Wound detection system, detection device and detection method

Abstract

The present invention relates to a wound detection system, a detection device, and a detection method. The wound detection system includes at least: an acquisition module for acquiring images of a patient's wound site and a processing module for processing the images acquired by the acquisition module. The processing module's processing of the image includes at least: processing the image using a modeling unit to establish a three-dimensional model of the patient's wound site; analyzing the three-dimensional model using an analysis unit to obtain characteristic parameters of the patient's wound site and / or evaluation information on the healing status of the patient's wound site. By establishing a three-dimensional model corresponding to the patient's wound site and analyzing the three-dimensional model, the wound detection system can determine wound changes and facilitate monitoring of wound healing. The wound detection system can also provide effective reference information for wound treatment and healing monitoring, obtain accurate and comprehensive wound information, and dynamically track wound treatment.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to a wound detection system, a detection device and a detection method. Background Art

[0002] Wound measurement and assessment are the primary link and foundation of wound treatment, the prerequisite for wound management, and play a vital role in promoting wound healing. During the wound healing process, wounds need to be measured and analyzed to evaluate the healing status of the wound. Existing wound measurement parameters include area, depth, fluid accumulation, wound tissue shape, etc. When measuring the depth of a patient's wound, existing flaw detection devices usually place a sterile thin cotton swab perpendicular to the wound surface into the deepest part of the wound, clamp the cotton swab flush with the wound surface with curved pliers or tweezers, remove the cotton swab, and use a ruler to measure the length from the cotton swab head to the tweezers to obtain the result of the patient's wound depth. Although this method is relatively simple, it can easily cause pain to the injured person. At the same time, for healing wounds, it will damage the tissue at the wound site, which is not conducive to wound healing. Accordingly, non-invasive wound measurement methods have emerged. This measurement method avoids damaging the wound tissue while alleviating the patient's pain.

[0003] For example, patent publication number CN112107331A discloses a medical measurement system, including a wound measurement device and a server, wherein the wound measurement device is communicatively connected to the server, and the wound measurement device includes a wound depth detection subsystem; the wound depth detection subsystem includes: an ultrasonic generating module: for generating ultrasonic waves; an ultrasonic receiving module: for receiving reflected ultrasonic waves; an ultrasonic signal processing module: for generating ultrasonic flaw detection images and calculating wound measurement data; a display module: for displaying ultrasonic flaw detection images and wound measurement data; the server includes: a storage module: for receiving and storing wound measurement data; a medical record acquisition module: for acquiring patient medical records; a medical record import module: for automatically importing the detected wound measurement data and time information into the medical records and into a preset wound assessment report.

[0004] Patent publication number CN108814613B discloses an intelligent wound measurement method and mobile measurement terminal. The method includes: obtaining a patient's identity, obtaining and displaying the medical history information corresponding to the identity; obtaining the patient's wound image information, including a wound image and a reference ruler image; obtaining the length and width of the wound based on the relationship between the reference ruler image and the wound image, and obtaining the wound area based on the identified wound edge; recording the length, width, and area of the wound obtained in this measurement, as well as other wound information and treatment information input, into the patient's current measurement record; and obtaining a dynamic change diagram of the patient's wound assessment based on multiple measurement records of the patient obtained during multiple measurement processes. Through the above process, effective reference information can be provided for wound treatment and healing monitoring, and intelligent measurement can obtain accurate and comprehensive wound information, and dynamically track wound treatment.

[0005] Patent publication number CN113393420A discloses an intelligent wound assessment method based on infrared thermal imaging technology. The method includes measuring the wound thermal image area based on an irregular area calculation method; establishing an exudate image model based on the relationship between thermal image features and exudate volume; establishing an infrared thermal image model based on the differences in thermal radiation caused by different wound types; determining the dryness and wetness of the wound using a dryness and wetness evaluation method based on mean and variance; and outputting the assessment results. This invention has the following advantages and effects: Based on infrared thermal imaging of wounds, the invention can intelligently measure wound area, wound exudate, and tissue type, and automatically output individual scores and a total score for each of these three items, thereby achieving a more objective, accurate, and rapid intelligent assessment.

[0006] Although existing technologies can measure wounds by acquiring ultrasonic images, infrared thermal imaging images, etc. of patient wounds, due to differences in the shooting angles used each time the existing technologies acquire images of patient wounds, angle errors are introduced when comparing the current image of the patient's wound with historical images to assess the patient's wound healing status, thereby reducing the accuracy of the assessment.

[0007] In addition, on the one hand, there are differences in understanding among those skilled in the art; on the other hand, the applicant studied a large number of documents and patents when making the present invention, but due to space limitations, not all details and contents are listed in detail. However, this does not mean that the present invention does not have the characteristics of these prior arts. On the contrary, the present invention already has all the characteristics of the prior art, and the applicant reserves the right to add relevant prior art to the background technology. Summary of the Invention

[0008] To address the shortcomings of the prior art, the present invention provides a wound detection system. The wound detection system comprises at least an acquisition module and a processing module. The acquisition module is configured to acquire images of a patient's wound site. The processing module is configured to process the images acquired by the acquisition module. Preferably, the processing module processes the images by at least: processing the images using a modeling unit to create a three-dimensional model of the patient's wound site; and analyzing the three-dimensional model using an analysis unit to obtain characteristic parameters of the patient's wound site and / or information assessing the healing status of the patient's wound site.

[0009] Preferably, the wound detection system can determine wound changes by building a three-dimensional model corresponding to the patient's wound site and analyzing the three-dimensional model, facilitating monitoring of wound healing. The wound detection system can also provide effective reference information for wound treatment and healing monitoring, obtaining accurate and comprehensive wound information and dynamically tracking wound treatment.

[0010] According to a preferred embodiment, the acquisition module is provided with at least two cameras with different shooting angles to obtain images of the patient's wound site at different shooting angles at the same time, and transmit the images at different shooting angles to the processing module.

[0011] Preferably, the processing module can obtain the viewing angle differences of the patient's wound area image at different shooting angles, and map the depth information differences of each object in the corresponding image based on the viewing angle differences to achieve three-dimensional imaging.

[0012] According to a preferred embodiment, the modeling unit configured in the processing module establishes a three-dimensional model of the patient's wound site based on the images taken at different shooting angles and transmits the three-dimensional model to the analysis unit configured in the processing module to analyze the characteristic parameters of the patient's wound site and / or the healing condition of the patient's wound site.

[0013] According to a preferred embodiment, the analysis unit uses a first analysis model trained through deep learning using actual patient wound images as samples to perform image segmentation on the three-dimensional model to obtain characteristic parameters of the patient's wound area. Preferably, the characteristic parameters include at least one of wound depth, area, and tissue shape.

[0014] Preferably, the analysis unit inputs the three-dimensional model into the first analysis model to obtain characteristic parameters of the patient's wound site. Preferably, the first analysis model identifies visually based characteristic parameters based on the input three-dimensional model, allowing medical personnel to determine the area and depth of the wound, whether it is composed of rotten or loose tissue, and whether there is cavitation and pus accumulation.

[0015] According to a preferred embodiment, the analysis unit compares and analyzes the three-dimensional model with a second analysis model to obtain information assessing the healing status of the patient's wound. The second analysis model assesses the healing status of the patient's wound by comparing the three-dimensional model with historical medical data. Preferably, the historical medical data includes at least the historical three-dimensional model.

[0016] Preferably, the present invention evaluates the healing condition of the patient's wound through the second analysis model, thereby converting the subjective judgment of medical personnel into an objective judgment, thereby eliminating the interference of human experience factors on the evaluation results and improving the efficiency and effectiveness of wound healing evaluation.

[0017] According to a preferred embodiment, the second analysis model compares the three-dimensional model and the historical three-dimensional model by adjusting them to the same viewing direction.

[0018] Preferably, after the second analysis model adjusts the three-dimensional model and the historical three-dimensional model to the same viewing direction, the healing status of the patient's wound site can be determined by comparing the changes in the same site in the three-dimensional model.

[0019] According to a preferred embodiment, the processing module is further configured with a storage unit for storing historical medical data. Preferably, the analysis unit stores the three-dimensional model as historical medical data in the storage unit after completing the analysis.

[0020] Preferably, the storage unit can optimize the stored historical medical data. The specific optimization method can be to merge similar cases, thereby reducing the space required to store the historical medical data while ensuring the diversity of cases in the historical medical data.

[0021] The present invention also provides a wound detection method. The wound detection method at least comprises:

[0022] capturing images of the patient's wound;

[0023] establishing a three-dimensional model of the patient's wound site based on the image;

[0024] The three-dimensional model is analyzed using a first analysis model to obtain characteristic parameters of the patient's wound site.

[0025] According to a preferred embodiment, the wound detection method further comprises: analyzing the three-dimensional model using a second analysis model to obtain information assessing the healing status of the patient's wound site. Preferably, the second analysis model assesses the healing status of the patient's wound by comparing the three-dimensional model with historical medical data. Preferably, the historical medical data includes at least the historical three-dimensional model.

[0026] The present invention also provides a wound detection device. The wound detection device includes at least: an acquisition module, a processing module, and a display module. The acquisition module is equipped with at least two cameras with different shooting angles to capture images of the patient's wound site at different shooting angles at the same time, and transmits the images from different shooting angles to the processing module. The processing module processes the images and transmits the processing results to the display module for display. Preferably, the processing module processes the images by at least: establishing a three-dimensional model of the patient's wound site based on the images and analyzing the three-dimensional model to obtain characteristic parameters of the patient's wound site and / or evaluating the healing status of the patient's wound site. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a simplified schematic diagram of a wound detection system according to a preferred embodiment of the present invention;

[0028] Figure 2 This is a simplified schematic diagram of module connection relationships of a collection module according to a preferred embodiment of the present invention;

[0029] Figure 3 It is a simplified communication connection relationship diagram of a wound detection system according to a preferred embodiment of the present invention.

[0030] Reference Signs List

[0031] 100: Wound detection system; 110: Acquisition module; 111: Camera; 112: Housing; 120: Processing module; 121: Modeling unit; 122: Analysis unit; 123: Storage unit; 130: Display module. DETAILED DESCRIPTION

[0032] The following is combined with Figures 1 to 3 Provide detailed explanation.

[0033] Example 1

[0034] This embodiment provides a wound detection system 100. Figure 1 Preferably, the wound detection system 100 may include an acquisition module 110, a processing module 120, and a display module 130. Preferably, the acquisition module 110 is configured to acquire images of a patient's wound area. Preferably, the processing module 120 is configured to process the images acquired by the acquisition module 110. Preferably, the display module 130 is configured to display the processing results of the processing module 120.

[0035] Preferably, the processing module 120 can be connected to the acquisition module 110 and the display module 130 respectively in a wired or wireless manner.

[0036] Preferably, the acquisition module 110 can acquire images of the patient's wound site from two or more shooting angles. Preferably, the processing module 120 processes the images acquired by the acquisition module 110 to establish a three-dimensional model corresponding to the patient's wound site. The processing module 120 can also analyze the three-dimensional model to obtain characteristic parameters of the patient's wound site and / or assessment information on the healing status of the patient's wound site.

[0037] Preferably, the acquisition module 110 may include two or more cameras 111 with different shooting angles. Preferably, the acquisition module 110 may acquire images of the patient's wound site at different shooting angles at the same time through the cameras 111 with different shooting angles.

[0038] See also Figure 2 Preferably, the acquisition module 110 of this embodiment can be provided with three cameras 111. Preferably, the three cameras 111 are provided on the arc-shaped mounting housing 112 in a spaced manner. Preferably, the three cameras 111 include a first camera provided at the top center of the curved surface, and a second camera and a third camera provided around the first camera. Preferably, the distance between the second camera and the first camera is a first distance, and the distance between the third camera and the first camera is a second distance, wherein the second distance is greater than the first distance. Figure 2 Preferably, the first camera is set at the center of the arc surface, the angle between the second camera and the first camera on the arc surface about the center of the surface is 15°, and the angle between the third camera and the first camera on the arc surface about the center of the surface is 30°.

[0039] Preferably, the acquisition module 110 may be a handheld acquisition probe, on which are provided three non-equidistantly spaced cameras 111. Preferably, the three cameras 111 on the acquisition module 110 can acquire three images with different shooting angles and without mirror images.

[0040] Preferably, the acquisition module 110 of this embodiment can simultaneously obtain images of the patient's wound site at three shooting angles when acquiring images of the patient's wound site at any shooting angle, so that the processing module 120 can establish a three-dimensional model corresponding to the patient's wound site based on the images of the patient's wound site at the three shooting angles at the same time.

[0041] Preferably, the images acquired by the acquisition module 110 at three shooting angles can reflect the size difference of the same object in the image at different viewing angles. The image acquired from a single shooting angle can only obtain two-dimensional information of the patient's wound site. The acquisition module 110 uses the images acquired at three shooting angles to make the patient's wound site show different sizes in the three images. Specifically, the size of the patient's wound site shown in the image will change with the change of the shooting angle. The acquisition module 110 acquires images of the patient's wound site from three shooting angles. Since the three shooting angles are known, the processing module 120 can infer the three-dimensional size of the patient's wound site based on the size of the patient's wound site in different images, thereby acquiring three-dimensional information of the patient's wound site, so that the processing module 120 can establish a three-dimensional model corresponding to the patient's wound site and ensure the accuracy of the three-dimensional model.

[0042] See also Figure 3 Preferably, the processing module 120 may include a modeling unit 121, an analysis unit 122, and a storage unit 123. Preferably, the analysis unit 122 is data-connected to the modeling unit 121 and the storage unit 123, respectively. Preferably, the processing module 120 may be, for example, a logic gate array, a controller and an arithmetic logic unit, a digital signal processor, a microcomputer, a programmable logic controller, a field programmable gate array, a programmable logic array, a microprocessor, or any other device or combination of devices configured to respond to and execute instructions in a defined manner to achieve a desired result.

[0043] Preferably, the processing module 120 processes the images captured by the acquisition module 110, including: processing the images using the modeling unit 121 to create a three-dimensional model of the patient's wound; and analyzing the three-dimensional model using the analysis unit 122 to obtain characteristic parameters of the patient's wound and / or information assessing the healing status of the patient's wound. Preferably, the storage unit 123 is used to store historical medical data.

[0044] Preferably, the modeling unit 121 is data-connected to the acquisition module 110 to receive images of the patient's wound site captured by the acquisition module 110. Preferably, the modeling unit 121 receives the images of the patient's wound site captured by the acquisition module 110 and creates a three-dimensional model of the patient's wound site based on the images captured by the acquisition module 110 at different angles. Preferably, the modeling unit 121 transmits the created three-dimensional model to the analysis unit 122 configured for the processing module 120 for analysis.

[0045] Preferably, the modeling unit 121 can obtain the depth information of each object in the image by scanning the images of the patient's wound captured by the acquisition module 110 at different shooting angles. Preferably, the modeling unit 121 can obtain the depth information of each object in the image based on the perspective difference caused by the different shooting angles of each camera 111, thereby realizing three-dimensional imaging. Preferably, the multiple images transmitted to the modeling unit 121 by the acquisition module 110 include the shooting angle information of the camera 111 that captured the image. Since the shooting angles of each camera 111 are different, the images captured by different cameras 111 contain the depth information difference of each object in the image caused by the perspective difference. Therefore, the modeling unit 121 can obtain the perspective difference of the patient's wound area image generated at different shooting angles, and map the depth information difference of each object in the corresponding image based on the perspective difference to realize three-dimensional imaging.

[0046] Preferably, the modeling unit 121 can identify the size of the patient's wound site from an image at a single shooting angle, thereby obtaining the size of the patient's wound site mapped at three shooting angles. Since the three shooting angles are known, the modeling unit 121 can infer the actual size of the patient's wound site by obtaining the size of the patient's wound site mapped at the three shooting angles, thereby obtaining three-dimensional information of the patient's wound site.

[0047] Preferably, the analysis unit 122 analyzes the three-dimensional model using a deep learning analysis model. Preferably, the analysis unit 122 can be configured with a first analysis model for extracting characteristic parameters of the patient's wound site and a second analysis model for evaluating the patient's wound healing status.

[0048] Preferably, the first analysis model and the second analysis model may be neural network models trained through deep learning using a large number of actual patient wound images as samples.

[0049] Preferably, the analysis unit 122 performs image segmentation on the three-dimensional model using the first analysis model to obtain characteristic parameters of the patient's wound site. Preferably, the characteristic parameters include at least one or a combination of wound depth, area, and tissue shape.

[0050] Preferably, the analysis unit 122 inputs the three-dimensional model into the first analysis model to obtain characteristic parameters of the patient's wound site. Preferably, the first analysis model identifies visually based characteristic parameters based on the input three-dimensional model, allowing medical personnel to determine the area and depth of the wound, the presence of rotten or loose tissue, and the presence of cavities and pus accumulation.

[0051] Because the tissue at the patient's wound site exhibits distinct imaging features compared to the patient's normal tissue, and features such as rotten or loose tissue, cavities, and pus and fluid accumulation within the wound exhibit imaging features that distinguish it from healthy tissue, the first analysis model can preferably be a neural network model trained through deep learning using actual patient wound images as samples. Preferably, the sample images used in training the first analysis model can include images of sinus tracts, rotten tissue, pus and fluid accumulation, wound edges, and normal tissue, annotated by medical personnel. Preferably, when analyzing the 3D model, the first analysis model can slice the 3D model in any direction, thereby converting the 3D model into a stack of multiple images. Preferably, the first analysis model can identify the sliced images, demarcating injured tissue from normal tissue, and thereby determining the wound area and depth. Furthermore, the first analysis model can identify the images of the injured tissue to determine whether pathological features such as rotten or loose tissue, cavities, and pus and fluid accumulation are present.

[0052] Preferably, the analysis unit 122 analyzes the three-dimensional model using a second analysis model to obtain information assessing the healing status of the patient's wound. The second analysis model assesses the patient's wound healing status by comparing the three-dimensional model with historical medical data. Preferably, the historical medical data includes at least a historical three-dimensional model. Preferably, the historical medical data may include a three-dimensional model of the patient's previous wound examination and three-dimensional models of wounds of other patients with similar wounds.

[0053] Preferably, the analysis unit 122 is data-connected to the display module 130 , so that the analysis unit 122 can transmit the analysis results of the first analysis model and the second analysis model and the three-dimensional model to the display module 130 for display.

[0054] Preferably, after completing the analysis, the analysis unit 122 stores the three-dimensional model as historical medical data in the storage unit 123 .

[0055] Preferably, the storage unit 123 can optimize the stored historical medical data. A specific optimization method may be to merge similar cases, thereby reducing the space required to store the historical medical data while ensuring the diversity of cases in the historical medical data.

[0056] Preferably, the wound detection system 100 provided in this embodiment can be used to measure characteristic parameters of a patient's wound and also to evaluate the healing status of the patient's wound.

[0057] Preferably, when the wound detection system 100 provided in this embodiment is used to measure characteristic parameters of a patient's wound, medical personnel can use the acquisition module 110 to capture images of the patient's wound site at any angle. Preferably, the three cameras 111 on the acquisition module 110 can simultaneously capture images of the patient's wound site from three angles. Preferably, the cameras 111 transmit the captured images to the modeling unit 121 of the processing module 120 to create a three-dimensional model. Preferably, the wound detection system 100 can utilize near-infrared imaging principles to capture near-infrared images of the patient's wound site. Preferably, the camera 111 can capture optical image information of the patient's wound site under near-infrared light. Preferably, the camera 111 can obtain the distribution and orientation of blood vessels in the patient's wound by capturing near-infrared images of the patient's wound site. Because hemoglobin in blood absorbs near-infrared light, the near-infrared light reflected by the hemoglobin to the camera 111 is attenuated.

[0058] Preferably, when establishing the three-dimensional model, the modeling unit 121 in the processing module 120 can model the blood distribution in the three-dimensional model based on the near-infrared image captured by the camera 111 .

[0059] Preferably, the first analysis model of the analysis unit 122 can determine whether bleeding is occurring within the wound by detecting blood distribution within the patient's wound. Preferably, when bleeding occurs within the patient's wound, the first analysis model of the analysis unit 122 can detect the presence of blood distributed outside the patient's blood vessels. Preferably, the wound detection system 100 can detect bleeding points within the wound before bleeding occurs, facilitating timely treatment by medical personnel.

[0060] As the wound heals, oxygen metabolism in the injured area increases, oxygen in the blood vessels is consumed, and hemoglobin changes. Specifically, oxygen metabolism in the wound area increases, oxygen is consumed, and the concentration of oxyhemoglobin in hemoglobin decreases, while the concentration of deoxyhemoglobin increases.

[0061] The camera 111 can acquire a near-infrared image representing the content of oxygenated hemoglobin and deoxygenated hemoglobin in the patient's wound area.

[0062] Preferably, when building the three-dimensional model, the modeling unit 121 in the processing module 120 can render the blood vessels in the three-dimensional model based on the near-infrared image captured by the camera 111. The depth of the blood vessel color reflects the concentration of oxyhemoglobin and deoxyhemoglobin. Preferably, when comparing the three-dimensional model with three-dimensional models in historical medical data, the second analysis model of the analysis unit 122 can determine the concentration changes of oxyhemoglobin and deoxyhemoglobin by comparing the changes in blood vessel color, thereby determining the healing status of the wound site.

[0063] Preferably, when the wound detection system 100 provided in this embodiment is used to measure the characteristic parameters of a patient's wound, medical personnel can use the acquisition module 110 to capture images of the patient's wound site at any shooting angle. Preferably, the three cameras 111 on the acquisition module 110 can obtain images of the patient's wound site at three shooting angles at the same moment. Preferably, the camera 111 transmits the captured image to the modeling unit 121 of the processing module 120 to establish a three-dimensional model. Preferably, the three-dimensional model includes blood vessel distribution. Preferably, the first analysis model of the analysis unit 121 identifies the three-dimensional model, which makes it easier for medical personnel to clearly see the internal conditions of the sinus wound, and makes it easier for medical personnel to more accurately measure the depth and width of the sinus wound and the size of the eroded grooves or holes on the side walls of the sinus wound.

[0064] The present invention provides a wound detection system 100 that can not only measure characteristic parameters of a wound, but also evaluate the healing condition of a patient's wound.

[0065] When evaluating the healing status of a patient's wound using existing technical means, medical personnel mostly make judgments based on measurement parameters. The accuracy of the judgment results is mainly determined by the accuracy of the measurement parameters and the experience of the medical personnel.

[0066] Preferably, the present invention collects images of the patient's wound site at three shooting angles through the acquisition module 110 and models the images, so that the accuracy of the three-dimensional model is guaranteed.

[0067] Preferably, the analysis unit 122 obtains the measurement parameters through the first analysis model, and uses the first analysis model trained by deep learning to identify the three-dimensional model modeled by fusing the multi-shooting angle images, thereby ensuring the accuracy of the measurement parameters.

[0068] Preferably, the present invention also evaluates the healing condition of the patient's wound through a second analysis model, thereby converting the subjective judgment of medical personnel into an objective judgment, thereby eliminating the interference of human experience factors on the evaluation results and improving the efficiency and effectiveness of wound healing evaluation.

[0069] For patients with chronic wounds, after applying medicine to their wounds, medical staff need to conduct irregular inspections of the patients' wounds to monitor the healing of the wounds and avoid adverse conditions such as infection of the wounds.

[0070] Preferably, when medical personnel are caring for a patient's wound, they can use the wound detection system 100 provided by the present invention to detect the patient's wound and evaluate the patient's wound healing condition.

[0071] Preferably, before treating the patient's wound, medical staff can use the wound detection system 100 to obtain measurement parameters of the patient's wound site, thereby providing data support for medical staff to perform debridement, suturing, and medication on the patient's wound.

[0072] Preferably, before treating a patient's wound, medical personnel can use acquisition module 110 to obtain simultaneous images of the patient's wound site from three different angles. Modeling unit 121 creates a three-dimensional model based on the images captured by acquisition module 110. The first analysis model in analysis unit 122 analyzes the three-dimensional model to obtain characteristic parameters of the patient's wound site.

[0073] Preferably, for patients receiving full-course care, after completing wound debridement, suturing, and medication, medical personnel can use the wound detection system 100 to obtain a three-dimensional model of the wound site after debridement, suturing, and medication application, and store the three-dimensional model in the storage unit 123. Preferably, the analysis unit 122 of the wound detection system 100 can compare the three-dimensional model with historical medical data using a second analysis model, and filter out historical cases from the historical medical data that most closely match the three-dimensional model. Preferably, after filtering out the historical cases, the analysis unit 122 can set the historical cases as reference cases for setting the testing strategy. Preferably, the examination plan includes at least the time interval between the current test and the next test. Preferably, the time interval between each test in the testing strategy set by the analysis unit 122 is the same as the time interval between each test in the reference case. For example, the analysis unit 122 can set the time interval between each test in the testing strategy to two days based on the reference case.

[0074] Preferably, the analysis unit 122 transmits the detection strategy to the display module 130 for display to the medical staff. Preferably, the medical staff can detect the patient's wound site according to the detection strategy set by the wound detection system 100.

[0075] Preferably, when medical personnel inspect the patient's wound site at time intervals according to the inspection strategy, the analysis unit 122 can compare the three-dimensional model obtained from this inspection with the three-dimensional model of the patient's last inspection through the second analysis model to evaluate the patient's wound healing condition.

[0076] Preferably, during testing, medical personnel can use the acquisition module 110 to capture images of the patient's wound area at any angle. The modeling unit 121 of the processing module 120 can create a three-dimensional model based on the images captured by the acquisition module 110. Preferably, when comparing the three-dimensional model acquired during the current test with the three-dimensional model of the patient's previous test, the second analysis model of the analysis unit 122 can adjust the three-dimensional model and the historical three-dimensional model to the same viewing direction for comparison, thereby determining the healing status of the patient's wound area.

[0077] During each test, the image capture angle of acquisition module 110 may change due to changes in the patient's posture or the medical staff's shooting angle, resulting in a different viewing direction of the three-dimensional model created by modeling unit 121. Preferably, the three-dimensional model created by modeling unit 121 includes vascular information. Since the distribution of blood vessels in human tissue is relatively fixed, the second analysis model can use the vascular position in the three-dimensional model as a reference system, adjust the viewing direction of the three-dimensional model by aligning the blood vessels in the three-dimensional model created for the current test with those in the three-dimensional model created for the previous test, and then perform a comparison.

[0078] Preferably, the second analysis model compares the three-dimensional model with the historical three-dimensional model to evaluate the patient's wound healing status. Preferably, the second analysis model's evaluation of the patient's wound healing status includes determining whether new adverse healing conditions have occurred, such as subcutaneous abscesses, cavities, tissue necrosis, bleeding, etc.; and determining changes in characteristic parameters of the wound, such as a decrease or increase in wound depth or area.

[0079] Preferably, the second analysis model compares the 3D model with the historical 3D model to assess whether the patient's wound is worsening or healing well. Preferably, when the second analysis model assesses wound worsening, such as the formation of a subcutaneous abscess cavity or partial tissue decay, the analysis unit 122 transmits the assessment result to the display module 130, prompting medical personnel to treat the patient's wound. Preferably, after treating the patient's wound, medical personnel can use the wound detection system 100 to inspect the treated wound and re-establish the inspection strategy.

[0080] Preferably, when the evaluation result of the second analysis model is good healing, that is, the patient's wound area, wound depth and other parameters have decreased, and no poor healing conditions such as abscesses, cavities or sinuses have appeared, the analysis unit 122 adjusts the detection strategy and transmits the adjusted detection strategy and evaluation results to the display module 130 for display to medical personnel. Preferably, when the evaluation result of the second analysis model is good healing, the analysis unit 122 can compare the evaluation result of the second analysis model with the healing conditions of the reference case to adjust the detection strategy. Preferably, when the evaluation result of the second analysis model is good healing, but the patient's wound healing is worse than that of the reference case, that is, the reduction in the patient's wound area, wound depth and other parameters is smaller than that of the reference case, indicating that the patient's wound healing speed is slow, the analysis unit 122 can extend the time interval between each detection in the detection strategy. Preferably, the analysis unit 122 can extend the time interval between each detection in the detection strategy to 3 days. Preferably, when the evaluation result of the second analysis model indicates good healing and the reduction in parameters such as wound area and wound depth of the patient is greater than that of the reference case, it indicates that the patient's wound is healing faster, and the analysis unit 122 can shorten the time interval between each test in the detection strategy. Preferably, the analysis unit 122 can shorten the time interval between each test in the detection strategy to 1 day.

[0081] Preferably, the wound detection system 100 can compare the three-dimensional model with the historical three-dimensional model through the second analysis model to evaluate the healing condition of the patient's wound, and the analysis unit 122 can adjust the time interval of each detection in the detection strategy according to the evaluation results, so as to reasonably allocate medical resources according to the patient's wound healing condition.

[0082] Example 2

[0083] This embodiment is a further improvement of embodiment 1, and repeated contents will not be repeated here.

[0084] The present invention also provides a wound detection device. The wound detection device includes at least: an acquisition module 110, a processing module 120, and a display module 130. The acquisition module 110 is equipped with at least two cameras 111 with different shooting angles to capture images of the patient's wound site at different shooting angles at the same time, and transmit the images from different shooting angles to the processing module 120. The processing module 120 processes the images and transmits the processing results to the display module 130 for display. Preferably, the processing module 120 processes the images by at least: creating a three-dimensional model of the patient's wound site based on the images and analyzing the three-dimensional model to obtain characteristic parameters of the patient's wound site and / or assess the healing status of the patient's wound site.

[0085] Preferably, the acquisition module 110 of this embodiment can be equipped with three cameras 111. Preferably, the three cameras 111 are spaced apart on the arc-shaped curved mounting housing 112. Preferably, the three cameras 111 include a first camera positioned at the top center of the curved surface, and a second camera and a third camera positioned around the first camera. Preferably, the second camera is spaced apart from the first camera by a first distance, and the third camera is spaced apart from the first camera by a second distance, wherein the second distance is greater than the first distance.

[0086] Preferably, the processing module 120 may include a modeling unit 121, an analysis unit 122, and a storage unit 123. Preferably, the analysis unit 122 is data-connected to the modeling unit 121 and the storage unit 123, respectively.

[0087] Preferably, the modeling unit 121 can obtain the depth information of each object in the image by scanning the images of the patient's wound captured by the acquisition module 110 at different shooting angles. Preferably, the modeling unit 121 can obtain the depth information of each object in the image based on the perspective difference caused by the different shooting angles of each camera 111, thereby realizing three-dimensional imaging. Preferably, the multiple images transmitted to the modeling unit 121 by the acquisition module 110 include the shooting angle information of the camera 111 that captured the image. Since the shooting angles of each camera 111 are different, the images captured by different cameras 111 contain the depth information difference of each object in the image caused by the perspective difference. Therefore, the modeling unit 121 can obtain the perspective difference of the patient's wound area image generated at different shooting angles, and map the depth information difference of each object in the corresponding image based on the perspective difference to realize three-dimensional imaging.

[0088] Preferably, the analysis unit 122 analyzes the three-dimensional model using a deep learning analysis model. Preferably, the analysis unit 122 can be configured with a first analysis model for extracting characteristic parameters of the patient's wound site and a second analysis model for evaluating the patient's wound healing status.

[0089] Preferably, the analysis unit 122 inputs the three-dimensional model into the first analysis model to obtain characteristic parameters of the patient's wound site. Preferably, the first analysis model identifies visually based characteristic parameters based on the input three-dimensional model, allowing medical personnel to determine the area and depth of the wound, whether it is composed of rotten or loose tissue, and whether there is cavitation and pus accumulation.

[0090] Preferably, when comparing the three-dimensional model with the three-dimensional model in the historical medical data, the second analysis model of the analysis unit 122 can determine the concentration changes of oxyhemoglobin and deoxyhemoglobin by comparing the changes in blood vessel color, and thus determine the healing condition of the wound site.

[0091] Example 3

[0092] This embodiment is a further improvement of Embodiment 1 and Embodiment 2, and the repeated contents will not be repeated here.

[0093] The present invention also provides a wound detection method. The wound detection method at least comprises:

[0094] capturing images of the patient's wound site;

[0095] A three-dimensional model of the patient's wound site is created based on the images;

[0096] The three-dimensional model is analyzed using the first analysis model to obtain characteristic parameters of the patient's wound site.

[0097] According to a preferred embodiment, the wound detection method further includes analyzing the three-dimensional model using a second analysis model to obtain information assessing the healing status of the patient's wound site. Preferably, the second analysis model assesses the patient's wound healing status by comparing the three-dimensional model with historical medical data. Preferably, the historical medical data includes at least the historical three-dimensional model.

[0098] Preferably, in this embodiment, when acquiring images of the wound portion of the patient, the images of the wound portion of the patient can be acquired from more than two shooting angles.

[0099] Preferably, when establishing a three-dimensional model of a patient's wound area based on an image of the patient's wound area, this embodiment can obtain depth information for each object in the image based on the perspective differences resulting from different shooting angles, thereby achieving three-dimensional imaging. Because the shooting angles are different, the image used for modeling contains the depth information differences for each object in the image resulting from the perspective differences. Therefore, during modeling, the perspective differences resulting from the different shooting angles of the patient's wound area image can be obtained, and the depth information differences for each object in the image can be mapped based on the perspective differences, achieving three-dimensional imaging.

[0100] Preferably, the present invention uses a deep learning analysis model to analyze the three-dimensional model. Preferably, the analysis model used to analyze the three-dimensional model includes a first analysis model for extracting characteristic parameters of the patient's wound site and a second analysis model for evaluating the patient's wound healing status.

[0101] Preferably, the first analysis model identifies visually-based feature parameters based on the input 3D model, allowing medical personnel to determine the area and depth of the wound, whether it is composed of decayed or loose tissue, and whether there are cavities and pus accumulation. Preferably, the second analysis model can compare the 3D model with a historical 3D model, adjusting them to the same viewing direction, to determine the healing status of the patient's wound.

[0102] It should be noted that the above-mentioned specific embodiments are exemplary, and those skilled in the art can come up with various solutions inspired by the disclosure of the present invention, and these solutions also belong to the disclosure scope of the present invention and fall within the protection scope of the present invention. Those skilled in the art should understand that the present invention specification and its drawings are illustrative and do not constitute a limitation of the claims. The scope of protection of the present invention is defined by the claims and their equivalents. Throughout the text, the features introduced by "preferably" are only an optional method and should not be understood as being required. Therefore, the applicant reserves the right to abandon or delete the relevant preferred features at any time. The present invention specification contains multiple inventive concepts, such as "preferably", "according to a preferred embodiment" or "optionally", which means that the corresponding paragraph discloses an independent concept, and the applicant reserves the right to file a divisional application based on each inventive concept.

Claims

1. A wound detection system, characterized in that: The wound detection system includes an acquisition module and a processing module; The acquisition module is provided with at least two cameras with different shooting angles, which are used to acquire images of the patient's wound site at different shooting angles at the same time, and transmit the images to the processing module; The processing module is used to process the images collected by the collection module; The processing module processes the image, including: using a modeling unit to obtain depth information of each object in the image based on the perspective differences caused by the different shooting angles of each camera, to establish a three-dimensional model of the patient's wound site, and rendering blood vessels in the three-dimensional model based on the near-infrared image captured by the camera, where the depth of the blood vessel color reflects the concentration of oxyhemoglobin and deoxyhemoglobin; analyzing the three-dimensional model using an analysis unit configured with a first analysis model for extracting characteristic parameters of the patient's wound site and a second analysis model for evaluating the patient's wound healing status to obtain characteristic parameters of the patient's wound site and / or evaluation information on the patient's wound healing status; The analysis unit compares and analyzes the three-dimensional model using a second analysis model to obtain assessment information on the healing status of the patient's wound. When comparing the three-dimensional model with historical medical data, the second analysis model determines the concentration changes of oxyhemoglobin and deoxyhemoglobin by comparing blood vessel color changes, thereby determining the healing status of the patient's wound. The historical medical data includes the historical three-dimensional model. The second analysis model adjusts the three-dimensional model and the historical three-dimensional model to the same viewing direction for comparison. The three-dimensional model established by the modeling unit includes vascular information. The second analysis model uses the position of the blood vessels in the three-dimensional model as a reference system and adjusts the viewing direction of the three-dimensional model by overlapping the blood vessels in the three-dimensional model established in the current detection with the blood vessels in the three-dimensional model established in the previous detection.

2. The wound detection system according to claim 1, characterized in that The analysis unit (122) uses a first analysis model that is trained through deep learning using actual patient wound images as samples to perform image segmentation on the three-dimensional model to obtain characteristic parameters of the patient's wound site, wherein the characteristic parameters include at least one of wound depth, area, and tissue shape.

3. The wound detection system according to claim 1, wherein: The processing module (120) is further configured with a storage unit (123) for storing historical medical data; After completing the analysis, the analysis unit (122) stores the three-dimensional model as historical medical data in the storage unit (123).

4. A wound detection method using the wound detection system according to any one of claims 1 to 3, characterized in that: The trauma detection method at least comprises: capturing images of the patient's wound; establishing a three-dimensional model of the patient's wound site based on the image; The three-dimensional model is analyzed using a first analysis model to obtain characteristic parameters of the patient's wound site.

5. A wound detection device, characterized in that: The wound detection device includes: an acquisition module, a processing module and a display module; The acquisition module is provided with at least two cameras with different shooting angles to obtain images of the patient's wound site at different shooting angles at the same time, and transmit the images at different shooting angles to the processing module; The processing module processes the image and transmits the processing results to the display module for display; The processing module processes the image, including: establishing a three-dimensional model of the patient's wound site based on the image and analyzing the three-dimensional model to obtain characteristic parameters of the patient's wound site and / or evaluating the healing status of the patient's wound site; using a modeling unit to obtain depth information of each object in the image based on the perspective difference caused by the different shooting angles of each camera to establish a three-dimensional model of the patient's wound site, and rendering the blood vessels in the three-dimensional model based on the near-infrared image captured by the camera, the depth of the blood vessel color reflects the concentration of oxyhemoglobin and deoxyhemoglobin; an analysis unit configured with a first analysis model for extracting characteristic parameters of the patient's wound site and a second analysis model for evaluating the patient's wound healing status, performing comparative analysis on the three-dimensional model through the second analysis model to obtain evaluation information on the healing status of the patient's wound site; when the second analysis model compares the three-dimensional model with historical medical data, the concentration change of oxyhemoglobin and deoxyhemoglobin is determined by comparing the blood vessel color change, thereby determining the healing status of the patient's wound, and the historical medical data includes the historical three-dimensional model; The second analysis model adjusts the 3D model and the historical 3D model to the same viewing direction for comparison. The second analysis model uses the position of the blood vessels in the 3D model as a reference system and adjusts the viewing direction of the 3D model by overlapping the blood vessels in the 3D model established by the current detection with the blood vessels in the 3D model established by the previous detection.

Images