Blood concentration-based automatic flushing method, endoscope main unit, and endoscope system

Abstract

The application relates to the technical field of medical devices, and discloses an automatic flushing method based on blood concentration, an endoscope host and an endoscope system. The method comprises the following steps: collecting a target image of a surgical area by using a camera, and determining a green channel intensity value of the target image; determining a current blood concentration of the target image by using a preset concentration model based on the green channel intensity value, the preset concentration model being a linear relationship model between different blood concentrations and corresponding green channel intensity values; determining a corresponding target rotating speed according to the current blood concentration, and controlling a flushing pump to flush the surgical area according to the target rotating speed. Compared with the existing manual control mode, the application does not need manual control, thereby improving the timeliness of flushing and safety.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and in particular to an automatic flushing method based on blood concentration, an endoscope host, and an endoscope system. Background Technology

[0002] Currently, during endoscopic surgery, the surgical area typically needs to be instilled with saline solution to create an operating space. This means the endoscope sheath can have a saline delivery channel with an irrigation pump to inject saline solution into the surgical area. However, surgical procedures inevitably involve touching blood vessels, leading to bleeding. When blood mixes with saline solution, it reduces the water's transparency, making the images captured by the endoscope's camera blurry. This severely impacts the surgeon's ability to identify the anatomical structures of the surgical area and the precision of the surgical procedure.

[0003] Currently, to promptly remove blood and fluid, a manual method is generally used. This involves the doctor or assistant adjusting the speed of the irrigation pump via a foot pedal or hand control while observing the surgical procedure. However, this method is prone to problems such as delayed irrigation, prolonged surgical time, and lower safety standards. Summary of the Invention

[0004] The main purpose of this application is to provide an automatic flushing method based on blood concentration, an endoscope host, and an endoscope system, aiming to solve the technical problems of existing manual flushing methods, which are prone to untimely flushing and low safety.

[0005] To achieve the above objectives, this application provides an automatic flushing method based on blood concentration, wherein the method is applied to the endoscope host in an endoscope system; The endoscope system also includes: an endoscope with a camera and a transport channel, wherein a flushing pump is provided on the transport channel, and the flushing pump is used to control the flushing speed of physiological saline in the transport channel on the surgical area; The method includes: The camera is used to capture a target image of the surgical area, and the green channel intensity value of the target image is determined. The current blood concentration of the target image is determined based on the green channel intensity value using a preset concentration model, wherein the preset concentration model is a linear relationship model between different blood concentrations and their corresponding green channel intensity values. The target rotation speed is determined based on the current blood concentration, and the irrigation pump is controlled to irrigate the surgical area according to the target rotation speed.

[0006] In one embodiment, the step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: Determine the first and second coefficients in the preset concentration model, and determine the intensity difference between the preset reference intensity value and the green channel intensity value; The current blood concentration of the target image is determined based on the intensity difference value, the first coefficient, and the second coefficient.

[0007] In one embodiment, prior to the step of acquiring a target image of the surgical area using the camera, the method further includes: Obtain different calibrated blood concentrations and their corresponding calibrated green channel intensity values; The initial concentration model is fitted by each of the calibrated blood concentrations and the corresponding calibrated green channel intensity values ​​to obtain the first coefficient and the second coefficient. A preset concentration model is constructed based on the first coefficient, the second coefficient, and the initial concentration model.

[0008] In one embodiment, the step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: The pixel blood concentration of each pixel is determined by a preset concentration model based on the green channel intensity value of each pixel in the target image. The blood pressure concentrations of each pixel are summed to obtain a first summation result; Obtain the image size of the target image, and calculate the mean of the first summation result based on the image size to obtain the first mean calculation result; The first mean value is used as the current blood concentration of the target image.

[0009] In one embodiment, the step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: The pixel blood concentration of each pixel is determined by a preset concentration model based on the green channel intensity value of each pixel in the target image. The blood concentration of each pixel is squared, and the blood concentrations of the pixels after squared operations are summed to obtain a second summation result; Obtain the image size of the target image, and calculate the mean of the second summation result based on the image size to obtain the second mean calculation result; The result of the second mean calculation is used as the current blood concentration of the target image.

[0010] In one embodiment, the step of determining the corresponding target rotation speed based on the current blood concentration includes: Determine the concentration difference between the target blood concentration and the current blood concentration; The target rotation speed is determined based on the preset proportional gain and the concentration difference value.

[0011] In one embodiment, before the step of determining the corresponding target rotation speed based on the current blood concentration, the method further includes: Determine whether the current blood concentration is higher than a first preset concentration threshold; If the current blood concentration is higher than the first preset concentration threshold, the adaptive control function is activated, and the step of determining the corresponding target rotation speed based on the current blood concentration is executed.

[0012] In one embodiment, after the step of determining whether the current blood concentration is higher than a first preset concentration threshold, the method further includes: If the current blood concentration is not higher than the first preset concentration threshold, determine whether the current blood pressure concentration is lower than the second preset concentration threshold, wherein the first preset concentration threshold is higher than the second preset concentration threshold; If the current blood concentration is lower than the second preset concentration threshold, the adaptive control function is turned off, and the reference rotation speed is used as the target rotation speed. If the current blood concentration is not lower than the second preset concentration threshold, the adaptive control function remains on / off.

[0013] In addition, to achieve the above objectives, this application also proposes an endoscope host, which includes: a memory, a processor, and an automatic flushing program based on blood concentration stored in the memory and executable on the processor. When the automatic flushing program based on blood concentration is executed by the processor, it implements the steps of the automatic flushing method based on blood concentration as described above.

[0014] In addition, to achieve the above objectives, this application also proposes an endoscope system, which includes: an endoscope with a camera and a transport channel, and an endoscope host as described above; The transport channel is equipped with a flushing pump, which is used to control the flushing speed of physiological saline on the surgical area within the transport channel.

[0015] This application provides an automatic flushing method based on blood concentration, an endoscope host, and an endoscope system. The method is applied to the endoscope host in the endoscope system. The endoscope system further includes an endoscope with a camera and a transport channel. The transport channel is equipped with a flushing pump, which controls the flushing speed of physiological saline in the transport channel on the surgical area. The method includes: acquiring a target image of the surgical area using the camera and determining the green channel intensity value of the target image; determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model, wherein the preset concentration model is a linear relationship model between different blood concentrations and corresponding green channel intensity values; determining a corresponding target rotation speed according to the current blood concentration, and controlling the flushing pump to flush the surgical area according to the target rotation speed.

[0016] Since green light falls within the light waves primarily absorbed by blood, this application can pre-construct a linear relationship model between different blood concentration models and corresponding green channel intensity values. In practical use, a target image of the surgical area can be captured using a camera, followed by the extraction of the green channel intensity value from the target image. Based on this green channel intensity value, the current blood concentration in the target image is determined using the pre-constructed concentration model. Finally, the target rotation speed of the flushing pump is determined based on this current blood concentration, and the flushing pump is controlled to flush the surgical area at this target rotation speed. Because this application can pre-construct a linear relationship model between different blood concentrations and corresponding green channel intensity values, it can identify the green channel intensity value in the target image, determine the current blood concentration based on the model, and automatically control the flushing pump to perform flushing based on the current blood concentration. Compared to existing methods that require manual control, this application eliminates the need for manual intervention, thereby improving the timeliness of flushing and ultimately enhancing safety. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the endoscope host 1 structure of the hardware operating environment involved in the embodiments of this application; Figure 2 This is a schematic flowchart of the first embodiment of the automatic flushing method based on blood concentration according to this application; Figure 3 This is a schematic diagram of the endoscope system in the first embodiment of the automatic flushing method based on blood concentration in this application; Figure 4 This is a flowchart illustrating the control principle in the first embodiment of the automatic flushing method based on blood concentration according to this application; Figure 5 This is a schematic flowchart of the second embodiment of the automatic flushing method based on blood concentration according to this application; Figure 6 This is a schematic flowchart of the third embodiment of the automatic flushing method based on blood concentration in this application; Figure 7 This is a schematic diagram of the PID control process in the third embodiment of the automatic flushing method based on blood concentration in this application; Figure 8 This is a schematic diagram of the threshold determination process in the third embodiment of the automatic flushing method based on blood concentration in this application.

[0020] Explanation of icon numbers:

[0021] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] Reference Figure 1 , Figure 1 This is a schematic diagram of the endoscope host 1, which is part of the hardware operating environment involved in the embodiments of this application.

[0024] like Figure 1As shown, the endoscope host 1 may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include an interface for connecting to a display screen; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. In this application, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0025] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the endoscope host 1, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0026] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an automatic flushing program based on blood concentration.

[0027] exist Figure 1 In the endoscope host 1 shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the user equipment; the endoscope host 1 calls the automatic flushing program based on blood concentration stored in the memory 1005 through the processor 1001 and executes the automatic flushing method based on blood concentration provided in the embodiments of this application.

[0028] It should be noted that currently, during endoscopic surgery, the surgical area typically needs to be infused with saline solution to create an operating space. Specifically, the endoscope sheath of the endoscope 2 can be equipped with a saline transport channel 3, and an irrigation pump 4 is installed on this channel 3 to inject saline solution into the surgical area. However, surgical procedures inevitably involve touching blood vessels, leading to bleeding. The mixture of blood and saline solution reduces the water's transparency, causing the image captured by the endoscope's camera 5 to be blurry. This severely affects the surgeon's ability to identify the anatomical structures of the surgical area and the precision of the surgical procedure.

[0029] Currently, to promptly remove blood and fluid, a manual method is generally used. This involves the doctor or assistant adjusting the speed of the irrigation pump 4 via a foot switch or hand control button while observing the surgical procedure. However, this method is prone to problems such as delayed irrigation, prolonged surgical time, and lower safety standards.

[0030] Therefore, to address the aforementioned shortcomings, this embodiment provides an automatic flushing method based on blood concentration. Since green light falls within the light waves primarily absorbed by blood, this embodiment can pre-construct a linear relationship model between different blood concentration models and corresponding green channel intensity values. In practical use, the camera 5 first acquires a target image of the surgical area, then extracts the green channel intensity value from the target image, determines the current blood concentration of the target image based on this green channel intensity value using the pre-constructed concentration model, and finally determines the target rotation speed of the flushing pump 4 based on the current blood concentration, controlling the flushing pump 4 to flush the surgical area according to this target rotation speed. Because this embodiment can pre-construct a linear relationship model between different blood concentrations and corresponding green channel intensity values, it can identify the green channel intensity value in the target image, determine the current blood concentration based on the model, and automatically control the flushing pump 4 to perform flushing based on the current blood concentration. Compared to existing methods requiring manual control, this embodiment eliminates the need for manual intervention, thereby improving the timeliness of flushing and thus enhancing safety.

[0031] For ease of understanding, the following is combined with Figures 2 to 8 The automatic flushing method based on blood concentration provided in the embodiments of this application will be described in detail.

[0032] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the automatic flushing method based on blood concentration according to this application. The first embodiment of the automatic flushing method based on blood concentration according to this application is presented as follows: Figure 2 As shown, in this embodiment, the specific method includes: Step S10: Use the camera 5 to acquire a target image of the surgical area and determine the green channel intensity value of the target image.

[0033] It is understood that the method of this embodiment can be applied to any device with data processing, program execution and positioning functions, such as the endoscope host 1 in the endoscope 2 system, and this embodiment does not limit it. However, for ease of understanding, this embodiment uses the endoscope host 1 (hereinafter referred to as the device) as the execution subject to describe this embodiment and the following embodiments.

[0034] It is also understood that the endoscope 2 system described in this embodiment further includes: an endoscope 2 with a camera 5 and a transport channel 3, wherein a flushing pump 4 is provided on the transport channel 3, and the flushing pump 4 is used to control the flushing speed of the saline solution in the transport channel 3 on the surgical area.

[0035] For ease of understanding, please refer to Figure 3 , Figure 3 This is a schematic diagram of the endoscope 2 system in the first embodiment of the automatic flushing method based on blood concentration of this application. Figure 3 As shown, the aforementioned endoscope 2 system can be a complete medical device system for performing minimally invasive endoscopic 2 surgery. For example, it typically includes an endoscope host 1, an endoscope 2, a light source, etc.

[0036] Figure 3 The aforementioned endoscope 2 can be inserted into natural human cavities or tiny incisions (i.e., Figure 3 The surgical cavity is formed by the skin tissue 6), and the endoscope 2 can be equipped with a camera 5 and a lighting device at its front end. The endoscope 2 is connected to the endoscope host 1 and is used to transmit the in vivo images captured by the camera 5 to the endoscope host 1 (i.e., Figure 3 The images are acquired and processed before being displayed on an external screen.

[0037] It should be emphasized that the camera 5 in this embodiment can be the camera 5 built into the endoscope 2 itself, or an additional camera 5 can be set at the front end of the endoscope 2. In order to save costs, this embodiment can directly use the camera 5 of the endoscope 2 itself for description. The specific position of the camera 5 can be set according to the actual situation, and this embodiment does not limit it.

[0038] It should also be emphasized that the aforementioned transport channel 3 can be used to transport goods to the surgical area (i.e., Figure 3 The surgical cavity within the skin tissue (6) is a channel for perfusing physiological saline, such as... Figure 3 As shown, an additional micro-channel can be installed, with one end extending into the surgical cavity, to deliver saline solution from the outside to the surgical area for irrigation.

[0039] In order to control the rinsing speed with saline solution, such as Figure 3 As shown, a flushing pump 4 can generally be installed on the transport channel 3, and this flushing pump 4 can be electrically connected to the endoscope host 1, thereby receiving control signals from the endoscope host 1 (i.e., Figure 3 (Controlled by a water pump), precisely driving physiological saline at a specific flow rate through transport channel 3 to inject into the surgical area.

[0040] It should be understood that the aforementioned surgical area can be a localized area within the body where the surgical procedure is being performed, as seen under the view of endoscope 2. For example... Figure 3As shown, the surgical cavity can be filled with infused saline solution to form a surgical cavity. The aforementioned target image can be an image representing the real-time state of the surgical area captured by camera 5.

[0041] In actual use, the camera 5 located at the front end of the endoscope 2 can capture target images of the surgical area and transmit them to the endoscope host 1.

[0042] It should also be noted that in digital color images, the color of each pixel is typically composed of the intensity values ​​of three channels: red (R), green (G), and blue (B). The intensity value of each channel is a numerical value (e.g., 0-255 in an 8-bit image), representing the strength of that color component. Therefore, in this embodiment, the green channel intensity value mentioned above can be the intensity value of the green (G) channel in the target image.

[0043] Reference Figure 4 , Figure 4 This is a flowchart illustrating the control principle in the first embodiment of the automatic flushing method based on blood concentration according to this application. Figure 4 As shown, in actual use, after the target image is acquired by the camera 5, it can be transmitted to the endoscope host 1 (i.e., Figure 4 The system captures images of surgical scenes in a blood-water mixture using an endoscope (and transmits the target image to the host computer to complete image acquisition). After obtaining the target image, the green channel intensity value of the target image can be directly extracted from it.

[0044] Step S20: Determine the current blood concentration of the target image based on the green channel intensity value using a preset concentration model, wherein the preset concentration model is a linear relationship model between different blood concentrations and their corresponding green channel intensity values.

[0045] It should also be noted that since blood only absorbs visible light of a specific wavelength, the blood concentration can be inferred by judging the intensity of that specific wavelength of light in the image. Human blood absorbs light primarily in the 400nm~600nm range in the visible light spectrum, while green light absorbs light at 530nm. Therefore, in this embodiment, the blood concentration can be inferred by judging the intensity of green light. The lower the green intensity, the higher the blood concentration; thus, this embodiment can determine the current blood concentration using the green channel intensity value.

[0046] It is understood that the aforementioned preset concentration model can be a pre-defined linear relationship model between different blood concentrations and corresponding green channel intensity values. Since the relationship between different blood concentrations and corresponding green channel intensity values ​​can be represented by a linear function mathematical model, this embodiment can pre-construct the aforementioned preset concentration model to determine the corresponding current blood concentration.

[0047] It is also understood that the current blood concentration mentioned above could be the blood concentration in the current operating room.

[0048] Therefore, in this embodiment, the aforementioned preset concentration model can be pre-constructed, and then the obtained green channel intensity value can be input into the aforementioned preset concentration model to obtain the corresponding current blood concentration (i.e., Figure 4 (Middle blood concentration detection algorithm).

[0049] Step S30: Determine the corresponding target rotation speed based on the current blood concentration, and control the irrigation pump 4 to irrigate the surgical area according to the target rotation speed.

[0050] It is understood that the aforementioned target rotational speed can be the rotational speed executed by the flushing pump 4. It can be obtained based on the current blood concentration according to a preset mapping table, or calculated in real time. This embodiment does not limit the specific mapping table or real-time calculation method (i.e.,...). Figure 4 (Medium-water pump speed control algorithm).

[0051] In actual use, blood vessels are inevitably encountered during surgery, causing bleeding that flows into the surgical cavity and affects visualization. The endoscope host 1, after obtaining the current blood concentration, can determine the corresponding target rotation speed based on this concentration. Generally, the higher the blood concentration, the stronger the irrigation required, and thus the higher the corresponding target rotation speed. The endoscope host 1 then contains the control command for the target rotation speed (i.e.,... Figure 4 The control command (from the water pump control) is sent to the flushing pump 4. Upon receiving the control command, the flushing pump 4 immediately adjusts its speed to the target speed (i.e., the water pump control). Figure 3 Medium-sized water injection pump, that is Figure 4 A medium-pressure water pump can be used to change the injection rate of saline solution, thereby achieving irrigation of the surgical area (i.e.,...). Figure 4 (Dilution of blood concentration). Therefore, since this embodiment can identify the green channel intensity value in the target image and determine the current blood concentration through a preset concentration model, and automatically control the flushing pump 4 to perform flushing according to the current blood concentration, compared with the existing method that requires manual control, this embodiment does not require manual operation, thereby improving the timeliness of flushing and thus improving safety.

[0052] Furthermore, considering that the relationship between blood concentration and green channel intensity value is a linear function, and since the preset concentration model can specifically characterize the relationship between different levels of green light absorption and blood concentration, in this embodiment, the step of determining the current blood concentration of the target image based on the green channel intensity value using the preset concentration model includes: Step S21: Determine the first coefficient and the second coefficient in the preset concentration model, and determine the intensity difference value between the preset reference intensity value and the green channel intensity value.

[0053] It should be noted that the first coefficient and the second coefficient mentioned above can both be parameters in the preset concentration model. For a preset concentration model with a linear function relationship, if the first coefficient represents the slope of the relationship and is denoted as k, and the second coefficient represents the intercept of the relationship and is denoted as a, then the preset concentration model can be M=k*c+a, where c is the current blood concentration and M is the intensity difference value mentioned above.

[0054] It should also be noted that hemoglobin in blood strongly absorbs green light. Therefore, the more concentrated the blood, the more green light is absorbed, and consequently, the weaker the remaining green light (G value) in the target image. Therefore, in order to establish a positive correlation between "increased value representing increased concentration", this embodiment can use the intensity difference between the aforementioned preset reference intensity value and the green channel intensity value to characterize the "degree of green light absorption".

[0055] The aforementioned preset reference intensity value can be the theoretical maximum brightness value that the green channel of the target image can achieve under ideal conditions of complete bloodlessness and the clearest field of vision. In this embodiment, for an 8-bit depth target image, this value can be 255. Furthermore, if the green channel intensity value is denoted as G, then the aforementioned preset density model can be 255-G=k*c+a.

[0056] Therefore, in actual use, the aforementioned preset concentration model can be pre-constructed, and the first coefficient k and the second coefficient a are known coefficients. In actual detection, the first coefficient and the second coefficient can be directly obtained, and then the preset reference intensity value 255 can be obtained. The difference between the preset reference intensity value and the green channel intensity value is calculated to obtain the intensity difference value 255-G.

[0057] Step S22: Determine the current blood concentration of the target image based on the intensity difference value, the first coefficient, and the second coefficient.

[0058] After obtaining the above intensity difference value, the first coefficient, the second coefficient, and the intensity difference value can be substituted into the above preset concentration model to obtain the current blood concentration c.

[0059] It should be emphasized that, in this embodiment, the green channel intensity value mentioned above can specifically refer to the green channel intensity value of a pixel in the target image. Then, the green channel intensity value of each pixel in the target image can be substituted into the preset concentration model to obtain the current blood concentration corresponding to each pixel. Then, the average value can be calculated to obtain the current blood concentration of the entire target image.

[0060] As another implementation, in this embodiment, the green channel intensity value mentioned above can also specifically refer to the green channel intensity value of the entire target image. That is, the green channel intensity value of each pixel in the target image can be obtained first, and then the average value can be calculated to obtain the green channel intensity value of the target image. Then, the green channel intensity value of the target image is substituted into the preset concentration model to directly obtain the current blood concentration of the target image.

[0061] Furthermore, in order to obtain the aforementioned preset concentration model, in this embodiment, before the step of acquiring the target image of the surgical area using the camera 5, the method further includes: Step S01: Obtain different calibrated blood concentrations and their corresponding calibrated green channel intensity values.

[0062] It is understood that the aforementioned calibrated blood concentration can be a known blood concentration. In practical use, a known concentration of blood-physiological saline solution can be prepared in advance under laboratory conditions, which can then be used as the aforementioned calibrated blood concentration. These calibrated blood concentrations (e.g., c1, c2, c3...cn, etc.) can be used as standard reference values.

[0063] It is also understood that the aforementioned calibrated green channel intensity values ​​can be calculated from the images obtained by photographing samples with calibrated blood concentrations under standard lighting and shooting conditions (e.g., G1, G2, G3...Gn, etc.). Each G value corresponds to a known concentration c.

[0064] Step S02: Fit the initial concentration model by matching each of the calibrated blood concentrations with the corresponding calibrated green channel intensity values ​​to obtain the first coefficient and the second coefficient; Step S03: Construct a preset concentration model based on the first coefficient, the second coefficient, and the initial concentration model.

[0065] It should be understood that the aforementioned initial concentration model can be a theoretical model that only has a mathematical form and whose specific parameters are unknown before calibration. In this embodiment, it is in the form of the linear equation: -G = k*c + a, where k and a are unknown.

[0066] In practical use, the corresponding calibration intensity difference value Mi can be calculated for each calibrated green channel intensity value based on the preset reference intensity value. Mi = preset reference intensity value - Gi (i.e., 255 - Gi). Then, with concentration c as the X-axis and M as the Y-axis, all ci and the corresponding Mi are plotted on the coordinate system. Finally, a fitting algorithm (such as the least squares method) is used to calculate the first coefficient k and the second coefficient a to obtain the preset concentration model.

[0067] Since green light falls within the light waves primarily absorbed by blood, this embodiment can pre-build a linear relationship model between different blood concentration models and corresponding green channel intensity values. In actual use, camera 5 first captures a target image of the surgical area, then extracts the green channel intensity value from the target image, and uses the pre-built concentration model to determine the current blood concentration of the target image based on this green channel intensity value. Finally, based on the current blood concentration, the target rotation speed of the flushing pump 4 is determined, and the flushing pump 4 is controlled to flush the surgical area at this target rotation speed. Because this embodiment can pre-build a linear relationship model between different blood concentrations and corresponding green channel intensity values, it can identify the green channel intensity value in the target image, determine the current blood concentration based on the model, and automatically control the flushing pump 4 to flush according to the current blood concentration. Compared to existing methods that require manual control, this embodiment eliminates the need for manual intervention, thereby improving the timeliness of flushing and thus enhancing safety.

[0068] Reference Figure 5 , Figure 5 This is a flowchart illustrating the second embodiment of the automatic flushing method based on blood concentration according to this application. Based on the first embodiment described above, the second embodiment of the automatic flushing method based on blood concentration according to this application is proposed.

[0069] To obtain the above current blood concentration, such as Figure 5 As shown, in this embodiment, the step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: Step S231: Based on the green channel intensity value of each pixel in the target image, determine the pixel blood concentration of each pixel using a preset concentration model.

[0070] It should be noted that the aforementioned pixel blood concentration can be the blood concentration calculated for a single pixel in the target image based on the green channel intensity value of that pixel using a preset concentration model. This pixel blood concentration can be used to characterize the blood concentration in a local area of ​​that pixel. For ease of explanation later, the pixel blood concentration for a pixel with coordinates (x, y) can be denoted as c(x, y).

[0071] In practical use, the green channel intensity value of each pixel in the target image can be read first, and then the green channel intensity value of each pixel can be substituted into the above-mentioned preset concentration model to obtain the pixel blood concentration of each pixel.

[0072] Step S232: Summate the blood pressure concentration of each pixel to obtain a first summation result; Step S233: Obtain the image size of the target image, and calculate the mean of the first summation result based on the image size to obtain the first mean calculation result; Step S234: Use the first mean calculation result as the current blood concentration of the target image. Understandably, the first summation result mentioned above could be the sum of the blood concentrations of all pixels. The image size mentioned above could refer to the width and height of the target image, which can be denoted as W and H, respectively. Then, the number of pixels in the target image would be H*W.

[0073] In practical use, the blood concentration of each pixel can be summed to obtain the first summation result. Then, the image size of the target image is obtained to obtain the number of pixels in the target image. Then, an arithmetic mean is calculated based on the first summation result and the number of pixels, and the obtained first mean is used as the current blood concentration of the target image.

[0074] Furthermore, considering that directly calculating the mean would not easily distinguish different bleeding patterns, for example, referring to... Figure 5 , Figure 5 This is a schematic diagram of diffuse oozing and concentrated bleeding in the second embodiment of the automatic flushing method based on blood concentration in this application. Scenario A corresponds to diffuse oozing, and scenario B corresponds to concentrated bleeding. Because the bleeding conditions differ between the two scenarios, the overall blood concentration is not the same. For scenario A, there is prolonged bleeding from a small wound, resulting in a larger blood-containing area but a lower overall blood concentration. For scenario B, there is short-term bleeding from a large wound, resulting in a smaller blood-containing area but a higher overall blood concentration. For both scenarios, scenario A represents minor bleeding, so the flushing pump 4 should operate at a slower speed, and the identified blood concentration should be lower. Scenario B represents major bleeding, so the flushing pump 4 should operate at a faster speed, and the identified blood concentration should be higher. Therefore, to accurately determine the current blood concentration, in this embodiment, the step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: Step S241: Determine the pixel blood concentration of each pixel based on the green channel intensity value of each pixel in the target image using a preset concentration model.

[0075] It should be noted that the implementation process of this step is the same as step S231 above. In actual use, the green channel intensity value of each pixel in the target image can be read first, and then the green channel intensity value of each pixel can be substituted into the preset concentration model above to obtain the pixel blood concentration of each pixel.

[0076] Step S242: Squaring the blood concentration of each pixel and summing the blood concentrations of the pixels after squaring to obtain a second summation result; Step S243: Obtain the image size of the target image, and calculate the mean of the second summation result based on the image size to obtain the second mean calculation result; Step S244: Use the result of the second mean calculation as the current blood concentration of the target image. Understandably, the second summation result mentioned above can be obtained by summing the squared values ​​of the pixel blood concentrations for all pixels. If the pixel blood concentration of pixel (x, y) is c(x, y), then the second summation result mentioned above is... .

[0077] After obtaining the second summation result, the mean of the second summation result can be calculated based on the image size, and the obtained second mean calculation result can be used as the current blood concentration. If the current blood concentration is denoted as C, then... .

[0078] It is important to emphasize that the squaring operation described above is a non-linear amplification process. This means that the contribution of high-concentration pixels to the sum is exponentially amplified (e.g., a pixel with concentration 2 contributes 4, a pixel with concentration 3 contributes 9, and a pixel with concentration 4 contributes 16), while the contribution of low-concentration pixels is relatively weakened (concentration 1 contributes 1, concentration 0.5 contributes 0.25). Therefore, this weighting method makes the final index exceptionally sensitive to the presence of local high-concentration areas (i.e., active bleeding points or blood accumulation areas) in the image, thus more accurately reflecting different bleeding patterns. Therefore, for scene A, the high-concentration area is small, resulting in a lower current blood concentration; for scene B, the high-concentration area is large, resulting in a higher current blood concentration.

[0079] Reference Figure 6 , Figure 6 This is a flowchart illustrating the third embodiment of the automatic flushing method based on blood concentration according to this application. Based on the above embodiments, the third embodiment of the automatic flushing method based on blood concentration according to this application is proposed.

[0080] In order to adaptively adjust the speed of the flushing pump 4 according to the current blood concentration, in this embodiment, as follows: Figure 6 As shown, the step of determining the corresponding target rotation speed based on the current blood concentration includes: Step S31: Determine the concentration difference between the target blood concentration and the current blood concentration; Step S32: Determine the corresponding target rotation speed based on the preset proportional gain and the concentration difference value.

[0081] It should be noted that the target blood concentration mentioned above can be a preset ideal blood concentration that is expected to be maintained at that level in the surgical field through automatic control. The specific value can be set according to the actual situation, and this embodiment does not limit it.

[0082] It should also be noted that the above concentration difference value can be the difference between the current blood concentration and the target blood concentration. In this embodiment, it can be denoted as e(t). e(t) > 0 indicates that the blood is too concentrated and needs to be rinsed; e(t) < 0 indicates that the blood is too diluted and does not need to be rinsed or needs to be rinsed less.

[0083] Understandably, the aforementioned preset proportional gain can be a parameter used to control the response sensitivity to concentration differences. It can be denoted as... ,in The larger the value, the greater the speed adjustment required for the same concentration difference, and the more aggressive the reaction. The smaller the value, the milder the reaction.

[0084] In practical use, refer to Figure 7 , Figure 7 This is a schematic diagram of the PID control flow in the third embodiment of the automatic flushing method based on blood concentration in this application. Figure 7 As shown, the target blood concentration can be preset (i.e., Figure 7 (Set a target concentration), and then calculate the concentration difference value based on the current blood concentration and the target blood concentration (i.e., Figure 7 The current concentration is obtained and the difference e(t) is calculated.

[0085] After obtaining the concentration difference value, the water pump can be controlled according to a preset control algorithm (i.e., Figure 4 In this embodiment, a PID control algorithm can be used to control the speed of the water pump (i.e., the speed control algorithm of the water pump). Figure 7 In PID calculation, the concentration difference value e(t) is input into the PID control algorithm. The algorithm can comprehensively calculate the target speed (i.e., the current value of the concentration difference value e(t) (proportional P), the historical cumulative value (integral I), and the changing trend (derivative D). Figure 7 (Output of medium speed value). The specific calculation process is as follows: .

[0086] Among them, K p The preset proportional gain; T t T is the integration time constant; D Let e(t) be the differential time constant; u(t) be the output signal of the PID controller (i.e., the target speed). Therefore, if e(t) > 0, the algorithm can output a higher target speed. If e(t) < 0, the algorithm can output a lower or even zero target speed.

[0087] Once the target rotation speed is obtained, the endoscope host 1 sends the target rotation speed command to the flushing pump 4, and the flushing pump 4 immediately adjusts its own rotation speed to that value.

[0088] Furthermore, considering that prolonged high-speed irrigation with a water pump during surgery can increase organ pressure and cause some damage to the patient, this embodiment further includes the following step before determining the target rotation speed based on the current blood concentration: Step S301: Determine whether the current blood concentration is higher than a first preset concentration threshold; Step S302: When the current blood concentration is higher than the first preset concentration threshold, activate the adaptive control function and execute the step of determining the corresponding target rotation speed based on the current blood concentration.

[0089] It should be noted that the aforementioned first preset concentration threshold can be a pre-set concentration critical value. The aforementioned adaptive control function is the aforementioned PID control function.

[0090] For ease of understanding, please refer to Figure 8 , Figure 8 This is a schematic diagram of the threshold determination process in the third embodiment of the automatic flushing method based on blood concentration in this application. Figure 8 As shown, if the first preset concentration threshold is denoted as A, then in actual use, after obtaining the current blood concentration, it can be determined whether the current blood concentration is higher than the first preset concentration threshold (i.e., Figure 8 If the concentration is greater than A, it indicates that the concentration is high, thus triggering the step of determining the target rotation speed based on the current blood concentration (i.e., ...). Figure 8 (Activate PID control for water pump).

[0091] Furthermore, after the step of determining whether the current blood concentration is higher than the first preset concentration threshold, the method further includes: Step S303: If the current blood concentration is not higher than the first preset concentration threshold, determine whether the current blood pressure concentration is lower than the second preset concentration threshold, wherein the first preset concentration threshold is higher than the second preset concentration threshold.

[0092] It should also be noted that the above-mentioned second preset concentration threshold can be a pre-set concentration critical value, and in this embodiment, the first preset concentration threshold can be higher than the second preset concentration threshold. That is, if the second preset concentration threshold is denoted as B, then A > B.

[0093] In practical use, if the current blood concentration is not higher than the first preset concentration threshold, it indicates that the concentration is not high. Then, it can be determined whether the current blood concentration is lower than the second preset concentration threshold (i.e., ...). Figure 8 Medium concentration < B).

[0094] Step S304: When the current blood concentration is lower than the second preset concentration threshold, the adaptive control function is turned off, and the reference rotation speed is used as the target rotation speed; Step S305: If the current blood concentration is not lower than the second preset concentration threshold, maintain the on / off state of the adaptive control function.

[0095] It should be understood that the aforementioned reference speed can be a preset low speed or a zero speed.

[0096] In practical use, if the current blood concentration is lower than the second preset concentration threshold, it indicates that the concentration is low, and the 4PID function of the flushing pump can be turned off (i.e., Figure 8 The PID control of the water pump is turned off, thereby controlling the flushing pump 4 to rotate according to the reference speed (which can be a lower speed or 0) as the target speed.

[0097] If the current blood concentration is not lower than the second preset concentration threshold, it indicates that the concentration may still be high. Therefore, the adaptive control function is kept on. Since the blood concentration is gradually reduced from high to low, and the PID is on when it is high, the adaptive control function is kept on when the concentration is not lower than the second preset concentration threshold, and the PID is kept on to reduce the blood concentration.

[0098] When the blood concentration gradually increases, the current blood concentration can be lower than the second preset concentration threshold. The PID function is kept off. Then, when the concentration rises to a level not lower than the second preset concentration threshold, the PID function is kept off. When the concentration continues to rise to the first preset concentration threshold, it indicates that the concentration is high. The PID function can then be activated to reduce the concentration. This cycle continues, thereby reducing the damage to the patient.

[0099] In addition, to achieve the above objectives, this application embodiment also provides an endoscope 2 system, which may include: an endoscope 2 with a camera 5 and a transport channel 3, and an endoscope host 1 as described above; The transport channel 3 is equipped with a flushing pump 4, which is used to control the flushing speed of the saline solution in the transport channel 3 on the surgical area.

[0100] Since the endoscope host 1 in this embodiment can be implemented in accordance with the specific implementation of the above method embodiment, the specific implementation of the endoscope 2 system in this embodiment and the beneficial effects thereon can be referred to the above method embodiment. This embodiment will not elaborate on this.

[0101] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0102] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0104] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An automated flushing method based on blood concentration, characterized in that, The method is applied to the endoscope host in an endoscope system; The endoscope system also includes: an endoscope with a camera and a transport channel, wherein a flushing pump is provided on the transport channel, and the flushing pump is used to control the flushing speed of physiological saline in the transport channel on the surgical area; The method includes: The camera is used to capture a target image of the surgical area, and the green channel intensity value of the target image is determined. The current blood concentration of the target image is determined based on the green channel intensity value using a preset concentration model, wherein the preset concentration model is a linear relationship model between different blood concentrations and their corresponding green channel intensity values. The target rotation speed is determined based on the current blood concentration, and the irrigation pump is controlled to irrigate the surgical area according to the target rotation speed.

2. The method as described in claim 1, characterized in that, The step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: Determine the first and second coefficients in the preset concentration model, and determine the intensity difference between the preset reference intensity value and the green channel intensity value; The current blood concentration of the target image is determined based on the intensity difference value, the first coefficient, and the second coefficient.

3. The method as described in claim 2, characterized in that, Before the step of acquiring a target image of the surgical area using the camera, the method further includes: Obtain different calibrated blood concentrations and their corresponding calibrated green channel intensity values; The initial concentration model is fitted by each of the calibrated blood concentrations and the corresponding calibrated green channel intensity values ​​to obtain the first coefficient and the second coefficient. A preset concentration model is constructed based on the first coefficient, the second coefficient, and the initial concentration model.

4. The method as described in claim 1, characterized in that, The step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: The pixel blood concentration of each pixel is determined by a preset concentration model based on the green channel intensity value of each pixel in the target image. The blood pressure concentrations of each pixel are summed to obtain a first summation result; Obtain the image size of the target image, and calculate the mean of the first summation result based on the image size to obtain the first mean calculation result; The first mean value is used as the current blood concentration of the target image.

5. The method as described in claim 1, characterized in that, The step of determining the current blood concentration of the target image based on the green channel intensity value using a preset concentration model includes: The pixel blood concentration of each pixel is determined by a preset concentration model based on the green channel intensity value of each pixel in the target image. The blood concentration of each pixel is squared, and the blood concentrations of the pixels after squared operations are summed to obtain a second summation result; Obtain the image size of the target image, and calculate the mean of the second summation result based on the image size to obtain the second mean calculation result; The result of the second mean calculation is used as the current blood concentration of the target image.

6. The method as described in claim 1, characterized in that, The step of determining the corresponding target rotation speed based on the current blood concentration includes: Determine the concentration difference between the target blood concentration and the current blood concentration; The target rotation speed is determined based on the preset proportional gain and the concentration difference value.

7. The method as described in claim 1, characterized in that, Before the step of determining the corresponding target rotation speed based on the current blood concentration, the method further includes: Determine whether the current blood concentration is higher than a first preset concentration threshold; If the current blood concentration is higher than the first preset concentration threshold, the adaptive control function is activated, and the step of determining the corresponding target rotation speed based on the current blood concentration is executed.

8. The method as described in claim 7, characterized in that, After the step of determining whether the current blood concentration is higher than the first preset concentration threshold, the method further includes: If the current blood concentration is not higher than the first preset concentration threshold, determine whether the current blood pressure concentration is lower than the second preset concentration threshold, wherein the first preset concentration threshold is higher than the second preset concentration threshold; If the current blood concentration is lower than the second preset concentration threshold, the adaptive control function is turned off, and the reference rotation speed is used as the target rotation speed. If the current blood concentration is not lower than the second preset concentration threshold, the adaptive control function remains on / off.

9. An endoscope main unit, characterized in that, The endoscope host includes: a memory, a processor, and an automatic flushing program based on blood concentration stored in the memory and executable on the processor, wherein the automatic flushing program based on blood concentration, when executed by the processor, implements the steps of the automatic flushing method based on blood concentration as described in any one of claims 1 to 8.

10. An endoscope system, characterized in that, The endoscope system includes: an endoscope with a camera and a transport channel, and an endoscope host as described in claim 9; The transport channel is equipped with a flushing pump, which is used to control the flushing speed of physiological saline on the surgical area within the transport channel.

Images