A method and system for detection and irrigation of deep infective wounds sinuses

Abstract

The present application relates to a kind of based on deep infectious wound sinus tract detection flushing method and system, belong to medical intelligent detection instrument technical field.Wherein, the method includes: through the micro endoscope of detection flushing device probe connection obtains sinus tract internal image signal, and by real-time transmission to external display device;Terminal application of external display device receives sinus tract internal image signal and is converted into identifiable image information, based on image information self-adapting identification infection area and potential necrotic tissue in sinus tract, and set flushing parameter;Terminal application will flush parameter be transmitted to the wireless receiver of detection flushing device, and control module will be received flush parameter generation control instruction;According to control instruction, adjust flushing pressure and flushing flow to flush sinus tract.It has realized the accurate detection and efficient flushing of deep infectious wound sinus tract, improves the pertinence and effectiveness of flushing.

Description

Technical Field

[0001] This invention belongs to the field of medical intelligent detection device technology, specifically relating to a detection and irrigation method and system for sinus tracts in deeply infected wounds. Background Technology

[0002] Traditional sinus tract management relies heavily on the physician's visual judgment and manual probe palpation, lacking objective quantitative tools. The manual irrigation process has significant technical shortcomings: relying on the syringe injection speed to adjust the pressure may result in actual pressure fluctuations exceeding the safe threshold; open irrigation systems cannot maintain a constant flow rate, leading to uneven distribution of irrigation fluid and insufficient coverage of deep infection lesions; and the lack of a real-time temperature feedback mechanism may damage newly formed granulation tissue when the irrigation fluid temperature deviates from the ideal range.

[0003] The reuse of metal probes creates sterilization blind spots, leading to increased infection rates, especially with poor control of drug-resistant bacteria. Each debridement session is time-consuming and requires multiple follow-up visits, significantly increasing the consumption of medical resources. Currently, although some automated irrigation devices have been proposed, most of these devices are single-function and lack intelligent identification and control capabilities, failing to meet the complex treatment needs of deep-infected wound sinuses. For example, while current mainstream devices have pressure / temperature regulation functions, irrigation parameter settings rely on preset programs and cannot be dynamically adjusted based on real-time imaging (such as endoscopic views). Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, the present invention provides a method and system for detecting and rinsing sinus tracts in deeply infected wounds;

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] S1: Obtain image signals inside the sinus tract through a miniature endoscope connected to a probe in the detection flushing device, and transmit the image signals to an external display device in real time through a wireless transceiver module integrated in the microcontroller;

[0007] S2: The external display device receives the internal image signal of the sinus tract through the wireless communication module of the terminal application and converts it into image information that can be recognized by a computer. The terminal application adaptively identifies the infected area and potential necrotic tissue in the sinus tract based on the image information and sets the flushing parameters.

[0008] S3: The terminal application feeds back the rinsing parameters to the wireless transceiver module of the detection rinsing device through the wireless communication module, and the microcontroller generates rinsing control commands according to the rinsing parameters;

[0009] S4: The flushing pressure and flushing flow rate of the flushing pipeline are adaptively controlled by a micro motor and flow regulation module according to the flushing control command.

[0010] Specifically, the detection and flushing device in S1 includes a probe, a micro-endoscope, a microcontroller, a flushing button, a switch button, a power module, a micro motor, a flow regulation module, a flushing channel, a liquid storage chamber, and a flushing fluid buffer chamber. One end of the probe is connected to the micro-endoscope, and the other end is used to insert into the sinus tract for deep detection. The micro-endoscope integrates an LED lighting module to provide illumination inside the sinus tract. The microcontroller integrates a wireless transceiver module to transmit the image signal inside the sinus tract to an external display device in real time and to receive flushing parameters transmitted from the external display device. The microcontroller is electrically connected to the micro motor and the flow regulation module. The flushing button is connected to the micro motor for start / stop control. The switch button is electrically connected to the power module to turn the entire detection and flushing device on or off. The flushing channel passes sequentially through the probe, the flushing fluid buffer chamber, and the liquid storage chamber. The micro motor regulates the pressure of the flushing fluid buffer chamber to control the flushing flow rate, and the flow regulation module regulates the flushing fluid flowing from the liquid storage chamber into the flushing fluid buffer chamber through the flushing channel.

[0011] Specifically, the microcontroller generates a PWM duty cycle control signal and a flow control analog signal based on the received flushing parameters, and transmits them to the micro motor and the flow regulation module via the drive circuit. The micro motor adjusts the duty cycle to change the output pressure through the PWM duty cycle signal, and the flow regulation module controls the flushing flow rate through the flow control analog signal.

[0012] Specifically, the flushing button triggers the micro motor to start, pushing the stored flushing fluid into the flushing channel; when the capacitive sensor detects that the flushing fluid buffer chamber is empty, it sends a feedback signal to the microcontroller.

[0013] Specifically, the flow regulation module generates a proportional voltage to drive the stroke length of the liquid pump based on the flow control analog signal via a D / A converter;

[0014] After the flushing button is triggered, the microcontroller sends a flow control analog signal and a liquid pump start signal to the flow regulation module through the received feedback signal.

[0015] Specifically, the adaptive recognition method in S2 is as follows:

[0016] S201: Determine the segmentation threshold for each pixel by dynamically calculating the gray-level statistics of the local region of the image information; dynamically segment the gray-level difference between enhanced lesions and normal tissues according to the segmentation threshold; extract and analyze the target localization region based on the segmentation results;

[0017] S202: Extract morphological features from the target location region, construct a combined classifier based on the kernel function output of different feature subsets in the morphological features, and optimize the classifier parameters according to the minimum classification error;

[0018] S203: After the classifier is trained, the confidence level of the infected area and potential necrotic tissue based on the target location area is output. The target location area with a confidence level greater than a preset threshold is marked on the image display interface of the terminal application to realize the automatic identification of the infected area and potential necrotic tissue. The identification result is fed back to the terminal application to set the corresponding flushing parameters.

[0019] Specifically, the dynamic segmentation enhancement method described in S201 is as follows:

[0020] Calculate the local mean and variance for each pixel's neighborhood; use the local mean to filter brightness and select regions with values ​​less than the global mean as candidate dark areas; use the variance to filter contrast and perform image enhancement processing on low-contrast regions.

[0021] Specifically, the morphological features in S202 include high eccentricity features, low compactness features, low intrinsicity features, and structural heterogeneity features; the kernel function adaptation strategy for different feature subsets in the morphological features is as follows:

[0022] Based on the high eccentricity and low compactness features, a subset of shape complexity is constructed, and a radial basis function kernel is used to capture nonlinear boundaries; based on the low intrinsicity features, a subset of topological structure is constructed, and a polynomial kernel is used to enhance convexity differences; based on the structural heterogeneity features, a subset of organizational heterogeneity is constructed, and a linear kernel is used to improve classification efficiency; by combining different kernel functions with weight coefficients, the classifier parameters are optimized.

[0023] Specifically, the objective function for optimizing the minimum classification error in S203 is set as follows:

[0024]

[0025] Where λ is the Lagrange multiplier of the support vector machine, n is the total number of training samples, and y i Let x represent the true label of the i-th sample. i for, Let represent the predicted value for the i-th sample, where α is the regularization coefficient and K is the kernel function.

[0026] A detection and irrigation system for sinus tracts in deeply infected wounds includes: a detection and communication module, a terminal application identification unit, a feedback control module, and an irrigation execution unit;

[0027] The detection and communication module is used to acquire image signals inside the sinus tract through a miniature endoscope connected to a probe in the detection and flushing device, and to transmit the image signals to an external display device in real time through a wireless transceiver module integrated in the microcontroller.

[0028] The terminal application identification unit is used by the external display device to receive the internal image signal of the sinus tract through the wireless communication module of the terminal application and convert it into image information that can be recognized by a computer. The terminal application adaptively identifies the infected area and potential necrotic tissue in the sinus tract based on the image information and sets the flushing parameters.

[0029] The feedback control module feeds back the flushing parameters to the wireless transceiver module of the detection flushing device through the wireless communication module according to the terminal application, and the microcontroller generates flushing control commands according to the flushing parameters.

[0030] The flushing execution unit uses a micro motor and a flow regulation module to adaptively control the flushing pressure and flow rate of the flushing pipeline according to the flushing control command.

[0031] The beneficial effects of this invention are as follows:

[0032] The detection and flushing system provided by this invention enables real-time monitoring and intelligent processing of the internal conditions of sinus tracts in deeply infected wounds. This system not only adaptively identifies infected areas and potentially necrotic tissue within the sinus tract but also dynamically adjusts flushing parameters based on the identification results, ensuring the safety and effectiveness of the flushing process. Simultaneously, through precise control of a micro-motor and flow regulation module, adaptive adjustment of flushing pressure and flow rate is achieved, avoiding problems such as pressure fluctuations and uneven flow rates that may occur in traditional flushing processes. Furthermore, the system of this invention also features wireless communication capabilities, enabling real-time data transmission and interaction with external display devices, improving operational convenience and flexibility. Attached Figure Description

[0033] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0034] Figure 1 This is a schematic flowchart of a method for detecting and rinsing sinus tracts in deeply infected wounds according to the present invention.

[0035] Figure 2 This is a structural block diagram of the detection and flushing device in this invention.

[0036] In the diagram: 1. Probe; 2. Flushing channel; 3. Miniature endoscope; 4. Flushing button; 5. Switch button; 6. Miniature motor; 7. Flushing fluid buffer chamber; 8. Flow regulation module; 9. Power module; 10. Microcontroller; 11. Liquid storage chamber; 12. Capacitive sensor. Detailed Implementation

[0037] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0038] Please see Figure 1-2 A method for detecting and irrigating sinus tracts in deeply infected wounds, characterized by comprising:

[0039] S1: Obtain image signals inside the sinus tract through a miniature endoscope connected to a probe in the detection flushing device, and transmit the image signals to an external display device in real time through a wireless transceiver module integrated in the microcontroller;

[0040] S2: The external display device receives the internal image signal of the sinus tract through the wireless communication module of the terminal application and converts it into image information that can be recognized by a computer. The terminal application adaptively identifies the infected area and potential necrotic tissue in the sinus tract based on the image information and sets the flushing parameters.

[0041] S3: The terminal application feeds back the rinsing parameters to the wireless transceiver module of the detection rinsing device through the wireless communication module, and the microcontroller generates rinsing control commands according to the rinsing parameters;

[0042] S4: The flushing pressure and flushing flow rate of the flushing pipeline are adaptively controlled by a micro motor and flow regulation module according to the flushing control command.

[0043] Specifically, the detection and flushing device in S1 includes a probe, a micro-endoscope, a microcontroller, a flushing button, a switch button, a power module, a micro motor, a flow regulation module, a flushing channel, a liquid storage chamber, and a flushing fluid buffer chamber. One end of the probe is connected to the micro-endoscope, and the other end is used to insert into the sinus tract for deep detection. The micro-endoscope integrates an LED lighting module to provide illumination inside the sinus tract. The microcontroller integrates a wireless transceiver module to transmit the image signal inside the sinus tract to an external display device in real time and to receive flushing parameters transmitted from the external display device. The microcontroller is electrically connected to the micro motor and the flow regulation module. The flushing button is connected to the micro motor for start / stop control. The switch button is electrically connected to the power module to turn the entire detection and flushing device on or off. The flushing channel passes sequentially through the probe, the flushing fluid buffer chamber, and the liquid storage chamber. The micro motor regulates the pressure of the flushing fluid buffer chamber to control the flushing flow rate, and the flow regulation module regulates the flushing fluid flowing from the liquid storage chamber into the flushing fluid buffer chamber through the flushing channel.

[0044] Specifically, the microcontroller generates a PWM duty cycle control signal and a flow control analog signal based on the received flushing parameters, and transmits them to the micro motor and the flow regulation module via the drive circuit. The micro motor adjusts the duty cycle to change the output pressure through the PWM duty cycle signal, and the flow regulation module controls the flushing flow rate through the flow control analog signal.

[0045] Specifically, the flushing button triggers the micro motor to start, pushing the stored flushing fluid into the flushing channel; when the capacitive sensor detects that the flushing fluid buffer chamber is empty, it sends a feedback signal to the microcontroller.

[0046] Specifically, the flow regulation module generates a proportional voltage to drive the stroke length of the liquid pump based on the flow control analog signal via a D / A converter;

[0047] After the flushing button is triggered, the microcontroller sends a flow control analog signal and a liquid pump start signal to the flow regulation module through the received feedback signal.

[0048] Specifically, the adaptive recognition method in S2 is as follows:

[0049] S201: Determine the segmentation threshold for each pixel by dynamically calculating the gray-level statistics of the local region of the image information; dynamically segment the gray-level difference between enhanced lesions and normal tissues according to the segmentation threshold; extract and analyze the target localization region based on the segmentation results;

[0050] S202: Extract morphological features from the target location region, construct a combined classifier based on the kernel function output of different feature subsets in the morphological features, and optimize the classifier parameters according to the minimum classification error;

[0051] S203: Train the optimized classifier. After training, the classifier outputs the confidence level of the infected area and potential necrotic tissue based on the target location area. The target location area with a confidence level greater than a preset threshold is marked on the image display interface of the terminal application to realize the automatic identification of the infected area and potential necrotic tissue. The identification result is fed back to the terminal application to set the corresponding flushing parameters.

[0052] Specifically, the dynamic segmentation enhancement method described in S201 is as follows:

[0053] Calculate the local mean and variance for each pixel's neighborhood; use the local mean to filter brightness and select regions with values ​​less than the global mean as candidate dark areas; use the variance to filter contrast and perform image enhancement processing on low-contrast regions.

[0054] In this embodiment, for the neighborhood Sxy of each pixel (x,y), the local mean and variance are calculated:

[0055]

[0056] Where N is the number of neighborhood pixels, rs,t is the pixel grayscale value, and mxy is the local mean. The variance is the local mean, which reflects brightness, while the local mean measures contrast.

[0057] Brightness and contrast are filtered by threshold determination; dynamic segmentation is achieved using Halcon's dyn_threshold function, which compares the original image with the smoothed threshold image (Gaussian filter result) and controls the segmentation sensitivity by combining the offset.

[0058] Specifically, the morphological features in S202 include high eccentricity features, low compactness features, low intrinsicity features, and structural heterogeneity features; the kernel function adaptation strategy for different feature subsets in the morphological features is as follows:

[0059] Based on the high eccentricity and low compactness features, a subset of shape complexity is constructed, and a radial basis function kernel is used to capture nonlinear boundaries; based on the low intrinsicity features, a subset of topological structure is constructed, and a polynomial kernel is used to enhance convexity differences; based on the structural heterogeneity features, a subset of organizational heterogeneity is constructed, and a linear kernel is used to improve classification efficiency; by combining different kernel functions with weight coefficients, the classifier parameters are optimized.

[0060] In this embodiment, infected areas (such as inflammation or tumors) often exhibit irregular growth patterns with significant differences between their long and short axes, leading to increased eccentricity. For example, the invasive growth at the edge of a malignant tumor disrupts symmetry; eccentricity describes the degree of deviation of the target shape from the ideal ellipse, with higher eccentricity indicating a more complex shape.

[0061] Where 'a' represents the length of the major axis of the identified shape within the target region, and 'b' represents the length of the minor axis of the identified shape within the target region; the value range is 0 (circular) to 1 (linear). Infected areas (such as malignant tumors) exhibit significant differences between their major and minor axes due to invasive growth, resulting in increased eccentricity and a shape that deviates from symmetry.

[0062] Low compactness reflects the tortuosity of the target region's boundary; the lower the compactness, the more complex the boundary.

[0063] Where P represents the total number of pixels in the boundary region of the identified shape in the target region, and A represents the total number of pixels inside the identified shape in the target region. A larger value indicates a more complex shape (more tortuous boundaries). Necrotic tissue, due to liquefaction or fibrosis, experiences a slower area growth due to increased perimeter and reduced compactness, resulting in a low value.

[0064] Low intrinsicity features are used to measure the difference between a target region and its convex hull, reflecting the topological complexity of the region.

[0065] Where A represents the total number of internal pixels of the identified shape in the target region, and Aconvex represents the total number of internal pixels of the most convex polygon that completely encloses the identified shape. The closer the value is to 1, the more convex the shape; the lower the value, the more depressions or holes there are. Necrotic areas have a convex hull area that is much larger than the actual area due to internal collapse or voids, resulting in reduced inherentness.

[0066] Structural heterogeneity features focus on the uniformity of pixel grayscale values ​​or colors within the target region, used to describe the heterogeneity of the organization, and are calculated based on the entropy of the gray-level co-occurrence matrix (GLCM):

[0067] Where p(i,j) represents the joint probability of gray values ​​i and j in the gray-level co-occurrence matrix under a specific direction and distance; N represents the number of gray levels.

[0068] These morphological features together provide important evidence for the identification of infected areas and potentially necrotic tissue.

[0069] Specifically, the objective function for optimizing the minimum classification error in S203 is set as follows:

[0070]

[0071] Where λ is the Lagrange multiplier of the support vector machine, n is the total number of training samples, and y i Let x represent the true label of the i-th sample. i for, Let represent the predicted value for the i-th sample, where α is the regularization coefficient and K is the kernel function.

[0072] A detection and irrigation system for sinus tracts in deeply infected wounds includes: a detection and communication module, a terminal application identification unit, a feedback control module, and an irrigation execution unit;

[0073] The detection and communication module is used to acquire image signals inside the sinus tract through a miniature endoscope connected to a probe in the detection and flushing device, and to transmit the image signals to an external display device in real time through a wireless transceiver module integrated in the microcontroller.

[0074] The terminal application identification unit is used by the external display device to receive the internal image signal of the sinus tract through the wireless communication module of the terminal application and convert it into image information that can be recognized by a computer. The terminal application adaptively identifies the infected area and potential necrotic tissue in the sinus tract based on the image information and sets the flushing parameters.

[0075] The feedback control module feeds back the flushing parameters to the wireless transceiver module of the detection flushing device through the wireless communication module according to the terminal application, and the microcontroller generates flushing control commands according to the flushing parameters.

[0076] The flushing execution unit uses a micro motor and a flow regulation module to adaptively control the flushing pressure and flow rate of the flushing pipeline according to the flushing control command.

[0077] In this embodiment, the microcontroller, as the core control unit of the device, establishes a physical layer connection with the wireless transceiver module through the UART / SPI high-speed communication protocol, and receives flushing parameters (pressure value, flow rate value, and pulse mode) sent by the external terminal in real time; it adopts an analytical algorithm based on a finite state machine (FSM) to convert digital signals into two types of drive commands:

[0078] Piezoelectric pressure control command: Maps the target pressure value (0-50kPa) into a 0-5V analog voltage signal, which is then output via a 16-bit DAC module;

[0079] Flow control analog signal: The target flow rate value is mapped to a 0-10V analog voltage signal, which is then output via a 12-bit DAC module. The flow regulation module adjusts the flow rate of the flushing fluid via a proportional solenoid valve based on the received flow control analog signal.

[0080] Once the flush button is triggered, the preset anti-impact start sequence (pressure ramp-up, flow gradual opening) is immediately activated; the switch button adopts a long press protection mechanism (effective for 3 seconds) to avoid accidental touch that could cause abnormal power outage of the system.

[0081] The microcontroller is also used to distribute power to the power module, ensuring a stable power supply to all components.

[0082] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A detection and irrigation system for sinus tracts in deeply infected wounds, used to perform a detection and irrigation method for sinus tracts in deeply infected wounds, characterized in that, Includes: a detection and communication module, a terminal application identification unit, a feedback control module, and a flushing execution unit; The detection and communication module is used to acquire image signals inside the sinus tract through a miniature endoscope connected to a probe in the detection and flushing device, and to transmit the image signals to an external display device in real time through a wireless transceiver module integrated in the microcontroller. The terminal application identification unit is used by the external display device to receive the internal image signal of the sinus tract through the wireless communication module of the terminal application and convert it into image information that can be recognized by a computer. The terminal application adaptively identifies the infected area and potential necrotic tissue in the sinus tract based on the image information and sets the flushing parameters. The adaptive recognition method is as follows: The segmentation threshold for each pixel is determined by dynamically calculating the grayscale statistics of the local region of the image information. The grayscale difference between enhanced lesions and normal tissues is dynamically segmented according to the segmentation threshold. The target localization region is extracted and analyzed based on the segmentation results. Morphological features are extracted from the target location region of the analysis, and a combined classifier is constructed based on the kernel function output of different feature subsets in the morphological features. The classifier parameters are optimized according to the minimum classification error. The optimized classifier is trained, and the trained classifier outputs the confidence scores of the infected area and potential necrotic tissue based on the target location area. The target location areas with confidence scores greater than a preset threshold are marked on the image display interface of the terminal application to achieve automatic identification of infected areas and potential necrotic tissue. The identification results are fed back to the terminal application to set the corresponding flushing parameters. The dynamic segmentation enhancement method is as follows: Calculate the local mean and variance based on the neighborhood of each pixel; use the local mean to filter brightness and select regions with a value less than the global mean as candidate dark areas; use the variance to filter contrast and perform image enhancement processing on low-contrast regions. The morphological features include high eccentricity features, low compactness features, low intrinsicity features, and structural heterogeneity features; the kernel function adaptation strategy for different feature subsets in the morphological features is as follows: Based on the high eccentricity and low compactness features, a subset of shape complexity is constructed, and a radial basis function kernel is used to capture nonlinear boundaries; based on the low intrinsicity features, a subset of topological structure is constructed, and a polynomial kernel is used to enhance convexity differences; based on the structural heterogeneity features, a subset of organizational heterogeneity is constructed, and a linear kernel is used to improve classification efficiency; by combining different kernel functions with weight coefficients, the classifier parameters are optimized. The feedback control module feeds back the flushing parameters to the wireless transceiver module of the detection flushing device through the wireless communication module according to the terminal application, and the microcontroller generates flushing control commands according to the flushing parameters. The flushing execution unit uses a micro motor and a flow regulation module to adaptively control the flushing pressure and flow rate of the flushing pipeline according to the flushing control command.

2. The system according to claim 1, characterized in that, The detection and flushing device includes a probe, a micro-endoscope, a microcontroller, a flushing button, a switch button, a power module, a micro-motor, a flow regulation module, a flushing channel, a liquid storage chamber, and a flushing fluid buffer chamber. One end of the probe is connected to the micro-endoscope, and the other end is used to insert into the sinus tract for deep detection. The micro-endoscope integrates an LED illumination module. The microcontroller integrates a wireless transceiver module for transmitting real-time image signals from inside the sinus tract to an external display device and receiving flushing parameters transmitted from the external display device. The microcontroller is electrically connected to the micro-motor and the flow regulation module. The flushing button is connected to the micro-motor. The switch button is electrically connected to the power module. The flushing channel sequentially passes through the probe, the flushing fluid buffer chamber, and the liquid storage chamber. The micro-motor regulates the pressure in the flushing fluid buffer chamber, and the flow regulation module regulates the flow of flushing fluid from the liquid storage chamber into the flushing fluid buffer chamber through the flushing channel.

3. The system according to claim 2, characterized in that, The microcontroller generates a PWM duty cycle control signal and a flow control analog signal based on the received flushing parameters, and transmits them to the micro motor and the flow regulation module via the drive circuit. The micro motor adjusts the duty cycle to change the output pressure through the PWM duty cycle signal, and the flow regulation module controls the flushing flow rate through the flow control analog signal.

4. The system according to claim 2, characterized in that, The flushing button triggers the micro motor to start, pushing the stored flushing fluid into the flushing channel; when the capacitive sensor detects that the flushing fluid buffer chamber is empty, it sends a feedback signal to the microcontroller.

5. The system according to claim 2, characterized in that, The flow regulation module generates a proportional voltage to drive the stroke length of the liquid pump based on the flow control analog signal via a D / A converter. After the flushing button is triggered, the microcontroller sends a flow control analog signal and a liquid pump start signal to the flow regulation module through the received feedback signal.

Images