CN112603240A - Medical endoscope system capable of realizing intelligent image processing - Google Patents
Medical endoscope system capable of realizing intelligent image processing Download PDFInfo
- Publication number
- CN112603240A CN112603240A CN202011484238.8A CN202011484238A CN112603240A CN 112603240 A CN112603240 A CN 112603240A CN 202011484238 A CN202011484238 A CN 202011484238A CN 112603240 A CN112603240 A CN 112603240A
- Authority
- CN
- China
- Prior art keywords
- image
- light source
- mode
- processing
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 128
- 238000005286 illumination Methods 0.000 claims abstract description 45
- 230000000694 effects Effects 0.000 claims abstract description 13
- 230000003595 spectral effect Effects 0.000 claims abstract description 10
- 238000004587 chromatography analysis Methods 0.000 claims description 34
- 238000004458 analytical method Methods 0.000 claims description 26
- 238000013473 artificial intelligence Methods 0.000 claims description 21
- 238000001228 spectrum Methods 0.000 claims description 18
- 230000003902 lesion Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 12
- 239000013307 optical fiber Substances 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 230000000762 glandular Effects 0.000 claims description 5
- 210000004400 mucous membrane Anatomy 0.000 claims description 5
- 210000004088 microvessel Anatomy 0.000 claims description 4
- 235000005811 Viola adunca Nutrition 0.000 claims description 3
- 240000009038 Viola odorata Species 0.000 claims description 3
- 235000013487 Viola odorata Nutrition 0.000 claims description 3
- 235000002254 Viola papilionacea Nutrition 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 206010065042 Immune reconstitution inflammatory syndrome Diseases 0.000 claims 2
- 238000003745 diagnosis Methods 0.000 description 12
- 238000000034 method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000001839 endoscopy Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000001079 digestive effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 210000002784 stomach Anatomy 0.000 description 3
- 206010028980 Neoplasm Diseases 0.000 description 2
- 208000005718 Stomach Neoplasms Diseases 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 210000003238 esophagus Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 210000002429 large intestine Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 208000025865 Ulcer Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000000426 electronic spectroscopy Methods 0.000 description 1
- 206010017758 gastric cancer Diseases 0.000 description 1
- 206010020718 hyperplasia Diseases 0.000 description 1
- 230000000968 intestinal effect Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 201000011591 microinvasive gastric cancer Diseases 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 201000011549 stomach cancer Diseases 0.000 description 1
- 201000000498 stomach carcinoma Diseases 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 231100000397 ulcer Toxicity 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/04—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/00002—Operational features of endoscopes
- A61B1/00004—Operational features of endoscopes characterised by electronic signal processing
- A61B1/00009—Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/06—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements
- A61B1/0661—Endoscope light sources
- A61B1/0684—Endoscope light sources using light emitting diodes [LED]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/06—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements
- A61B1/07—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements using light-conductive means, e.g. optical fibres
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0082—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes
- A61B5/0084—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes for introduction into the body, e.g. by catheters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Optics & Photonics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Endoscopes (AREA)
Abstract
The invention discloses a medical endoscope system capable of realizing intelligent image processing, which comprises an endoscope, an image processor and a cold light source system, wherein the endoscope is connected with the image processor; the endoscope collects images under the illumination light output by the cold light source system and transmits the collected images to the image processor for image processing. The image processor and the multispectral cold light source realize linkage control, and when the lighting effect of different spectral characteristic combinations of the cold light source is selected, the image processor adopts the corresponding chromatographic processing effect, so that the difference or the edge between the focus and the normal tissue can be more clearly displayed on the image.
Description
Technical Field
The present invention relates to a medical endoscope system, and more particularly, to a medical endoscope system capable of realizing intelligent image processing.
Background
At present, the endoscope technology has made great progress, and the image definition and the contrast are greatly improved. With the application of technologies such as contrast enhancement, contour enhancement and the like, the display definition of the focus (such as a convex lump and a concave ulcer) with obviously changed focus shape and color is greatly improved compared with that of the traditional endoscope. However, it is difficult to diagnose and even to make a missed diagnosis of small and flat early cancer, abnormal hyperplasia, and the like.
Therefore, in recent years, technologies such as pigment endoscopy, electronic spectroscopy, narrow-band imaging and the like are introduced in large quantities by endoscope companies at home and abroad, and the display definition of early canceration is greatly improved and the diagnosis level of an operator is obviously improved by utilizing novel digital image processing technologies such as narrow-band illumination, chromatographic enhancement, noise suppression and the like. However, these products require the physician experience to select the enhancement mode, e.g., different lesion features require different spectral combination illumination or image chromatograpy, but often inexperienced physicians have no choice or require long training to better differentiate the diagnosis.
It is reported that, in the current diagnosis of digestive endoscopy, particularly, in the examination and diagnosis of endoscopic early cancer of the stomach, the diagnosis rate in Japan is 70%, the diagnosis rate in Korea is 55%, and the diagnosis rate in China is only about 20%. Among them, the reason why the diagnosis rate of gastric cancer in early stage in China is not high is positively correlated with the high-low ratio of the diagnosis level of doctors and the missed diagnosis during examination. Therefore, how to improve the diagnostic level of an endoscopist by using technical means becomes the direction of efforts of the industry.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a medical endoscope system capable of realizing intelligent image processing, which can enable more information with diagnostic value to be displayed on an image acquired by an endoscope.
In order to solve the above technical problems, the medical endoscope system capable of realizing intelligent image processing according to the present invention comprises:
comprises an endoscope, an image processor and a cold light source system; the endoscope collects images under the illumination light output by the cold light source system and transmits the collected images to the image processor for image processing; the image processor comprises an image processing controller, the image processing controller transmits image information to an image enhancement processing module, and the image enhancement processing module performs enhancement processing on the image information and outputs an enhanced image to the image processing controller; the image enhancement processing module is connected with the image chromatography processing output module, and the image chromatography processing output module is provided with at least three image chromatography processing output modes so as to send images with different frequency spectrum characteristics to the image processing controller; the cold light source system comprises a blue laser light source, a green laser light source and a white light LED light source, wherein the blue laser light source, the green laser light source and the white light LED light source are respectively connected with a light source driver, and each light source driver is connected with a light source controller; the light source controller controls the three light source drivers to enable the three light sources to output different illumination spectrum combinations to form at least three spectrum illumination modes; the light source controller is connected with the image processing controller of the image processor through the communication module, and the communication module can realize the transmission of instruction signals between the image processor and the cold light source system.
In another embodiment, the three image chromatography processing output modes are a TP mode, a TV mode, and a TT mode; the TP mode is used for displaying glandular ducts and mucous membrane fine structures; under a TP mode, an image chromatography processing output module decomposes an image into R, G, B three channels and is matched with an amplification function; the TV mode is used for displaying microvessels; in the TV mode, the image chromatographic processing output module decomposes an image into R, G, B three channels, and R channel components are removed; the TT mode is used for realizing linkage control with the cold light source system, so that the image chromatography is used for processing and outputting the spectrum illumination mode control of the cold light source system.
In another embodiment, in the TT mode, the image chromatography processing output module sends an instruction to the light source controller through the communication module, so that the light source controller selects among three spectral illumination modes; and meanwhile, the image chromatographic processing output module automatically adjusts the image output color combination according to different spectral lighting modes selected by the light source controller.
In another embodiment, the three spectral illumination modes are a TE mode, a TG mode, and a TC mode; in the TE mode, the light source controller controls the three light source drivers to enable the illumination output to be the combination of blue laser and white light; the image chromatography processing output module dynamically reduces red development in the image; in the TG mode, the light source controller controls the three light source drivers to enable the illumination output to be the combination of blue laser, green laser and white light; the image chromatography processing output module dynamically increases the color development of blue light and green light while keeping the dynamic red reduction in the TE mode; under the TC mode, the light source controller controls the three light source drivers to enable the illumination output to be the combination of high-brightness blue laser and white light; the image chromatography processing output module keeps the dynamic red color reduction in the TE mode and enables the blue-violet illumination output to be in a high-brightness state.
In another embodiment, the image processor further comprises an artificial intelligence module, and the image processing controller transmits the image information to the artificial intelligence module for intelligent analysis and then transmits the image information subjected to intelligent analysis to the image processing controller.
In another embodiment, the artificial intelligence module comprises a multi-model fusion unit and a lesion tracking unit; the artificial intelligence module detects and tracks suspicious focuses in the image information through AI intelligent analysis, marks the suspicious focuses on the focus positions, and then sends an intelligent analysis result to the image processing controller, the image processing controller sends the intelligent analysis result to a light source controller of the cold light source system through the communication module, and the light source controller controls three light source drivers according to the intelligent analysis result so that the three light sources output different light sources according to the intelligent analysis result; meanwhile, the image processing controller sends the image with the intelligent analysis result to the image enhancement processing module, and the image enhancement processing module carries out image enhancement processing on the image with the intelligent analysis result.
In another embodiment, the image processor further comprises an automatic dimming module, the automatic dimming module outputs an automatic dimming command to the light source controller of the cold light source system according to the image display effect, and the light source controller adjusts the illumination brightness of the three light sources according to the automatic dimming command.
In another embodiment, the blue laser light source, the green laser light source and the white light LED light source are respectively connected to an optical fiber combiner through couplers; the optical fiber beam combiner is connected with the speckle removing device, the speckle removing device is connected with the optical path expander and the collimator through optical fibers, and the optical path expander and the collimator are fixedly arranged at the front part of the IRIS diaphragm assembly; the despeckle device and the IRIS diaphragm assembly are connected with the light source controller.
In another embodiment, the blue laser has a wavelength of 415 nm; the wavelength of the green laser is 532 nm; the wavelength of the white light LED is 400-800 nm.
In another embodiment, the image information from the endoscope is input to the image processing controller through a signal and power isolator.
The invention can achieve the technical effects that:
the image processor and the multispectral cold light source realize linkage control, and when the lighting effect of different spectral characteristic combinations of the cold light source is selected, the image processor adopts the corresponding chromatographic processing effect, so that the difference or the edge between the focus and the normal tissue can be more clearly displayed on the image.
According to the invention, the artificial intelligence module is embedded in the image processor, when the image processor captures the focus property or the inspection area judged by artificial intelligence, the image processing controller of the image processor outputs a corresponding command to the cold light source, and the cold light source outputs a corresponding illumination spectrum combination according to the command, so that the displayed endoscope image focus is easier to identify.
The artificial intelligence module embedded in the image processor is provided with a focus tracking unit, and can automatically track and mark the focus judged by the artificial intelligence system in the process of endoscopy so as to prompt doctors to observe intensively.
The artificial intelligence module embedded in the image processor is provided with a multi-model fusion unit, and can display the focus area block diagram judged by artificial intelligence in real time.
The invention combines the control and image enhancement processing of the light source with artificial intelligence AI, and can display more information with diagnostic value on the image collected by the endoscope.
The invention adopts multi-spectrum illumination light formed by the laser light source and the white light source, combines the narrow-band spectrum generated by the laser light source with the wide-band spectrum generated by the white light source, and can enable the image collected by the endoscope under the illumination light to present more information with diagnostic significance.
Drawings
It is to be understood by those skilled in the art that the following description is only exemplary of the principles of the present invention, which may be applied in numerous ways to achieve many different alternative embodiments. These descriptions are made for the purpose of illustrating the general principles of the present teachings and are not meant to limit the inventive concepts disclosed herein.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the general description given above and the detailed description of the drawings given below, serve to explain the principles of the invention.
The invention is described in further detail below with reference to the following figures and detailed description:
FIG. 1 is a schematic diagram of a medical endoscope system capable of intelligent image processing in accordance with the present invention;
FIG. 2 is a schematic flow chart of the method for diagnosing early gastric cancer based on deep learning multi-model fusion technology adopted by the multi-model fusion unit of the artificial intelligence module;
FIG. 3 is a schematic flow chart of a digestive endoscopy lesion tracking method based on time series characteristic learning, which is adopted by a lesion tracking unit of an artificial intelligence module according to the present invention;
FIG. 4 is a diagram of the image display effect in the TE mode;
fig. 5 is a diagram of an image display effect in the TG mode;
fig. 6 is a diagram of an image display effect in the TC mode.
Detailed Description
In order to make the objects, 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 drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention. Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. As used herein, the terms "first," "second," and the like, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" and similar words are intended to mean that the elements or items listed before the word cover the elements or items listed after the word and their equivalents, without excluding other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As shown in fig. 1, the medical endoscope system capable of realizing intelligent image processing of the present invention includes an endoscope, an image processor, and a cold light source system; the endoscope collects images under the illumination light output by the cold light source system and transmits the collected images to the image processor for image processing;
the image processor comprises an image processing controller, and image information collected by the endoscope is input into the image processing controller through a signal and power supply isolator; the signal and power supply isolator is a circuit measure taken for safety, so that an electric signal photoelectric isolation circuit is formed between the endoscope and the image processor;
the image processing controller transmits the image information to the image enhancement processing module, the image enhancement processing module carries out edge enhancement, structure enhancement, contrast enhancement and denoising processing on the image, and the image subjected to enhancement processing is output to the image processing controller; the image enhancement processing module is connected with the image chromatography processing output module, and the image chromatography processing output module has three image chromatography processing output modes, namely a TP mode, a TV mode and a TT mode, so that images with different spectrum characteristics are sent to the image processing controller;
the image processing controller is connected with the video signal processing module, and the image processing controller realizes video output of the received image with the frequency spectrum characteristic on the color display through the video signal processing module; the video signal processing module can output digital video signals and analog video signals;
the image processor also comprises an artificial intelligence module (AI module), the image processing controller transmits the image information to the artificial intelligence module for intelligent analysis, and then transmits the image information subjected to the intelligent analysis to the image processing controller;
the image processor also comprises an automatic dimming module (IRIS), the automatic dimming module can output an automatic dimming command to a light source controller of the cold light source system according to an image display effect, and the light source controller adjusts the illumination brightness of the three light sources according to the automatic dimming command, so that the illumination brightness is automatically reduced when the endoscope is close to a focus and the illumination brightness is too high; when the endoscope is far away from the focus to observe a large range, the illumination brightness is increased.
The cold light source system comprises 415nmLD light source, 532nmLD light source and white light LED (wavelength is 400-800 nm) light source, thereby having multi-spectrum illumination characteristic; the 415nmLD light source, the 532nmLD light source and the white light LED light source are respectively connected with a light source driver, and each light source driver is respectively connected with a light source controller; the light source controller controls the three light source drivers to enable the three light sources to output different illumination spectrum combinations to form three spectrum illumination modes, namely a TE mode, a TG mode and a TC mode; the light source controller is connected with an image processing controller of the image processor through a communication module, and the communication module can realize the transmission of instruction signals between the image processor and the cold light source system;
the 415nmLD light source, the 532nmLD light source and the white light LED light source are respectively connected with the optical fiber beam combiner through couplers; the optical fiber beam combiner is connected with the speckle remover, the speckle remover is connected with the optical path expander (namely a beam expander) and the collimator through optical fibers, and the optical path expander and the collimator are fixedly arranged at the front part of the IRIS diaphragm assembly;
the speckle remover and the IRIS diaphragm assembly are connected with the light source controller; the light source controller is connected with the control panel to realize the control of the light source controller;
the 415nmLD light source, the 532nmLD light source and the white light LED light source output optical fibers in a mode of optical fiber coupling output under the drive of respective drivers, and are mixed by an optical fiber beam combiner to form one path of light which is output to a speckle remover; when the 415nmLD light source and the 532nmLD light source work, the light source controller controls the speckle removing device to work so as to solve the speckle influence during laser illumination; the light path forms an illumination spot with the diameter of 6mm after passing through the light path expander and the collimator;
the light source controller has two modes of manual dimming and automatic dimming; when the manual dimming is selected, the illumination brightness can be manually adjusted on the control panel; when the automatic dimming is selected, the brightness of the output illumination is controlled by the output instruction of the automatic dimming module.
The TP mode of the image chromatography processing output module is used for displaying the glandular duct and mucous membrane microstructure, namely the property of the focus needing to be enhanced or the part of the focus under the TP mode is the glandular duct and mucous membrane microstructure; under a TP mode, the image chromatography processing output module decomposes an image into R, G, B three channels so as to increase the level of the integral R channel, so that lesions are displayed more obviously through color change, and meanwhile, the image chromatography processing output module is matched with an amplification function so as to observe the slight change of the glandular duct and the mucous membrane; the TP mode can be started in the whole process of the inspection;
the TV mode of the image chromatography processing output module is used for displaying the microvessels, namely the focus property needing to be enhanced or the part under the TV mode is the microvessels; in a TV mode, the image is decomposed into R, G, B channels by the image chromatography processing output module, R channel components are artificially removed, and because the blood absorbs short-wavelength light (G, B) during imaging, the change of the microvasculature can be displayed, and the benign or malignant degree of the lesion can be judged according to the change of the microvasculature;
the TT mode of the image chromatography processing output module can realize linkage control with the cold light source system; in the TT mode, an image chromatography processing output module of the image enhancement processing module sends an instruction to the light source controller through the communication module, so that the light source controller can select from the TE mode, the TG mode and the TC mode; meanwhile, the image chromatographic processing output module automatically adjusts image output color combinations according to different modes selected by the light source controller, and outputs different RGB three-color combinations so as to adapt to endoscope images under illumination of three special spectrum combinations; the spectral characteristic image output in the TT mode is controlled by a light source controller of the cold light source system and an image chromatographic processing output module of the image enhancement processing module;
the TE mode is used for displaying the esophagus, namely the enhancement property of the focus under the TE mode or the esophagus is the position of the focus; in the TE mode, the light source controller controls the three light source drivers to enable the illumination output to be a combination of 415nm violet-blue light and white light; the image chromatography processing output module dynamically reduces red development in the image, and the display effect of the processed image is that the whole image is blue, so that the capillary vessels in the endoscopic image are enhanced, as shown in fig. 4;
the TG mode is used for displaying the stomach, namely the property of the focus needing to be enhanced or the part of the focus under the TG mode is the stomach; in a TG mode, the light source controller controls three light source drivers to enable the illumination output to be the combination of 415nm blue laser, 532nm green laser and white light; the image chromatography processing output module dynamically increases the color development of blue light and green light while keeping the dynamic red color reduction in the TE mode, so that the flat focus in the endoscopic image is enhanced and displayed, as shown in fig. 5;
the TC mode is used for displaying the large intestine, namely the property of the focus needing enhancement or the part of the focus under the TC mode is the large intestine; in the TC mode, the light source controller controls three light source drivers to enable the illumination output to be the combination of high-brightness 415nm blue laser and white light; the image chromatography processing output module keeps the dynamic red color reduction in the TE mode, and simultaneously makes the blue-violet illumination output in a high-brightness state, so that the contrast effect on the focus and the normal tissue is obvious when the image chromatography processing output module is applied to the intestinal examination, as shown in fig. 6.
The artificial intelligence module (AI module) comprises a multi-model fusion unit and a focus tracking unit; the artificial intelligence module detects and tracks suspicious focuses in the images through AI intelligent analysis, marks the suspicious focuses on the focus positions, and then sends intelligent analysis results to the image processing controller, the image processing controller sends the intelligent analysis results to the light source controller of the cold light source system through the communication module, and the light source controller controls the three light source drivers according to the intelligent analysis results, so that the three light sources output different light sources according to the intelligent analysis results; meanwhile, the image processing controller sends the image with the intelligent analysis result to the image enhancement processing module, and the image enhancement processing module carries out image enhancement processing on the image with the intelligent analysis result;
the multi-model fusion unit adopts a stomach early cancer auxiliary diagnosis method (application date: 7/14/2020 and application number: 2020106754760) based on a deep learning multi-model fusion technology disclosed by Chinese invention patent document CN111899229A, utilizes the deep learning multi-model fusion technology to identify lesions in an image, detects suspicious lesions in the image, marks the lesion parts by frames, and marks high-risk lesions; for example, a high risk region is represented by a red frame mark at a lesion site, and a low risk region is represented by a green frame mark at the lesion site, as shown in fig. 2;
the focus tracking unit adopts a focus tracking method under a digestive endoscopy based on time sequence characteristic learning (application date: 7/14/2020 and application number: 2020106745831) disclosed by Chinese invention patent document CN111915573A, and the specific method is shown in FIG. 3 for tracking the area and position of the focus in real time in the endoscopic examination process.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents.
Claims (10)
1. A medical endoscope system capable of realizing intelligent image processing is characterized by comprising an endoscope, an image processor and a cold light source system; the endoscope collects images under the illumination light output by the cold light source system and transmits the collected images to the image processor for image processing;
the image processor comprises an image processing controller, the image processing controller transmits image information to an image enhancement processing module, and the image enhancement processing module performs enhancement processing on the image information and outputs an enhanced image to the image processing controller; the image enhancement processing module is connected with the image chromatography processing output module, and the image chromatography processing output module is provided with at least three image chromatography processing output modes so as to send images with different frequency spectrum characteristics to the image processing controller;
the cold light source system comprises a blue laser light source, a green laser light source and a white light LED light source, wherein the blue laser light source, the green laser light source and the white light LED light source are respectively connected with a light source driver, and each light source driver is connected with a light source controller; the light source controller controls the three light source drivers to enable the three light sources to output different illumination spectrum combinations to form at least three spectrum illumination modes; the light source controller is connected with the image processing controller of the image processor through the communication module, and the communication module can realize the transmission of instruction signals between the image processor and the cold light source system.
2. The medical endoscope system capable of realizing intelligent image processing according to claim 1, wherein the three image chromatography processing output modes are TP mode, TV mode and TT mode;
the TP mode is used for displaying glandular ducts and mucous membrane fine structures; under a TP mode, an image chromatography processing output module decomposes an image into R, G, B three channels and is matched with an amplification function;
the TV mode is used for displaying microvessels; in the TV mode, the image chromatographic processing output module decomposes an image into R, G, B three channels, and R channel components are removed;
the TT mode is used for realizing linkage control with the cold light source system, so that the image chromatography is used for processing and outputting the spectrum illumination mode control of the cold light source system.
3. The medical endoscope system capable of realizing intelligent image processing according to claim 2, wherein in the TT mode, the image chromatography processing output module sends a command to the light source controller through the communication module, so that the light source controller can select from three spectral illumination modes; and meanwhile, the image chromatographic processing output module automatically adjusts the image output color combination according to different spectral lighting modes selected by the light source controller.
4. The medical endoscope system capable of realizing intelligent image processing according to claim 1 or 3, wherein the three spectral illumination modes are a TE mode, a TG mode and a TC mode;
in the TE mode, the light source controller controls the three light source drivers to enable the illumination output to be the combination of blue laser and white light; the image chromatography processing output module dynamically reduces red development in the image;
in the TG mode, the light source controller controls the three light source drivers to enable the illumination output to be the combination of blue laser, green laser and white light; the image chromatography processing output module dynamically increases the color development of blue light and green light while keeping the dynamic red reduction in the TE mode;
under the TC mode, the light source controller controls the three light source drivers to enable the illumination output to be the combination of high-brightness blue laser and white light; the image chromatography processing output module keeps the dynamic red color reduction in the TE mode and enables the blue-violet illumination output to be in a high-brightness state.
5. The medical endoscope system capable of realizing intelligent image processing according to claim 1, wherein said image processor further comprises an artificial intelligence module, said image processing controller transmits said image information to said artificial intelligence module for intelligent analysis, and then transmits said intelligently analyzed image information to said image processing controller.
6. The medical endoscope system capable of intelligent image processing according to claim 5, wherein the artificial intelligence module comprises a multi-model fusion unit and a lesion tracking unit; the artificial intelligence module detects and tracks suspicious focuses in the image information through AI intelligent analysis, marks the suspicious focuses on the focus positions, and then sends an intelligent analysis result to the image processing controller, the image processing controller sends the intelligent analysis result to a light source controller of the cold light source system through the communication module, and the light source controller controls three light source drivers according to the intelligent analysis result so that the three light sources output different light sources according to the intelligent analysis result; meanwhile, the image processing controller sends the image with the intelligent analysis result to the image enhancement processing module, and the image enhancement processing module carries out image enhancement processing on the image with the intelligent analysis result.
7. The medical endoscope system capable of realizing intelligent image processing according to claim 1, wherein the image processor further comprises an automatic dimming module, the automatic dimming module outputs an automatic dimming command to the light source controller of the cold light source system according to the image display effect, and the light source controller adjusts the illumination brightness of the three light sources according to the automatic dimming command.
8. The medical endoscope system capable of realizing intelligent image processing according to claim 1, wherein the blue laser light source, the green laser light source and the white light LED light source are respectively connected with an optical fiber beam combiner through couplers; the optical fiber beam combiner is connected with the speckle removing device, the speckle removing device is connected with the optical path expander and the collimator through optical fibers, and the optical path expander and the collimator are fixedly arranged at the front part of the IRIS diaphragm assembly; the despeckle device and the IRIS diaphragm assembly are connected with the light source controller.
9. The medical endoscope system capable of realizing intelligent image processing according to claim 1, wherein the wavelength of the blue laser light is 415 nm; the wavelength of the green laser is 532 nm; the wavelength of the white light LED is 400-800 nm.
10. The medical endoscope system according to claim 1, wherein the image information from the endoscope is inputted to the image processing controller via a signal and power isolator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011484238.8A CN112603240A (en) | 2020-12-16 | 2020-12-16 | Medical endoscope system capable of realizing intelligent image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011484238.8A CN112603240A (en) | 2020-12-16 | 2020-12-16 | Medical endoscope system capable of realizing intelligent image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112603240A true CN112603240A (en) | 2021-04-06 |
Family
ID=75240950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011484238.8A Pending CN112603240A (en) | 2020-12-16 | 2020-12-16 | Medical endoscope system capable of realizing intelligent image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112603240A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113576382A (en) * | 2021-07-05 | 2021-11-02 | 合肥德铭电子有限公司 | 4K fluorescence integration chamber mirror system with intelligence function of coincide |
| CN116437221A (en) * | 2023-04-21 | 2023-07-14 | 极限人工智能有限公司 | Method and system for intercepting endoscope video image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201948983U (en) * | 2010-12-10 | 2011-08-31 | 孔令华 | Real-time multi-spectral endoscope |
| CN202960439U (en) * | 2012-08-01 | 2013-06-05 | 深圳市雷迈科技有限公司 | Multi-purpose light source for medical endoscope |
| CN103169446A (en) * | 2013-04-15 | 2013-06-26 | 叶衍铭 | Suspicious early-stage cancer lesion examination device suitable for endoscopy |
| US20160022126A1 (en) * | 2013-03-15 | 2016-01-28 | Ajay RAMESH | Endoscopic light source and imaging system |
| CN109222865A (en) * | 2018-10-17 | 2019-01-18 | 卓外（上海）医疗电子科技有限公司 | A kind of multi-modality imaging endoscopic system |
-
2020
- 2020-12-16 CN CN202011484238.8A patent/CN112603240A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201948983U (en) * | 2010-12-10 | 2011-08-31 | 孔令华 | Real-time multi-spectral endoscope |
| CN202960439U (en) * | 2012-08-01 | 2013-06-05 | 深圳市雷迈科技有限公司 | Multi-purpose light source for medical endoscope |
| US20160022126A1 (en) * | 2013-03-15 | 2016-01-28 | Ajay RAMESH | Endoscopic light source and imaging system |
| CN103169446A (en) * | 2013-04-15 | 2013-06-26 | 叶衍铭 | Suspicious early-stage cancer lesion examination device suitable for endoscopy |
| CN109222865A (en) * | 2018-10-17 | 2019-01-18 | 卓外（上海）医疗电子科技有限公司 | A kind of multi-modality imaging endoscopic system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113576382A (en) * | 2021-07-05 | 2021-11-02 | 合肥德铭电子有限公司 | 4K fluorescence integration chamber mirror system with intelligence function of coincide |
| CN116437221A (en) * | 2023-04-21 | 2023-07-14 | 极限人工智能有限公司 | Method and system for intercepting endoscope video image |
| CN116437221B (en) * | 2023-04-21 | 2024-04-05 | 极限人工智能有限公司 | Method and system for intercepting endoscope video image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4009626B2 (en) | Endoscope video signal processor | |
| US10779714B2 (en) | Image processing apparatus, method for operating image processing apparatus, and image processing program | |
| JP4732548B2 (en) | Endoscope system and endoscope image processing apparatus | |
| KR101184841B1 (en) | Endoscopic device and its processing method | |
| CN108109134B (en) | Image processing apparatus and method for operating the same | |
| JP5997817B2 (en) | Endoscope system | |
| US20190069769A1 (en) | Living body observation system | |
| WO2007116663A1 (en) | Endoscope device | |
| CN112603240A (en) | Medical endoscope system capable of realizing intelligent image processing | |
| JP6259747B2 (en) | Processor device, endoscope system, operating method of processor device, and program | |
| CN112367898A (en) | Endoscope device and method for operating endoscope device | |
| CN106963328A (en) | The LASER Light Source and means of illumination of illumination are dyed for Medical endoscope spectrum | |
| EP4035585A1 (en) | Image processing device, endoscopic system, and operation method of image processing | |
| US20070269087A1 (en) | Endoscope processor, computer program product, endoscope system, and endoscope image playback apparatus | |
| JP6285373B2 (en) | Endoscope system, processor device, and operation method of endoscope system | |
| JP7217351B2 (en) | Image processing device, endoscope system, and method of operating image processing device | |
| JPH06269409A (en) | Endoscope apparatus | |
| CN111568549A (en) | Visualization system with real-time imaging function | |
| US20240013392A1 (en) | Processor device, medical image processing device, medical image processing system, and endoscope system | |
| JP2013005981A (en) | Light source device and imaging system | |
| CN217365794U (en) | Endoscope lighting device | |
| JPH06339459A (en) | Endoscope device | |
| JP5885652B2 (en) | Imaging apparatus, endoscope apparatus, and biological pattern enhancement processing method | |
| JP3892699B2 (en) | Electronic endoscope system | |
| JP7090699B2 (en) | How to operate the endoscope device and the endoscope device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |