Integrated diagnostic device for wound surface evaluation

Abstract

The invention provides an integrated diagnostic device for wound surface assessment, and relates to the technical field of medical equipment, the device comprises a cover-shaped main body, a light-shielding cover, a light-shielding cover, a light-shielding cover, a light-shielding cover and a light-shielding cover, the light source system is arranged on the inner side surface of the cover-shaped main body, comprises a plurality of light sources and is used for correspondingly providing light source conditions required by shooting; the image acquisition module is arranged on the inner side surface of the cover-shaped main body and is used for shooting a target wound surface at the opening end of the cover-shaped main body; and the control processing module is electrically connected with the light source system and the image acquisition module, and is used for regulating and controlling the image acquisition module and each light source to carry out shooting operation, carrying out analysis processing based on an image data sequence obtained by shooting, generating diagnosis information and outputting the diagnosis information. According to the technical scheme provided by the invention, different-dimension examination data information of the wound surface can be obtained under approximately the same time-space condition, so that the accuracy and reliability of a final evaluation result can be ensured.

Description

Technical Field

[0001] This application relates to the technical field of medical devices, and particularly to an integrated diagnostic device for wound surface assessment. Background Art

[0002] In the medical field, accurately assessing the wound condition is crucial for formulating effective treatment plans. However, existing wound assessment tools and technologies often have limitations. Generally speaking, relevant identification and detection tools and items can only provide single-dimensional information. For example, although fluorescence method can effectively identify bacterial infections, it cannot provide information about the size, shape of the wound surface or the health status of the surrounding tissues. Another example is that traditional natural light-based photography methods can show the color and morphology of the wound surface, but are powerless for subcutaneous blood vessel conditions or deep tissue injuries, etc.

[0003] In the process of implementing the present invention, the inventors noticed that although existing technical solutions can obtain information on various dimensions of a certain wound surface (such as bacterial infection situation, wound size and shape, etc.) respectively, the collection of this information often relies on different devices and requires subsequent manual summarization and analysis. This decentralized data collection method is not only inefficient, but also due to the fact that data on different dimensions are not obtained under the same spatio-temporal conditions, leading to significant correlation problems. Specifically, in actual operation, medical staff may need to use a variety of special devices to detect the same wound in sequence, which is not only time-consuming and laborious, but also may introduce errors due to changes in the patient's condition or different environmental conditions. In addition, when integrating data from different devices for comprehensive analysis, due to the lack of a unified time and space reference, the correlation and consistency between data are questioned, thus affecting the accuracy and reliability of the final assessment results.

[0004] Therefore, there is an urgent need in the existing practice for a device that can integrate multiple sensing technologies, so as to obtain inspection data on different dimensions of the wound surface under approximately the same spatio-temporal conditions, and then conduct immediate and comprehensive analysis based on this, thereby improving the efficiency of the overall assessment and being conducive to ensuring the accuracy and reliability of the final assessment results.

[0005] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] To overcome at least to some extent the problems existing in the related art, the embodiments of this application provide an integrated diagnostic device for wound surface assessment, which adopts specific device compositions and configurations to facilitate obtaining inspection data information on different dimensions of the wound surface under approximately the same spatio-temporal conditions, and further facilitate ensuring the accuracy and reliability of the final assessment results.

[0007] In some embodiments of the present application, an integrated diagnostic device for wound surface assessment is provided. The integrated diagnostic device includes: A hood-shaped main body for forming a light-shielding environment required for shooting; A light source system disposed on the inner side surface of the hood-shaped main body, including a variety of light sources for correspondingly providing light source conditions required for shooting; An image acquisition module disposed on the inner side surface of the hood-shaped main body for shooting a target wound surface placed at the open end of the hood-shaped main body; A control and processing module electrically connected to the light source system and the image acquisition module for regulating the image acquisition module and each light source to perform a shooting operation, and analyzing and processing based on the obtained image data sequence to generate and output diagnostic information.

[0008] In a possible implementation manner, the variety of light sources include visible light sources, near-infrared light sources, and fluorescence excitation light sources; the process of regulating the image acquisition module and each light source to perform a shooting operation includes: In response to a first message indicating the start of an operation, turning on the visible light source, using the RGB camera in the image acquisition module to perform natural imaging, and generating a first image in the image data sequence; In response to the generation of the first image, turning off the visible light source and turning on the near-infrared light source, using the thermal imaging camera in the image acquisition module to perform infrared imaging, and generating a second image in the image data sequence; In response to the generation of the second image, turning off the near-infrared light source and turning on the fluorescence excitation light source, using the fluorescence imaging device in the image acquisition module to perform fluorescence imaging, and generating a third image in the image data sequence; In response to the generation of the third image, turning off the fluorescence excitation light source and turning on the visible light source, using the RGB camera to perform natural imaging again, and generating a fourth image in the image data sequence; And in response to the generation of the fourth image, generating a second message indicating the completion of the operation.

[0009] In a possible implementation manner, the process of analyzing and processing based on the obtained image data sequence includes: For the first image, performing wound surface boundary segmentation and calculating the RGB values of sub-regions of the segmented and confirmed wound surface area to obtain the color hierarchy information of the wound from the inside to the outside; For the second image, using a pre-constructed deep learning model to perform recognition processing to confirm the size information of the wound surface, the information of the subcutaneous blood vessels, and the information of the granulation; For the third image, identify the fluorescence region and fluorescence intensity, and obtain information on the bacterial infection status of the wound surface based on this; And calculate the difference image between the fourth image and the first image, and obtain information on the speed of wound exudate based on the difference image.

[0010] In a possible implementation, the calculating the difference image between the fourth image and the first image, and obtaining information on the speed of wound exudate based on the difference image specifically includes: Perform preprocessing on the first image and the fourth image, and correspondingly obtain the processed fifth image and sixth image; Use the feature point matching algorithm to register and align the sixth image and the fifth image, and perform difference processing to obtain the difference image; Perform threshold segmentation on the difference image, confirm the pixel regions representing the presence of exudate, accumulate the areas of each of the pixel regions, and obtain exudate area information; Based on the exudate area information and the time stamp difference information between the fourth image and the first image, calculate and obtain the information on the speed of the wound exudate.

[0011] In a possible implementation, the performing wound surface boundary segmentation on the first image specifically is: Perform HSV color space conversion on the first image, and use the region growing algorithm in the H channel to perform wound surface boundary segmentation.

[0012] In a possible implementation, the deep learning model is implemented based on the U-Net model.

[0013] In a possible implementation, in the process of generating and outputting the diagnostic information, it includes: Retrieve the personal basic information of the patient corresponding to the target wound surface, and use the pre-constructed decision tree model to generate diagnostic information based on the personal basic information and the wound assessment information obtained through analysis and processing; Among them, the personal basic information includes age information, BMI information, medical history information, and medication situation information; the wound assessment information specifically is the color hierarchy information, the size information of the wound surface, the subcutaneous blood vessel situation information, the granulation situation information, the bacterial infection situation information, and the information on the speed of the wound exudate.

[0014] In a possible implementation, the open end of the hood-shaped main body is also covered with a detachable light-shielding cloth, and an opening for exposing the target wound surface is provided on the light-shielding cloth.

[0015] In a possible implementation, it further includes a display interaction module disposed on the outer side surface of the hood-shaped main body, and the display interaction module is electrically connected to the control processing module; The control processing module is configured to receive external operation instructions through the display interaction module and perform display output of the diagnostic information.

[0016] In a possible implementation, it further includes a power supply module embedded in the hood main body; the power supply module is implemented based on a rechargeable battery module and is used to provide electrical energy required for the device to operate.

[0017] The integrated diagnostic device for wound surface assessment provided by the embodiments of the present application includes: a hood-shaped main body for forming a light-shielding environment required for shooting; a light source system disposed on the inner side surface of the hood-shaped main body, including multiple light sources for correspondingly providing light source conditions required for shooting; an image acquisition module disposed on the inner side surface of the hood-shaped main body for shooting a target wound surface placed at the open end of the hood-shaped main body; a control processing module electrically connected to the light source system and the image acquisition module for regulating the image acquisition module and each light source to perform shooting operations, and analyzing and processing based on the obtained image data sequence to generate diagnostic information and output. In the technical solution of the present application, by configuring a light source system including multiple light sources inside the hood-shaped main body and being able to regulate and switch different types of light sources (such as visible light, near-infrared, etc.) as needed, high-quality shooting of the wound surface can be ensured under various lighting conditions. This design not only meets the requirements of diverse clinical scenarios but also provides a stable and objective imaging environment, which is conducive to obtaining multi-dimensional detection data of the wound surface under approximately the same time and space conditions. In this way, the accuracy and reliability of the final evaluation result can be effectively improved, providing strong support for precision medicine.

[0018] Other advantages, objectives, and features of the present application will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings are used to provide further understanding of the technical solution of the present application or the prior art and constitute a part of the specification. Among them, the drawings expressing the embodiments of the present application are used together with the embodiments of the present application to explain the technical solution of the present application, but do not constitute a limitation to the technical solution of the present application.

[0020] Figure 1 It is a schematic diagram of the electrical connection of the integrated diagnostic device for wound surface assessment provided by an embodiment of the present application; Figure 2Schematic structural illustration of an integrated diagnostic device for wound surface assessment in an embodiment of the present application Figure 1 ; Figure 3 Schematic structural illustration of an integrated diagnostic device for wound surface assessment in an embodiment of the present application Figure 2 ; Figure 4 Schematic flow chart illustration of an integrated diagnostic device for performing a shooting operation in an embodiment of the present application; Figure 5 Schematic flow chart illustration of an integrated diagnostic device for performing wound exudate assessment in an embodiment of the present application.

[0021] In the figure, 10 - hood-shaped main body; 20 - light source system; 30 - image acquisition module; 40 - control and processing module; 50 - light-shielding cloth; 51 - opening; 60 - display and interaction module; 70 - power supply module. Detailed implementation manners

[0022] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described in detail below. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation manners obtained by those of ordinary skill in the art without creative efforts shall fall within the scope protected by the present application.

[0023] As described in the background art, in the process of implementing the present invention, the inventors noticed that although the existing technical solutions can respectively obtain information on various dimensions of a certain wound surface (such as the situation of bacterial infection, the size and shape of the wound surface, etc.), the acquisition of this information often relies on different devices and requires subsequent manual summarization and analysis. This decentralized data acquisition method is not only inefficient, but also due to the fact that data on different dimensions are not obtained under the same spatio-temporal conditions, leading to significant correlation problems; specifically, in actual operation, medical staff may need to use a variety of special devices to sequentially detect the same wound, which is not only time-consuming and laborious, but also may introduce errors due to changes in the patient's condition or different environmental conditions. In addition, when integrating data from different devices for comprehensive analysis, due to the lack of a unified time and space reference, the correlation and consistency between the data are questioned, thus affecting the accuracy and reliability of the final assessment results. Therefore, there is an urgent need in the existing practice for a device that can integrate multiple sensing technologies, so that inspection data on different dimensions of a wound surface can be obtained under approximately the same spatio-temporal conditions, and then based on this, immediate and comprehensive analysis can be carried out, thereby improving the overall assessment efficiency and being conducive to ensuring the accuracy and reliability of the final assessment results.

[0024] Based on this, the present application proposes an integrated diagnostic device for wound surface assessment, which adopts specific device compositions and configurations to facilitate obtaining different-dimensional inspection data information of the wound surface under approximately the same space-time conditions, thereby facilitating ensuring the accuracy and reliability of the final assessment result.

[0025] As Figures 1 to 3 shown, in one embodiment, the integrated diagnostic device for wound surface assessment proposed by the present application includes: A cover-shaped main body 10 for forming a light-shielding environment required for shooting; A light source system 20 is arranged on the inner side surface of the cover-shaped main body 10, including a variety of light sources for correspondingly providing the light source conditions required for shooting; An image acquisition module 30 is arranged on the inner side surface of the cover-shaped main body 10 for shooting a target wound surface placed at the open end of the cover-shaped main body; A control and processing module 40 is electrically connected to the light source system 20 and the image acquisition module 30, and is used for regulating the image acquisition module 30 and each light source to implement a shooting operation, and analyzing and processing based on the obtained image data sequence to generate diagnostic information and output it.

[0026] For example, as Figure 2 shown is a schematic structural illustration of the integrated diagnostic device after being partially cut open in a specific embodiment (the filled part in the figure is the cross-section plane), Figure 3 shown is a schematic structural illustration of another angled cut-away part in this embodiment. In this embodiment, the overall shape of the cover-shaped main body 10 is cube-like, with an open bottom end. The light source system 20 is arranged on the inner side surface of the top of the cover-shaped main body 10 ( Figure 3 only one light source device, an LED lamp column, is schematically shown), and the image acquisition module 30 is also placed on the inner side surface of the top of the cover-shaped main body 10, and its shooting field of view is opposite to the open bottom end of the cover-shaped main body. The control and processing module in the technical solution of the present application can be embedded in the cover-shaped main body (not shown in the figure).

[0027] In the actual application of the integrated diagnostic device in the present application, the wound surface of the patient can be placed at the open bottom end of the cover-shaped main body. The control and processing module, under the trigger of an external instruction, schedules and controls each light source and the image acquisition module to implement a shooting operation to obtain images under different light source conditions, so as to form an image data sequence required for subsequent evaluation and analysis. Furthermore, according to the image data sequence, the processing algorithm built in the control and processing module is used to evaluate the diagnostic information of the patient's wound surface.

[0028] In the technical solution of this application, a light source system including multiple light sources is configured inside the cover-shaped main body, and different types of light sources (such as visible light, near-infrared, etc.) can be regulated and switched according to needs, so as to ensure high-quality shooting of the wound surface under various lighting conditions. This design not only meets the requirements of diverse clinical scenarios, but also provides a stable and objective imaging environment, which is conducive to obtaining multi-dimensional detection data of the wound surface under approximately the same time and space conditions. In this way, the accuracy and reliability of the final evaluation result can be effectively improved, providing strong support for precision medicine.

[0029] Based on the above embodiments, in some embodiments, the multiple light sources in the light source system 20 specifically include a visible light source, a near-infrared light source, and a fluorescence excitation light source; It is easy for those skilled in the art to understand that in the wound detection scenario, the visible light source is the most basic and common light source. The wavelength range of the visible light source here is 390nm to 780nm. Under the illumination conditions of the visible light source, the characteristics such as the color, size, and shape of the wound can be clearly displayed; while the near-infrared light source is particularly useful for detecting deep tissue damage. For example, the wavelength of the near-infrared light source here is 850nm, which can be used to detect subcutaneous blood vessels, etc.; In addition, wound fluorescence detection is a currently emerging non-invasive technology for evaluating wound health status. Its principle is that a specific wavelength of excitation light is irradiated on the wound, and certain substances in the wound (such as porphyrin substances produced by bacteria) will be activated and emit fluorescence with a specific wavelength. The wound is evaluated by observing or measuring this fluorescence. The fluorescence excitation light source here is to provide this excitation light. For example, the fluorescence excitation light source here can emit ultraviolet excitation light with a wavelength of 365nm.

[0030] The integrated diagnostic device of this application aims to provide multiple light source conditions and obtain multi-dimensional data under approximately the same time and space conditions through centralized shooting to ensure the relevance of the data and improve the overall efficiency. In this process, the configuration of the acquisition order of different-dimensional data is involved. Given that the detection is carried out centrally, there may be mutual influences between some acquisition processes, which is not conducive to quickly and accurately collecting the required multi-dimensional data. Therefore, in the process of implementing the present invention, in response to this newly emerging demand, the inventor has made a comprehensive consideration and adopted the following specific implementation methods.

[0031] Based on the above embodiments, in some embodiments, as Figure 4 shown, the process of the control processing module realizing the regulation of the image acquisition module and each light source to perform the shooting operation includes: Step S41: In response to a first message indicating the start of an operation, turn on the visible light source, and use the RGB camera in the image acquisition module to perform natural imaging to generate the first image in the image data sequence. It should be noted that the first message here can be triggered by a medical staff user inputting a relevant instruction for indicating the start of the shooting operation after the wound surface of a certain patient A is placed at the opening end of the device. And the RGB camera, as known to those skilled in the art, is a digital camera that can capture three basic color channels of red, green, and blue. Its working principle is based on the way the human eye perceives colors. Therefore, the first image obviously includes color-related information of the wound surface.

[0032] Then perform Step S42: In response to the generation of the first image, turn off the visible light source and turn on the near-infrared light source, and use the thermal imaging camera in the image acquisition module to perform infrared imaging to generate the second image in the image data sequence; It should be noted that the configuration of performing infrared imaging after natural imaging here is considered because there will be residual near-infrared radiation in the application of the near-infrared light source. If infrared imaging is performed first, without setting a relatively long switching time interval, it is easy to cause color distortion in natural imaging. And the original intention of the technical solution of this application is to provide approximate same spatio-temporal conditions for data acquisition. Therefore, it is necessary to switch as fast as possible and avoid the interference of infrared imaging on natural imaging. So in the actual implementation of the solution, the setting of performing infrared imaging after natural imaging is adopted.

[0033] Then perform Step S43: In response to the generation of the second image, turn off the near-infrared light source and turn on the fluorescence excitation light source, and use the fluorescence imaging device in the image acquisition module to perform fluorescence imaging to generate the third image in the image data sequence; Similarly, in the technical scenario of this application, if fluorescence imaging is performed before natural imaging, there will also be similar color distortion and efficiency problems. Therefore, fluorescence imaging should be set after natural imaging; and the fluorescence excitation light may accidentally activate photosensitive substances, while infrared imaging does not require special marking. Performing fluorescence imaging after infrared imaging can avoid non-specific fluorescence interference. For example, the porphyrin-like metabolites of Staphylococcus aureus emit red light under blue light excitation. If fluorescence imaging is performed first, it may cover up subsequent vascular features, that is, non-specific fluorescence interference.

[0034] Then perform Step S44: In response to the generation of the third image, turn off the fluorescence excitation light source and turn on the visible light source, and use the RGB camera to perform natural imaging again to generate the fourth image in the image data sequence; It should be noted that the fourth image here is mainly used for correlation analysis with the first image to evaluate the situation of wound exudate (the specific implementation method will be described in detail later). This evaluation actually requires a certain time interval between the acquisition times of the fourth image and the first image. Therefore, considering the overall efficiency and actual requirements comprehensively, the fourth image in the image sequence is obtained last here.

[0035] After that, step S45 is performed. In response to the generation of the fourth image, a second message indicating the completion of the operation is generated to mark the end of the shooting operation for the wound surface of patient A in the control implementation.

[0036] In the above embodiments, by implementing steps through specific methods, not only the mutual interference between different light sources is avoided, but also various types of image data can be efficiently obtained, providing strong support for the accurate diagnosis of wounds.

[0037] Based on the above embodiments, in some embodiments, the process of analyzing and processing the image data sequence obtained by shooting includes: For the first image, the wound surface boundary is segmented, and the RGB values of different regions of the segmented and confirmed wound surface area are calculated to obtain the color hierarchy information of the wound from the inside to the outside.

[0038] Specifically, as a specific implementation method, during the process of segmenting the wound surface boundary, the first image can be converted to the HSV color space, and the region growing algorithm is used in the H channel to segment the wound surface boundary; the HSV color space is closer to human visual perception, where H represents hue, S represents saturation, and V represents value. This conversion helps to improve the effect of subsequent processing steps; after completing the HSV color space conversion, the information of the H channel is used to apply the region growing algorithm. The H channel can effectively distinguish different colors and is particularly suitable for distinguishing the color differences between healthy skin and wound tissue. Through the above process, it is beneficial to accurately implement the wound surface boundary segmentation and provide basic data for the next color hierarchy analysis; After determining the wound surface boundary, the RGB values of different regions of the segmented and confirmed wound surface area can be calculated. By calculating the average RGB values of different parts of the wound from the inside to the outside, the color hierarchy information of this region can be obtained. In the technical scenario of this application, this color hierarchy information is of great significance for understanding the wound healing status and judging whether there is an infection, etc.

[0039] In this embodiment, for the second image, the pre-constructed deep learning model is used for recognition processing to confirm the size information of the wound surface, the information of the subcutaneous blood vessels, and the information of the granulation situation; As a specific implementation, the deep learning model here is implemented based on the U-Net model. Similar to the prior art, the construction of the relevant dataset is also involved in the process of building the model here. For example, a large number of wound infrared images are collected and manually annotated. Based on the constructed dataset, the relevant pre-trained model is retrained and adjusted, and performance evaluation is carried out, etc. The model that passes the evaluation is used as the model that can be actually deployed and used. The relevant technical principles of this part can be found in the existing public technical materials, and will not be elaborated here in this application.

[0040] In this embodiment, for the third image, the fluorescence region and the fluorescence intensity are identified, and the information on the bacterial infection situation of the wound surface is obtained accordingly. The third image is a fluorescence image, and the bacterial autofluorescence information it contains can specifically show the presence and distribution of bacteria at the wound site. To identify the fluorescence region, the third image needs to be preprocessed first, including operations such as denoising and contrast enhancement, so as to more clearly identify the fluorescence region. Then, an image segmentation algorithm, such as the Otsu threshold segmentation method or the adaptive threshold segmentation method, etc., is applied to mark the set of pixels with fluorescence intensity (corresponding to the gray value) higher than a certain threshold in the image as the possible bacterial presence region, so as to define the specific location of the bacterial infection. Furthermore, within the identified fluorescence region, the average fluorescence intensity of each sub-region is further calculated. Since the autofluorescence characteristics of different types of bacteria are different, the fluorescence intensity can be an important indicator for judging the type and concentration of bacteria. Therefore, according to the pre-established standard database, which should contain the fluorescence intensity data of known types of bacteria under the same imaging conditions, the fluorescence intensity values in the third image are compared and quantified, so as to infer the types and relative quantities of bacteria at the wound, and obtain the information on the bacterial infection situation of the wound surface.

[0041] In this embodiment, the process of analysis and processing further includes calculating the difference image between the fourth image and the first image, and obtaining the information on the speed situation of the wound exudate based on the difference image. Specifically, as a specific implementation, such as Figure 5 shown, the following steps are used to analyze and determine the wound exudate information: Step S51, preprocess the first image and the fourth image, and correspondingly obtain the processed fifth image and sixth image. It is easy to understand that the preprocessing here also includes denoising, enhancement processing, etc. Step S52, use the feature point matching algorithm to register and align the sixth image and the fifth image, and perform differential processing to obtain the difference image. The feature point matching algorithm here can use algorithms such as SIFT, SURF, ORB algorithms, etc. For example, in actual implementation here, the ORB algorithm is used to have high computational efficiency while ensuring sufficient accuracy. Its implementation process includes: Extract the feature points of two images through the ORB algorithm, and achieve precise alignment between the images based on the distances and other geometric relationships between these feature points; then perform differential processing to obtain a differential image, which shows the changed areas between the two input images. In the technical scenario of this application, these changed areas generally correspond to the positions of exudates.

[0042] Furthermore, step S53 can be performed. For the differential image obtained in step S52, perform threshold segmentation to confirm the pixel regions representing the existence of exudates, accumulate the areas of each pixel region, and obtain the exudate area information. Regarding the threshold here, in practice, a suitable threshold can be set according to experiments or experience. Pixels higher than this threshold are considered to be part of the exudate. For example, the differential image can be converted into a binary image; in this binary image, all pixel points with gray levels higher than the threshold (which may be the exudate area) are set to 1, while pixel points lower than the threshold (background or non-exudate area) are set to 0. Then, perform area statistics on all pixel regions marked as exudates, that is, calculate the total number of pixels in these regions and convert it into the actual physical area. It should be noted that to determine the conversion relationship between these pixel points and the actual size, common existing size calibration methods can be used to achieve this. For example, set a reference object with a known size and a determined positional relationship with the wound imaging plane in the shooting field of view, and calculate and determine this conversion relationship through relevant perspective imaging relationships.

[0043] Finally, perform step S54. According to the exudate area information and the time stamp difference information between the fourth image and the first image, calculate and obtain the speed situation information of the wound exudate. It is easy to understand that here the time stamp difference is the time interval between the shooting of the first image and the fourth image. Divide the exudate area information determined in S53 by this time interval information, and the speed situation information of the wound exudate is obtained.

[0044] Based on the above embodiments, in some embodiments, during the process of the control processing module generating and outputting diagnostic information, it specifically includes: Retrieve the personal basic information of the patient corresponding to the target wound surface, and generate diagnostic information using the pre-constructed decision tree model according to the personal basic information and the wound assessment information obtained through analysis and processing. It should be noted that the personal basic information here includes age information, BMI information, medical history information, and medication situation information; the wound assessment information is specifically the color hierarchy information, wound size information, subcutaneous blood vessel situation information, granulation situation information, bacterial infection situation information, and speed situation information of the wound exudate mentioned in the previous embodiments.

[0045] For example, the personal basic information here can be directly input by the medical user or pulled from an external system (such as a hospital information system or an electronic medical record system) based on relevant interaction configurations. Regarding the decision tree model, as is known to those skilled in the art, a decision tree is a model that uses a tree-shaped data structure to display decision rules and classification results. Specifically in this application, the decision tree model here is constructed based on existing construction methods, combined with the cutting-edge technologies and concepts of domestic and foreign wound experts, as well as guiding opinions such as consensus and standards. It belongs to the application of a general method in the specific scenario of wound medical diagnosis. Similar implementations can be seen in relevant public technical materials, and details are not elaborated here in this application.

[0046] Finally, the technical solution of this application will be further described from the aspect of structural arrangement. For example, Figure 2 As shown, in some embodiments, the open end of the hood-shaped main body 10 is also covered with a detachable light-shielding cloth 50, and an opening 51 for exposing the target wound surface is provided on the light-shielding cloth 50. With this setting, for different wound surface conditions in practice, it can be flexibly adjusted by replacing the light-shielding cloth with openings of different conditions (position, size), so as to obtain the required light-shielding environment, which is beneficial to the effective progress of subsequent shooting operations. Such an implementation method not only improves the flexibility and adaptability of device use, but also ensures that clear and accurate wound images can be obtained under various lighting conditions, providing a guarantee for accurate evaluation and treatment. In addition, the detachable design of the light-shielding cloth is conducive to facilitating replacement and cleaning, and thus helps to maintain hygienic conditions and avoid the risk of cross-infection.

[0047] For example, Figure 1 and Figure 2 As shown, in some embodiments, the device further includes a display interaction module 60 provided on the outer side surface of the hood-shaped main body 10, and this module is electrically connected to the control processing module 40. The control processing module 40 is configured to receive external operation instructions and perform display output of diagnostic information through the display interaction module 60, so that the device can be used completely independently without connecting any external display screen or computer device. This design not only improves the portability and convenience of use of the device, but also ensures that users can operate efficiently and obtain instant feedback in different environments, enhancing the overall user experience. In addition, the integrated solution helps to reduce the complexity and failure points that may be brought by connecting external devices, and improves the stability and reliability of the system; Furthermore, for example, Figure 1As shown, the device also includes a power supply module 70 embedded in the cover body 10. The power supply module 70 is implemented based on a rechargeable battery module and is used to provide the device with the power required for operation. Such a device is not only suitable for daily diagnosis and evaluation of wounds, but also suitable for outdoor environments or areas with underdeveloped primary medical facilities. This design enables the device to operate effectively in an environment with a lack of stable power supply or limited medical resources, greatly expanding its scope of use and scene flexibility, and providing users in different environments with convenient and immediate medical service solutions.

[0048] In summary, the integrated diagnostic device in the technical solution of the present application can ensure high-quality photography of wound surfaces under various lighting conditions by arranging multiple light source systems inside the hood-shaped body and automatically switching different types of light sources (such as visible light, near infrared, etc.) as needed. This design can not only adapt to different clinical scenarios and wound types, but also provide consistent and objective imaging conditions, thereby improving the accuracy and reliability of image acquisition.

[0049] The control processing module regulates the workflow of the light source system and the image acquisition module, so that a multi-dimensional image data sequence of the target wound surface can be obtained under different lighting conditions. Combined with relevant image analysis algorithms, such as color hierarchy analysis, region growing method, and deep learning models, rich feature information can be extracted from these images, including but not limited to wound surface size, shape, color change, subcutaneous tissue structure, and exudate conditions. This provides doctors with a more comprehensive and accurate basis for diagnosis, which helps to formulate more effective treatment plans.

[0050] The technical solution of this application realizes the automation of a series of processes from light source adjustment, image capture to data analysis, greatly reducing the need for manual intervention. At the same time, with the advancement of machine learning algorithms, the device can also continuously optimize its diagnostic capabilities, accumulate more case data over time, and further improve the accuracy of diagnosis.

[0051] In addition, through the integrated display interaction module, based on the specific interaction configuration, the user can directly view the diagnosis results and make necessary adjustments or confirmations, which promotes the intelligent development of the diagnosis and treatment process. And because the integrated diagnostic device adopts a portable design and has a built-in rechargeable battery module, it can be used in wards or even in telemedicine environments without relying on a fixed power source location, which greatly improves the convenience of use. For medical staff, this means completing wound assessment tasks more quickly and reducing the time cost of repetitive work; for patients, it means getting more timely and accurate medical services, improving the overall medical experience.

[0052] All the defects existing in the above solutions are the results obtained by the inventors through practice and careful research. Therefore, the process of discovering the above problems and the solutions proposed by the present application for the above problems in the following text should be the contributions made by the inventors to the present application during the process of the present application. As described above, the above is only a preferred specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0053] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and the content not detailed in some embodiments can be seen in the same or similar content of other embodiments.

[0054] It should be noted that in the description of the present application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "a plurality" refers to at least two.

[0055] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of executable instructions including one or more steps for implementing a specific logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a manner that is not shown or discussed, including in a substantially simultaneous manner according to the involved functions or in a reverse order, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0056] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0057] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An integrated diagnostic device for wound surface assessment, characterized in that: include: The hood-shaped main body is used to form a light-shielding environment required for shooting; A light source system, arranged on the inner side of the cover-shaped body, including a plurality of light sources, for correspondingly providing light source conditions required for shooting; An image acquisition module, disposed on the inner side of the cover-shaped body, and used to photograph a target wound surface disposed at the opening end of the cover-shaped body; The control processing module is electrically connected to the light source system and the image acquisition module, and is used to control the image acquisition module and each of the light sources to implement the shooting operation, and to analyze and process the image data sequence obtained by shooting, generate diagnostic information and output it.

2. The integrated diagnostic device for wound surface assessment according to claim 1, wherein: The multiple light sources include visible light sources, near infrared light sources and fluorescent excitation light sources; the process of regulating the image acquisition module and each of the light sources to implement the shooting operation includes: In response to a first message indicating the start of an operation, turning on the visible light source, performing natural imaging using an RGB camera in the image acquisition module, and generating a first image in the image data sequence; In response to the generation of the first image, the visible light source is turned off and the near-infrared light source is turned on, and infrared imaging is performed using a thermal imaging camera in the image acquisition module to generate a second image in the image data sequence; In response to the generation of the second image, the near-infrared light source is turned off and the fluorescence excitation light source is turned on, and fluorescence imaging is performed using the fluorescence imaging device in the image acquisition module to generate a third image in the image data sequence; In response to the generation of the third image, the fluorescent excitation light source is turned off and the visible light source is turned on, and natural imaging is performed again using the RGB camera to generate a fourth image in the image data sequence; And in response to the generation of the fourth image, generating a second message indicating that the operation is completed.

3. The integrated diagnostic device for wound surface assessment according to claim 2, wherein: The process of analyzing and processing the image data sequence obtained by shooting includes: For the first image, the wound surface boundary is segmented, and the RGB value of the wound surface area confirmed by the segmentation is calculated by region to obtain the color level information of the wound from the inside to the outside; For the second image, a pre-built deep learning model is used to perform recognition processing to confirm the size information of the wound surface, the condition information of the subcutaneous blood vessels, and the condition information of the granulation tissue; For the third image, the fluorescence area and the fluorescence intensity are identified, and the bacterial infection information of the wound surface is obtained accordingly; And a differential image between the fourth image and the first image is calculated, and speed information of wound exudate is obtained based on the differential image.

4. The integrated diagnostic device for wound surface assessment according to claim 3, wherein: The calculating a difference image between the fourth image and the first image, and obtaining the velocity information of the wound exudate based on the difference image, specifically includes: Preprocessing the first image and the fourth image to obtain a processed fifth image and a processed sixth image; Using a feature point matching algorithm to register and align the sixth image and the fifth image, and performing a difference process to obtain the difference image; Performing threshold segmentation on the differential image to identify pixel regions indicating the presence of exudate, and accumulating the areas of each pixel region to obtain exudate area information; The speed information of the wound exudate is calculated based on the exudate area information and the timestamp difference information between the fourth image and the first image.

5. The integrated diagnostic device for wound surface assessment according to claim 3, wherein: The wound surface boundary segmentation is performed on the first image, specifically: The first image is converted into HSV color space, and the wound boundary is segmented using a region growing algorithm in the H channel.

6. The integrated diagnostic device for wound surface assessment according to claim 3, wherein: The deep learning model is implemented based on the U-Net model.

7. The integrated diagnostic device for wound surface assessment according to claim 3, wherein: The process of generating and outputting the diagnostic information includes: Retrieving basic personal information of the patient corresponding to the target wound surface, and generating diagnostic information using a pre-built decision tree model based on the basic personal information and wound assessment information obtained through analysis and processing; Among them, the personal basic information includes age information, BMI information, medical history information and medication information; the wound assessment information specifically includes the color level information, the wound size information, subcutaneous blood vessel information and granulation information, the bacterial infection information and the wound exudate speed information.

8. The integrated diagnostic device for wound surface assessment according to claim 1, wherein: The open end of the cover-shaped main body is also covered with a detachable shading cloth, and the shading cloth is provided with an opening for exposing the target wound surface.

9. The integrated diagnostic device for wound surface assessment according to claim 8, wherein: It also includes a display interaction module disposed on the outer side of the cover-shaped body, and the display interaction module is electrically connected to the control processing module; The control processing module is configured to receive external operation instructions through the display interaction module and display and output the diagnostic information.

10. The integrated diagnostic device for wound surface assessment according to claim 9, wherein: It also includes a power supply module embedded in the cover body; the power supply module is implemented based on a rechargeable battery module and is used to provide the device with the electrical energy required for operation.

Images