Chromatographic endoscopic microscopic spectroscopic imaging system

Abstract

The present application relates to the field of medical devices, in particular to a chromatography endoscopic microscopic spectral imaging system. It comprises: a light emitting component for emitting a light beam; a structured light component for converting the light beam into structured light; a turning component for turning the structured light and transmitting the fluorescence of the tissue to be detected; a detection component for collecting the fluorescence and forming the spatial image and spectral information of the tissue to be detected; a processor for receiving the spatial image and spectral information sent by the detection component, and evaluating the image quality of the spatial image to obtain the quality evaluation result corresponding to the spatial image. The quality corresponding to the spatial image is evaluated, and the accuracy of the quality evaluation result corresponding to the spatial image obtained is ensured. In addition, the above-mentioned chromatography endoscopic microscopic spectral imaging system does not need professional optical equipment to evaluate the quality of the spatial image, and the cost is low. And it does not need a large number of optical path calculations, so it is convenient and simple, and the efficiency is high.

Description

Technical Field

[0001] This invention relates to the field of medical devices, and more specifically to a tomographic endoscopic microscopic spectral imaging system. Background Technology

[0002] Microscopic endoscopes are widely used in medical observation and testing. Fiber optics and galvanometers are crucial components of microscopic endoscopes. A single fiber optic cable typically consists of tens of thousands of fiber units, each with a fixed center position. However, in practice, due to limitations in galvanometer scanning accuracy and the bending and deformation of the fiber during use, it's impossible to guarantee that each scan will be performed at the exact same position, even with a fixed end face. Therefore, over time, the galvanometer scanning position and the fiber position will change, and correspondingly, the center positions of the individual fiber units within the entire fiber will also change. This phenomenon is known as fiber drift.

[0003] Due to fiber drift, there is a certain pixel difference in the center position between two time points. During image reconstruction, it is necessary to determine the position of the center of each fiber unit to implement a fast degrinding method. However, the existence of fiber drift will cause the extraction of fiber information at incorrect positions during fiber image processing, thus greatly affecting the image quality of the endoscopic microscopic spectral imaging system.

[0004] In existing technologies, the inability to assess image quality leads to the inability to obtain accurate results from images. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a tomographic endoscopic microscopic spectral imaging system, which aims to solve the problem in the prior art that the inability to assess image quality leads to the inability to obtain accurate results from images.

[0006] According to a first aspect, embodiments of the present invention provide a tomographic endoscopic microscopy spectral imaging system, the tomographic endoscopic microscopy spectral imaging system comprising: a light emitting component, a structured light component, a steering component, a detection component, and a processor, wherein:

[0007] Optical emitting components, used to emit light beams;

[0008] Structured light components are used to convert light beams into structured light.

[0009] Steering assembly for directing structured light and transmitting fluorescence through the tissue to be examined:

[0010] The detection component is used to collect fluorescence and form a spatial image and spectral information of the tissue to be detected;

[0011] The processor is used to receive spatial images and spectral information sent by the detection component, evaluate the image quality of the spatial images, and obtain the corresponding quality evaluation results of the spatial images.

[0012] The tomographic endoscopic microscopy spectral imaging system provided in this invention includes: a light emitting component, a structured light component, a steering component, a detector component, and a processor. The light emitting component emits a light beam; the structured light component converts the light beam into structured light; the steering component steering the structured light and transmitting fluorescence from the tissue to be detected; and the detector component collects fluorescence and forms a spatial image and spectral information of the tissue to be detected. This tomographic endoscopic microscopy spectral imaging system uses a surface light source to excite the tissue to be detected and uses the detector component to detect the excitation light, which can greatly improve the imaging speed of tissue molecules, achieve real-time spatial imaging, and acquire the spectral information of the tissue to be detected. The use of structured light reconstruction technology in this tomographic endoscopic microscopy spectral imaging system solves the image blurring problem caused by interference from background light above and below the focusing plane in wide-field imaging. Furthermore, in this tomographic endoscopic microscopy spectral imaging system, the processor receives the spatial image and spectral information sent by the detector component and evaluates the image quality of the spatial image to obtain a quality evaluation result corresponding to the spatial image, thus ensuring the accuracy of the obtained quality evaluation result. This ensures that accurate results are obtained based on the quality assessment results corresponding to the spatial images. Furthermore, the aforementioned tomographic endoscopic microspectral imaging system does not require specialized optical equipment to assess the quality of spatial images, resulting in lower costs. It also does not require extensive optical path calculations, making it convenient, simple, and highly efficient.

[0013] In conjunction with the first aspect, in the first embodiment of the first aspect, the processor is configured to acquire a positioning image corresponding to a spatial image, perform a quality assessment on the positioning image, and determine a quality assessment result corresponding to the spatial image based on the result of the quality assessment of the positioning image; the positioning image refers to an image acquired from the excited air by a laser light source.

[0014] The tomographic endoscopic microscopy spectral imaging system provided in this invention includes a processor for acquiring a positioning image corresponding to a spatial image, performing a quality assessment on the positioning image, and ensuring the accuracy of the quality assessment results. Based on the quality assessment results of the positioning image, the quality assessment result corresponding to the spatial image is determined, ensuring the accuracy of the determined quality assessment result corresponding to the spatial image.

[0015] In conjunction with the first embodiment of the first aspect, in the second embodiment of the first aspect, the processor is configured to perform image recognition on the positioning image to determine the number of fiber optic centers included in the positioning image; if the number of fiber optic centers does not meet the preset number requirement, the evaluation quality of the positioning image is determined to be Level 1 quality, and Level 1 quality is used to characterize the worst image quality; based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality.

[0016] The tomographic endoscopic microscopy spectral imaging system provided in this invention includes a processor that performs image recognition on a positioning image to determine the number of fiber optic centers included in the positioning image, ensuring the accuracy of the determined number of fiber optic centers. If the number of fiber optic centers does not meet a preset requirement, the evaluation quality of the positioning image is determined to be Level 1 quality, ensuring the accuracy of the determined Level 1 quality result. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality, ensuring the accuracy of the determined Level 1 quality result for the spatial image.

[0017] In conjunction with the second embodiment of the first aspect, in the third embodiment of the first aspect, the processor is further configured to, when the number of fiber optic centers meets the preset number requirement, perform grayscale value recognition on the positioning image, determine the grayscale value of each fiber optic center, and calculate the grayscale mean and grayscale standard deviation of all fiber optic centers accordingly; determine the evaluation quality of the positioning image based on the grayscale value, grayscale mean, and grayscale standard deviation of each fiber optic center, and determine the quality evaluation result corresponding to the spatial image.

[0018] The tomographic endoscopic microscopy spectral imaging system provided in this invention includes a processor that, when the number of fiber optic centers meets a preset requirement, performs grayscale value recognition on the positioning image to determine the grayscale value of each fiber optic center, ensuring the accuracy of the determined grayscale values. Based on this, it calculates the mean grayscale value and standard deviation of all fiber optic centers, ensuring the accuracy of the calculated mean grayscale value and standard deviation. Based on the grayscale value, mean grayscale value, and standard deviation of each fiber optic center, it determines the evaluation quality of the positioning image and the corresponding quality evaluation result of the spatial image, ensuring the accuracy of the determined evaluation quality of the positioning image and the corresponding quality evaluation result of the spatial image.

[0019] In conjunction with the third embodiment of the first aspect, in the fourth embodiment of the first aspect, the processor is configured to determine whether the distribution of gray values ​​of all fiber centers in the positioning image conforms to a Gaussian distribution based on the gray values, gray mean, and gray standard deviation of each fiber center; when the distribution of gray values ​​of fiber centers does not conform to a Gaussian distribution, the evaluation quality of the positioning image is determined to be level two quality, and the image quality corresponding to level two quality is higher than level one quality; based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level two quality.

[0020] The tomographic endoscopic microscopic spectral imaging system provided in this invention includes a processor that determines whether the gray value distribution of all fiber centers in the positioning image conforms to a Gaussian distribution based on the gray value, gray mean, and gray standard deviation of each fiber center. This ensures the accuracy of the result regarding whether the gray value distribution of all fiber centers in the determined positioning image conforms to a Gaussian distribution. When the gray value distribution of the fiber centers does not conform to a Gaussian distribution, the evaluation quality of the positioning image is determined to be of secondary quality, ensuring the accuracy of the result regarding secondary quality. Then, the quality evaluation result corresponding to the spatial image is determined to be of secondary quality, ensuring the accuracy of the result regarding secondary quality.

[0021] In conjunction with the fourth embodiment of the first aspect, in the fifth embodiment of the first aspect, the processor is further configured to: when the grayscale value distribution of the fiber center conforms to a Gaussian distribution, acquire the number of fiber centers whose grayscale values ​​are within the range of the grayscale mean plus or minus the grayscale value standard deviation, and calculate a first proportion of this number to the total number of fiber centers; when the first proportion does not meet a preset proportion requirement, determine that the evaluation quality of the positioning image is level three quality, and the image quality corresponding to level three quality is higher than level two quality; based on the evaluation quality of the positioning image, determine that the quality evaluation result corresponding to the spatial image is level three quality; when the first proportion meets the preset proportion requirement, determine that the evaluation quality of the positioning image is level four quality, and the image quality corresponding to level four quality is higher than level three quality; based on the evaluation quality of the positioning image, determine that the quality evaluation result corresponding to the spatial image is level four quality.

[0022] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor that, when the grayscale value distribution of the fiber center corresponding to the positioning image conforms to a Gaussian distribution, acquires the number of fiber centers whose grayscale values ​​are within the range of the grayscale mean plus or minus the grayscale standard deviation, and calculates a first proportion of this number to the total number of fiber centers. When the first proportion does not meet a preset proportion requirement, the evaluation quality of the positioning image is determined to be level three, ensuring the accuracy of the determined evaluation quality of the positioning image being level three. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level three, ensuring the accuracy of the determined quality evaluation result corresponding to the spatial image being level three. When the first proportion meets the preset proportion requirement, the evaluation quality of the positioning image is determined to be level four, ensuring the accuracy of the determined evaluation quality of the positioning image being level four. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level four, ensuring the accuracy of the determined evaluation quality of the positioning image being level four.

[0023] In conjunction with any one of the first to fifth embodiments of the first aspect, in the sixth embodiment of the first aspect, the processor is further configured to output adjustment recommendations for at least one optical component among the light emitting component, the structured light component, the steering component, and the detection component, based on the quality assessment results.

[0024] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor that is further configured to output adjustment suggestions for at least one optical component among the light emitting component, structured light component, steering component, and detection component based on the quality assessment results, thereby ensuring the accuracy of the output adjustment suggestions for at least one optical component among the light emitting component, structured light component, steering component, and detection component.

[0025] In conjunction with the sixth embodiment of the first aspect, in the seventh embodiment of the first aspect, the processor is configured to compare the quality assessment result with a preset quality assessment level, and when the quality assessment result is less than or equal to the preset quality assessment level, acquire the shape of the light spot and the center position of the light spot at each location in the positioning image, and adjust the position and angle of at least one optical component among the light emitting component, the structured light component, the steering component and the detection component according to the shape of the light spot and the center position of the light spot at each location.

[0026] The tomographic endoscopic microscopy spectral imaging system provided in this invention includes a processor that compares the quality assessment result with a preset quality assessment level, ensuring the accuracy of the comparison result. When the quality assessment result is less than or equal to the preset quality assessment level, the processor acquires the spot shape and center position of the light at each location in the positioning image, ensuring the accuracy of the acquired spot shape and center position. Based on the spot shape and center position of each location, the processor adjusts the position and angle of at least one optical component among the light emitting component, structured light component, steering component, and detection component, ensuring the accuracy of the adjustment of the position and angle of at least one optical component among the light emitting component, structured light component, steering component, and detection component.

[0027] In conjunction with the seventh embodiment of the first aspect, in the eighth embodiment of the first aspect, the processor is configured to prohibit adjustment of the light emitting component, the structured light component, the steering component, and the detection component when the quality assessment result is greater than a preset quality assessment level.

[0028] The tomographic endoscopic microscopy spectral imaging system provided in this invention includes a processor that prohibits adjustments to the light-emitting component, structured light component, steering component, and detection component when the quality assessment result exceeds a preset quality assessment level. This ensures the accuracy of prohibiting adjustments to the light-emitting component, structured light component, steering component, and detection component.

[0029] In conjunction with the first aspect, in the ninth embodiment of the first aspect, the detection component is wholly or partially covered with a sterile membrane.

[0030] The endoscopic tomographic microscopy imaging system provided in this invention has a probe component that is wholly or partially covered with a sterile membrane, which avoids repeated disinfection and sterilization of the probe component, reduces the wear and tear on the probe component, and increases the service life of the probe component. Attached Figure Description

[0031] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 This is a schematic diagram of the structure of the tomographic endoscopic microspectral imaging system provided in the embodiments of the present invention;

[0033] Figure 2 This is a schematic diagram of the structure of a tomographic endoscopic microspectral imaging system provided by another embodiment of the present invention. Detailed Implementation

[0034] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0035] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can also refer to the internal connection of two components; and they can refer to a wireless connection or a wired connection. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0036] In the description of this invention, it should be noted that the term "and / or" as used in this application specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0037] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0038] 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.

[0039] The applicant noted the following drawbacks to evaluating image quality from the perspective of optical system measurement: it requires specialized optical measurement equipment, which is expensive; it requires extensive optical path calculations, which are complex and labor-intensive; existing methods, whether measurement methods during the design phase or after manufacturing, can measure the image quality of a portion of the optical system, but for a complete actual system, if the optical system is understood as the excitation end and the image is considered as the response of the excitation end, the quality of the excitation end and the image quality are not 100% equivalent. That is, evaluating image quality solely from the perspective of optical system measurement using existing methods cannot guarantee the quality of the optical system's response in the final image. Even if existing experimental methods can evaluate the excitation end to some extent, the actual application environment is more complex, and in specific application scenarios, the final evaluation of the imaging effect cannot be achieved solely from the perspective of optical measurement.

[0040] Based on the above considerations, this application provides a tomographic endoscopic microscopic spectral imaging system that can solve the problem that the imaging effect cannot be ultimately evaluated from the perspective of optical measurement alone.

[0041] In one embodiment of this application, such as Figure 1 As shown, a tomographic endoscopic microscopy spectral imaging system is provided. The system includes: a light emitting component 110, a structured light component 120, a steering component 130, a detection component 140, and a processor 150, wherein:

[0042] The light emitting component 110 is used to emit a light beam.

[0043] Structured light component 120 is used to convert a light beam into structured light.

[0044] The steering component 130 is used to direct the structured light and transmit the fluorescence of the tissue to be examined.

[0045] The detector component 140 is used to collect fluorescence and form a spatial image and spectral information of the tissue to be detected.

[0046] The processor 150 is used to receive spatial images and spectral information sent by the detection component, evaluate the image quality of the spatial images, and obtain the corresponding quality evaluation results of the spatial images.

[0047] Specifically, the principle by which the above-mentioned tomographic endoscopic microscopy spectral imaging system generates spatial images and spectral information can be as follows: The light emitting component 110 may include a light source 112 and a beam expander 114. The light source 112 is used to emit a collimated beam. The light source 112 can be a laser that emits collimated laser light of a specific wavelength. The specific wavelength range can be 20nm-2000nm. Laser light within this wavelength range can excite a wide range of phosphors. The light source 112 can be a quantum well laser, a solid-state laser, a gas laser (e.g., an argon ion laser), or a laser diode. The beam expander 114 is disposed at the outlet of the light source 112 and is used to expand the collimated beam emitted by the light source 112. In a preferred embodiment, the beam expander 114 may include a narrowband filter (not shown) and a beam expander arranged sequentially. The narrowband filter is used to filter the collimated beam emitted by the light source 112. The narrowband filter can filter out light of the desired wavelength, for example, allowing 500nm-600nm optical fibers to pass through the narrowband filter to excite a wide range of fluorescence. A beam expander may include two beam expanding lenses, L1 and L2, which work together to expand the beam passing through the narrowband filter in order to change the diameter of the collimated beam.

[0048] The collimated beam emitted by the light source 112 is expanded by the beam expander 114 and then transformed into structured light by the structured light component 120.

[0049] The structured light component 120 may include a grating and a driver (e.g., a motor) for controlling the movement of the grating. The grating may be a cosine grating. The light beam emitted by the light emitting component 110 is projected onto the tissue to be inspected through the grating, forming structured light illumination. When three source images are formed in each cycle (i.e., the grating movement cycle), each movement of 1 / 3 of the grating cycle corresponds to a 2π / 3 phase shift in the grating pattern. Simultaneously, the exposure speed of the detection component 140 is synchronized with the grating movement. Three phase shifts (0, 2π / 3, 4π / 3) yield three source images of the tissue to be inspected, which are then reconstructed by structured light to obtain a single tomographic image of the tissue.

[0050] Specifically, the steering component 130 is located downstream of the structured light component 120 and is used to steering the structured light generated by the structured light component 120, while allowing the fluorescence of the tissue to be detected to pass through. The steering component 130 is used to separate the structured light generated by the structured light component 120 from the fluorescence excited by the tissue to be detected. The transmittance of the steering component 130 for fluorescence can reach more than 90%, while reflecting almost all light of other wavelengths. The steering component 130 can be a dichroic mirror. Preferably, the wavelength range of the dichroic mirror is in the range of 40nm-2200nm. Thus, the structured light generated by the structured light component 120 is reflected by the steering component 130 to the endoscope component 160 located downstream of the steering component 130.

[0051] The endoscope assembly 160 is used to guide and focus the light beam directed by the steering assembly 130 onto the tissue to be examined, and to receive the fluorescence emitted by the tissue. This fluorescence is then collected by the detector assembly 140 after passing through the steering assembly 130.

[0052] In a preferred embodiment, the endoscopic assembly 160 may include a coupling objective, a miniature objective, and an imaging fiber bundle coupled between the coupling objective and the miniature objective. The coupling objective is used to couple (e.g., focus) a light beam into the proximal end (near the operator) of the imaging fiber bundle. The imaging fiber bundle is used to conduct the light beam to the distal end (away from the operator). The miniature objective is used to focus the laser beam conducted by the imaging fiber bundle onto a detection surface of the tissue to be examined. The detection surface may be located at a desired depth below the surface of the tissue to be examined. A fluorophore at this detection surface of the tissue to be examined is excited to fluoresce.

[0053] The fluorescence emitted by the tissue to be detected, which is illuminated by the beam on the focusing plane, is received. The detection component 140 can form a complete image each time. That is, the imaging speed of this tomographic endoscope microscopy imaging system is the imaging speed of the array detection component 140, thereby enabling the rapid realization of observable tissue molecular images.

[0054] The detection component 140 collects the fluorescence returned sequentially by the endoscope component 160 and the steering component 130, forming a spatial image and spectral information of the tissue to be detected. The spatial image of the tissue to be detected includes a two-dimensional image of the detection surface of the tissue. The spectral information includes the energy distribution of the fluorescence generated by the tissue under stimulation in different wavelengths, which is used to help obtain tissue information (e.g., for tumor analysis).

[0055] Specifically, after forming the spatial image and spectral information, the processor 150 can receive the spatial image and spectral information sent by the detection component.

[0056] In one optional embodiment of this application, the processor 150 can use an image quality recognition model to perform image quality recognition on the spatial image, and then evaluate the image quality of the spatial image based on the recognition result to obtain the quality evaluation result corresponding to the spatial image.

[0057] The image quality recognition model can be based on handcrafted features, such as the Deformable Parts Model (DPM), or it can be based on convolutional neural networks, such as the YOLO (You Only Look Once) detector, R-CNN (Region-based Convolutional Neural Networks), SSD (Single Shot MultiBox) detector, and Mask R-CNN (Mask Region-based Convolutional Neural Networks). This application does not specifically limit the image quality recognition model.

[0058] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes: a light emitting component 110, a structured light component 120, a steering component 130, a detector component 140, and a processor 150. The light emitting component emits a light beam; the structured light component converts the light beam into structured light; the steering component steering the structured light and transmitting fluorescence from the tissue to be detected; and the detector component acquiring fluorescence and forming a spatial image and spectral information of the tissue to be detected. This tomographic endoscopic microscopy spectral imaging system uses a surface light source to excite the tissue to be detected and uses the detector component to detect the excitation light, which can greatly improve the imaging speed of tissue molecules, achieve real-time spatial imaging, and acquire spectral information of the tissue to be detected. The use of structured light reconstruction technology in the tomographic endoscopic microscopy spectral imaging system solves the image blurring problem caused by interference from background light above and below the focal plane in wide-field imaging. Furthermore, in the aforementioned tomographic endoscopic microscopic spectral imaging system, the processor 150 receives spatial images and spectral information transmitted by the detection component, evaluates the image quality of the spatial images, and obtains the corresponding quality evaluation results. This ensures the accuracy of the obtained quality evaluation results for the spatial images. Consequently, accurate results for the spatial images can be obtained based on the quality evaluation results. Moreover, the aforementioned tomographic endoscopic microscopic spectral imaging system does not require specialized optical equipment to evaluate the quality of spatial images, resulting in lower costs. It also does not require extensive optical path calculations, making it convenient, simple, and highly efficient.

[0059] In an optional embodiment of this application, the processor 150 is configured to acquire a positioning image corresponding to a spatial image, perform a quality assessment on the positioning image, and determine a quality assessment result corresponding to the spatial image based on the result of the quality assessment of the positioning image.

[0060] Among them, the positioning image refers to the image collected from the excited air by the laser light source.

[0061] Specifically, the processor 150 can receive a positioning image corresponding to a spatial image input by the user, or a positioning image corresponding to a spatial image sent by other devices. The processor 150 can also emit a light beam based on the light emitting component 110 to excite the air, and perform image acquisition on the excited air to generate a positioning image corresponding to the spatial image. This application embodiment does not specifically limit the method by which the processor 150 acquires the positioning image corresponding to the spatial image.

[0062] Since the localization image is not affected by the tissue to be detected, the localization image corresponding to the spatial image can accurately characterize the image quality of the spatial image.

[0063] In one optional implementation, after acquiring the positioning image corresponding to the spatial image, the processor 150 can use an image quality recognition model to perform image quality recognition on the positioning image, and then evaluate the image quality of the positioning image based on the recognition result to obtain the quality evaluation result of the positioning image. Then, based on the quality evaluation result of the positioning image, the quality evaluation result corresponding to the spatial image is determined.

[0064] The image quality recognition model can be based on handcrafted features, such as the Deformable Parts Model (DPM), or it can be based on convolutional neural networks, such as the YOLO (You Only Look Once) detector, R-CNN (Region-based Convolutional Neural Networks), SSD (Single Shot MultiBox) detector, and Mask R-CNN (Mask Region-based Convolutional Neural Networks). This application does not specifically limit the image quality recognition model.

[0065] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor 150, which acquires a positioning image corresponding to a spatial image, performs quality assessment on the positioning image, and ensures the accuracy of the quality assessment results. Based on the quality assessment results of the positioning image, the quality assessment result corresponding to the spatial image is determined, ensuring the accuracy of the determined quality assessment result corresponding to the spatial image.

[0066] In an optional embodiment of this application, the processor 150 is configured to perform image recognition on the positioning image to determine the number of fiber optic centers included in the positioning image; if the number of fiber optic centers does not meet the preset number requirement, the evaluation quality of the positioning image is determined to be Level 1 quality, which is used to characterize the worst image quality; based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality.

[0067] The optical fiber consists of a cladding and a core. The core has high transmittance, and the pixel with the highest transmittance in each optical fiber (hexagonal structure) is considered the fiber center.

[0068] Specifically, the processor 150 can use image recognition methods to perform image recognition on the fiber optic centers in the positioning image, thereby determining the number of fiber optic centers included in the positioning image.

[0069] The image recognition method can be an image recognition method based on artificial neural networks, an image recognition method based on wavelet moments, or an image recognition method based on fractal features. This application does not specifically limit the image recognition method.

[0070] After determining the number of fiber optic centers included in the positioning image, the processor 150 can determine whether the number of fiber optic centers meets the preset number requirement.

[0071] The preset number requirement can be a preset range of fiber optic centers or a preset numerical value. When the preset number requirement is a preset range, the preset range can be N ± N × 5%, where N can be 3000, 2000, or 2500. This application embodiment does not specifically limit the preset range. For example, when N is 3000, the preset range is 30000*0.95 to 30000*1.05. When the preset number requirement is a preset numerical value, this value can be 3000, 2000, or 2500. This application embodiment does not specifically limit the preset numerical value.

[0072] Optionally, when the preset number requirement is within a preset range, the processor 150 can compare the number of fiber optic centers with the maximum and minimum values ​​within the preset range to determine whether the number of fiber optic centers meets the preset requirement. When the number of fiber optic centers is not within the preset range, the current positioning image is determined to have the worst quality. Therefore, the evaluation quality of the positioning image is determined to be Level 1 quality, which characterizes the worst image quality. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality.

[0073] Optionally, when the preset number requirement is a preset number value, the processor 150 can compare the number of fiber centers with the preset number value. When the number of fiber centers is not the preset number value, it is determined that the quality of the current positioning image is the worst. Therefore, the evaluation quality of the positioning image is determined to be Level 1 quality. Level 1 quality is used to characterize the worst image quality. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality.

[0074] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor 150, which performs image recognition on a positioning image to determine the number of fiber optic centers included in the positioning image, ensuring the accuracy of the determined number of fiber optic centers. If the number of fiber optic centers does not meet a preset requirement, the evaluation quality of the positioning image is determined to be Level 1 quality, ensuring the accuracy of the determined Level 1 quality result. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality, ensuring the accuracy of the determined Level 1 quality result for the spatial image.

[0075] In one optional embodiment of this application, the processor 150 is further configured to, when the number of fiber optic centers meets a preset number requirement, perform grayscale value recognition on the positioning image, determine the grayscale value of each fiber optic center, and calculate the mean grayscale value and standard deviation of grayscale value of all fiber optic centers accordingly; determine the evaluation quality of the positioning image based on the grayscale value, mean grayscale value, and standard deviation of grayscale value of each fiber optic center, and determine the quality evaluation result corresponding to the spatial image.

[0076] Specifically, the processor 150 can use an image recognition method to perform image recognition on the fiber optic center in the positioning image, thereby determining the number of fiber optic centers included in the positioning image. When the number of fiber optic centers meets the preset number requirement, the processor 150 can use a grayscale value recognition method to identify the grayscale value of each fiber optic center in the positioning image, thereby determining the grayscale value of each fiber optic center.

[0077] After determining the grayscale value of each fiber optic center, the processor 150 can calculate the mean grayscale value μ of all fiber optic centers based on the grayscale value of each fiber optic center. Then, the processor 150 uses the following formula to calculate the standard deviation of the grayscale values ​​of all fiber optic centers.

[0078]

[0079] Where N is the number of fiber centers, μ is the average gray value of the fiber center, and x i The grayscale value is the center value of each optical fiber.

[0080] After calculating the mean gray value and standard deviation of gray value for all fiber centers, the processor 150 can determine the evaluation quality of the positioning image based on the relationship between the gray value, mean gray value and standard deviation of gray value for each fiber center, and determine the quality evaluation result corresponding to the spatial image.

[0081] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention, with processor 150, is further configured to perform grayscale value recognition on the positioning image when the number of fiber optic centers meets a preset requirement, determining the grayscale value of each fiber optic center, thus ensuring the accuracy of the determined grayscale values. Based on this, the mean grayscale value and standard deviation of all fiber optic centers are calculated, ensuring the accuracy of the calculated mean grayscale value and standard deviation of all fiber optic centers. Based on the grayscale value, mean grayscale value, and standard deviation of each fiber optic center, the evaluation quality of the positioning image is determined, and the quality evaluation result corresponding to the spatial image is determined, ensuring the accuracy of the determined evaluation quality of the positioning image and the quality evaluation result corresponding to the spatial image.

[0082] In one optional embodiment of this application, the processor 150 is configured to determine whether the gray value distribution of all fiber centers in the positioning image conforms to a Gaussian distribution based on the gray value, gray mean, and gray standard deviation of each fiber center; when the gray value distribution of the fiber centers does not conform to a Gaussian distribution, the evaluation quality of the positioning image is determined to be level two quality, and the image quality corresponding to level two quality is higher than level one quality; based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level two quality.

[0083] Specifically, after acquiring the grayscale value, mean grayscale value, and standard deviation of each fiber optic center, the processor 150 can determine whether the grayscale value distribution of all fiber optic centers in the positioning image conforms to a Gaussian distribution. When the grayscale value distribution of the fiber optic centers does not conform to a Gaussian distribution, the quality of the current positioning image is determined to be poor, and therefore, the evaluation quality of the positioning image is determined to be level two. Level two quality corresponds to an image quality higher than level one.

[0084] Then, based on the evaluation quality of the positioning image, the processor 150 determines that the quality evaluation result corresponding to the spatial image is level two quality.

[0085] The tomographic endoscopic microscopic spectral imaging system provided in this embodiment of the invention includes a processor 150, which is used to determine whether the gray value distribution of all fiber centers in the positioning image conforms to a Gaussian distribution based on the gray value, gray mean, and gray standard deviation of each fiber center, thus ensuring the accuracy of the result of whether the gray value distribution of the fiber centers corresponding to the determined positioning image conforms to a Gaussian distribution; when the gray value distribution of the fiber centers does not conform to a Gaussian distribution, the evaluation quality of the positioning image is determined to be level two quality, thus ensuring the accuracy of the result of determining the evaluation quality of the positioning image to be level two quality; then, the quality evaluation result corresponding to the spatial image is determined to be level two quality, thus ensuring the accuracy of determining the quality evaluation result corresponding to the spatial image to be level two quality.

[0086] In one optional embodiment of this application, the processor 150 is further configured to: when the grayscale value distribution of the fiber center conforms to a Gaussian distribution, obtain the number of fiber centers whose grayscale values ​​are within the range of the grayscale mean plus or minus the grayscale value standard deviation, and calculate a first proportion of this number to the total number of fiber centers; when the first proportion does not meet a preset proportion requirement, determine that the evaluation quality of the positioning image is level three, and the image quality corresponding to level three is higher than level two; based on the evaluation quality of the positioning image, determine that the quality evaluation result corresponding to the spatial image is level three; when the first proportion meets the preset proportion requirement, determine that the evaluation quality of the positioning image is level four, and the image quality corresponding to level four is higher than level three; based on the evaluation quality of the positioning image, determine that the quality evaluation result corresponding to the spatial image is level four.

[0087] Specifically, when the gray value distribution of the fiber center conforms to a Gaussian distribution, the processor 150 can calculate the number of fiber centers whose gray values ​​are within the range of gray mean plus or minus gray value standard deviation. Then, by dividing this number by the total number of fiber centers, the processor 150 obtains the first proportion of this number to the total number of fiber centers.

[0088] Then, the processor 150 can receive a preset ratio requirement input by the user, or it can receive a preset ratio requirement sent by other devices. This application embodiment does not specifically limit the method by which the processor 150 obtains the preset ratio requirement.

[0089] The preset ratio requirement can be that the first ratio is within a preset ratio range, or the preset ratio requirement can be that the difference between the first ratio and the preset ratio threshold is less than a preset difference threshold; the embodiments of this application do not specifically limit the preset ratio requirement.

[0090] In one optional implementation, when the preset ratio requirement is that the first ratio is within a preset ratio range, the processor 150 can compare the first ratio with the maximum and minimum ratios within the preset ratio range. If the first ratio is greater than the maximum ratio or less than the minimum ratio, it is determined that the first ratio does not meet the preset ratio requirement, and therefore, the evaluation quality of the positioning image is determined to be level three quality. Level three quality corresponds to an image quality higher than level two quality. When the first ratio is less than the maximum ratio but greater than the minimum ratio, it is determined that the first ratio meets the preset ratio requirement, and therefore, the evaluation quality of the positioning image is determined to be level four quality. Level four quality corresponds to an image quality higher than level three quality.

[0091] The preset ratio range can be 67%-68% or 65%-66%, and this application embodiment does not specifically limit the preset ratio range.

[0092] In another optional implementation, when the preset ratio requirement is that the difference between the first ratio and the preset ratio threshold is less than a preset difference threshold, the processor 150 can calculate the difference between the first ratio and the preset ratio threshold and compare the difference with the preset difference threshold. When the difference between the first ratio and the preset ratio threshold is greater than the preset difference threshold, the processor 150 determines that the image quality of the current positioning image is high and determines the evaluation quality of the positioning image to be level three. Level three quality corresponds to an image quality higher than level two quality.

[0093] When the difference between the first ratio and the preset ratio threshold is less than or equal to the preset difference threshold, the processor 150 determines that the current positioning image has the best quality and classifies the positioning image as level four quality. Level four quality corresponds to an image quality higher than level three quality.

[0094] Then, based on the evaluation quality of the positioning image, the processor 150 determines that the quality evaluation result corresponding to the spatial image is level four.

[0095] The preset ratio threshold can be 68% or 67%, and this application embodiment does not specifically limit the preset ratio. The preset difference threshold can be 0.5% or 1%, and this application embodiment does not specifically limit the preset difference threshold.

[0096] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor 150. When the grayscale value distribution of the fiber center corresponding to the positioning image conforms to a Gaussian distribution, the processor acquires the number of fiber centers whose grayscale values ​​fall within the range of the grayscale mean plus or minus the grayscale standard deviation, and calculates a first proportion of this number to the total number of fiber centers. When the first proportion does not meet a preset proportion requirement, the evaluation quality of the positioning image is determined to be level three, ensuring the accuracy of the determined level three quality. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level three, ensuring the accuracy of the determined level three quality. When the first proportion meets the preset proportion requirement, the evaluation quality of the positioning image is determined to be level four, ensuring the accuracy of the determined level four quality result. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level four, ensuring the accuracy of the determined level four quality.

[0097] In one alternative embodiment of this application, the processor 150 is further configured to output adjustment recommendations for at least one optical element among the light emitting component, structured light component, steering component, and detection component, based on the quality assessment results.

[0098] Specifically, after determining the quality assessment results of the spatial image, the processor 150 can output adjustment suggestions for at least one optical component among the light emitting component, structured light component, steering component, and detection component, based on the quality assessment results of the spatial image.

[0099] This step will be explained in detail below.

[0100] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor 150, which is further configured to output adjustment suggestions for at least one optical component among the light emitting component, structured light component, steering component, and detection component based on the quality assessment results, thereby ensuring the accuracy of the output adjustment suggestions for at least one optical component among the light emitting component, structured light component, steering component, and detection component.

[0101] In one optional embodiment of this application, the processor 150 is used to compare the quality assessment result with a preset quality assessment level. When the quality assessment result is less than or equal to the preset quality assessment level, the processor obtains the shape of the light spot and the center position of the light spot at each location in the positioning image. Based on the shape of the light spot and the center position of the light spot at each location, the processor adjusts the position and angle of at least one optical component among the light emitting component, the structured light component, the steering component, and the detection component.

[0102] Specifically, after determining the quality assessment result of the spatial image, the processor 150 can compare the quality assessment result with a preset quality assessment level. The preset quality assessment level can be one of three quality levels.

[0103] When the quality assessment result is less than or equal to the preset quality assessment level, the processor 150 can identify the positioning image, obtain the shape of the light spot and the center position of the light spot at each location in the positioning image, and adjust the position and angle of at least one optical component among the light emitting component, structured light component, steering component and detection component according to the shape of the light spot and the center position of the light spot at each location.

[0104] For example, assuming the quality assessment result of the spatial image is level 2, and the preset quality assessment level can be level 3, then the quality assessment result of the spatial image is lower than the preset quality assessment level. The processor adjusts the position and angle of at least one optical component among the light emitting component, structured light component, steering component and detection component according to the shape of the light spot and the center position of the light spot at each location.

[0105] In one optional implementation, when the quality assessment result is lower than a preset quality assessment level, after the processor 150 obtains the shape and center position of the light spot at each location in the positioning image, it can first make a large-scale coarse adjustment to the position and angle of at least one optical element among the light emitting component, structured light component, steering component, and detection component based on the shape and center position of the light spot at each location, so that the shape of the light spot is close to a circle and the center position of the light spot is on the central axis of the optical path. Then, it makes a fine adjustment to the position and angle of at least one optical element among the light emitting component, structured light component, steering component, and detection component to improve the quality of the positioning image.

[0106] When the quality assessment result is equal to the preset quality assessment level, after the processor 150 obtains the shape of the light spot and the center position of the light spot at each location in the positioning image, it can make fine adjustments to the position and angle of at least one optical component among the light emitting component, structured light component, steering component and detection component, so as to improve the quality of the positioning image.

[0107] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor 150, which compares the quality assessment result with a preset quality assessment level to ensure the accuracy of the comparison result. When the quality assessment result is less than or equal to the preset quality assessment level, the processor acquires the spot shape and center position of each location in the positioning image, ensuring the accuracy of the acquired spot shape and center position. Based on the spot shape and center position of each location, the processor adjusts the position and angle of at least one optical component among the light emitting component, structured light component, steering component, and detection component, ensuring the accuracy of the adjustment of the position and angle of at least one optical component among the light emitting component, structured light component, steering component, and detection component.

[0108] In one optional embodiment of this application, the processor 150 is configured to prohibit adjustments to the light emitting component, structured light component, steering component, and detection component when the quality assessment result is greater than a preset quality assessment level, thereby ensuring the accuracy of prohibiting adjustments to the light emitting component, structured light component, steering component, and detection component.

[0109] Specifically, when the quality assessment result is greater than the preset quality assessment level, the processor 150 determines that the quality of the current spatial image is high, and therefore prohibits adjustments to the light emitting component, structured light component, steering component, and detection component.

[0110] The tomographic endoscopic microscopy spectral imaging system provided in this embodiment of the invention includes a processor 150 that prohibits adjustments to the light-emitting component, structured light component, steering component, and detection component when the quality assessment result exceeds a preset quality assessment level. This ensures the accuracy of prohibiting adjustments to the light-emitting component, structured light component, steering component, and detection component.

[0111] In one optional embodiment of this application, such as Figure 2 As shown, the detection component is wholly or partially covered with a sterile membrane 170.

[0112] Specifically, the sterile membrane 170 can be a colorless, transparent film with a light transmittance of not less than 90%, a thickness of ≤50um, a size that matches the detection component 140, and a tight fit with the detection component 140.

[0113] The endoscopic tomographic microscopy imaging system provided in this invention has a probe component wholly or partially covered with a sterile membrane 170, which avoids repeated disinfection and sterilization of the probe component, reduces the wear and tear of the probe component, and increases the service life of the probe component.

[0114] 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 tomographic endoscopic microspectral imaging system, characterized in that, The tomographic endoscopic microscopic spectral imaging system includes: a light emitting component, a structured light component, a steering component, a detection component, and a processor, wherein: The light emitting component is used to emit a light beam; The structured light component is used to convert the light beam into structured light; The steering component is used to direct the structured light and transmit the fluorescence of the tissue to be detected; The detection component is used to collect the fluorescence and form a spatial image and spectral information of the tissue to be detected; The processor is configured to receive the spatial image and the spectral information sent by the detection component, evaluate the image quality of the spatial image, and obtain the quality evaluation result corresponding to the spatial image; The processor is configured to acquire a positioning image corresponding to the spatial image, perform a quality assessment on the positioning image, and determine a quality assessment result corresponding to the spatial image based on the quality assessment result of the positioning image; the positioning image refers to an image acquired by exciting air with a laser light source. The processor is configured to perform image recognition on the positioning image to determine the number of fiber optic centers included in the positioning image; if the number of fiber optic centers does not meet a preset number requirement, the evaluation quality of the positioning image is determined to be Level 1 quality, which is used to characterize the worst image quality; based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be Level 1 quality.

2. The tomographic endoscopic microscopic spectral imaging system according to claim 1, characterized in that, The processor is further configured to, when the number of optical fiber centers meets the preset number requirement, perform grayscale value recognition on the positioning image, determine the grayscale value of each optical fiber center, and calculate the grayscale mean and grayscale standard deviation of all optical fiber centers accordingly; determine the evaluation quality of the positioning image based on the grayscale value of each optical fiber center, the grayscale mean, and the grayscale standard deviation, and determine the quality evaluation result corresponding to the spatial image.

3. The tomographic endoscopic microspectral imaging system according to claim 2, characterized in that, The processor is configured to determine whether the gray value distribution of all fiber centers in the positioning image conforms to a Gaussian distribution based on the gray value of each fiber center, the mean gray value, and the standard deviation of the gray value; when the gray value distribution of the fiber centers does not conform to a Gaussian distribution, the evaluation quality of the positioning image is determined to be level two quality, and the image quality corresponding to level two quality is higher than level one quality; based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be level two quality.

4. The tomographic endoscopic microspectral imaging system according to claim 3, characterized in that, The processor is further configured to, when the gray value distribution of the optical fiber center conforms to a Gaussian distribution, obtain the number of optical fiber centers whose gray values ​​are within the range of the gray value mean plus or minus the gray value standard deviation, and calculate the first proportion of the number to the total number of optical fiber centers; when the first proportion does not meet the preset proportion requirement, determine that the evaluation quality of the positioning image is level three quality, and the image quality corresponding to level three quality is higher than that of level two quality. Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be the third-level quality; when the first ratio meets the preset ratio requirement, the evaluation quality of the positioning image is determined to be the fourth-level quality, and the image quality corresponding to the fourth-level quality is higher than the third-level quality; Based on the evaluation quality of the positioning image, the quality evaluation result corresponding to the spatial image is determined to be the fourth-level quality.

5. The tomographic endoscopic microspectral imaging system according to any one of claims 1-4, characterized in that, The processor is further configured to output adjustment recommendations for at least one optical component among the light emitting component, the structured light component, the steering component, and the detection component, based on the quality assessment results.

6. The tomographic endoscopic microspectral imaging system according to claim 5, characterized in that, The processor is configured to compare the quality assessment result with a preset quality assessment level. When the quality assessment result is less than or equal to the preset quality assessment level, it acquires the shape and center position of the light spot at each location in the positioning image. Based on the shape and center position of the light spot at each location, it adjusts the position and angle of at least one optical component among the light emitting component, the structured light component, the steering component, and the detection component.

7. The tomographic endoscopic microspectral imaging system according to claim 6, characterized in that, The processor is configured to prohibit adjustments to the light emitting component, the structured light component, the steering component, and the detection component when the quality assessment result is greater than the preset quality assessment level.

8. The tomographic endoscopic microspectral imaging system according to claim 1, characterized in that, The detection components are wholly or partially covered with a sterile membrane.

Images