A flap temperature infrared monitoring method and system

Abstract

The present application relates to a kind of flap temperature infrared monitoring method and system, the method comprises the following steps: obtaining the infrared thermal image of to be measured flap;The infrared thermal image is preprocessed, and the flap region image data set is obtained;Based on the flap region image data set, utilize Harris algorithm to extract the image data feature of flap region, establish feature matrix;The temperature state hypergraph optimization model of flap region image is constructed, and based on feature matrix, the temperature state hypergraph optimization model is solved, and the score matrix of flap temperature data is obtained;The temperature state of flap is identified based on the score matrix, and the identification result is output.Compared with prior art, the present application has the advantages of high degree of automation, high measurement accuracy, fast monitoring speed and the like, and the temperature state hypergraph optimization of acquisition temperature data is more intuitive, and the working efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a method and system for infrared monitoring of skin flap temperature. Background Technology

[0002] Measuring skin temperature is one of the important indicators of blood supply to skin flaps. It requires patient and meticulous observation of the skin flap temperature and then comprehensive judgment, which is conducive to early detection and treatment of problems.

[0003] In existing technologies, digital thermometers are mostly used to measure postoperative skin temperature after various skin flap procedures. While digital thermometers are suitable for measuring the temperature of various gases, liquids, and solids, and can be used to measure body temperature and surface temperature by changing different types of sensors, they can only measure positive and negative temperatures, the display is not intuitive, and the allowable error is generally ±0.3℃. However, if the temperature of the transplanted skin flap differs from the normal skin temperature by less than 2℃, there is a risk of circulatory disorders. Furthermore, measuring skin temperature requires contact with the skin, and since postoperative bleeding after skin flap surgery is significant, blood contact poses a risk of infectious disease transmission. Blood is also a good culture medium for bacteria, easily leading to cross-infection. Although 75% ethanol is used for disinfection before and after the procedure, the procedure is cumbersome and does not achieve thorough sterilization. The digital thermometer sensor has a glass contact head, which is easily broken, resulting in a high scrap rate. The readings are always fluctuating, leading to low measurement accuracy. Moreover, the results from the digital thermometer still need to be manually read and compared, which not only relies on extensive clinical experience but may also be subjective in its judgment.

[0004] Chinese patent application CN113425267A discloses a method and instrument for remote infrared monitoring of blood supply in tissue flaps. It considers environmental temperature and humidity monitoring factors, and after obtaining the temperature difference between the tissue flap and normal skin, it combines this with changes in environmental temperature and humidity to comprehensively determine the actual temperature difference between the tissue flap and normal skin. However, existing solutions generally suffer from low automation and inefficient work due to the lack of intuitive flap temperature display. Summary of the Invention

[0005] The purpose of this invention is to overcome the defects of the prior art and provide a method and system for infrared monitoring of skin flap temperature.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] As a first aspect of the present invention, a method for infrared monitoring of skin flap temperature is provided, the method comprising the following steps:

[0008] Acquire infrared thermal images of the flap to be tested;

[0009] The infrared thermal images are preprocessed to obtain a dataset of images of the skin flap region;

[0010] Based on the skin flap region image dataset, the Harris algorithm was used to extract features from the skin flap region image data and establish a feature matrix.

[0011] A temperature state hypergraph optimization model for the flap region image is constructed, and the model is solved based on the feature matrix to obtain the score matrix of the flap temperature data.

[0012] The temperature status of the skin flap is identified based on the scoring matrix, and the identification result is output.

[0013] Preferably, the infrared thermal image acquisition step includes:

[0014] Infrared thermal images of the flap area are acquired within a preset time using an infrared camera unit, and the infrared thermal images are grayscale images.

[0015] The flap region R = (x, y, w, h) of the infrared thermal image is located using a recognition algorithm; where the upper left corner of the infrared thermal image is the origin of the pixel coordinates, (x, y) are the coordinates of the flap region relative to the upper left corner origin, and h and w are the maximum boundaries of the flap rectangular region, respectively.

[0016] Preferably, the preprocessing step includes:

[0017] Multiple flap region images are obtained by extracting flap region images from each frame of infrared thermal image;

[0018] The grayscale values ​​of each flap region image are converted into corresponding temperature values ​​to obtain temperature state histograms of multiple flap region images.

[0019] The images of the skin flap region are classified and organized according to the temperature state histogram to obtain a skin flap region image dataset.

[0020] Preferably, the feature extraction step includes:

[0021] The shape features of the temperature state histogram were extracted using the Harris algorithm.

[0022] A feature matrix is ​​constructed based on the shape feature extraction results, where each feature matrix includes a point with the highest temperature value.

[0023] Preferably, the calculation steps for the score matrix of the flap temperature data include:

[0024] A temperature-state hypergraph optimization model for the flap region image is constructed. The specific temperature-state hypergraph optimization model is as follows:

[0025]

[0026] Where F represents the score matrix of the flap temperature data, Y represents the feature matrix, Δ represents the Laplacian matrix of the temperature state hypergraph, and λ is the trade-off parameter.

[0027] The temperature state hypergraph optimization model is solved to obtain the score matrix of the flap temperature data.

[0028] Preferably, the method further includes an alarm step, as follows:

[0029] The skin temperature of the healthy side was collected using an infrared probe.

[0030] The highest temperature value in the identification results is selected and compared with the collected skin temperature point on the healthy side.

[0031] If the highest temperature value is lower than the set temperature threshold compared to the skin temperature of the healthy side, an early warning report will be issued.

[0032] As a second aspect of the present invention, a skin flap temperature infrared monitoring system is provided, comprising:

[0033] The acquisition module is used to acquire infrared thermal images of the skin flap to be tested;

[0034] A preprocessing module, connected to the acquisition module, is used to preprocess the infrared thermal image to obtain a skin flap region image dataset;

[0035] The feature extraction module, connected to the preprocessing module, is used to extract features of the flap region image data based on the flap region image dataset using the Harris algorithm, and to establish a feature matrix.

[0036] The calculation module, connected to the feature extraction module, is used to construct a temperature state hypergraph optimization model for the flap region image, and solve the temperature state hypergraph optimization model based on the feature matrix to obtain the score matrix of the flap temperature data.

[0037] The identification module, connected to the calculation module, is used to identify the temperature status of the skin flap based on the scoring matrix and output the identification result.

[0038] Preferably, the feature extraction module includes:

[0039] The feature extraction unit is used to extract shape features using the Harris algorithm. The specific formula is as follows:

[0040] S1 = Harris(TEMP)

[0041] TEMP is a temperature state histogram.

[0042] The feature matrix calculation unit, connected to the feature extraction unit, is used to construct a feature matrix based on the feature extraction results, wherein each feature matrix includes a point with the highest temperature value.

[0043] Preferably, the computing module includes:

[0044] The building unit is used to construct a temperature state hypermap optimization model for the flap region image. The specific temperature state hypermap optimization model is as follows:

[0045]

[0046] Where F represents the score matrix of the flap temperature data, Y represents the feature matrix, Δ represents the Laplacian matrix of the temperature state hypergraph, and λ is the trade-off parameter.

[0047] The scoring matrix calculation unit, connected to the construction unit, is used to solve the temperature state hypergraph optimization model to obtain the scoring matrix of the flap temperature data.

[0048] Preferably, the acquisition module further includes: an infrared probe for acquiring skin temperature at the healthy side;

[0049] This includes an analysis module that filters out the highest temperature values ​​in the identification results and compares the highest temperature values ​​with the collected skin temperature points on the healthy side.

[0050] It includes an early warning module connected to the analysis module. If the highest temperature value is lower than the set temperature threshold compared to the healthy side's skin temperature, an early warning report will be issued.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1) This invention discloses a method and system for infrared monitoring of skin flap temperature. Through data acquisition, processing, and calculation, temperature state histograms of multiple skin flap region images are obtained. A hypergraph optimization model of the temperature state of the skin flap region images is constructed, and the score matrix of the skin flap temperature data is calculated. Finally, the monitoring results are obtained. Using the above method and system, the approximation between the temperature values ​​of the skin flap region and the temperature values ​​of the healthy side can be automatically obtained and output. It features high automation, high measurement accuracy, and fast monitoring speed, and the display is more intuitive, allowing medical staff to better understand the temperature status of the skin flap blood supply, thus improving work efficiency.

[0053] 2) This invention also collects skin temperature points on the healthy side and selects the highest temperature value from the monitoring results. By comparing the highest temperature value with the collected skin temperature points on the healthy side, if the monitoring result is more than 2°C lower than the normal skin temperature, it indicates that blood circulation disorders will occur, improving the automation of monitoring, eliminating the need for real-time observation and care by nursing staff, and improving work efficiency. Attached Figure Description

[0054] Figure 1 This is a schematic flowchart of an infrared monitoring method for skin flap temperature according to the present invention.

[0055] Figure 2 This is a schematic diagram of the structure of a skin flap temperature infrared monitoring system according to the present invention. Detailed Implementation

[0056] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0057] Example 1

[0058] See appendix Figure 1 As shown in the figure, an embodiment of the present invention discloses a method for infrared monitoring of skin flap temperature, the steps of which include:

[0059] S1 acquires the infrared thermal image of the flap to be tested;

[0060] S2 preprocessing module 2, connected to acquisition module 1, is used to preprocess infrared thermal images to obtain a skin flap region image dataset;

[0061] S3 Feature Extraction Module 3, connected to Preprocessing Module 2, is used to extract features of flap region image data based on flap region image dataset using the Harris algorithm and establish a feature matrix.

[0062] S4 calculation module 4, connected to feature extraction module 3, is used to construct a temperature state hypergraph optimization model for the flap region image, and solve the temperature state hypergraph optimization model based on the feature matrix to obtain the score matrix of the flap temperature data.

[0063] The S5 recognition module 5, connected to the calculation module 4, is used to identify the temperature status of the skin flap based on the scoring matrix and output the recognition results.

[0064] In one specific embodiment, step S1 includes:

[0065] Acquire infrared thermal images of the flap area within a preset time period;

[0066] The recognition algorithm is used to locate the flap region R = (x, y, w, h) in the infrared thermal image, where the upper left corner of the infrared thermal image is the origin of the pixel coordinates, (x, y) are the coordinates of the upper left corner of the flap region, and h and w are the maximum boundaries of the flap rectangular region, with units in pixels.

[0067] In one specific embodiment, an infrared camera unit is used to capture an image of the skin flap region formed by radiation in the infrared band, resulting in an infrared thermal image of the skin flap region. The infrared thermal image is a grayscale image.

[0068] In one specific embodiment, step S2 includes:

[0069] Multiple flap region images are obtained by extracting flap region images from each frame of infrared thermal image;

[0070] The grayscale values ​​of each flap region image are converted into corresponding temperature values ​​to obtain temperature state histograms of multiple flap region images.

[0071] The flap region images are classified and organized according to the temperature state histogram to obtain the flap region image dataset.

[0072] In one specific embodiment, step S3 includes:

[0073] The shape features are extracted using the Harris algorithm, and the specific formula is as follows:

[0074] S1 = Harris(TEMP)

[0075] TEMP is a temperature state histogram;

[0076] A feature matrix is ​​constructed based on the feature extraction results, where each feature matrix includes a point with the highest temperature value.

[0077] In one specific embodiment, step S4 includes:

[0078] A temperature-state hypergraph optimization model for the flap region image is constructed. The specific temperature-state hypergraph optimization model is as follows:

[0079]

[0080] Where F represents the score matrix of the flap temperature data, Y represents the feature matrix, Δ represents the Laplacian matrix of the temperature state hypergraph, and λ is the trade-off parameter.

[0081] The temperature state hypergraph optimization model is solved to obtain the score matrix of the flap temperature data.

[0082] In one specific embodiment, step S5 includes:

[0083] Based on the score matrix of skin flap temperature data, the temperature distribution of the skin flap region image is identified in chronological order.

[0084] Output the recognition results.

[0085] In one specific embodiment, step S6 includes:

[0086] Infrared probes were used to collect skin temperature data from the healthy side.

[0087] The highest temperature value in the screening and identification results is compared with the collected skin temperature point on the healthy side.

[0088] Generally, the temperature of a transplanted skin flap should differ from that of the healthy side by 0.5℃-2℃. If the difference is less than 2℃, it indicates impaired blood circulation. If the highest temperature point differs from the healthy side's temperature point by less than 2℃, a warning report will be issued, indicating impaired blood circulation.

[0089] Specifically, accurate skin temperature readings are an important indicator for assessing vascular crisis in skin flaps. This system compares skin temperature measurements with corresponding points on the healthy side under the same environmental conditions to improve monitoring accuracy.

[0090] More specifically, generally speaking, the affected limb should be the same temperature as or 1°C lower than the healthy side, while the transplanted skin flap may sometimes be 1°C higher than the healthy limb. Under normal circumstances, the skin temperature of symmetrical parts of the body is similar. Asymmetry in skin temperature in symmetrical parts is often regarded as a pathological manifestation caused by disordered vasoconstriction, disordered sweating, or inflammatory reaction in the diseased area. Postoperative observation of blood supply is crucial after skin flap surgery. By measuring skin temperature and observing skin color, fullness, and swelling, it is possible to determine whether there is a vascular crisis in the skin flap. Normal skin temperature should be between 30°C and 3°C, with a temperature difference of less than 2°C compared to the healthy side. After routine skin flap surgery, due to the effect of anesthesia, a skin temperature 3°C lower than normal is considered normal, but it usually recovers within 3 hours. Therefore, in this embodiment, the preset time range can be set to 3 hours, and the infrared camera unit 11 can acquire infrared thermal images of the skin flap area within 3 hours.

[0091] Generally, a temperature difference of 0.5–2°C indicates good blood circulation, a sudden difference of 3°C or more suggests arterial embolism, and a gradual increase to 3°C or more indicates venous embolism. Therefore, through processing and calculation, temperature state histograms of multiple flap region images are obtained. A hypergraph optimization model of the temperature state of the flap region images is constructed to obtain the score matrix of the flap temperature data, and the final monitoring results are obtained. Research shows that the flap temperature infrared monitoring system provided by this invention has low error in judging vascular crises, high automation, high measurement accuracy, fast monitoring speed, and intuitive display, enabling medical staff to better understand the temperature status of flap blood supply and improving work efficiency.

[0092] Example 2

[0093] See appendix Figure 2 As shown, an embodiment of the present invention discloses a skin flap temperature infrared monitoring system, comprising:

[0094] Acquisition module 1 is used to acquire infrared thermal images of the skin flap to be tested;

[0095] Preprocessing module 2, connected to acquisition module 1, is used to preprocess infrared thermal images to obtain a skin flap region image dataset;

[0096] Feature extraction module 3, connected to preprocessing module 2, is used to extract features of flap region image data based on flap region image dataset using Harris algorithm and establish feature matrix.

[0097] The calculation module 4, connected to the feature extraction module 3, is used to construct a temperature state hypergraph optimization model for the flap region image, and solve the temperature state hypergraph optimization model based on the feature matrix to obtain the score matrix of the flap temperature data.

[0098] The recognition module 5, connected to the calculation module 4, is used to identify the temperature status of the skin flap based on the scoring matrix and output the recognition results.

[0099] In one specific embodiment, the acquisition module 1 includes:

[0100] Infrared camera unit 11 is used to acquire infrared thermal images of the flap area within a preset time period;

[0101] The capture unit 12 is used to lock the flap region R = (x, y, w, h) of the infrared thermal image using a recognition algorithm, where the upper left corner of the infrared thermal image is the origin of the pixel coordinates, (x, y) are the coordinates of the upper left corner of the flap region, and h and w are the maximum boundaries of the flap rectangular region, respectively, in pixels.

[0102] In one specific embodiment, the infrared camera unit 11 acquires an image of the skin flap region formed by radiation in the infrared band, and obtains an infrared thermal image of the skin flap region, which is a grayscale image.

[0103] In one specific embodiment, the preprocessing module 2 includes:

[0104] Image cropping unit 21 is used to crop the flap region image in each frame of infrared thermal image to obtain multiple flap region images;

[0105] Image processing unit 22, connected to image cropping unit 21, is used to convert the grayscale value of each flap region image into the corresponding temperature value and obtain a temperature state histogram of multiple flap region images.

[0106] The classification and sorting unit 23 is connected to the image processing unit 22 and is used to classify and sort the flap region images according to the temperature state histogram to obtain the flap region image dataset.

[0107] In one specific embodiment, the feature extraction module 3 includes:

[0108] Feature extraction unit 31 is used to extract shape features using the Harris algorithm, and the specific formula is as follows:

[0109] S1 = Harris(TEMP)

[0110] TEMP is a temperature state histogram;

[0111] The feature matrix calculation unit 32 is connected to the feature extraction unit 31 and is used to construct a feature matrix based on the feature extraction results, wherein each feature matrix includes a point with the highest temperature value.

[0112] In one specific embodiment, the calculation module 4 includes:

[0113] Building unit 41 is used to construct a temperature state hypermap optimization model for the flap region image. The specific temperature state hypermap optimization model is as follows:

[0114]

[0115] Where F represents the score matrix of the flap temperature data, Y represents the feature matrix, Δ represents the Laplacian matrix of the temperature state hypergraph, and λ is the trade-off parameter.

[0116] The scoring matrix calculation unit 42, connected to the construction unit 41, is used to solve the temperature state hypergraph optimization model to obtain the scoring matrix of the flap temperature data.

[0117] In one specific embodiment, the identification module 5 includes:

[0118] The recognition unit 51 identifies the temperature distribution state of the flap region image in chronological order based on the score matrix of the flap temperature data.

[0119] Output unit 52 outputs the recognition result.

[0120] In one specific embodiment, the acquisition module 1 further includes an infrared probe for acquiring the skin temperature of the healthy side.

[0121] In one specific embodiment, it also includes an analysis module 6, which filters out the highest temperature value in the identification results and compares the highest temperature value with the collected healthy side skin temperature point.

[0122] Specifically, the temperature of a transplanted skin flap should generally differ from that of the healthy side by 0.5℃-2℃. If the difference is less than 2℃ from the normal skin temperature, it indicates that blood circulation disorders will occur.

[0123] In one specific embodiment, an early warning module 7 is also included, which is connected to the analysis module 6. If the difference between the highest temperature value and the skin temperature of the healthy side is less than 2°C, an early warning report is issued, indicating that blood circulation disorder will occur.

[0124] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0125] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method for infrared monitoring of skin flap temperature, characterized in that, The method includes the following steps: Acquire infrared thermal images of the flap to be tested; The infrared thermal images are preprocessed to obtain a dataset of images of the skin flap region; Based on the skin flap region image dataset, the Harris algorithm was used to extract features from the skin flap region image data and establish a feature matrix. A temperature state hypergraph optimization model for the flap region image is constructed, and the model is solved based on the feature matrix to obtain the score matrix of the flap temperature data. The temperature status of the skin flap is identified based on the scoring matrix, and the identification result is output.

2. The method for infrared monitoring of skin flap temperature according to claim 1, characterized in that, The infrared thermal image acquisition steps include: Infrared thermal images of the flap area are acquired within a preset time period by an infrared camera unit (11), wherein the infrared thermal images are grayscale images; The flap region R = (x, y, w, h) of the infrared thermal image is located using a recognition algorithm; where the upper left corner of the infrared thermal image is the origin of the pixel coordinates, (x, y) are the coordinates of the flap region relative to the upper left corner origin, and h and w are the maximum boundaries of the flap rectangular region, respectively.

3. The method for infrared monitoring of skin flap temperature according to claim 2, characterized in that, The preprocessing steps include: Extract the flap region image from each frame of infrared thermal image to obtain multiple flap region images; The grayscale values ​​of each flap region image are converted into corresponding temperature values ​​to obtain temperature state histograms of multiple flap region images. The images of the skin flap region are classified and organized according to the temperature state histogram to obtain a skin flap region image dataset.

4. The method for infrared monitoring of skin flap temperature according to claim 1, characterized in that, Feature extraction steps include: The shape features of the temperature state histogram were extracted using the Harris algorithm. A feature matrix is ​​constructed based on the shape feature extraction results, where each feature matrix includes a point with the highest temperature value.

5. The method for infrared monitoring of skin flap temperature according to claim 1, characterized in that, The calculation steps for the score matrix of the flap temperature data include: A temperature-state hypergraph optimization model for the flap region image is constructed. The specific temperature-state hypergraph optimization model is as follows: ； Where F represents the score matrix of the flap temperature data, Y represents the feature matrix, Δ represents the Laplacian matrix of the temperature state hypergraph, and λ is the trade-off parameter. The temperature state hypergraph optimization model is solved to obtain the score matrix of the flap temperature data.

6. The method for infrared monitoring of skin flap temperature according to claim 1, characterized in that, The method also includes an alarm step, as detailed below: The skin temperature of the healthy side was collected using an infrared probe. The highest temperature value in the identification results is selected and compared with the collected skin temperature point on the healthy side. If the highest temperature value is lower than the set temperature threshold compared to the skin temperature of the healthy side, an early warning report will be issued.

7. A skin flap temperature infrared monitoring system, characterized in that, include: The acquisition module (1) is used to acquire infrared thermal images of the skin flap to be tested; The preprocessing module (2) is connected to the acquisition module (1) and is used to preprocess the infrared thermal image to obtain a skin flap region image dataset. The feature extraction module (3) is connected to the preprocessing module (2) and is used to extract the features of the flap region image data based on the flap region image dataset using the Harris algorithm to establish a feature matrix; The calculation module (4) is connected to the feature extraction module (3) and is used to construct a temperature state hypergraph optimization model for the flap region image. Based on the feature matrix, the temperature state hypergraph optimization model is solved to obtain the score matrix of the flap temperature data. The identification module (5) is connected to the calculation module (4) and is used to identify the temperature status of the skin flap based on the scoring matrix and output the identification result.

8. The skin flap temperature infrared monitoring system according to claim 7, characterized in that, The feature extraction module (3) includes: The feature extraction unit (31) is used to extract shape features using the Harris algorithm. The specific formula is as follows: S1 = Harris(TEMP) TEMP is a temperature state histogram. The feature matrix calculation unit (32) is connected to the feature extraction unit (31) and is used to construct a feature matrix based on the feature extraction results, wherein each feature matrix includes a point with the highest temperature value.

9. The skin flap temperature infrared monitoring system according to claim 7, characterized in that, The computing module (4) includes: The construction unit (41) is used to construct the temperature state hypermap optimization model of the flap region image. The specific temperature state hypermap optimization model is as follows: ； Where F represents the score matrix of the flap temperature data, Y represents the feature matrix, Δ represents the Laplacian matrix of the temperature state hypergraph, and λ is the trade-off parameter. The scoring matrix calculation unit (42) is connected to the construction unit (41) and is used to solve the temperature state hypergraph optimization model to obtain the scoring matrix of the flap temperature data.

10. The skin flap temperature infrared monitoring system according to claim 7, characterized in that, The acquisition module (1) also includes: Infrared probe used to collect skin temperature data on the healthy side; Analysis module (6) filters out the highest temperature value in the identification results and compares the highest temperature value with the collected healthy side skin temperature point; The early warning module (7) is connected to the analysis module (6). If the highest temperature value is lower than the set temperature threshold compared with the healthy side skin temperature, an early warning report is issued.

Images