Blood oxygen saturation image generation method and device and computer device

Abstract

This application relates to a method, apparatus, and computer device for generating blood oxygen saturation images. The method includes: receiving a reflected beam obtained after a measurement beam is reflected by a target region; performing imaging processing on the reflected beam to obtain an image of the target region; determining the target coordinates of each first-link pixel in the target region image in a parameter lookup table based on three-channel data of each first-link pixel in the target region image; determining the blood oxygen saturation of each first-link pixel in the target region image based on the target coordinates; and generating a blood oxygen saturation image based on the blood oxygen saturation of each first-link pixel in the target region image. The blood oxygen saturation image generated by this method can provide overall spatial information of the target region in terms of blood oxygen saturation, improving the accuracy and generation efficiency of the blood oxygen saturation image.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus and computer device for generating blood oxygen saturation images. Background Technology

[0002] With the development of image processing technology, in routine digestive tract examinations and early cancer screenings, for areas with lesions, pre-lesions, or other areas that are difficult to observe directly with the naked eye, medical endoscopes with blood oxygen saturation measurement are usually used to obtain medical images. This allows for the acquisition of lesion location information, which in turn enables further diagnostic conclusions.

[0003] Current blood oxygen saturation measurement technologies, on the one hand, can usually only provide blood oxygen saturation data at a single location and cannot capture the spatial information of tissue oxygenation distribution as a whole. On the other hand, due to the characteristics of contrast agents, contrast imaging in fluorescence imaging usually has high requirements for examination time. Obviously, there is still a lot of room for improvement in the imaging efficiency of existing blood oxygen saturation images. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for generating blood oxygen saturation images that can improve the accuracy and generation efficiency of blood oxygen saturation images, in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for generating a blood oxygen saturation image, comprising:

[0006] The received measurement beam is the reflected beam obtained after the measurement beam is reflected by the target part. The measurement beam is a multi-spectral beam.

[0007] The reflected beam is imaged to obtain an image of the target area;

[0008] Based on the three-channel data of each first link pixel in the target area image, the target coordinates of each first link pixel in the target area image are determined in the parameter lookup table;

[0009] Based on the target coordinates, determine the blood oxygen saturation of each first link pixel in the target area image;

[0010] A blood oxygen saturation image is generated based on the blood oxygen saturation of each first link pixel in the target area image.

[0011] Secondly, this application also provides a blood oxygen saturation image generation device, comprising:

[0012] The endoscope module is used to receive the reflected beam obtained after the measurement beam is reflected by the target area. The measurement beam is a multi-spectral beam. The reflected beam is processed to obtain an image of the target area.

[0013] The processing module is used to determine the target coordinates of each first link pixel in the target area image in the parameter lookup table based on the three-channel data of each first link pixel in the target area image; determine the blood oxygen saturation of each first link pixel in the target area image based on the target coordinates; and generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target area image.

[0014] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement some or all of the steps described in any method of the first aspect of the embodiments of this application.

[0015] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements some or all of the steps described in any method of the first aspect of the embodiments of this application.

[0016] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements some or all of the steps described in any method of the first aspect of the embodiments of this application.

[0017] The aforementioned method, apparatus, computer device, computer-readable storage medium, and computer program product for generating blood oxygen saturation images receive a reflected beam obtained after a measurement beam is reflected from a target location. The measurement beam is a multispectral beam. The reflected beam is imaged to obtain an image of the target location. Based on the three-channel data of each first-link pixel in the target location image, the target coordinates of each first-link pixel in the target location image are determined in a parameter lookup table. Based on the target coordinates, the blood oxygen saturation of each first-link pixel in the target location image is determined. Based on the blood oxygen saturation of each first-link pixel in the target location image, a blood oxygen saturation image is generated. Using the blood oxygen saturation image generation method provided in this embodiment, the blood oxygen saturation of each first-link pixel in the target location image can be determined based on the three-channel data and parameter lookup table. Therefore, the generated blood oxygen saturation image can provide overall spatial information of the target location in terms of blood oxygen saturation, improving the accuracy and generation efficiency of the blood oxygen saturation image. Attached Figure Description

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

[0019] Figure 1 This is an application environment diagram of the blood oxygen saturation image generation method in one embodiment;

[0020] Figure 2 This is a flowchart illustrating a method for generating blood oxygen saturation images in one embodiment;

[0021] Figure 3 This is a schematic diagram comparing a target area image and a blood oxygen saturation image in one embodiment;

[0022] Figure 4 A schematic diagram of the absorbance curves of oxidized hemoglobin and reduced hemoglobin provided in one embodiment;

[0023] Figure 5 This is a schematic diagram of a parameter lookup table in one embodiment;

[0024] Figure 6 This is a structural block diagram of a blood oxygen saturation image generation device in one embodiment;

[0025] Figure 7 This is an internal structural diagram of a computer device in one embodiment;

[0026] Figure 8 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0028] The blood oxygen saturation image generation method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with medical device 104 via a network. A data storage system can store data that medical device 104 needs to process. The data storage system can be integrated into medical device 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. For example, medical device 104 can be an electronic endoscope capable of acquiring images of a target area. Further, the electronic endoscope can be an upper gastrointestinal endoscope or a lower gastrointestinal endoscope.

[0029] In one exemplary embodiment, such as Figure 2 As shown, a method for generating blood oxygen saturation images is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps 202 to 210. Wherein:

[0030] Step 202: Receive the reflected beam obtained after the measurement beam is reflected by the target part. The measurement beam is a multi-spectral beam.

[0031] Among them, the measuring beam refers to the beam emitted from the light source and illuminating the target area; the measuring beam is a multi-spectral beam, which can be used to excite the optical properties of the target area.

[0032] A reflected beam is a beam of light reflected back from a target area and received by the image sensor of the terminal. The reflected beam contains the optical response information of the target area to the measurement beam, thereby enabling the imaging of the target area and the determination of the blood oxygen saturation of the target area through the optical response information.

[0033] The target site can be a tissue site; for example, the target site can be the upper digestive tract, lower digestive tract, or other sites. Furthermore, the target site can be a tissue site of a human body or an animal.

[0034] Specifically, the measurement beam is a multispectral beam, meaning it can simultaneously emit beams of multiple different wavelengths. These different wavelengths can be continuous spectral bands or discrete beams of specific wavelengths. The wavelength range of the multiple beams in the measurement beam is determined by the optical characteristics of the target area.

[0035] Step 204: Perform imaging processing on the reflected beam to obtain an image of the target area.

[0036] The target site image can be a tissue site image; for example, it can be an image of the upper digestive tract, lower digestive tract, or other parts of the body. Furthermore, the target site image can be a tissue site image of a human body or an animal.

[0037] Specifically, imaging processing of the reflected beam means that the terminal's image sensor converts the received reflected beam from an optical signal into an electrical signal, and then digitizes the electrical signal through an analog-to-digital converter to form digital image data to obtain an image of the target area.

[0038] Step 206: Based on the three-channel data of each first link pixel in the target area image, determine the target coordinates of each first link pixel in the target area image in the parameter lookup table.

[0039] Among them, the three-channel data of each first link pixel refers to the red channel data (R), green channel data (G), and blue channel data (B) of each first link pixel, that is, the initial three-channel data of each first link pixel.

[0040] The parameter lookup table is a pre-built two-dimensional data lookup table stored in the terminal's register. Based on the three-channel data of each first-link pixel in the obtained target area image, the parameter lookup table determines the target coordinates of each first-link pixel within the lookup table, enabling the determination of the blood oxygen saturation of each first-link pixel based on the three-channel data of the target area image. Optionally, the parameter lookup table can be constructed using Monte Carlo Modeling of Light (MCML) simulation technology, a technique for simulating the interaction between light and tissue.

[0041] The parameter lookup table includes multiple blood oxygen saturation contour lines, and each blood oxygen saturation contour line can include multiple discretized known coordinates. Optionally, the parameter lookup table can include 11 blood oxygen saturation contour lines with blood oxygen saturation of 0%, 10%, 20%...100%, and each blood oxygen saturation contour line can include 15 known coordinates, thus the parameter lookup table contains 11*15=165 known coordinates. Specifically, the multiple blood oxygen saturation contour lines and the known coordinates on each blood oxygen saturation contour line in the parameter lookup table can be determined during the construction of the parameter lookup table. The known coordinates on each blood oxygen saturation contour line can be used as auxiliary data to determine the blood oxygen saturation of each first link pixel in the target area image.

[0042] In one exemplary embodiment, the parameter lookup table includes 11 blood oxygen saturation contour lines, and the difference in blood oxygen saturation between adjacent blood oxygen saturation contour lines is 10%.

[0043] Since the parameter lookup table includes 11 blood oxygen saturation contour lines, and the difference in blood oxygen saturation between adjacent blood oxygen saturation contour lines is 10%, it is easy to understand that the parameter lookup table in this embodiment includes 11 blood oxygen saturation contour lines with blood oxygen saturation of 0%, 10%, 20%...100%.

[0044] Optionally, each of the 11 blood oxygen saturation contour lines in this embodiment may also include 15 known coordinates, thus, the parameter lookup table in this embodiment contains 11*15=165 known coordinates.

[0045] Specifically, the target coordinates of each first link pixel in the parameter lookup table represent the coordinate position of each first link pixel in the parameter lookup table. Thus, based on the coordinate position and the multiple blood oxygen saturation contour lines included in the parameter lookup table, the target coordinates of each first link pixel in the parameter lookup table can be further determined.

[0046] Step 208: Based on the target coordinates, determine the blood oxygen saturation of each first link pixel in the target area image.

[0047] Among them, the blood oxygen saturation of each first link pixel is the real-time blood oxygen saturation of each first link pixel.

[0048] Specifically, when the parameter lookup table includes multiple blood oxygen saturation contour lines, and each blood oxygen saturation contour line includes multiple known coordinates, if the target coordinates of the first link pixel in the parameter lookup table coincide with the known coordinates, then the blood oxygen saturation corresponding to the blood oxygen saturation contour line corresponding to the known coordinates is directly determined as the blood oxygen saturation of the first link pixel; if the target coordinates of the first link pixel in the parameter lookup table are located outside the multiple blood oxygen saturation lines, that is, they do not coincide with any known coordinates, then the target coordinates need to be determined to further determine the blood oxygen saturation of the first link pixel.

[0049] Step 210: Generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target area image.

[0050] The process of generating the blood oxygen saturation image is performed pixel by pixel. That is to say, there is a one-to-one correspondence between each first link pixel in the target area image and each second link pixel in the blood oxygen saturation image. The image information of each second link pixel in the blood oxygen saturation image is determined by the blood oxygen saturation of the corresponding first link pixel in the target area image.

[0051] Specifically, the generated blood oxygen saturation image has the same image size as the target area image.

[0052] In the above-described method for generating a blood oxygen saturation image, a reflected beam is received after a measurement beam is reflected from a target location. The measurement beam is a multispectral beam. Imaging processing is performed on the reflected beam to obtain an image of the target location. Based on the three-channel data of each first-link pixel in the target location image, the target coordinates of each first-link pixel in the target location image are determined in a parameter lookup table. Based on the target coordinates, the blood oxygen saturation of each first-link pixel in the target location image is determined. Based on the blood oxygen saturation of each first-link pixel in the target location image, a blood oxygen saturation image is generated. Using the blood oxygen saturation image generation method provided in this embodiment, the blood oxygen saturation of each first-link pixel in the target location image can be determined based on the three-channel data and parameter lookup table. Therefore, the generated blood oxygen saturation image can provide overall spatial information of the target location in terms of blood oxygen saturation, improving the accuracy and generation efficiency of the blood oxygen saturation image.

[0053] In an exemplary embodiment, generating a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target region image includes:

[0054] Based on the allocation rules between blood oxygen saturation and three-channel data, the three-channel data of the second link pixel corresponding to the blood oxygen saturation of each first link pixel is determined.

[0055] The three-channel data of each first-link pixel is converted into three-channel data of the second-link pixel to obtain a blood oxygen saturation image including multiple second-link pixels; or...

[0056] Among multiple first link pixels, the first link pixel with blood oxygen saturation less than a preset threshold is identified as the target link pixel;

[0057] Based on the allocation rules between blood oxygen saturation and three-channel data, the three-channel data of the second link pixel corresponding to the blood oxygen saturation of each target link pixel is determined.

[0058] The three-channel data of each target link pixel is converted into the three-channel data of the second link pixel, resulting in a blood oxygen saturation image including multiple first link pixels with blood oxygen saturation greater than or equal to a preset threshold and multiple second link pixels.

[0059] The allocation rule between blood oxygen saturation and the three-channel data can be pre-set and stored in the terminal's registers, with different blood oxygen saturation levels corresponding to different three-channel data. Optionally, one blood oxygen saturation range can correspond to one channel of data. For example, a blood oxygen saturation of 0-10% corresponds to one three-channel data, a blood oxygen saturation of 10-20% corresponds to one three-channel data, and so on, with a blood oxygen saturation of 90-100% corresponding to one three-channel data.

[0060] Specifically, the allocation rule between blood oxygen saturation and the three-channel data is used to assign a corresponding color to each first-link pixel according to its blood oxygen saturation after the analysis and calculation of the blood oxygen saturation of each first-link pixel in the target area image, thereby obtaining multiple second-link pixels with reassigned colors. In other words, the allocation rule between blood oxygen saturation and the three-channel data can essentially be understood as a color mapping table for blood oxygen saturation. Therefore, according to the color mapping table, first-link pixels with different blood oxygen saturations are reassigned corresponding colors to obtain multiple second-link pixels with reassigned colors. In other words, this color mapping table is used to map the blood oxygen saturation of each first-link pixel to the color of each second-link pixel in the blood oxygen saturation image, thereby generating a pseudo-color image of the blood oxygen saturation image.

[0061] Specifically, the three-channel data of the first link pixel is used to present the true color information of the target area; the three-channel data of the second link pixel is used to present the blood oxygen saturation information of the target area. The second link pixel is a pseudo-color pixel, and its color information is not the true color information of the target area.

[0062] In one exemplary embodiment, in the allocation rule between blood oxygen saturation and three-channel data, there is a negative correlation between the magnitude of blood oxygen saturation and the magnitude of the color temperature of the blood oxygen saturation image.

[0063] Color temperature is a physical quantity that describes the color characteristics of a light source. At lower color temperatures, the light beam has a warmer hue, such as orange or red; at higher color temperatures, the light beam has a cooler hue, such as blue or purple.

[0064] In an exemplary embodiment, the allocation rule between blood oxygen saturation and three-channel data is as follows: when the blood oxygen saturation of the first link pixel is 0-10%, the corresponding three-channel data represents the color of the second link pixel as purple; when the blood oxygen saturation of the first link pixel is 10-20%, the corresponding three-channel data represents the color of the second link pixel as blue; when the blood oxygen saturation of the first link pixel is 20-30%, the corresponding three-channel data represents the color of the second link pixel as bright blue; when the blood oxygen saturation of the first link pixel is 30-40%, the corresponding three-channel data represents the color of the second link pixel as cyan; when the blood oxygen saturation of the first link pixel is 40-50%, the corresponding three-channel data... The color representing the second link pixel is green; when the blood oxygen saturation of the first link pixel is 50-60%, the corresponding three-channel data represents the color of the second link pixel as yellow-green; when the blood oxygen saturation of the first link pixel is 60-70%, the corresponding three-channel data represents the color of the second link pixel as yellow; when the blood oxygen saturation of the first link pixel is 70-80%, the corresponding three-channel data represents the color of the second link pixel as orange; when the blood oxygen saturation of the first link pixel is 80-90%, the corresponding three-channel data represents the color of the second link pixel as dark orange; when the blood oxygen saturation of the first link pixel is 90-100%, the corresponding three-channel data represents the color of the second link pixel as red.

[0065] Optionally, the preset threshold can be manually set beforehand and used as a critical dividing point to characterize whether there is an abnormality in the numerical value of blood oxygen saturation. Blood oxygen saturation below the preset threshold indicates that the blood oxygen saturation of the first link pixel is abnormal, and the pixel location with abnormal blood oxygen saturation indicates that there may be a lesion at that location. Conversely, blood oxygen saturation greater than or equal to the preset threshold indicates that the blood oxygen saturation of the first link pixel is normal, and the pixel location with normal blood oxygen saturation indicates that the tissue at that location is in a normal and healthy state. For example, the preset threshold can be blood oxygen saturation of 50% or other values. Based on this, target link pixels with blood oxygen saturation below the preset threshold are the first link pixels in the blood oxygen saturation image that have abnormal blood oxygen saturation values. That is to say, target link pixels are first link pixels that may have lesions and therefore need to be specially observed.

[0066] Optionally, the preset threshold can also be determined based on disease indicators in pathology; that is, the preset threshold can be determined based on the target clinical state. For example, the target clinical symptom can include mild hypoxemia, moderate hypoxemia, and severe hypoxemia. Therefore, the size of the preset threshold will vary depending on the target clinical symptom. Specifically, the preset threshold for mild hypoxemia is lower than that for moderate hypoxemia, and the preset threshold for moderate hypoxemia is lower than that for severe hypoxemia. It can be seen that when the size of the preset threshold is determined based on the target clinical state that medical staff wish to observe, it is beneficial to generate blood oxygen saturation images with different display effects, flexibly meeting the needs of medical staff under different observation purposes.

[0067] Specifically, based on the allocation rules between blood oxygen saturation and three-channel data, the three-channel data of the second-link pixel corresponding to the blood oxygen saturation of each first-link pixel is determined. This involves determining the three-channel data of the second-link pixel corresponding to all first-link pixels in the target area image. The three-channel data of each first-link pixel is then converted into the three-channel data of the second-link pixel to obtain a blood oxygen saturation image including multiple second-link pixels. This involves converting all the three-channel data of the first-link pixels in the target area image into the corresponding three-channel data of the second-link pixels. Thus, the blood oxygen saturation image obtained at this time can visually and intuitively represent the blood oxygen saturation of all second-link pixels through the three-channel data of all second-link pixels.

[0068] Specifically, based on the allocation rules between blood oxygen saturation and three-channel data, the three-channel data of the second link pixel corresponding to the blood oxygen saturation of each target link pixel is determined. This identifies the three-channel data corresponding to the first link pixels in the target area image where blood oxygen saturation is abnormal. The three-channel data of each target link pixel is converted into the three-channel data of the second link pixels, resulting in a blood oxygen saturation image including multiple first link pixels with blood oxygen saturation less than or equal to a preset threshold and multiple second link pixels. This process converts the three-channel data of the first link pixels in the target area image where blood oxygen saturation is abnormal into the second link pixels. The three-channel data of the link pixels result in a blood oxygen saturation image that includes multiple first link pixels with normal blood oxygen saturation and multiple second link pixels with abnormal blood oxygen saturation. The three-channel data of the second link pixels with abnormal blood oxygen saturation can be used to show the abnormal blood oxygen saturation. Based on the blood oxygen saturation image, blood oxygen saturation imaging is performed only on the image pixels with abnormal blood oxygen saturation, while the pixels corresponding to the normal parts are processed according to the white light mode imaging. Therefore, it is possible to visually and intuitively show the areas with normal blood oxygen saturation and the areas with abnormal blood oxygen saturation.

[0069] It is easy to understand that, since the three-channel data of each second-link pixel in the blood oxygen saturation image is obtained through the allocation rule between blood oxygen saturation and the three-channel data, that is, the three-channel data of each second-link pixel is not the true channel data of the target area image, the blood oxygen saturation image is essentially a pseudo-color image. Furthermore, since the blood oxygen saturation of each first-link pixel is the real-time blood oxygen saturation of that first-link pixel, the blood oxygen saturation image is a real-time blood oxygen saturation image.

[0070] For example, such as Figure 3 As shown in (a), this is an image of the target area, as follows: Figure 3 As shown in (b), the blood oxygen saturation image is obtained after converting the three-channel data of each first link pixel in the target area image into the three-channel data of the second link pixel. It can be seen that, based on the blood oxygen saturation image, the distribution of blood oxygen saturation in the target area corresponding to the target area image can be intuitively observed from the overall spatial perspective. That is to say, the blood oxygen saturation determination method provided in this embodiment can determine the blood oxygen saturation of all first link pixels; therefore, the blood oxygen saturation image obtained in this embodiment has overall spatial information on blood oxygen saturation.

[0071] In this embodiment, the blood oxygen saturation image can either reflect the blood oxygen saturation of all first-link pixels, thus meeting the need to observe the overall blood oxygen saturation of the observed area; or it can only reflect the blood oxygen saturation of some first-link pixels with abnormal blood oxygen saturation, thus meeting the need to focus on observing the blood oxygen saturation of lesions. Based on different blood oxygen saturation image generation methods, the needs of different observation situations can be met, thereby improving the relevance and flexibility of blood oxygen saturation images in different application scenarios.

[0072] Optionally, the allocation rule between blood oxygen saturation and the three-channel data can be presented not only through the color temperature of the blood oxygen saturation image but also through grayscale levels. Thus, in an exemplary embodiment, the allocation rule between blood oxygen saturation and the three-channel data shows a positive correlation between the magnitude of blood oxygen saturation and the magnitude of the grayscale level. For example, when blood oxygen saturation is 100%, the three-channel data is presented as white with a grayscale level of 255; conversely, when blood oxygen saturation is 0%, the three-channel data is presented as black with a grayscale level of 0. Presenting different blood oxygen saturation levels using different grayscale levels effectively avoids the interference of color on visual effects, allowing for a simpler and more accurate determination of the overall spatial information of blood oxygen saturation.

[0073] In an exemplary embodiment, the allocation rules between blood oxygen saturation and three-channel data include multiple allocation rules between blood oxygen saturation ranges and three-channel data, with a one-to-one correspondence between the blood oxygen saturation ranges and the three-channel data; after determining the blood oxygen saturation of each first link pixel in the target area image, the above method further includes:

[0074] Based on the blood oxygen saturation of multiple first link pixels, determine the maximum and minimum blood oxygen saturation.

[0075] Determine the difference in blood oxygen saturation between the maximum and minimum blood oxygen saturation;

[0076] When the difference in blood oxygen saturation is less than a preset difference, an adjustment coefficient for the allocation rule is generated based on the difference in blood oxygen saturation.

[0077] Based on the allocation rule adjustment coefficient, the number of blood oxygen saturation ranges and the number of three-channel data included in the allocation rule between blood oxygen saturation and three-channel data are increased to obtain a new allocation rule between blood oxygen saturation and three-channel data. The new allocation rule between blood oxygen saturation and three-channel data includes multiple new allocation rules between blood oxygen saturation ranges and new three-channel data, and there is a one-to-one correspondence between the new blood oxygen saturation ranges and the new three-channel data.

[0078] The above-mentioned allocation rules based on blood oxygen saturation and three-channel data determine the three-channel data of the second-link pixel corresponding to the blood oxygen saturation of each first-link pixel, including:

[0079] Based on the new allocation rule between blood oxygen saturation and three-channel data, the three-channel data of the second link pixel corresponding to the blood oxygen saturation of each first link pixel is determined.

[0080] Among them, there is a negative correlation between the difference in blood oxygen saturation and the allocation rule adjustment coefficient. That is to say, the closer the maximum blood oxygen saturation is to the minimum blood oxygen saturation, the larger the generated allocation rule adjustment coefficient will be.

[0081] Specifically, the larger the allocation rule adjustment coefficient, the greater the effect on increasing the number of blood oxygen saturation ranges in the allocation rule between blood oxygen saturation and three-channel data. Similarly, the greater the effect on increasing the number of channel data in the allocation rule between blood oxygen saturation and three-channel data. In other words, the larger the allocation rule adjustment coefficient, the greater the number of new blood oxygen saturation ranges included in the new allocation rule between blood oxygen saturation and three-channel data, and the greater the number of new three-channel data.

[0082] Specifically, the number of blood oxygen saturation ranges in the allocation rules between blood oxygen saturation and three-channel data can be increased. Originally, there were 10 blood oxygen saturation ranges, including 0-10%, 10-20%...90-100%, which can be increased to 20 blood oxygen saturation ranges, including 0-5%, 5-10%...95-100%.

[0083] Optionally, in the new allocation rule between blood oxygen saturation and three-channel data, there is a negative correlation between the magnitude of blood oxygen saturation and the magnitude of the color temperature of the blood oxygen saturation image.

[0084] For example, if the maximum blood oxygen saturation of multiple first link pixels is 98% and the minimum blood oxygen saturation is 93%, and the allocation rule between blood oxygen saturation and three-channel data indicates that the color of the second link pixel corresponding to a blood oxygen saturation of 90-100% is red, then the generated blood oxygen saturation image will appear as a sea of ​​red. Obviously, this makes it difficult to visually observe the true state of blood oxygen saturation. Therefore, a new allocation rule between blood oxygen saturation and three-channel data is constructed by adjusting the allocation rule coefficient. In this new allocation rule, the color of the second link pixel corresponding to a blood oxygen saturation of 95-100% is red, and the color of the second link pixel corresponding to a blood oxygen saturation of 90-95% is dark orange. In this case, the blood oxygen saturation of the two first link pixels can be distinguished by the color of the two second link pixels.

[0085] In this embodiment, when the difference between the maximum and minimum blood oxygen saturation is small, a channel data adjustment coefficient is generated based on the blood oxygen saturation difference. This coefficient is then used to increase the number of blood oxygen saturation ranges and the number of three-channel data points included in the allocation rule between blood oxygen saturation and the three-channel data, resulting in a new allocation rule between blood oxygen saturation and the three-channel data. Since this new allocation rule includes more blood oxygen saturation ranges and corresponding three-channel data points, when the difference in blood oxygen saturation between the first link pixels in the target area image is small, the mapping relationship between the blood oxygen saturation range and the three-channel data can be expanded to allow the blood oxygen saturation image to reflect the distribution of blood oxygen saturation in the overall space with more subtle color changes.

[0086] In one exemplary embodiment, the method further includes:

[0087] Push the target area image and / or blood oxygen saturation image to the display interface.

[0088] The display interface can be a display device connected to the terminal. Specifically, the terminal pushes the image of the target area and / or the blood oxygen saturation image to the display interface of the display device. Optionally, the display device can be a monitor provided for medical personnel to observe the images.

[0089] Optionally, the target area image and the blood oxygen saturation image displayed on the display interface can each have different display sizes. For example, a large and a small display size can be used to achieve a "picture-in-picture" effect. For instance, if the display size of the blood oxygen saturation image is larger than that of the target area image, then the larger blood oxygen saturation image can be focused on for observation, allowing medical staff to determine the location of the lesion based on the more visualized blood oxygen saturation image.

[0090] Optionally, the target area image and blood oxygen saturation image displayed in the real interface may or may not overlap, depending on the specific actual needs.

[0091] In this embodiment, the terminal can push the target area image or blood oxygen saturation image to the display device for display separately, or it can push both the target area image and the blood oxygen saturation image to the display device for display simultaneously. Furthermore, the blood oxygen saturation image can be a complete pseudo-color image in which all second link pixels are used to represent blood oxygen saturation, or it can be a partial pseudo-color image in which only some target link pixels with abnormal blood oxygen saturation are used to represent blood oxygen saturation. Thus, through a targeted and flexible image display method, the needs of medical staff under different observation purposes can be met.

[0092] In this embodiment, the target area image and the blood oxygen saturation image are displayed. By displaying the two data links simultaneously, the flexibility of image display is achieved, thereby enabling medical staff to more intuitively understand the blood oxygen saturation distribution of the target area through image comparison.

[0093] In an exemplary embodiment, after obtaining an image of the target region including a plurality of first link pixels, the above method further includes:

[0094] The target area image is copied to obtain two target area images;

[0095] Among the two target area images, one target area image is used for display push, and the other target area image is used to generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel.

[0096] When the target area image is copied, there will be an original image and a copy of the target area image. Therefore, after copying, two target area images will be obtained.

[0097] Specifically, a target area image is used for display push, that is, the target area image used for display push is pushed to the display interface of the display device so that medical staff can perform high-visibility illumination observation of the target area based on the target area image.

[0098] Specifically, another target area image is used to generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel. That is, the blood oxygen saturation of each first link pixel in the target area image is determined by three-channel data calculation and analysis, thereby generating a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target area image.

[0099] Specifically, when a target region image is determined to be used to generate a blood oxygen saturation image based on the blood oxygen saturation of each of its first link pixels, firstly, the three-channel data of each of the first link pixels in the target region image are determined, and the target coordinates of each of the first link pixels in the target region image are determined in the parameter lookup table. Then, based on the target coordinates, the blood oxygen saturation of each of the first link pixels in the target region image is determined. Finally, based on the blood oxygen saturation of each of the first link pixels in the target region image, a blood oxygen saturation image is generated.

[0100] In an exemplary embodiment, the above-described imaging processing of the reflected beam to obtain a target area image includes: imaging the reflected beam to obtain a target area image; copying the target area image to obtain a first target area image and a second target area image; the above-described conversion of the three-channel data of each first link pixel point into the three-channel data of the second link pixel point to obtain a blood oxygen saturation image including multiple second link pixels includes: converting the three-channel data of each first link pixel point in the first target area image into the three-channel data of the corresponding second link pixel point to obtain a blood oxygen saturation image; the above-described conversion of the three-channel data of each target link pixel point into the three-channel data of the second link pixel point to obtain... Obtaining a blood oxygen saturation image comprising multiple first link pixels with blood oxygen saturation greater than or equal to a preset threshold and multiple second link pixels includes: converting the three-channel data of each target link pixel in the first target region image into the three-channel data of the second link pixels to obtain a blood oxygen saturation image comprising multiple first link pixels with blood oxygen saturation greater than or equal to a preset threshold and multiple second link pixels; the aforementioned pushing the target region image and / or blood oxygen saturation image to the display interface includes: after obtaining the first target region image and the second target region image, pushing the second target region image to the display interface; after obtaining the blood oxygen saturation image, pushing the blood oxygen saturation image to the display interface.

[0101] In this embodiment, by copying the target area image obtained from the imaging process, one of the target area images can be quickly displayed to provide medical personnel with high-visibility illumination observation. Simultaneously, the other target area image is used to convert the three-channel data of the first link pixels into target coordinates in a parameter lookup table, thereby determining the blood oxygen saturation of each first link pixel through the target coordinates. Thus, a blood oxygen saturation image is generated based on the other target area image. Obviously, in this embodiment, after obtaining two target area images through copying, one target area image is used for display, and the other target area image is used to analyze and calculate blood oxygen saturation to generate a blood oxygen saturation image. It can be seen that the dual-parallel processing method based on two target area images can simultaneously improve the display efficiency of the target area image and the generation efficiency of the blood oxygen saturation image.

[0102] In an exemplary embodiment, the reflected beam obtained after the receiving measurement beam is reflected by the target location includes:

[0103] Based on an image sensor equipped with a color filter array, the reflected beam obtained after the measurement beam is reflected by the target part is received;

[0104] The color filter array includes a blue filter for passing blue light, two green filters for passing green light, and a red filter for passing red light; the color filter array is 2*2 in size, and the two green filters are not adjacent to each other.

[0105] The image sensor can be a complementary metal-oxide-semiconductor (CMOS) image sensor or a charge-coupled device (CCD) image sensor.

[0106] Specifically, the color filter array can be a Bayer array. Since the color filter array includes one blue filter, one red filter, and two green filters, the image sensor can simultaneously acquire the blue channel data, red channel data, and green channel data of the target area at the same time. Furthermore, based on the three color channel data at the same time, the target area image and blood oxygen saturation image generated in this embodiment are both real-time images, and neither the target area image nor the blood oxygen saturation image exhibits any color shift artifacts.

[0107] Specifically, since the human eye is more sensitive to green channel data, in order to obtain a higher resolution image of the target area to better simulate the visual effect of the human eye, the number of green filters needs to be greater than the number of blue filters and red filters.

[0108] Specifically, since the size of the color filter array is 2*2 and the two green filters are not adjacent, the two green filters are diagonally positioned in the color filter array. That is to say, the two green filters only have a common point, but no common edge.

[0109] In this embodiment, based on an image sensor equipped with a color filter array, the reflected beam obtained after the measurement beam is reflected by the target part is received. Thus, the generated target part image has three-channel data at the same time. Since the color filter array includes a blue filter for passing blue light, two green filters for passing green light, and a red filter for passing red light, the blue channel data, green channel data, and red channel data in the target part image can be obtained separately, thereby improving the accuracy and determination efficiency of the target coordinates of each first link pixel in the target part image in the parameter lookup table.

[0110] In an exemplary embodiment, the above-described imaging processing of the reflected beam to obtain an image of the target area includes:

[0111] An initial part image is generated based on the three-channel data of the reflected beam;

[0112] Dark current correction and bad pixel correction are performed on the initial part image to obtain the corrected initial part image;

[0113] The corrected initial part image is de-mosaiced to obtain the target part image including multiple first link pixels.

[0114] Dark current correction is an image correction method used to reduce or eliminate the impact of dark current, caused by thermal noise inherent in the image sensor under no-light conditions, on image quality. Specifically, dark current correction involves recording the image sensor's output image under no-light conditions—a dark current reference image—and then using this reference image to perform noise reduction on the initial image.

[0115] Defect pixel correction is an image correction method used to identify and correct dead pixels on an image sensor that do not respond to light or consistently output incorrect signals. Specifically, the process involves detecting these dead pixels and replacing their three-channel data with the three-channel data of the surrounding pixels to avoid noticeable display anomalies in the final image.

[0116] Demosaicing is used to convert the incomplete color corrected initial part image into a target part image that displays full RGB color. In other words, demosaicing of the corrected initial part image can ensure that each first link pixel in the target part image has color channel data.

[0117] In an exemplary embodiment, the above-described de-mosaic processing of the corrected initial part image to obtain a target part image including multiple first link pixels includes: performing de-mosaic processing on the corrected initial part image to obtain a mosaic-processed initial part image; and performing image adjustment processing on the mosaic-processed initial part image to obtain a target part image including multiple first link pixels.

[0118] Image adjustment processing may include at least one of the following: white balance processing, tone mapping processing, dehazing processing, sharpening processing, gamma correction processing, color adjustment processing, noise reduction processing, contrast adjustment processing, and 3D-LUT processing.

[0119] In this embodiment, dark current correction and bad pixel correction are performed on the initial part image generated based on the three-channel data of the reflected beam to obtain a corrected initial part image. Then, the corrected initial part image is subjected to de-mosaic processing to obtain a target part image including multiple first link pixels. Thus, noise reduction and bad pixel removal can be performed on the initial part image through dark current correction and bad pixel correction, and color filling can be performed on the corrected initial part image through de-mosaic processing. This ensures that the final target part image has high image quality. Furthermore, based on the target part image with complete spatial information, the blood oxygen saturation of each first link pixel in the target part image can be accurately determined, avoiding the undesirable situation where the overall spatial information of blood oxygen saturation cannot be accurately determined due to image quality issues.

[0120] like Figure 4 As shown, it can be seen that oxyhemoglobin (HbO2) and deoxyhemoglobin (Hb) have different absorbance for different wavelengths of light.

[0121] Specifically, in the narrowband blue light of the 467±5nm wavelength range, there is a significant difference in absorbance between oxyhemoglobin and deoxyhemoglobin. According to the formula for the absorption coefficient of hemoglobin: Where C b Represented as the fraction of blood volume in a tissue; μ aHbO2 and μ aHb S represents the absorption coefficients of oxyhemoglobin and deoxyhemoglobin, respectively. t O2 represents the oxygen saturation of blood in tissues. It can be seen that the narrow-band blue light in the measurement beam can acquire information on the oxygen saturation and blood volume fraction of the target area.

[0122] Specifically, in the broadband green light band of 546±40nm, the absorbance difference between oxyhemoglobin and deoxyhemoglobin can be approximately canceled out. That is to say, under narrowband green light, the absorbance of the two can be regarded as equal. Furthermore, as can be seen from the above formula for the absorption coefficient of hemoglobin, the absorption coefficient of hemoglobin only changes with the blood volume fraction and is not related to the magnitude of blood oxygen saturation. Therefore, the broadband green light in the measurement beam is mainly used to obtain the blood volume fraction of the target site.

[0123] Specifically, in the narrowband red light of 627±10nm, although there is a difference in absorbance between oxyhemoglobin and deoxyhemoglobin, the absorbance of both is very low at this time. Therefore, it can be considered that the absorbance of both is rarely affected by blood volume fraction and blood oxygen saturation under narrowband red light. Thus, narrowband red light is mainly used as a reference channel data signal in the process of generating images of the target area, so as to correct the brightness changes caused by the distance changes between the medical device and the tissue area based on the reference channel data signal.

[0124] It can be seen that the measurement beam mainly obtains blood oxygen saturation information of the target area through its narrow-band blue light.

[0125] Based on this, in an exemplary embodiment, the measurement beam includes narrowband blue light in the 465±5nm or 470±5nm band, broadband green light in the 540±20nm band, and narrowband red light in the 620±10nm band.

[0126] Optionally, the wavelength of the narrowband blue light in the measurement beam can be 465±2nm or 467±3nm. Optionally, the wavelength of the broadband green light in the measurement beam can be 540±5nm or 540±10nm. Optionally, the wavelength of the narrowband red light in the measurement beam can be 620±5nm or 620±8nm.

[0127] In this embodiment, since the measurement of blood oxygen saturation depends on the absorption coefficient of light in a specific wavelength band, and the absorption and scattering coefficients of different tissue parts are closely related to the wavelength band, by strictly controlling the specific wavelength bands of different colors of light in the measurement beam used to acquire the target part image, the accuracy of the three-channel data of the acquired target part image can be ensured, thereby further ensuring the accuracy and reliability of the blood oxygen saturation of each first link pixel point.

[0128] In an exemplary embodiment, determining the target coordinates of each first link pixel in the target region image in the parameter lookup table based on the three-channel data of each first link pixel in the target region image includes:

[0129] Based on the whiteboard image acquired by visible light, the three-channel data of each first link pixel in the target area image are corrected to obtain the corrected three-channel data of each first link pixel. The corrected three-channel data includes the corrected blue channel data, the corrected green channel data, and the corrected red channel data.

[0130] Determine the first ratio between the corrected red channel data and the corrected green channel data of each first link pixel, and the second ratio between the corrected blue channel data and the corrected green channel data of each first link pixel;

[0131] Take the logarithm of the first ratio and the second ratio corresponding to each first link pixel point to obtain the first signal ratio and the second signal ratio corresponding to each first link pixel point;

[0132] Based on the first signal ratio and the second signal ratio of each first link pixel, the target coordinates of each first link pixel in the parameter lookup table are obtained.

[0133] The whiteboard image is pre-captured based on visible light and stored in the terminal's register. The resolution of the whiteboard image is 1080*1440 or 4096*2160. The whiteboard image is created by pre-capturing a standard whiteboard using medical equipment. The color rendering index of the whiteboard image can be greater than or equal to 90.

[0134] Specifically, the first signal ratio is mainly used as a reference signal to correct for changes in illumination caused by changes in distance between the medical device and the tissue site; the second signal ratio is mainly used to calculate the blood oxygen saturation information contained in the image information of the first link pixel.

[0135] For example, the blue channel data, green channel data, and red channel data included in the three-channel data of each first link pixel in the target area image are represented as B1, G1, and R1, respectively; the white board blue channel data, white board green channel data, and white board red channel data in the white board image are represented as B0, G0, and R0, respectively; and the corrected blue channel data, corrected green channel data, and corrected red channel data are represented as B1, G1, and R1, respectively. 校 G 校 and R 校 Then B 校 =B1 / B0, G 校 =G1 / G0, R 校 =R1 / R0, therefore, the first signal ratio = ln(R 校 / G 校 The second signal ratio = ln(B) 校 / G 校 ).

[0136] In this embodiment, the three-channel data of each first link pixel in the target area image is corrected based on the whiteboard image acquired by visible light. In this way, color deviations caused by external factors such as the image sensor, measurement beam, or tissue characteristics of the medical device that acquired the target area image can be corrected. This ensures that the measurement of blood oxygen saturation is not affected by these external factors and ensures the accuracy of the generated blood oxygen saturation image.

[0137] In an exemplary embodiment, obtaining the target coordinates of each first link pixel in the parameter lookup table based on the first signal ratio and the second signal ratio of each first link pixel includes:

[0138] Obtain the coordinates of a preset number of points on each blood oxygen saturation contour line in the parameter lookup table;

[0139] Based on the binary search method, among the coordinates of a preset number of points, determine the abscissas of the two first coordinates that are closest to the first signal ratio of each first link pixel, and determine the abscissa of each first link pixel in the parameter lookup table based on the abscissas of the two first coordinates.

[0140] Based on the binary search method, among the coordinates of a preset number of points other than the first coordinate, determine the ordinates of the two second coordinates that are closest to the second signal ratio of each first link pixel, and determine the ordinate of each first link pixel in the parameter lookup table based on the ordinates of the two second coordinates.

[0141] Based on the x-coordinate and y-coordinate of each first link pixel in the parameter lookup table, the target coordinates of each first link pixel in the parameter lookup table are determined.

[0142] In an exemplary embodiment, the above-mentioned determination of the blood oxygen saturation of each first link pixel in the target area image based on the target coordinates includes: using a linear interpolation calculation method in a parameter lookup table to determine the blood oxygen saturation of each first link pixel in the target area image based on the target coordinates.

[0143] For example, such as Figure 5 The figure shown is a schematic diagram of a parameter lookup table provided in this embodiment. The parameter lookup table includes 11 blood oxygen saturation contour lines. The horizontal axis X of the parameter lookup table represents the magnitude of the first signal ratio, and the vertical axis Y represents the magnitude of the second signal ratio.

[0144] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0145] Based on the same inventive concept, this application also provides a blood oxygen saturation image generation apparatus for implementing the blood oxygen saturation image generation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more blood oxygen saturation image generation apparatus embodiments provided below can be found in the limitations of the blood oxygen saturation image generation method described above, and will not be repeated here.

[0146] In one exemplary embodiment, such as Figure 6 As shown, a blood oxygen saturation image generation device is provided, including: an endoscope module 602 and a processing module 604, wherein:

[0147] The endoscope module 602 is used to receive the reflected beam obtained after the measurement beam is reflected by the target area. The measurement beam is a multi-spectral beam. The reflected beam is processed to obtain an image of the target area.

[0148] The processing module 604 is used to determine the target coordinates of each first link pixel in the target region image in the parameter lookup table based on the three-channel data of each first link pixel in the target region image; determine the blood oxygen saturation of each first link pixel in the target region image based on the target coordinates; and generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target region image.

[0149] In an exemplary embodiment, the processing module 604 is further configured to: determine the three-channel data corresponding to the blood oxygen saturation of each first link pixel based on the allocation rules between blood oxygen saturation and three-channel data; convert the three-channel data of each first link pixel into three-channel data of a second link pixel to obtain a blood oxygen saturation image including multiple second link pixels; or, determine the first link pixel with blood oxygen saturation greater than a preset threshold as the target link pixel among the multiple first link pixels; determine the three-channel data corresponding to the blood oxygen saturation of each target link pixel based on the allocation rules between blood oxygen saturation and three-channel data; convert the three-channel data of each target link pixel into three-channel data of a second link pixel to obtain a blood oxygen saturation image including multiple first link pixels with blood oxygen saturation less than or equal to a preset threshold and multiple second link pixels.

[0150] In an exemplary embodiment, the above-described device further includes a display module 606, which is used to push the target area image and / or blood oxygen saturation image to the display interface.

[0151] In one exemplary embodiment, in the allocation rule between blood oxygen saturation and three-channel data, there is a negative correlation between the magnitude of blood oxygen saturation and the magnitude of the color temperature of the blood oxygen saturation image.

[0152] In an exemplary embodiment, the endoscope module 602 is used to receive a reflected beam obtained after the measurement beam is reflected by the target part based on an image sensor provided with a color filter array; wherein, the color filter array includes a blue filter for passing blue light, two green filters for passing green light, and a red filter for passing red light; the size of the color filter array is 2*2, and the two green filters are not adjacent.

[0153] In an exemplary embodiment, the endoscope module 602 is further configured to generate an initial part image based on the three-channel data of the reflected beam; the processing module 604 is further configured to perform dark current correction and bad pixel correction on the initial part image to obtain a corrected initial part image; and to perform de-mosaic processing on the corrected initial part image to obtain a target part image including multiple first link pixels.

[0154] In an exemplary embodiment, the measurement beam includes narrowband blue light in the 465±5nm or 470±5nm band, broadband green light in the 540±20nm band, and narrowband red light in the 620±10nm band.

[0155] In one exemplary embodiment, the parameter lookup table includes 11 blood oxygen saturation contour lines, and the difference in blood oxygen saturation between adjacent blood oxygen saturation contour lines is 10%.

[0156] In an exemplary embodiment, after obtaining a target part image including multiple first link pixels, the processing module 604 is further configured to copy the target part image to obtain two target part images; wherein, in the two target part images, one target part image is used for display push, and the other target part image is used to generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel.

[0157] In an exemplary embodiment, the processing module 604 sends the target area image for display push to the display module 606 for display push; the processing module 604 generates a blood oxygen saturation image based on the target area image for generating a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel.

[0158] Each module in the aforementioned blood oxygen saturation image generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0159] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores parameter lookup table data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for generating blood oxygen saturation images.

[0160] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for generating blood oxygen saturation images. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0161] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0162] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0163] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0164] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0166] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0167] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0168] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating blood oxygen saturation images, characterized in that, The method includes: The received measurement beam is a multispectral beam obtained after the measurement beam is reflected by the target part. The reflected beam is imaged to obtain an image of the target area; Based on the three-channel data of each first link pixel in the target area image, the target coordinates of each first link pixel in the target area image are determined in the parameter lookup table; Based on the target coordinates, determine the blood oxygen saturation of each first link pixel in the target area image; A blood oxygen saturation image is generated based on the blood oxygen saturation of each first link pixel in the target area image.

2. The method according to claim 1, characterized in that, The step of generating a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target region image includes: Based on the allocation rules between blood oxygen saturation and three-channel data, the three-channel data of the second link pixel corresponding to the blood oxygen saturation of each first link pixel is determined. The three-channel data of each of the first link pixels is converted into three-channel data of the second link pixels to obtain a blood oxygen saturation image including multiple second link pixels; or... Among multiple first link pixels, the first link pixel with blood oxygen saturation less than a preset threshold is identified as the target link pixel; Based on the allocation rules between blood oxygen saturation and three-channel data, the three-channel data of the second link pixel corresponding to the blood oxygen saturation of each target link pixel is determined. The three-channel data of each target link pixel is converted into the three-channel data of the second link pixel to obtain a blood oxygen saturation image including multiple first link pixels with blood oxygen saturation greater than or equal to a preset threshold and multiple second link pixels.

3. The method according to claim 2, characterized in that, The method further includes: The image of the target area and / or the blood oxygen saturation image are pushed to the display interface.

4. The method according to claim 2, characterized in that, In the allocation rule between blood oxygen saturation and three-channel data, there is a negative correlation between the magnitude of blood oxygen saturation and the magnitude of the color temperature of the blood oxygen saturation image.

5. The method according to claim 1, characterized in that, The reflected beam obtained after the receiving measurement beam is reflected by the target location includes: Based on an image sensor equipped with a color filter array, the reflected beam obtained after the measurement beam is reflected by the target part is received; The color filter array includes a blue filter for passing blue light, two green filters for passing green light, and a red filter for passing red light; the color filter array is 2*2 in size, and the two green filters are not adjacent to each other.

6. The method according to claim 1, characterized in that, The imaging process of the reflected beam to obtain an image of the target area includes: An initial part image is generated based on the three-channel data of the reflected beam; Dark current correction and bad pixel correction are performed on the initial region image to obtain the corrected initial region image; The corrected initial part image is de-mosaiced to obtain the target part image including multiple first link pixels.

7. The method according to claim 1, characterized in that, The measurement beam includes narrowband blue light in the 465±5nm or 470±5nm band, broadband green light in the 540±20nm band, and narrowband red light in the 620±10nm band.

8. The method according to claim 1, characterized in that, The parameter lookup table includes 11 blood oxygen saturation contour lines, and the difference in blood oxygen saturation between adjacent blood oxygen saturation contour lines is 10%.

9. The method according to any one of claims 1-8, characterized in that, After obtaining the target region image including multiple first link pixels, the method further includes: The target area image is copied to obtain two target area images; Among the two target area images, one target area image is used for display push, and the other target area image is used to generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel.

10. A blood oxygen saturation image generation device, characterized in that, The device includes: An endoscope module is used to receive the reflected beam obtained after the measurement beam is reflected by the target area, wherein the measurement beam is a multispectral beam; and to perform imaging processing on the reflected beam to obtain an image of the target area; The processing module is used to determine the target coordinates of each first link pixel in the target region image in a parameter lookup table based on the three-channel data of each first link pixel in the target region image; determine the blood oxygen saturation of each first link pixel in the target region image based on the target coordinates; and generate a blood oxygen saturation image based on the blood oxygen saturation of each first link pixel in the target region image.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

Images