Medical image device and flushing control method, system, apparatus, and storage medium thereof

Abstract

This invention discloses a medical imaging device and its rinsing control method, system, apparatus, and storage medium. The method includes real-time acquisition of the rinsing speed of the rinsing device during the rinsing process; real-time monitoring of the images acquired by the medical imaging device during the rinsing process and determining the blurriness of the acquired images; and real-time adjustment of the rinsing speed of the rinsing device based on the blurriness, so that the blurriness of the acquired images monitored after adjusting the rinsing speed reaches a target blurriness. This invention achieves intelligent rinsing control of medical imaging devices, automatically adjusting the rinsing speed according to the blurriness of the image without manual intervention. It effectively solves the problems of slow response and complex operation in existing medical imaging device rinsing control technologies, reduces the tedium and uncertainty of manual operation, and allows medical imaging devices to provide a clear surgical field of view in real time.

Description

Technical Field

[0001] This invention relates to the field of medical imaging equipment, and more specifically to a medical imaging device and its washing control method, system, apparatus and storage medium. Background Technology

[0002] The precise execution of minimally invasive surgery relies heavily on a clear intraoperative field of vision. Medical imaging equipment, such as electronic endoscopes, surgical microscopes, and arthroscopes (especially endoscopic systems), are the core visual extension of modern minimally invasive surgery, providing real-time video images that are the fundamental basis for doctors' diagnostic and operational decisions. However, during surgery, bleeding, secretions, tissue debris, or smoke from energy instruments can easily adhere to or diffuse in front of the lens, leading to a significant decrease in image quality and blurred vision, thereby interfering with the surgical process and even increasing the risk of misoperation.

[0003] To maintain visual clarity, the current standard practice is to integrate or connect an external auxiliary irrigation system, using liquid flushing to clean the lens and surgical field, thus ensuring and maintaining visual clarity at the surgical site. However, this method of control significantly conflicts with the surgeon's primary surgical task. During surgery, the surgeon's hands need to concentrate on manipulating the instruments, performing complex actions such as clamping, lifting, cutting, and puncturing tissue, often requiring several fingers of one hand, or even coordination of two hands or multiple surgeons to complete the procedure. Requiring the surgeon to manually control the irrigation process at this point constitutes a significant operational bottleneck.

[0004] Furthermore, existing irrigation functions, as surgical aids, often only have one button switch for control. This single-button control has the following drawbacks: 1. Slow Response: To save space, some instruments are designed with a single physical button, requiring continuous clicking (e.g., single click, double click, triple click) to cycle through irrigation levels (e.g., off, low, medium, high). This mode is slow to respond and unreliable in actual surgery. Due to different operating habits of doctors, the system is prone to misinterpreting continuous clicking actions, leading to incorrect level switching. Doctors often need to try repeatedly, interrupting the continuity of the surgery. In emergency situations where a clear field of vision is urgently needed, this delay can pose a safety hazard.

[0005] 2. Complex Operation: Some systems add independent "+", "-" buttons or gear selection keys to improve control precision. However, this increases the mechanical complexity and cost of the instrument design, and further exacerbates the complexity of single-handed operation for the surgeon. While operating the main instrument, the surgeon needs to find and press additional buttons. This fine division of labor is difficult to achieve in tense surgeries, often requiring the intervention of another hand or an assistant, resulting in cumbersome procedures and coordination difficulties, which violates the principles of efficiency and precision in minimally invasive surgery.

[0006] Therefore, with the increasing prevalence and high performance of medical imaging equipment, there is an urgent need for an intelligent flushing control method that can be deeply integrated with the imaging system to automatically control the flushing system of medical imaging equipment, ensuring that the medical imaging equipment can provide a clear surgical field of view in real time and guaranteeing the normal conduct of the surgery. Summary of the Invention

[0007] In view of this, the present invention provides a medical imaging device and its rinsing control method, system, apparatus and storage medium to solve the problem that the rinsing control technology of existing medical imaging devices is slow to respond and complicated to operate, which makes it impossible for medical imaging devices to provide a clear surgical field of view in real time.

[0008] This invention provides a rinsing control method for a medical imaging device, used in a rinsing apparatus configured in a medical imaging device, the method comprising: The rinsing speed of the rinsing device during the rinsing process is acquired in real time; The medical imaging device acquires images during the rinsing process in real time, and determines the blurriness of the acquired images; Based on the ambiguity, the rinsing speed of the rinsing device is adjusted in real time so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity.

[0009] Optionally, the rinsing speed of the rinsing device is adjusted in real time according to the ambiguity, so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity, including: The blur level of the acquired image is determined by comparing the blur level with a preset blur range. Based on the blur level, the washing speed adjustment level of the acquired image is obtained by querying the preset blur level-washing speed adjustment level mapping table; The speed adjustment amount of the rinsing device is determined according to the rinsing speed adjustment level; According to the speed adjustment amount, the rinsing speed of the rinsing device is adjusted, and the update blur of the updated acquired image of the medical imaging device under the rinsing of the rinsing device after adjusting the rinsing speed is re-determined, so that the update blur reaches the target blur.

[0010] Optionally, the fuzziness level includes N first levels with fuzziness increasing sequentially; The flushing speed adjustment levels include N second levels with sequentially increasing speed adjustment amounts; In the fuzzy level-rinse speed adjustment level mapping table, N first levels correspond one-to-one with N second levels.

[0011] Optionally, for the kth second level, the corresponding speed adjustment amount satisfies: △v=α k ×dv; Where Δv is the speed adjustment amount corresponding to the kth second level, α k dv is the adjustment coefficient corresponding to the kth second level, and dv is the unit speed adjustment amount; k is an integer in the range [1, N]; α k+1 >α k And when k=1, α k =0; when k=N, α k ×dv=v max v max This is the maximum allowable adjustment amount.

[0012] Optionally, determining the blurriness of the acquired image includes: Acquire a clear reference image from the medical imaging device and calculate a reference gradient map corresponding to the clear reference image; Extract the real-time gradient map of the acquired image, and calculate the gradient decay mask based on the reference gradient map and the real-time gradient map; Extract the RGB color features of the acquired image, and calculate the red overload mask, saturation filter mask and chroma filter mask based on the RGB color features. The gradient attenuation mask, red excess mask, saturation filter mask, and chroma filter mask are merged to obtain a fused mask; The real-time gradient map and the reference gradient map are processed using the fusion mask, and the mean real-time gradient corresponding to the real-time gradient map and the mean reference gradient corresponding to the reference gradient map are calculated respectively. The blurriness of the acquired image is calculated based on the real-time gradient mean and the reference gradient mean.

[0013] Optionally, the formula for calculating the blur of the acquired image is as follows: Blur_Lev ; Where Blur_Lev is the blur level of the acquired image, G t_mean and G t_ref_mean These are the real-time gradient mean and the reference gradient mean, respectively.

[0014] Optionally, the formula for calculating the mean of the real-time gradients corresponding to the real-time gradient map is as follows: ; The formula for calculating the mean of the reference gradient corresponding to the reference gradient map is as follows: ; Wherein, H and W are the height and width of the real-time gradient map, respectively, and the size of the real-time gradient map is the same as the size of the reference gradient map; (i,j) is the pixel coordinate, mask_c(i,j) is the value of the fusion mask at pixel coordinate (i,j), which is 0 or 1; G_t(i,j) is the gradient magnitude of the real-time gradient map at pixel coordinate (i,j), and Ref_grad(i,j) is the gradient magnitude of the reference gradient map at pixel coordinate (i,j).

[0015] Optionally, the calculation formula for the fusion mask is as follows: ; Where mask_c(i,j) is the value of the fusion mask at pixel coordinate (i,j), mask_g(i,j), mask_r(i,j), mask_s(i,j) and mask_a(i,j) are the values ​​of the gradient attenuation mask, the red excess mask, the saturation filter mask and the chroma filter mask at pixel coordinate (i,j) respectively, and & represents the AND logical operation.

[0016] Optionally, based on the RGB color features, a red overload mask, a saturation filter mask, and a chroma filter mask are calculated respectively, including: The red excess mask is calculated based on the RGB color features; The RGB color features are converted into HSV color features, and the saturation filter mask is calculated based on the HSV color features. The RGB color features are converted into LAB color features, and the chromaticity filter mask is calculated based on the LAB color features.

[0017] Optionally, the calculation formula for the red excess mask is as follows: ; Where mask_r(i,j) is the value of the red overmask at pixel coordinates (i,j), and r ij g ij and b ij These represent the red, green, and blue feature component values ​​of the RGB color feature at pixel coordinates (i,j), respectively. min K is the threshold for the red feature. r_g K is the red-green relative proportion coefficient. r_b The red-blue relative ratio coefficient, & represents the AND logical operation; The specific formula for calculating the saturation filter mask is as follows: ; Where mask_s(i,j) is the value of the saturation filter mask at pixel coordinates (i,j), and s ij The saturation component value of the HSV color feature at pixel coordinates (i,j) is the HSV color feature. _max and HSV min These are the upper and lower limits of saturation, respectively. The specific formula for calculating the colorimetric filter mask is as follows: ; Where mask_a(i,j) is the value of the chroma filter mask at pixel coordinates (i,j), and a ij The LAB color feature is represented by its chromaticity component value at pixel coordinates (i,j). _max and LAB _min These are the upper and lower limits of chromaticity, respectively.

[0018] Optionally, a gradient decay mask is calculated based on the reference gradient map and the real-time gradient map, including: The gradient magnitude at each pixel coordinate of the real-time gradient map is compared one by one with the gradient magnitude at the corresponding pixel coordinate of the reference gradient map to obtain a comparison result matrix. The gradient attenuation mask is obtained based on the comparison result matrix. For pixel coordinates (i,j), the specific formula for comparing the gradient magnitude of the real-time gradient map at pixel coordinates (i,j) with the gradient magnitude of the reference gradient at pixel coordinates (i,j) is as follows: ; Wherein, mask_g(i,j) is the value of the gradient decay mask at pixel coordinate (i,j), K_g is the empirical parameter of the gradient decay mask, and G_t(i,j) and Ref_grad(i,j) are the gradient magnitudes of the real-time gradient map and the reference gradient map at pixel coordinate (i,j), respectively.

[0019] Furthermore, the present invention also provides a washing control system for medical imaging equipment, applied in the aforementioned washing control method for medical imaging equipment, the system comprising: The speed detection module is used to acquire the rinsing speed of the rinsing device configured in the medical imaging equipment during the rinsing process in real time; An image monitoring module is used to monitor the images acquired by the medical imaging device during the rinsing process in real time and determine the blurriness of the acquired images; The speed adjustment module is used to adjust the rinsing speed of the rinsing device in real time according to the ambiguity, so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity.

[0020] Furthermore, the present invention also provides a rinsing control device for a medical imaging device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed, it implements the method steps in the aforementioned rinsing control method for a medical imaging device.

[0021] Furthermore, the present invention also provides a medical imaging device, comprising: A rinsing device used to perform the rinsing process; A speed sensor, which is communicatively connected to the rinsing device, is used to collect the rinsing speed of the rinsing device in real time during the rinsing process; An imaging device is used to acquire images in real time during the rinsing process of the rinsing device; The aforementioned rinsing control device for medical imaging equipment is communicatively connected to the speed sensor, the imaging device, and the rinsing device; used for: The system acquires the rinsing speed in real time from the speed sensor and monitors the image acquired in real time from the imaging device; it determines the blurriness of the acquired image and, based on the blurriness, sends a control signal to the rinsing device in real time to adjust the rinsing speed. The rinsing device is used to receive the control signal in real time and adjust the rinsing speed in real time according to the control signal, so that the blurriness of the acquired image re-monitored by the rinsing control device of the medical imaging equipment reaches the target blurriness.

[0022] Optionally, the speed sensor is specifically a motor speed sensor, and the rinsing device includes a rinsing assembly and a rinsing motor; The rinsing motor is communicatively connected to the rinsing control device of the medical imaging equipment and the motor speed sensor. The rinsing motor is also drive-connected to the rinsing assembly. The flushing motor is used to drive the flushing assembly to inject flushing fluid in real time to perform the flushing process; it is also used to receive the control signal sent by the flushing control device of the medical imaging equipment in real time, and adjust the driving signal for driving the flushing assembly to inject flushing fluid according to the control signal, so as to adjust the flushing speed of the flushing assembly during the flushing process. The motor speed sensor is used to detect the rotation speed of the flushing motor when it drives the flushing assembly to work in real time, and to obtain the flushing speed corresponding to the flushing assembly based on the real-time detected rotation speed.

[0023] Furthermore, the present invention also provides a computer storage medium comprising: at least one instruction that, when executed by a computer, implements the method steps of the aforementioned rinsing control method for a medical imaging device.

[0024] The beneficial effects of this invention are as follows: During the rinsing process of the medical imaging equipment, the rinsing speed is collected to facilitate real-time adjustment. Simultaneously, the acquired images are monitored and their blurriness is determined, allowing for assessment of the current field of view's blurriness. Real-time monitoring of the field of view's clarity is achieved based on image recognition technology. Once the blurriness is determined, the rinsing speed is dynamically adjusted to ensure that the blurriness of the re-monitored acquired images reaches the target blurriness. Throughout the rinsing process, the rinsing speed and the blurriness of the acquired images are continuously acquired, forming a closed-loop feedback adjustment system. By continuously comparing the blurriness of the acquired images with the target blurriness, the rinsing speed is dynamically adjusted, ensuring that the medical imaging equipment always provides a clear surgical field of view during rinsing, thus providing a strong guarantee for the smooth progress of the surgery. The medical imaging device and its rinsing control method, system, apparatus, and storage medium of the present invention realize intelligent rinsing control of the medical imaging device. It can automatically adjust the rinsing speed according to the blurriness of the image without the need for manual intervention by the operator. It effectively solves the problems of slow response and complicated operation of existing medical imaging device rinsing control technology, reduces the tediousness and uncertainty of manual operation, and allows the medical imaging device to provide a clear surgical field of view in real time. It greatly improves the efficiency and reliability of the medical imaging device during medical surgery, better ensures the normal progress of the surgery, and brings important technological innovation and practical application value to the medical field. Attached Figure Description

[0025] The features and advantages of the invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the invention in any way. In the drawings: Figure 1 A flowchart of a rinsing control method for a medical imaging device according to Embodiment 1 of the present invention is shown; Figure 2 A structural diagram of a washing control system for a medical imaging device according to Embodiment 2 of the present invention is shown; Figure 3 A structural diagram of a medical imaging device according to Embodiment 4 of the present invention is shown; Figure 4 A structural diagram of the rinsing assembly in Embodiment 4 of the present invention is shown.

[0026] Explanation of reference numerals in the attached figures: 1. Flushing fluid storage bag; 2. Flushing tubing; 3. Peristaltic pump; 4. Flushing fluid; 5. Motor speed sensor. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] In this embodiment of the invention, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0030] In this embodiment of the invention, the term "multiple" refers to two or more, and other quantifiers are similar.

[0031] Example 1 This embodiment provides a flushing control method for medical imaging equipment, such as... Figure 1 As shown, the method includes: S1: Real-time acquisition of the rinsing speed of the rinsing device during the rinsing process; S2: Monitor the images acquired by the medical imaging device during the rinsing process in real time, and determine the blurriness of the acquired images; S3: Based on the ambiguity, the rinsing speed of the rinsing device is adjusted in real time so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity.

[0032] In this embodiment, during the rinsing process of the medical imaging equipment, the rinsing speed is collected to facilitate real-time adjustment. Simultaneously, the acquired images are monitored and their blurriness is determined, allowing for assessment of the current field of view's blurriness. Real-time monitoring of the field of view's clarity is achieved based on image recognition technology. Once the blurriness is determined, the rinsing speed is dynamically adjusted to ensure that the blurriness of the re-monitored acquired images reaches the target blurriness. Throughout the rinsing process, the rinsing speed and the blurriness of the acquired images are continuously acquired, forming a closed-loop feedback adjustment system. By continuously comparing the blurriness of the acquired images with the target blurriness, the rinsing speed is dynamically adjusted to ensure that the medical imaging equipment consistently provides a clear surgical field of view during rinsing, thus providing a strong guarantee for the smooth progress of the surgery.

[0033] The flushing control method for medical imaging equipment in this embodiment realizes intelligent flushing control of medical imaging equipment. It can automatically adjust the flushing speed according to the blurriness of the image without the need for manual intervention by the operator. It effectively solves the problems of slow response and complicated operation of existing medical imaging equipment flushing control technology, reduces the tediousness and uncertainty of manual operation, and allows medical imaging equipment to provide a clear surgical field of view in real time. It greatly improves the efficiency and reliability of medical imaging equipment during medical surgery, better ensures the normal progress of surgery, and brings important technological innovation and practical application value to the medical field.

[0034] It should be understood that the medical imaging equipment in this embodiment includes, but is not limited to, endoscopes, surgical microscopes, and arthroscopes. For ease of explanation, this embodiment uses an endoscope as an example. Furthermore, the above-described irrigation control method applies the endoscope and its irrigation device to a simulated tissue structure model, such as a simulated blood vessel model, to obtain the irrigation speed and acquired images during the irrigation of the simulated blood vessel model.

[0035] In addition, the target ambiguity refers to the ambiguity required by the doctor, which is usually the ambiguity that ensures the normal operation of the surgery or that the image quality meets certain requirements. It can be preset or adjusted.

[0036] The following provides a detailed description of each step of the rinsing control method for the medical imaging equipment in this embodiment.

[0037] In this embodiment S1, the rinsing speed of the rinsing device can be obtained by a speed sensor.

[0038] In this embodiment S2, the images acquired by the medical imaging device can be obtained either through the image components integrated within the medical imaging device (such as a CMOS image sensor) or through an externally mounted imaging device (such as a camera attached to the operating end of an endoscope). Both methods can achieve real-time image acquisition.

[0039] Preferably, in embodiment S2, determining the blurriness of the acquired image includes: S21: Obtain a clear reference image from the medical imaging device and calculate the reference gradient map corresponding to the clear reference image; S22: Extract the real-time gradient map of the acquired image, and calculate the gradient decay mask based on the reference gradient map and the real-time gradient map; S23: Extract the RGB color features of the acquired image, and calculate the red overload mask, saturation filter mask and chroma filter mask based on the RGB color features. S24: The gradient attenuation mask, red excess mask, saturation filter mask and chroma filter mask are merged to obtain a fused mask; S25: The real-time gradient map and the reference gradient map are processed using the fusion mask, and the mean real-time gradient corresponding to the real-time gradient map and the mean reference gradient corresponding to the reference gradient map are calculated respectively. S26: Calculate the blur of the acquired image based on the real-time gradient mean and the reference gradient mean.

[0040] In this embodiment, when determining the blurriness of the acquired image, the gradient map (i.e., the reference gradient map) of the clear reference image of the medical imaging device is first used as a benchmark to establish a quantitative standard for the "clear state" and provide a comparison benchmark for subsequent blurriness calculation, so as to ensure the objectivity and reliability of blurriness assessment.

[0041] Then, a real-time gradient map is extracted from the images acquired during the actual rinsing process and compared with the reference gradient map to generate a gradient attenuation mask. During the actual surgery, the outflow of fresh blood will spread and infiltrate the tissue surface, causing the micro-texture of the area to be temporarily "smoothed out". This is manifested in the image as a decrease in local contrast and blurred edges. Therefore, this embodiment uses a gradient attenuation mask to mark the areas in the acquired images where the gradient decreases significantly due to bleeding (i.e., the blurred areas caused by bleeding), avoiding interference from non-blurring factors (such as changes in lighting, or muscle tissue that is red but has a clear texture) and reducing false alarms.

[0042] Next, the RGB color features of the acquired image are extracted, and based on these RGB color features, red excess mask, saturation filter mask, and chroma filter mask are calculated respectively. This facilitates further differentiation between blurred and non-blurred areas caused by bleeding by combining color features. The processing of the fusion mask obtained by combining the gradient decay mask, red excess mask, saturation filter mask, and chroma filter mask ensures that the red detected in the image corresponds to the area of ​​target bleeding, rather than the area corresponding to other tissues and fluids. This ensures that the obtained real-time gradient mean can truly reflect the characteristics of target bleeding, and ensures that the final calculated blur is caused by target bleeding, thus guaranteeing the effectiveness of flushing control.

[0043] This embodiment combines information from four dimensions: texture variation (gradient), color intensity (RGB color features), color quality (HSV color features), and scientific colorimetry (LAB color features) to construct a multi-dimensional feature fusion quantization system. Through "multi-feature fusion + precise quantization", it solves the problems of "susceptibility to interference and strong subjectivity" in traditional ambiguity assessment, and provides core technical support for intelligent washing control of medical imaging equipment with both high precision and high robustness.

[0044] In step S21, the clear reference image can be either an image acquired when the field of view is clear, or a clear image from historical data.

[0045] In step S21, the reference gradient map corresponding to the sharp reference image is calculated, including: S211: Convert the clear reference image to grayscale to obtain a first grayscale image; S212: Using the Sobel operator, calculate the first horizontal gradient and the first vertical gradient of each pixel in the first grayscale image. S213: Calculate the gradient magnitude of each pixel in the first grayscale image based on the first horizontal gradient and the first vertical gradient of each pixel in the first grayscale image; S214: Based on the gradient magnitude of all pixels in the first grayscale image, obtain the reference gradient map corresponding to the clear reference image.

[0046] In step S211, converting the sharp reference image from color space to grayscale space simplifies the subsequent gradient calculation process and facilitates unified processing. The specific calculation method for grayscale conversion of the sharp reference image can be a weighted average method. This involves weighting the pixel values ​​of the red, green, and blue channels according to certain weights, based on the different sensitivities of the human eye to different colors. For example, setting the weight coefficients to 0.299, 0.587, and 0.114, the grayscale calculation formula for any pixel is: Grayscale value = 0.299 × red channel pixel value + 0.587 × green channel pixel value + 0.114 × blue channel pixel value. The grayscale values ​​of all pixels constitute the first grayscale image, which can be represented by I = Gray(Ref_Clr).

[0047] In S212, the Sobel operator is a discrete difference operator. Using this operator, the first horizontal gradient and the first vertical gradient of each pixel in the first grayscale image are calculated, thus obtaining the rate of change of the image in the horizontal and vertical directions. In the actual calculation process of this embodiment, the Sobel operator uses a 3×3 convolution kernel, including a horizontal kernel and a vertical kernel, to perform convolution operations on each pixel in the first grayscale image, thereby obtaining the gradient values ​​(i.e., the first horizontal gradient and the first vertical gradient) of each pixel in the horizontal and vertical directions.

[0048] The horizontal kernel and the vertical kernel are represented as follows: and ; G x and G y These are the horizontal core and the vertical core, respectively.

[0049] For pixel (i,j), the formulas for calculating the first horizontal gradient and the first vertical gradient are as follows: ; ; and Let be the first horizontal gradient and the first vertical gradient of pixel (i,j) in the first grayscale image, respectively. Let (m,n)∈{-1,0,1} be the neighborhood of the 3×3 convolution kernel, and let I(i+m,j+n) be the grayscale value of the first grayscale image at the pixel.

[0050] For S213, the gradient magnitude is calculated based on the first horizontal gradient and the first vertical gradient, which can comprehensively consider the changes of the image in the horizontal and vertical directions. In S214, a reference gradient map is obtained based on the gradient magnitude of all pixels in the first grayscale image. The reference gradient map reflects the texture and edge features of the clear reference image, providing an important basis for subsequent comparison with the real-time gradient map of the acquired image.

[0051] For pixel (i,j), the formula for calculating the gradient magnitude is as follows: ; Ref_gray(i,j) is the gradient magnitude of pixel (i,j) in the first grayscale image.

[0052] In step S22, the real-time gradient map of the acquired image is extracted, which is achieved using a method similar to steps S211~S214 above. The specific steps are as follows: S221: Convert the acquired image to grayscale to obtain a second grayscale image; S222: Using the Sobel operator, calculate the second horizontal gradient and the second vertical gradient of each pixel in the second grayscale image; S223: Calculate the gradient magnitude of each pixel in the second grayscale image based on the second horizontal gradient and the second vertical gradient of each pixel in the second grayscale image; S224: Based on the gradient magnitude of all pixels in the second grayscale image, obtain the real-time gradient map corresponding to the acquired image.

[0053] Since steps S221~S224 are similar to steps S211~S214, the specific formulas will not be listed here.

[0054] In step S22, the gradient decay mask is calculated based on the reference gradient map and the real-time gradient map, including: S225: Compare the gradient magnitude at each pixel coordinate of the real-time gradient map with the gradient magnitude at the corresponding pixel coordinate of the reference gradient map one by one to obtain a comparison result matrix; S226: Obtain the gradient attenuation mask based on the comparison result matrix; For pixel coordinates (i,j), the specific formula for comparing the gradient magnitude of the real-time gradient map at pixel coordinates (i,j) with the gradient magnitude of the reference gradient at pixel coordinates (i,j) is as follows: ; Wherein, mask_g(i,j) is the value of the gradient decay mask at pixel coordinate (i,j), K_g is the empirical parameter of the gradient decay mask, and G_t(i,j) and Ref_grad(i,j) are the gradient magnitudes of the real-time gradient map and the reference gradient map at pixel coordinate (i,j), respectively.

[0055] In step S225, the gradient magnitudes at corresponding pixel coordinates of the real-time gradient map and the reference gradient map are compared one by one. The generated comparison result matrix clearly reflects the gradient changes of the acquired image relative to the clear reference image at various positions, providing a data basis for the subsequent generation of the gradient attenuation mask. In step S226, the gradient attenuation mask is obtained based on the comparison result matrix. This mask can effectively mark the areas in the acquired image where the gradient drops significantly due to factors such as bleeding.

[0056] In step S23, the RGB color features of the acquired image are extracted, which can be achieved using conventional methods. The obtained RGB color features include the red feature component value, green feature component value, and blue feature component value at each pixel coordinate.

[0057] In step S23, based on the RGB color features, a red overload mask, a saturation filter mask, and a chroma filter mask are calculated respectively, including: S231: Calculate the red excess mask based on the RGB color features; S232: Convert the RGB color features into HSV color features, and calculate the saturation filter mask based on the HSV color features; S233: Convert the RGB color features into LAB color features, and calculate the chromaticity filter mask based on the LAB color features.

[0058] In step S231, a red excess mask is calculated based on RGB color features, which facilitates the subsequent combination of the red excess mask with saturation filter mask, chroma filter mask and gradient attenuation mask to more accurately identify the blurred areas in the image caused by bleeding.

[0059] In the HSV color space, saturation represents the vividness of a color. In step S232, converting RGB color features into HSV color features is to better analyze color saturation information, which helps to filter out some parts with low color saturation that may not be bleed areas, further narrowing down the possible bleed area range.

[0060] The LAB color space is more in line with human visual perception. In step S233, the RGB color features are converted into LAB color features, which makes it easier to consider the colorimetric aspect and ensure that the detected red is the typical colorimetric of the target bleeding, rather than other tissues or fluids, thus further accurately marking the possible bleeding area.

[0061] Specifically, in step S231, the calculation formula for the red excess mask is as follows: ; Where mask_r(i,j) is the value of the red overmask at pixel coordinates (i,j), and r ij g ij and b ij These represent the red, green, and blue feature component values ​​of the RGB color feature at pixel coordinates (i,j), respectively. min K is the threshold for the red feature. r_g K is the red-green relative proportion coefficient. r_b The red-blue relative ratio coefficient, & represents the AND logical operation; In step S232, the calculation formula for the saturation filter mask is as follows: ; Where mask_s(i,j) is the value of the saturation filter mask at pixel coordinates (i,j), and s ij The saturation component value of the HSV color feature at pixel coordinates (i,j) is the HSV color feature. _max and HSV min These are the upper and lower limits of saturation, respectively. In step S233, the calculation formula for the chromaticity filter mask is as follows: ; Where mask_a(i,j) is the value of the chroma filter mask at pixel coordinates (i,j), and a ij The LAB color feature is represented by its chromaticity component value at pixel coordinates (i,j). _max and LAB _min These are the upper and lower limits of chromaticity, respectively.

[0062] For a red over-mask, the red feature threshold R min Red-green relative proportion coefficient (i.e., the proportion coefficient of red relative to green) K r_gBoth the red-blue relative scaling factor (i.e., the red-to-blue scaling factor) and the red-blue relative scaling factor are empirical parameters, related to different surgical locations and the optical systems of medical imaging equipment. The calculated red excess mask is specifically a matrix table including 1s and 0s, meaning the red excess mask value at pixel coordinates (i,j) is either 1 or 0. When it is 1, it indicates that red is dominant, meaning that the pixel coordinate is a possible point of blood presence; while when it is 0, it indicates that the pixel coordinate is a non-blood presence point.

[0063] For saturation filter masks, the upper limit of saturation is HSV. _max and saturation lower limit HSV min All parameters are empirical, with the lower limit of saturation being HSV. min The default value is 50, and the upper limit of saturation is HSV. _max The default value is 160. The calculated saturation filter mask is also a matrix table containing 1s and 0s. When the value of the saturation filter mask at pixel coordinates (i,j) is 1, it indicates that the saturation at that pixel coordinate is within the HSV range. min With HSV _max Between these values, a pixel with color that is not overexposed is a possible point where blood may be present; while when the value is 0, it indicates that the pixel coordinates are too gray or overexposed, and therefore a point where blood may not be present.

[0064] For chroma filtering masks, the upper limit of chroma is LAB. _max and the lower limit of chromaticity LAB _min These are all empirical parameters, with default values ​​of 180 and 130 respectively. Similarly, the calculated chroma filter mask is also specifically a matrix table including 1s and 0s. When the value of the chroma filter mask at pixel coordinates (i,j) is 1, it indicates that the pixel coordinates are typical red blood points; while when it is 0, it indicates that the pixel coordinates are non-blood points.

[0065] In step S24, the calculation formula for the fusion mask is as follows: ; Where mask_c(i,j) is the value of the fusion mask at pixel coordinate (i,j), mask_g(i,j), mask_r(i,j), mask_s(i,j), and mask_a(i,j) are the values ​​of the gradient attenuation mask, the red excess mask, the saturation filter mask, and the chroma filter mask at pixel coordinate (i,j), respectively, and & represents the AND logical operation.

[0066] By using the calculation formula for the fusion mask described above, the gradient attenuation mask, red excess mask, saturation filtering mask, and chroma filtering mask are fused together. This allows for the comprehensive utilization of the advantages of each mask, enabling more accurate identification of areas in medical images that may contain bleeding. The fusion mask is also a matrix containing 1s and 0s. When the value of the fusion mask at pixel coordinates (i,j) is 1, it indicates that the pixel coordinates simultaneously meet multiple conditions such as gradient attenuation, red excess, appropriate color saturation, and chroma compliance. This indicates a newly appearing, color-abrupt, moderately saturated, red-dominant, and blurred pixel, which is likely the target bleeding area. When the value is 0, it indicates that the pixel coordinates do not meet the above conditions and are either a non-bleeding area or an artifact area.

[0067] In practical applications, fusion masks can quickly and accurately locate bleeding sites in medical images, providing doctors with intuitive diagnostic information. Doctors can assess the blurriness of the acquired image based on the bleeding area marked by the fusion mask, with high accuracy and robustness, thereby improving the reliability and stability of subsequent irrigation control.

[0068] In step S25, the formula for calculating the mean real-time gradient corresponding to the real-time gradient map is as follows: ; The formula for calculating the mean of the reference gradient corresponding to the reference gradient map is as follows: ; Wherein, H and W are the height and width of the real-time gradient map, respectively, and the size of the real-time gradient map is the same as the size of the reference gradient map; (i,j) is the pixel coordinate, mask_c(i,j) is the value of the fusion mask at pixel coordinate (i,j), which is 0 or 1; G_t(i,j) is the gradient magnitude of the real-time gradient map at pixel coordinate (i,j), and Ref_grad(i,j) is the gradient magnitude of the reference gradient map at pixel coordinate (i,j).

[0069] By calculating the real-time gradient mean and the reference gradient mean, the gradient difference between the acquired image and the sharp reference image can be further quantified. The real-time gradient mean reflects the overall gradient change of the acquired image, while the reference gradient mean represents the gradient characteristics of the sharp reference image. Therefore, calculating blur based on these two metrics allows for a more comprehensive and accurate assessment of the degree of blur in the acquired image.

[0070] In step S26, the formula for calculating the blur of the acquired image is as follows: Blur_Lev ; Where Blur_Lev is the blur level of the acquired image, Gt_mean and G t_ref_mean These are the real-time gradient mean and the reference gradient mean, respectively.

[0071] By using the aforementioned formula to calculate ambiguity, the real-time average gradient of the acquired image can be compared with the average gradient of a clear reference image, thus obtaining a quantified ambiguity value. This value directly reflects the degree of blurriness of the acquired image relative to the clear reference image. A larger ambiguity value indicates a significant difference in gradient changes between the acquired image and the clear reference image, resulting in a more blurred image. Conversely, a smaller ambiguity value indicates that the gradient characteristics of the acquired image and the clear reference image are relatively similar, resulting in a relatively clear image. Based on this quantified ambiguity value, subsequent efficient and accurate adjustments to the washing strategy are facilitated, thereby effectively ensuring the normal operation of medical imaging equipment and image quality.

[0072] It should be understood that the process of calculating ambiguity described in steps S21 to S26 of this embodiment is performed in real time, and the resulting ambiguity value is also based on the real-time changes during the washing process. When the calculated ambiguity reaches the target ambiguity, the monitoring of the acquired image and the calculation of ambiguity can be stopped.

[0073] Preferably, embodiment S3 includes: S31: Compare the blur degree with a preset blur degree range to determine the blur level of the acquired image; S32: Based on the blur level, query the preset blur level-rinse speed adjustment level mapping table to obtain the rinse speed adjustment level of the acquired image; S33: Determine the speed adjustment amount of the rinsing device according to the rinsing speed adjustment level; S34: Adjust the rinsing speed of the rinsing device according to the speed adjustment amount, and redetermine the update ambiguity corresponding to the updated acquired image of the medical imaging device under the rinsing of the rinsing device after adjusting the rinsing speed, so that the update ambiguity reaches the target ambiguity.

[0074] In step S31, the preset ambiguity range can be multiple ranges. By comparing multiple ranges, different ambiguity levels of the acquired image can be determined. By directly comparing the preset ambiguity ranges, the ambiguity level corresponding to the ambiguity can be quickly identified, which facilitates the subsequent rapid matching of the corresponding rinsing speed adjustment strategy.

[0075] In step S32, a preset fuzziness level-rinse speed adjustment level mapping table establishes a correspondence between different fuzziness levels and corresponding rinse speed adjustment levels. Based on the determined fuzziness level of the acquired image, the matching rinse speed adjustment level can be accurately and quickly retrieved from this mapping table.

[0076] In step S33, the specific speed adjustment amount of the rinsing device is determined based on the rinsing speed adjustment level obtained from the query. By adjusting the speed appropriately, the quality of the acquired images can be effectively improved without affecting the normal operation of the medical imaging equipment.

[0077] In step S34, the rinsing speed of the rinsing device is adjusted according to a determined speed adjustment amount. After adjustment, the medical image is reacquired and its updated ambiguity is calculated. By continuously repeating this process, that is, adjusting the rinsing speed again according to the updated ambiguity, a dynamic feedback adjustment mechanism is formed. Finally, the intelligent rinsing control of the rinsing device is used to achieve intelligent optimization of the image quality of the medical imaging equipment.

[0078] Preferably, the fuzziness level includes N first levels with fuzziness increasing sequentially; The flushing speed adjustment levels include N second levels with sequentially increasing speed adjustment amounts; In the fuzzy level-rinse speed adjustment level mapping table, N first levels correspond one-to-one with N second levels.

[0079] The above settings allow for multi-level adjustment of the rinsing speed, enabling flexible adjustment based on varying degrees of blur. This multi-level adjustment method allows for more precise and detailed adjustment of the rinsing speed, enabling personalized processing based on the actual blur level of the image.

[0080] Preferably, for the kth second level, the corresponding speed adjustment amount satisfies: △v=α k ×dv; Where Δv is the speed adjustment amount corresponding to the kth second level, α k dv is the adjustment coefficient corresponding to the kth second level, and dv is the unit speed adjustment amount; k is an integer in the range [1, N]; α k+1 >α k And when k=1, α k =0; when k=N, α k ×dv=v max v max This is the maximum allowable adjustment amount.

[0081] In the multi-level adjustment system of this embodiment, as the fuzzy level increases, the rinsing speed adjustment level also increases accordingly, and the adjustment coefficient α k As the speed increases, the speed adjustment Δv also increases. That is, when the image blurriness is low, the speed adjustment of the rinsing device is smaller to avoid excessive rinsing causing unnecessary impact on the medical imaging equipment and the acquisition process. Conversely, when the blurriness is high, a larger speed adjustment can more quickly improve image quality.

[0082] When the blur level of the acquired image is the first level (i.e., the lowest first level), it indicates that the blur is within an acceptable range, and the corresponding adjustment coefficient α1 for the second level is 0. At this time, the speed adjustment Δv is 0, meaning the washing speed does not need to be adjusted. As the blur increases, when a higher blur level is reached, such as the Nth first level, the corresponding adjustment coefficient α... N This ensures that the speed adjustment Δv reaches the maximum allowable adjustment v. max This can maximize the washing speed to quickly improve image quality.

[0083] Furthermore, within the aforementioned multi-level adjustment system, setting the unit speed adjustment increment (dv) as a basic adjustment unit effectively ensures the continuity and stability of speed adjustment. Different medical imaging devices and application scenarios can adjust the dv value according to actual needs to achieve the best rinsing effect.

[0084] It should be noted that in actual medical image acquisition, when the blurriness of a newly acquired image changes, the new blurriness value is obtained by calculating the real-time gradient mean and the reference gradient mean. Then, based on the correspondence between the blurriness level and the rinsing speed adjustment level, the rinsing device speed is adjusted in a timely manner. This ensures that the medical imaging equipment maintains high image quality at all times, providing doctors with clear and accurate diagnostic information, and improving the accuracy and reliability of medical diagnosis.

[0085] Furthermore, the fuzziness level includes six first levels with fuzziness increasing sequentially; The blur level of the acquired image is determined by comparing the blur degree with a preset blur degree range, including: When the blurriness is within the first blurriness range, the blur level of the acquired image is determined to be the first first level; When the blurriness is within the second blurriness range, the blur level of the acquired image is determined to be the second first level; the blurriness within the second blurriness range is greater than the blurriness within the first blurriness range; When the ambiguity is within the third ambiguity range, the ambiguity level of the acquired image is determined to be the third first level; the ambiguity within the third ambiguity range is greater than the ambiguity within the second ambiguity range; When the ambiguity is within the fourth ambiguity range, the ambiguity level of the acquired image is determined to be the fourth first level; the ambiguity within the fourth ambiguity range is greater than the ambiguity within the third ambiguity range; When the ambiguity is within the fifth ambiguity range, the ambiguity level of the acquired image is determined to be the fifth first level; the ambiguity within the fifth ambiguity range is greater than the ambiguity within the fourth ambiguity range; When the ambiguity is within the sixth ambiguity range, the ambiguity level of the acquired image is determined to be the sixth first level; the ambiguity within the sixth ambiguity range is greater than the ambiguity within the fifth ambiguity range.

[0086] Specifically, the first to sixth ambiguity ranges are [0,0.15], (0.15,0.30], (0.30,0.40], (0.40,0.60], (0.60,0.1], and (0.1,Blur_Lev_max], respectively, where Blur_Lev_max refers to the maximum ambiguity value, which can be preset or adjusted based on experience.

[0087] The above six ambiguity ranges correspond to six first levels. By comparing the ambiguity obtained from actual calculations with the above ambiguity ranges, the corresponding first level can be directly determined.

[0088] Specifically, for the six ambiguity ranges mentioned above, there are also six levels of ambiguity.

[0089] The speed adjustment values ​​corresponding to the six second levels are 0, dv, 2dv, 3dv, 5dv, and v, respectively. max .

[0090] It should be understood that the above-mentioned maximum allowable adjustment amount v max It can also be preset or adjusted based on experience. In addition, since the adjustment of the rinsing speed is a real-time adjustment process, when the adjusted rinsing speed reaches the maximum allowable speed Vmax at a certain moment, it is directly adjusted according to Vmax. This maximum allowable speed Vmax is usually preset or adjusted based on the equipment conditions or experience.

[0091] In one specific implementation, the actual operation of the flushing control method includes the following three stages: (1) Rinse preparation: Users assemble the flushing components in the flushing device according to the operating instructions (including connecting the flushing pipeline, adding flushing fluid, etc.), power on and perform a self-test. After the self-test is completed, start the venting operation to remove air from the pipeline and complete the flushing preparation.

[0092] (2) Rinse ready After the rinsing preparation is completed, the rinsing device waits for the medical imaging equipment; when the medical imaging equipment is ready, press the rinsing button and run at the preset initial rinsing speed Vinit (ml / s) to start rinsing the simulated blood vessel model.

[0093] (3) Speed ​​adjustment Based on empirical parameters, the maximum rinsing speed Vmax (ml / s) is set to ensure field of view clarity and safety requirements. Then, the unit speed adjustment dv is set, where dv = (Vmax - Vinit) × 0.1. The blur level Blur_Lev is calculated based on the acquired images from the medical imaging equipment. When Blur_Lev is in the range [0, 0.15], the rinsing speed remains unchanged; when Blur_Lev is in the range (0.15, 0.30], the rinsing speed is increased by dv, i.e., the speed adjustment amount dv is increased; when Blur_Lev is in the range (0.30, 0.40], the rinsing speed is increased by 2dv, i.e., the speed adjustment amount 2dv is increased; when Blur_Lev is in the range (0.40, 0.60], the rinsing speed is increased by 3dv, i.e., the speed adjustment amount 3dv is increased; when Blur_Lev is in the range (0.60, 1]), the rinsing speed is increased by 5dv, i.e., the speed adjustment amount 5dv is increased; when Blur_Lev exceeds 1, the rinsing speed is increased by v. max That is, according to the speed adjustment amount v max Increase the speed; during the above real-time adjustment process, if the flushing speed reaches Vmax after adjustment, then the flushing speed will be directly adjusted to Vmax.

[0094] (4) Rinsing complete Once the speed is adjusted and the blurriness of the real-time monitored image reaches the target blurriness (e.g., 0.05), press the flush button again to turn off flushing.

[0095] Of course, other button control methods can also be used to start and stop rinsing during the above operation, and these are not restricted here. For example, press and hold the rinsing button to start rinsing, and release the rinsing button when the blur of the acquired image reaches the target blur.

[0096] Example 2 A rinsing control system for a medical imaging device is applied in the rinsing control method of the medical imaging device in Embodiment 1, such as... Figure 2 As shown, the system includes: The speed detection module is used to acquire the rinsing speed of the rinsing device configured in the medical imaging equipment during the rinsing process in real time; An image monitoring module is used to monitor the images acquired by the medical imaging device during the rinsing process in real time and determine the blurriness of the acquired images; The speed adjustment module is used to adjust the rinsing speed of the rinsing device in real time according to the ambiguity, so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity.

[0097] In this embodiment, during the rinsing process of the medical imaging equipment, a speed detection module collects data on the rinsing speed to facilitate real-time adjustment. Simultaneously, an image monitoring module monitors the acquired images from the medical imaging equipment and determines their blurriness, allowing for the assessment of the current field of view's blurriness based on the blurriness. This enables real-time monitoring of the field of view's clarity using image recognition technology. Once the blurriness is determined, a speed adjustment module dynamically adjusts the rinsing speed based on the blurriness, ensuring that the blurriness of the re-monitored acquired images reaches the target blurriness. Throughout the rinsing process, the rinsing speed and the blurriness of the acquired images are continuously acquired, forming a closed-loop feedback adjustment system. By continuously comparing the blurriness of the acquired images with the target blurriness, the rinsing speed is dynamically adjusted to ensure that the medical imaging equipment consistently provides a clear surgical field of view during rinsing, thus providing a strong guarantee for the smooth progress of the surgery.

[0098] The flushing control system for medical imaging equipment in this embodiment realizes intelligent flushing control of medical imaging equipment. It can automatically adjust the flushing speed according to the blurriness of the image without the need for manual intervention by the operator. It effectively solves the problems of slow response and complicated operation of existing medical imaging equipment flushing control technology, reduces the tediousness and uncertainty of manual operation, and allows medical imaging equipment to provide a clear surgical field of view in real time. It greatly improves the efficiency and reliability of medical imaging equipment during medical surgery, better ensures the normal progress of surgery, and brings important technological innovation and practical application value to the medical field.

[0099] The functions of each module in the rinsing control system of the medical imaging equipment described in this embodiment are the same as the method steps of the rinsing control method of the medical imaging equipment described in Embodiment 1. Therefore, for details not covered in this embodiment, please refer to Embodiment 1 and... Figure 1 The specific details will not be repeated here.

[0100] Example 3 This embodiment also provides a rinsing control device for a medical imaging device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed, it implements the method steps in the rinsing control method for the medical imaging device of Embodiment 1.

[0101] By using a computer program stored in memory and running on a processor, intelligent flushing control of medical imaging equipment has been achieved. This system can automatically adjust the flushing speed according to the blurriness of the image without manual intervention from the operator. It effectively solves the problems of slow response and complex operation of existing medical imaging equipment flushing control technology, reduces the tedium and uncertainty of manual operation, and allows medical imaging equipment to provide a clear surgical field of view in real time. This greatly improves the efficiency and reliability of medical imaging equipment during medical surgery, better ensures the normal progress of the surgery, and brings important technological innovation and practical application value to the medical field.

[0102] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the computer device, connecting all parts of the computer device through various interfaces and lines.

[0103] Memory can be used to store computer programs and / or models. The processor performs various functions of the computer device by running or executing the computer programs and / or models stored in the memory, and by accessing data stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area can store the operating system and at least one application program required for a function (e.g., sound playback, image playback, etc.); the data storage area can store data created based on the use of the mobile phone (e.g., audio data, video data, etc.). Furthermore, memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMedia Cards (SMC), Secure Digital (SD) cards, Flash Cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0104] It should be understood that each block of a flowchart and / or block diagram, and combinations of blocks in a flowchart and / or block diagram, can be implemented by a computer program. These computer programs can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that instructions executable by the processor of the computer or other programmable data processing device generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer programs may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer programs may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] This embodiment also provides a computer storage medium, which includes at least one instruction that, when executed by a computer, implements the method steps of the rinsing control method for the medical imaging device of Embodiment 1.

[0108] By executing a computer storage medium containing at least one instruction, intelligent flushing control of medical imaging equipment is realized. It can automatically adjust the flushing speed according to the blurriness of the image without the need for manual intervention by the operator. This effectively solves the problems of slow response and complicated operation of existing medical imaging equipment flushing control technology, reduces the tediousness and uncertainty of manual operation, and allows medical imaging equipment to provide a clear surgical field of view in real time. This greatly improves the efficiency and reliability of medical imaging equipment during medical surgery, better ensures the normal progress of the surgery, and brings important technological innovation and practical application value to the medical field.

[0109] Similarly, for details not covered in this embodiment, please refer to Embodiment 1, Embodiment 2, and... Figures 1 to 2 The specific details will not be repeated here.

[0110] Example 4 This embodiment provides a medical imaging device, such as... Figure 3 As shown, it includes: A rinsing device used to perform the rinsing process; A speed sensor, which is communicatively connected to the rinsing device, is used to collect the rinsing speed of the rinsing device in real time during the rinsing process; An imaging device is used to acquire images in real time during the rinsing process of the rinsing device; The aforementioned rinsing control device for medical imaging equipment is communicatively connected to the speed sensor, the imaging device, and the rinsing device; used for: The system acquires the rinsing speed in real time from the speed sensor and monitors the image acquired in real time from the imaging device; it determines the blurriness of the acquired image and, based on the blurriness, sends a control signal to the rinsing device in real time to adjust the rinsing speed. The rinsing device is used to receive the control signal in real time and adjust the rinsing speed in real time according to the control signal, so that the blurriness of the acquired image re-monitored by the rinsing control device of the medical imaging equipment reaches the target blurriness.

[0111] In this embodiment, the medical imaging equipment, under the intelligent rinsing control of the rinsing device, can provide a clear surgical field of view without the need for manual intervention by the operator, greatly improving efficiency and reliability, and better ensuring the normal progress of the surgery.

[0112] Preferably, such as Figure 3 As shown, the speed sensor is specifically a motor speed sensor, and the rinsing device includes a rinsing assembly and a rinsing motor; The rinsing motor is communicatively connected to the rinsing control device of the medical imaging equipment and the motor speed sensor. The rinsing motor is also drive-connected to the rinsing assembly. The flushing motor is used to drive the flushing assembly to inject flushing fluid in real time to perform the flushing process; it is also used to receive the control signal sent by the flushing control device of the medical imaging equipment in real time, and adjust the driving signal for driving the flushing assembly to inject flushing fluid according to the control signal, so as to adjust the flushing speed of the flushing assembly during the flushing process. The motor speed sensor is used to detect the rotation speed of the flushing motor when it drives the flushing assembly to work in real time, and to obtain the flushing speed corresponding to the flushing assembly based on the real-time detected rotation speed.

[0113] The rinsing device with the above-mentioned structural design can achieve real-time feedback and closed-loop adjustment of rinsing speed under the control of the rinsing control device of the medical imaging equipment, thereby ensuring that the medical imaging equipment can always maintain a clear field of view.

[0114] Specifically, such as Figure 4 As shown, the rinsing assembly includes a rinsing fluid storage bag 1 and a rinsing conduit 2. These components are conventional components in rinsing devices, and their specific structures will not be described in detail here. Figure 4 In the diagram, 3 represents the peristaltic pump (i.e., the flushing motor), 4 represents the flushing fluid, and 5 represents the motor speed sensor.

[0115] Similarly, for details not covered in this embodiment, please refer to Embodiment 1, Embodiment 2, Embodiment 3, and... Figures 1 to 2 The specific details will not be repeated here.

[0116] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A washing control method for a medical imaging device, characterized in that, In a rinsing apparatus for configuring medical imaging equipment, the method includes: The rinsing speed of the rinsing device during the rinsing process is acquired in real time; The medical imaging device acquires images during the rinsing process in real time, and determines the blurriness of the acquired images; Based on the ambiguity, the rinsing speed of the rinsing device is adjusted in real time so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity.

2. The rinsing control method for medical imaging equipment according to claim 1, characterized in that, Based on the ambiguity, the rinsing speed of the rinsing device is adjusted in real time so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity, including: The blur level of the acquired image is determined by comparing the blur level with a preset blur range. Based on the blur level, the washing speed adjustment level of the acquired image is obtained by querying the preset blur level-washing speed adjustment level mapping table; The speed adjustment amount of the rinsing device is determined according to the rinsing speed adjustment level; According to the speed adjustment amount, the rinsing speed of the rinsing device is adjusted, and the update blur of the updated acquired image of the medical imaging device under the rinsing of the rinsing device after adjusting the rinsing speed is re-determined, so that the update blur reaches the target blur.

3. The rinsing control method for medical imaging equipment according to claim 2, characterized in that, The fuzziness levels include N first levels with fuzziness increasing sequentially; The flushing speed adjustment levels include N second levels with sequentially increasing speed adjustment amounts; In the fuzzy level-rinse speed adjustment level mapping table, N first levels correspond one-to-one with N second levels.

4. The rinsing control method for medical imaging equipment according to claim 3, characterized in that, For the kth second level, the corresponding speed adjustment amount satisfies: △v=α k ×dv; Where Δv is the speed adjustment amount corresponding to the kth second level, α k dv is the adjustment coefficient corresponding to the kth second level, and dv is the unit speed adjustment amount; k is an integer in the range [1, N]; α k+1 >α k And when k=1, α k =0; when k=N, α k ×dv=v max v max This is the maximum allowable adjustment amount.

5. The rinsing control method for a medical imaging device according to claim 1, characterized in that, Determining the blurriness of the acquired image includes: Acquire a clear reference image from the medical imaging device and calculate a reference gradient map corresponding to the clear reference image; Extract the real-time gradient map of the acquired image, and calculate the gradient decay mask based on the reference gradient map and the real-time gradient map; Extract the RGB color features of the acquired image, and calculate the red overload mask, saturation filter mask and chroma filter mask based on the RGB color features. The gradient attenuation mask, red excess mask, saturation filter mask, and chroma filter mask are merged to obtain a fused mask; The real-time gradient map and the reference gradient map are processed using the fusion mask, and the mean real-time gradient corresponding to the real-time gradient map and the mean reference gradient corresponding to the reference gradient map are calculated respectively. The blurriness of the acquired image is calculated based on the real-time gradient mean and the reference gradient mean.

6. The rinsing control method for a medical imaging device according to claim 5, characterized in that, The specific formula for calculating the blur of the acquired image is as follows: Blur_Lev ; Where Blur_Lev is the blur level of the acquired image, G t_mean and G t_ref_mean These are the real-time gradient mean and the reference gradient mean, respectively.

7. The rinsing control method for a medical imaging device according to claim 6, characterized in that, The formula for calculating the mean of the real-time gradient corresponding to the real-time gradient plot is as follows: ； The formula for calculating the mean of the reference gradient corresponding to the reference gradient map is as follows: ； Wherein, H and W are the height and width of the real-time gradient map, respectively, and the size of the real-time gradient map is the same as the size of the reference gradient map; (i,j) is the pixel coordinate, mask_c(i,j) is the value of the fusion mask at pixel coordinate (i,j), which is 0 or 1; G_t(i,j) is the gradient magnitude of the real-time gradient map at pixel coordinate (i,j), and Ref_grad(i,j) is the gradient magnitude of the reference gradient map at pixel coordinate (i,j).

8. The rinsing control method for a medical imaging device according to claim 5, characterized in that, The specific formula for calculating the fusion mask is as follows: ； Where mask_c(i,j) is the value of the fusion mask at pixel coordinate (i,j), mask_g(i,j), mask_r(i,j), mask_s(i,j) and mask_a(i,j) are the values ​​of the gradient attenuation mask, the red excess mask, the saturation filter mask and the chroma filter mask at pixel coordinate (i,j) respectively, and & represents the AND logical operation.

9. The rinsing control method for a medical imaging device according to claim 5, characterized in that, Based on the RGB color features, a red overload mask, a saturation filter mask, and a chroma filter mask are calculated, including: The red excess mask is calculated based on the RGB color features; The RGB color features are converted into HSV color features, and the saturation filter mask is calculated based on the HSV color features. The RGB color features are converted into LAB color features, and the chromaticity filter mask is calculated based on the LAB color features.

10. The rinsing control method for a medical imaging device according to claim 9, characterized in that, The specific formula for calculating the red excess mask is as follows: ； Where mask_r(i,j) is the value of the red overmask at pixel coordinates (i,j), and r ij g ij and b ij These represent the red, green, and blue feature component values ​​of the RGB color feature at pixel coordinates (i,j), respectively. min K is the threshold for the red feature. r_g K is the red-green relative proportion coefficient. r_b The red-blue relative ratio coefficient, & represents the AND logical operation; The specific formula for calculating the saturation filter mask is as follows: ； Where mask_s(i,j) is the value of the saturation filter mask at pixel coordinates (i,j), and s ij The saturation component value of the HSV color feature at pixel coordinates (i,j) is the HSV color feature. _max and HSV min These are the upper and lower limits of saturation, respectively. The specific formula for calculating the colorimetric filter mask is as follows: ； Where mask_a(i,j) is the value of the chroma filter mask at pixel coordinates (i,j), and a ij The LAB color feature is represented by its chromaticity component value at pixel coordinates (i,j). _max and LAB _min These are the upper and lower limits of chromaticity, respectively.

11. The rinsing control method for a medical imaging device according to claim 5, characterized in that, The gradient decay mask is calculated based on the reference gradient map and the real-time gradient map, including: The gradient magnitude at each pixel coordinate of the real-time gradient map is compared one by one with the gradient magnitude at the corresponding pixel coordinate of the reference gradient map to obtain a comparison result matrix. The gradient attenuation mask is obtained based on the comparison result matrix. For pixel coordinates (i,j), the specific formula for comparing the gradient magnitude of the real-time gradient map at pixel coordinates (i,j) with the gradient magnitude of the reference gradient at pixel coordinates (i,j) is as follows: ； Wherein, mask_g(i,j) is the value of the gradient decay mask at pixel coordinate (i,j), K_g is the empirical parameter of the gradient decay mask, and G_t(i,j) and Ref_grad(i,j) are the gradient magnitudes of the real-time gradient map and the reference gradient map at pixel coordinate (i,j), respectively.

12. A washing control system for a medical imaging device, characterized in that, The system, used in the rinsing control method for a medical imaging device as described in any one of claims 1 to 11, comprises: The speed detection module is used to acquire the rinsing speed of the rinsing device configured in the medical imaging equipment during the rinsing process in real time; An image monitoring module is used to monitor the images acquired by the medical imaging device during the rinsing process in real time and determine the blurriness of the acquired images; The speed adjustment module is used to adjust the rinsing speed of the rinsing device in real time according to the ambiguity, so that the ambiguity of the acquired image monitored after adjusting the rinsing speed reaches the target ambiguity.

13. A washing control device for a medical imaging equipment, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed, implements the method steps of the rinsing control method for a medical imaging device as described in any one of claims 1 to 11.

14. A medical imaging device, characterized in that, include: A rinsing device used to perform the rinsing process; A speed sensor, which is communicatively connected to the rinsing device, is used to collect the rinsing speed of the rinsing device in real time during the rinsing process; An imaging device is used to acquire images in real time during the rinsing process of the rinsing device; The rinsing control device for the medical imaging equipment as described in claim 13 is communicatively connected to the speed sensor, the imaging device, and the rinsing device. Used for: The system acquires the rinsing speed in real time from the speed sensor and monitors the image acquired in real time by the imaging device; it determines the blurriness of the acquired image and, based on the blurriness, sends a control signal to the rinsing device in real time to adjust the rinsing speed. The rinsing device is used to receive the control signal in real time and adjust the rinsing speed in real time according to the control signal, so that the blurriness of the acquired image re-monitored by the rinsing control device of the medical imaging equipment reaches the target blurriness.

15. The medical imaging device according to claim 14, characterized in that, The speed sensor is specifically a motor speed sensor, and the rinsing device includes a rinsing assembly and a rinsing motor. The rinsing motor is communicatively connected to the rinsing control device of the medical imaging equipment and the motor speed sensor. The rinsing motor is also drive-connected to the rinsing assembly. The flushing motor is used to drive the flushing assembly to inject flushing fluid in real time to perform the flushing process; it is also used to receive the control signal sent by the flushing control device of the medical imaging equipment in real time, and adjust the driving signal for driving the flushing assembly to inject flushing fluid according to the control signal, so as to adjust the flushing speed of the flushing assembly during the flushing process. The motor speed sensor is used to detect the rotation speed of the flushing motor when it drives the flushing assembly to work in real time, and to obtain the flushing speed corresponding to the flushing assembly based on the real-time detected rotation speed.

16. A computer storage medium, characterized in that, The computer storage medium includes at least one instruction that, when executed by a computer, implements the method steps of the rinsing control method for a medical imaging device as claimed in any one of claims 1 to 11.

Images