point. The larger the Frame near infrared image The greater the grayscale change between the preset neighborhood maximum value pixels in the preset surrounding area corresponding to the pixel point, the greater the grayscale change between the preset neighborhood maximum value pixels in the preset surrounding area corresponding to the pixel point. Frame near infrared image The greater the grayscale change in the preset surrounding area corresponding to the pixel point, the greater the grayscale change in the preset surrounding area. The pixel points represent the position of the part around the The greater the temperature change at the acquisition time corresponding to the frame near-infrared image, the greater the temperature change at the acquisition time corresponding to the frame near-infrared image. At the acquisition time corresponding to the frame near infrared image, The greater the pain level around the area represented by the pixels, the greater the pain level may be.

[0043] Step S4, determining the postoperative pain factor corresponding to each pixel point in the near-infrared image according to the temperature rise coefficient and the temperature fluctuation factor in the preset surrounding area corresponding to each pixel point in the near-infrared image.

[0044] As an example, this step may include the following steps: In the first step, the average value of the temperature fluctuation factors corresponding to all pixels in the preset surrounding area corresponding to each pixel is determined as the representative indicator of the temperature fluctuation corresponding to each pixel.

[0045] In the second step, the variance of the temperature rise coefficients corresponding to all pixels in the preset surrounding area corresponding to each pixel is normalized to obtain the temperature rise distribution factor corresponding to each pixel.

[0046] In the third step, the absolute value of the difference between the temperature fluctuation representative index and the temperature rise distribution factor corresponding to each pixel point is normalized to obtain the postoperative pain factor corresponding to each pixel point.

[0047] For example, the formula for determining the postoperative pain factor corresponding to a pixel point in a near-infrared image can be: ;in, It is Frame near infrared image The postoperative pain factor corresponding to each pixel. is the sequence number of the near-infrared image. It is the serial number of the pixel in each frame of near infrared image. is the hyperbolic tangent function. It is the absolute value function. It is Frame near infrared image The temperature fluctuation corresponding to the pixel represents the index, that is, Frame near infrared image The average value of the temperature fluctuation factors corresponding to all pixels in the preset surrounding area corresponding to the pixel point. It is Frame near infrared image The variance of the temperature rise coefficients corresponding to all pixels in the preset surrounding area corresponding to the pixel point. It is Frame near infrared image The temperature rise distribution factor corresponding to each pixel.

[0048] It should be noted that since the postoperative site often involves operations such as suturing, there may be some faults in the postoperative site, which leads to a more obvious temperature fluctuation distribution in the postoperative site. Therefore, the temperature fluctuation factor of the postoperative site is often large, and the pain level is relatively high. Inflammation may occur around the suture site, resulting in a difference between the temperature rise and the surrounding normal area. Since the embodiment of the present invention can identify pain within a short period of time after surgery, even if there is inflammation or infection in the surgical site, it is often relatively mild. Therefore, there are often normal areas around the inflamed or infected area. Therefore, due to the existence of normal areas around the inflamed or infected area, the overall temperature fluctuation level may be lowered, because the temperature fluctuation levels at different positions in the normal area are often small, and tend to widen the overall temperature rise difference.

[0049] when The bigger and The smaller the time, the more likely it is that Frame near infrared image The larger the temperature fluctuation around a pixel and the more uniform the temperature rise trend, the more likely it is that the Frame near infrared image The more likely the location represented by the pixel point is a postoperative surgical site with uneven temperature distribution and more consistent temperature rise, the greater the pain level. The smaller and The larger the Frame near infrared image The temperature fluctuation around the pixel is relatively small and the temperature rise trend is relatively discrete, which often indicates that the Frame near infrared image The more pixels represent the location, the more likely it is that there is inflammation or infection. The larger the Frame near infrared image The more pixels represent the location, the more likely it is that the surgery site, inflammation or infection is present. Frame near infrared image The pain level at the location represented by the pixel point is relatively greater.

[0050] Step S5, determining the pain occurrence factor corresponding to each pixel in the current near-infrared image based on the temperature rise coefficient and the postoperative pain factor in the current near-infrared image, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the historical near-infrared images of a preset number of frames before it.

[0051] The preset number may be a preset number of images, for example, 5.

[0052] As an example, this step may include the following steps: In the first step, the overall heating coefficient corresponding to the current near-infrared image is determined according to the heating coefficients and postoperative pain factors corresponding to all pixels in the current near-infrared image.

[0053] For example, the formula for determining the overall temperature rise coefficient corresponding to the current near infrared image can be: ;in, is the overall temperature rise coefficient corresponding to the current near-infrared image. is the hyperbolic tangent function. is the number of pixels in each frame of near-infrared image. It is the serial number of the pixel in each frame of near infrared image. It is the first near-infrared image The temperature rise coefficient corresponding to each pixel. is a natural exponential function. It is the first near-infrared image The postoperative pain factor corresponding to each pixel.

[0054] It should be noted that Can be used as When The smaller the time, the more likely it is that Frame near infrared image The more likely the part represented by the pixel point is a normal part, the more its corresponding temperature rise situation can represent the temperature rise situation in the normal area of ​​the human body, and the more its temperature rise situation should be retained. It can characterize the overall temperature rise in the normal area of ​​the human body.

[0055] In the second step, each frame of the historical near infrared image in a preset number of frames before the current near infrared image is determined as a reference infrared image, so as to obtain a preset number of frames of reference infrared images.

[0056] The third step is to determine the pain occurrence factor corresponding to each pixel in the current near-infrared image based on the above-mentioned overall temperature rise coefficient, the grayscale value corresponding to each pixel in the current near-infrared image and the grayscale value corresponding to the pixel at the same position in the reference infrared image of a preset number of frames, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the reference infrared image of a preset number of frames,

[0057] For example, the formula for determining the pain occurrence factor corresponding to the pixel point in the current near-infrared image may be: ; ; ; ;in, It is the first near-infrared image The pain occurrence factor corresponding to each pixel. It is the serial number of the pixel in each frame of near infrared image. is a normalization function. It is the first near-infrared image The gray value corresponding to the pixel is the same as the gray value of the reference infrared image in the preset number of frames. The accumulated value of the grayscale value corresponding to each pixel. is the overall temperature rise coefficient corresponding to the current near-infrared image. is a natural exponential function. Characterization The temperature change of each pixel. is the preset quantity. is the serial number of the reference infrared image, which may be the serial number obtained by sorting the reference infrared images in the order of acquisition time. It is The frame reference infrared image The difference between the temperature rise coefficient corresponding to a pixel point and the temperature rise coefficient corresponding to the pixel point at the same position in the next frame of infrared image. It is The frame reference infrared image The difference between the temperature rise coefficient corresponding to a pixel point and the temperature rise coefficient corresponding to the pixel point at the same position in the next frame of infrared image. It is The frame reference infrared image The temperature rise coefficient corresponding to each pixel. It is The first infrared image after the frame reference infrared image The temperature rise coefficient corresponding to each pixel. It is The frame reference infrared image The temperature rise coefficient corresponding to each pixel. It is The first infrared image after the frame reference infrared image The next infrared image after the last reference infrared image can be the current near infrared image.

[0058] It should be noted that It can represent the overall temperature rise in the normal area of ​​the human body. The smaller the value, the smaller the temperature rise of the patient, which means that the patient is less likely to feel pain and less likely to develop further inflammation. The larger the The grayscale of the pixel in the continuous frame infrared image is large, which often indicates that the The higher the temperature of the part where the pixel represents, the higher the temperature is. In actual situations, during the normal recovery process after surgery, the temperature rise of the surgical site tends to gradually decrease, and the degree of decrease becomes smaller and smaller. During this process, the pain felt by the patient is relatively low. and It can characterize the first The degree of reduction in temperature rise corresponding to each pixel. Can characterize the The change in the degree of temperature reduction corresponding to each pixel point, the larger the value, the more the degree of reduction conforms to the law of gradual decrease, which often indicates that the first The pain level at the location represented by the pixel point is relatively low. The larger the The more pixels represent the location, the more likely it is that a higher pain level will occur.

[0059] Step S6, determining the target pain level corresponding to each pixel point in the current near infrared image according to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near infrared image.

[0060] As an example, this step may include the following steps: In the first step, the product of the pain occurrence factor and the postoperative pain factor corresponding to each pixel in the current near-infrared image is normalized to obtain the target pain index corresponding to each pixel in the current near-infrared image.

[0061] For example, the formula for determining the target pain index corresponding to the pixel point in the current near-infrared image can be: ;in, It is the first near-infrared image The target pain index corresponding to each pixel. It is the serial number of the pixel in each frame of near infrared image. is a normalization function. It is the first near-infrared image The pain occurrence factor corresponding to each pixel. It is the first near-infrared image The postoperative pain factor corresponding to each pixel.

[0062] It should be noted that when The larger the The more pixels represent the location, the more likely it is that a higher pain level will occur. When the value is larger, it often indicates that the part represented by the pixel point in the current near-infrared image is more likely to be a surgical site, an inflammation or infection site, and it often indicates that the pixel point in the current near-infrared image is more likely to be a surgical site, an inflammation or infection site. The pain level of the part represented by the pixel point is relatively greater. The larger the The greater the pain level at the location represented by the pixel points, the greater the pain level at the location represented by the pixel points.

[0063] The second step, according to the target pain index corresponding to each pixel point in the current near infrared image, determines the target pain level corresponding to each pixel point in the current near infrared image, which may include the following sub-steps: In the first sub-step, if the target pain index corresponding to the pixel point is greater than a preset pain threshold, the pixel point is determined as a pain pixel point.

[0064] The preset pain threshold may be a preset threshold for determining the degree of pain. For example, the preset pain threshold may be 0.7.

[0065] In the second sub-step, if the pixel is a pain pixel and the proportion of pain pixels in its corresponding preset neighborhood is greater than or equal to the preset proportion, the target pain level corresponding to the pixel is set to a high pain level, otherwise the target pain level corresponding to the pixel is set to a low pain level.

[0066] The preset ratio may be a preset pixel ratio, for example, 0.5.

[0067] It should be noted that the more pixels with high pain levels in the current near-infrared image, the more severe the pain level of the patient to be detected at the current moment. If there are more pixels with high pain levels in multiple historical near-infrared images that are continuous with the current near-infrared image, it often means that the patient to be detected has been in high pain for a period of time and often needs to be given appropriate analgesics. Among them, commonly used analgesics may include but are not limited to: non-steroidal anti-inflammatory drugs (NSAIDs) and opioids. Non-steroidal anti-inflammatory drugs may include but are not limited to: ibuprofen and acetaminophen. Opioids may include but are not limited to: morphine and fentanyl. Therefore, based on the target pain level of the pixel points, the pain condition of the patient to be detected at the current moment can be judged to assist doctors in identifying the patient's postoperative pain. Specifically, based on the target pain level of the pixel points, judging the pain condition of the patient to be detected at the current moment may include the following steps: First, if the proportion of pixels with high pain levels in the near-infrared image is greater than 40%, the near-infrared image is determined to be a high-pain image.

[0068] Next, if the current near-infrared image and its previous 9 historical near-infrared images are all high-pain images, the pain condition of the patient to be tested at the current moment is determined to be severe pain, and the information is sent to the doctor to assist the doctor in further pain assessment and determine whether appropriate analgesics need to be given to the patient based on the assessment results.

[0069] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a system for assisting the identification of postoperative pain in patients after anesthesia based on near infrared technology. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the above computer program is executed by the processor, the steps of the method for assisting the identification of postoperative pain in patients after anesthesia based on near infrared technology may specifically include: A near infrared image acquisition module 201 is used to acquire near infrared images of the surgical site of the patient to be detected after anesthesia surgery at a historical moment and a current moment, as a historical near infrared image and a current near infrared image respectively; A temperature rise coefficient determination module 202 is used to determine the temperature rise coefficient corresponding to each pixel in the near-infrared image according to the grayscale value corresponding to each pixel in the near-infrared image and the difference between the grayscale value corresponding to the pixel at the same position in the previous frame of the near-infrared image; The temperature fluctuation factor determination module 203 is used to determine the temperature fluctuation factor corresponding to each pixel point in the near-infrared image according to the distribution of the preset neighborhood maximum value pixel points in the preset surrounding area corresponding to each pixel point in the near-infrared image; A postoperative pain factor determination module 204 is used to determine the postoperative pain factor corresponding to each pixel point in the near infrared image according to the temperature rise coefficient and the temperature fluctuation factor in the preset surrounding area corresponding to each pixel point in the near infrared image; The pain occurrence factor determination module 205 is used to determine the pain occurrence factor corresponding to each pixel point in the current near-infrared image according to the temperature rise coefficient and the postoperative pain factor in the current near-infrared image, and the difference between the temperature rise coefficient corresponding to each pixel point in the current near-infrared image and the temperature rise coefficient corresponding to the pixel point at the same position in the historical near-infrared images of a preset number of frames before it; The target pain level determination module 206 is used to determine the target pain level corresponding to each pixel point in the current near-infrared image according to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image.

[0070] Figure 3 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any of the above-mentioned methods for assisting in identifying post-anesthesia pain in patients based on near-infrared technology.

[0071] Based on the same inventive concept as the above method embodiment, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes any of the above-mentioned methods for assisting in identifying pain after anesthesia in patients based on near infrared technology.

[0072] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, enables the computer to execute any one of the above-mentioned methods for auxiliary identification of post-anesthesia pain in patients based on near-infrared technology.

[0073] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned methods for auxiliary identification of post-anesthesia pain in patients based on near-infrared technology.

[0074] In summary, the present invention quantifies multiple factors related to the temperature distribution of the surgical site, such as the temperature rise coefficient and the temperature fluctuation factor, by analyzing historical near-infrared images and current near-infrared images, thereby quantifying factors related to the degree of pain, such as the postoperative pain factor and the pain occurrence factor, and then relatively objectively quantifies the target pain level that characterizes the pain level at different locations of the surgical site, reducing the influence of the patient's subjective psychological factors or subjective pain understanding factors to a certain extent, thereby improving the accuracy of the patient's post-anesthesia pain recognition.

[0075] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for assisting in identifying pain after anesthesia surgery of patients based on near infrared technology, characterized in that: The following steps are involved: Acquire near infrared images of the surgical site of the patient to be detected after anesthesia at a historical moment and a current moment, as the historical near infrared image and the current near infrared image respectively; Determine the temperature rise coefficient corresponding to each pixel in the near-infrared image according to the grayscale value corresponding to each pixel in the near-infrared image and the difference between the grayscale value corresponding to the pixel at the same position in the previous frame of near-infrared image; Determine the temperature fluctuation factor corresponding to each pixel point in the near-infrared image according to the distribution of the preset neighborhood maximum value pixel points in the preset surrounding area corresponding to each pixel point in the near-infrared image; Determine a postoperative pain factor corresponding to each pixel point in the near-infrared image according to a temperature rise coefficient and a temperature fluctuation factor in a preset surrounding area corresponding to each pixel point in the near-infrared image; Determine the pain occurrence factor corresponding to each pixel in the current near-infrared image according to the temperature rise coefficient and the postoperative pain factor in the current near-infrared image, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the previous preset number of frames of historical near-infrared images; According to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image, the target pain level corresponding to each pixel point in the current near-infrared image is determined.

2. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 1, characterized in that: The method of determining the temperature rise coefficient corresponding to each pixel in the near infrared image according to the gray value corresponding to each pixel in the near infrared image and the difference between the gray value corresponding to the pixel at the same position in the previous frame of the near infrared image comprises: Determine any pixel point in any frame of near-infrared image as a marked pixel point, and select pixels with the same position as the marked pixel point from the previous frame of near-infrared image to which the marked pixel point belongs as reference pixels; Normalizing the difference between the grayscale value corresponding to the marked pixel and the grayscale value corresponding to the reference pixel to obtain a grayscale difference index corresponding to the marked pixel; The product of the grayscale value corresponding to the marked pixel and the grayscale difference index is normalized to obtain the temperature rise coefficient corresponding to the marked pixel.

3. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 1, characterized in that: The step of determining the temperature fluctuation factor corresponding to each pixel point in the near infrared image according to the distribution of the preset neighborhood maximum value pixel points in the preset surrounding area corresponding to each pixel point in the near infrared image comprises: Filter out the pixel with the largest gray value from the preset neighborhood corresponding to each pixel as the pixel with the maximum value in the preset neighborhood; The temperature fluctuation factor corresponding to each pixel in the near-infrared image is determined based on the distances between different preset neighborhood maximum value pixels and their nearest preset neighborhood maximum value pixel in the preset surrounding area corresponding to each pixel in the near-infrared image, and the grayscale distribution between the preset neighborhood maximum value pixel and its nearest preset neighborhood maximum value pixel in the preset surrounding area corresponding to each pixel in the near-infrared image.

4. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 3 is characterized in that: The formula for the temperature fluctuation factor corresponding to the pixel point in the near-infrared image is: ;in, It is Frame near infrared image The temperature fluctuation factor corresponding to each pixel; is the serial number of the near-infrared image; is the serial number of the pixel in each frame of near-infrared image; is the hyperbolic tangent function; It is Frame near infrared image The number of pixels with a preset neighborhood maximum value in the preset surrounding area corresponding to the pixel point; It is Frame near infrared image The sequence number of the pixel point with the preset neighborhood maximum value in the preset surrounding area corresponding to the pixel point; It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The gray value corresponding to the maximum value pixel of the preset neighborhood; It is Frame near infrared image The gray value corresponding to the maximum pixel point in the target neighborhood in the preset surrounding area corresponding to the pixel point; the maximum pixel point in the target neighborhood is the gray value corresponding to the pixel point The preset neighborhood maximum value pixel point closest to the preset neighborhood maximum value pixel point; It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The mean of the grayscale values ​​corresponding to all pixels on the line between the maximum pixel point in the preset neighborhood and the maximum pixel point in the target neighborhood; is a pre-set factor greater than 0; It is Frame near infrared image In the preset surrounding area corresponding to the pixel point, The distance between the maximum pixel point in the preset neighborhood and the maximum pixel point in the target neighborhood.

5. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 1, characterized in that: The method of determining the postoperative pain factor corresponding to each pixel point in the near infrared image according to the temperature rise coefficient and the temperature fluctuation factor in the preset surrounding area corresponding to each pixel point in the near infrared image comprises: The average value of the temperature fluctuation factors corresponding to all the pixels in the preset surrounding area corresponding to each pixel is determined as the temperature fluctuation representative indicator corresponding to each pixel; Normalizing the variance of the temperature rise coefficients corresponding to all pixels in the preset surrounding area corresponding to each pixel to obtain a temperature rise distribution factor corresponding to each pixel; The absolute value of the difference between the temperature fluctuation representative index and the temperature rise distribution factor corresponding to each pixel point is normalized to obtain the postoperative pain factor corresponding to each pixel point.

6. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 1, characterized in that: The method of determining the pain occurrence factor corresponding to each pixel in the current near infrared image according to the temperature rise coefficient and the postoperative pain factor in the current near infrared image, and the difference between the temperature rise coefficient corresponding to each pixel in the current near infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the previous preset number of frames of historical near infrared images, comprises: Determine the overall temperature rise coefficient corresponding to the current near infrared image according to the temperature rise coefficients and postoperative pain factors corresponding to all pixels in the current near infrared image; Determine each frame of historical near infrared images among a preset number of frames of historical near infrared images before the current near infrared image as a reference infrared image; The pain occurrence factor corresponding to each pixel in the current near-infrared image is determined based on the overall temperature rise coefficient, the grayscale value corresponding to each pixel in the current near-infrared image and the grayscale value corresponding to the pixel at the same position in the reference infrared image of a preset number of frames, and the difference between the temperature rise coefficient corresponding to each pixel in the current near-infrared image and the temperature rise coefficient corresponding to the pixel at the same position in the reference infrared image of a preset number of frames.

7. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 6, characterized in that: The formula for the overall temperature rise coefficient corresponding to the current near-infrared image is: ;in, is the overall temperature rise coefficient corresponding to the current near-infrared image; is the hyperbolic tangent function; is the number of pixels in each frame of near-infrared image; is the serial number of the pixel in each frame of near-infrared image; It is the first near-infrared image The temperature rise coefficient corresponding to each pixel; is a natural exponential function; It is the first near-infrared image The postoperative pain factor corresponding to each pixel.

8. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 6, characterized in that: The formula corresponding to the pain occurrence factor corresponding to the pixel point in the current near-infrared image is: ； ； ； ;in, It is the first near-infrared image The pain occurrence factor corresponding to each pixel; is the serial number of the pixel in each frame of near-infrared image; is the normalization function; It is the first near-infrared image The gray value corresponding to the pixel is the same as the gray value of the reference infrared image in the preset number of frames. The accumulated value of the grayscale value corresponding to each pixel; is the overall temperature rise coefficient corresponding to the current near-infrared image; is a natural exponential function; Characterization The temperature change of each pixel location; is the preset quantity; is the serial number of the reference infrared image; It is The frame reference infrared image The difference between the temperature rise coefficient corresponding to a pixel point and the temperature rise coefficient corresponding to the pixel point at the same position in the next frame of infrared image; It is The frame reference infrared image The difference between the temperature rise coefficient corresponding to a pixel point and the temperature rise coefficient corresponding to the pixel point at the same position in the next frame of infrared image; It is The frame reference infrared image The temperature rise coefficient corresponding to each pixel; It is The first infrared image after the frame reference infrared image The temperature rise coefficient corresponding to each pixel; It is The frame reference infrared image The temperature rise coefficient corresponding to each pixel; It is The first infrared image after the frame reference infrared image The temperature rise coefficient corresponding to each pixel.

9. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 1, characterized in that: Determining the target pain level corresponding to each pixel point in the current near infrared image according to the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near infrared image includes: Normalize the product of the pain occurrence factor and the postoperative pain factor corresponding to each pixel point in the current near-infrared image to obtain the target pain index corresponding to each pixel point in the current near-infrared image; According to the target pain index corresponding to each pixel point in the current near infrared image, the target pain level corresponding to each pixel point in the current near infrared image is determined.

10. The method for assisting in identifying pain after anesthesia surgery of a patient based on near infrared technology according to claim 9, characterized in that: Determining the target pain level corresponding to each pixel point in the current near infrared image according to the target pain index corresponding to each pixel point in the current near infrared image includes: If the target pain index corresponding to the pixel point is greater than the preset pain threshold, the pixel point is determined as a pain pixel point; If the pixel is a pain pixel and the proportion of pain pixels in its corresponding preset neighborhood is greater than or equal to the preset proportion, the target pain level corresponding to the pixel is set to a high pain level, otherwise the target pain level corresponding to the pixel is set to a low pain level.

Images