Medical image tuning device

Abstract

The utility model relates to a medical image tuning device, and belongs to the technical field of image processing. The utility model relates to a medical image tuning device, which comprises a lighting element, a camera, an optical hard mirror, a photosensitive element, a camera cable, a camera host, a signal connecting line and a rear end device, by adopting the design of the utility model, low-delay and high-pixel transmission is satisfied, the image information is completely reserved, the camera host can better complete image processing, and the final image quality is guaranteed; the problem of image information loss caused by image processing at the camera module end is reduced, and the problems of module temperature rise, component damage, influence on imaging quality and the like caused by image processing at the camera module end are solved.

Description

TECHNICAL FIELD

[0001] The utility model relates to belong to image processing technical field especially, relate to a kind of medical image tuning device. BACKGROUND

[0002] The endoscope is generally inserted into the body of the subject in an elongated flexible insertion portion, and the illumination light supplied by the light source device is illuminated from the front end of the insertion portion. The image inside the body is captured by the reflection light of the illumination light received by the camera portion at the front end of the insertion portion.

[0003] The disclosed patent: invention name, GPU-based endoscope real-time image processing method and system, publication number: CN117593437A, application publication date 2024.02.23. The system comprises: a data acquisition module for acquiring endoscope real-time images and endoscope related parameter information, the related parameter information at least includes endoscope position, moving direction, moving speed, jitter offset value and specification parameter, the endoscope real-time image includes multiple narrowband images; image processing module, for fusing the multiple narrowband images to obtain first image information, and based on the first image information, constructing the corresponding three-dimensional scene; correction module, for determining the target parameter evaluation value based on the related parameter information, and correcting the three-dimensional scene according to the target parameter evaluation value to obtain second image information; information pushing module, for responding to detecting that the second image information meets the preset standard, rendering the second image information by GPU, and pushing the rendered second image information to the display terminal.

[0004] The above disclosed patent technology does not know that image processing is not processed at the same time, and first image and second image are obtained in turn; the system can only be used for endoscope image system;

[0005] Patent disclosed: invention name: a 3D fluorescence endoscope, imaging method, device and debugging method, publication number: CN117398043A, application publication date: 2024.01.16. A kind of 3D fluorescence endoscope, imaging method, device and debugging method are disclosed, belong to endoscope field, endoscope includes endoscope sleeve, objective lens and photosensitive element arranged in endoscope sleeve, objective lens and photosensitive element are provided with light splitting device, light splitting device is divided into left visible light beam, left fluorescent beam, right visible light beam and right fluorescent beam of light beam passing through objective lens to photosensitive element, light splitting device and photosensitive element are provided with left focusing mirror of making left visible light beam and left fluorescent beam optical path consistent and right focusing mirror of making right visible light beam and right fluorescent beam optical path consistent. The endoscope can make four light beams image on photosensitive element at the same time, left and right images have no time difference, visible light image and fluorescent image also have no time difference, the whole endoscope only uses a photosensitive element, can realize time, focal plane consistency in smaller space, it is conducive to realizing 3D fluorescence endoscope miniaturization and high sensitivity display. The technology of the above disclosed patent is unknown: there are four photosensitive elements, the image obtained by the light reflected twice on the photosensitive element is the mirror image of the mirror image of the real object, the direction is consistent with the light directly passing through the dichroic mirror 21, which is convenient for image processing operation during imaging; the system can only be used for 3D imaging endoscope system; it does not involve image tuning, but only processes image signals.

[0006] It is necessary to research and develop a medical endoscope image tuning device to improve image quality and accuracy. Practical new type content

[0007] In order to overcome the shortcomings of the existing medical endoscope image technology, a medical image tuning device is invented.

[0008] A medical image tuning device, comprising an illumination element, further comprising a camera front end, a camera host, and a rear end device;

[0009] The camera front end comprises an optical rigid scope, a camera, an optical bayonet, a filter, a photosensitive element, a gyroscope, a key plate, a camera mainboard, a serial board, and a camera cable.

[0010] The gyroscope is connected with the key plate, and the key plate is connected with the camera mainboard.

[0011] The filter is arranged at the front end of the photosensitive element, and the gyroscope is built-in on the camera key plate.

[0012] The filter filters out interfering colors, and transmits the filtered image to the photosensitive element.

[0013] The photosensitive element transmits image data to the input interface of the camera host through the camera cable, and the gyroscope also transmits state information to the camera host, and the camera host processes the image according to the gyroscope information;

[0014] The camera host comprises a host mainboard, a video output board, a core board, a hard disk, a deserializing board, a touch screen, a host power supply, a fan, a video expansion board, a network port, a USB port, an RS232 port, a signal output port, a display, a signal connection line, and a signal input interface.

[0015] The camera cable is a GMSL3 data line.

[0016] The photosensitive element is used for collecting the image obtained by the camera.

[0017] The host mainboard comprises a core board, and the core board comprises a fusion algorithm module, wherein the fusion algorithm module comprises an acquisition module, a DPC module, a BLC module, a WB module, a Demosaic module, a Gamma correct module, a CCM module, a Contrast / Brightness Enhancement module, an NR module, an EdgeEnhancement module, an output module, an AEStat module, and an AE Control module.

[0018] The output module comprises a video output board, a video expansion board, and a signal output end, and the signal output end comprises a signal output port, a network port, a USB port, and an RS232 port.

[0019] The host mainboard is connected with the touch screen, the video expansion board, and the signal output end, and the rear-end device comprises a display or a remote receiving device.

[0020] The hardware connection relationship of the medical image tuning device is that the lens of the optical rigid scope collects image information of a target area, the optical rigid scope is connected with an optical bayonet in a matched mode, the collected image information is optically transmitted to a filter, the photosensitive element is connected with a camera host board, the gyroscope is connected with the camera host board, a key board is connected with the camera host board, the camera host board is connected with a serial board, the serial board is connected with a deserializing board through a camera cable, the deserializing board is connected with a core board, the core board is connected with a hard disk and a video output board, the video output board is connected with a video expansion board, the video expansion board is connected with a signal output port, and a signal input interface is connected with a display.

[0021] The image data transmission relationship of the medical image optimization device is: the camera converts the collected optical signal into an electrical signal through a photosensitive element and transmits it to the camera mainboard; the gyroscope collects the state information of the photosensitive element and outputs it to the camera mainboard; the serial board converts the data of the camera mainboard into serial data and transmits it to the deserializing board at a high speed through the camera cable; the deserializing board converts the serial data into parallel data and inputs it to the camera host; the camera host processes the image based on the gyroscope information; the number of connected cameras and the pixels are read by the fusion algorithm module on the core board of the camera host, and the built-in image processing algorithm module is automatically matched; preprocessing is performed through the exposure algorithm module, the noise reduction algorithm module, and the contrast enhancement algorithm module to obtain a single or multiple images as state 1; the image features of state 1 are extracted, and a single image algorithm module or a multiple image fusion algorithm module is automatically selected to obtain state 2 through the fusion algorithm module; the state 2 image is distributed and recognized as a single image, and the processed spectral filtered image and normal image are output respectively; the core board is connected with the image ISP processing module, the ISP processing module is connected with the host mainboard, the host mainboard outputs image data to the signal output port, the signal output port outputs to the display, and the display displays the optimized image, or the signal output port transmits the image to a remote device through wired or wireless network.

[0022] The camera collects single, double, four or six camera images; single camera refers to one camera sensor chip; double camera refers to double camera sensor chip; four camera refers to four camera sensor chip; six camera refers to six sensor chip; the camera is divided into left camera and right camera.

[0023] The filter is used to filter stray light and allow only 400-650nm light to enter the photosensitive element.

[0024] The photosensitive element is any one of CMOS, CCD or infrared sensor chip.

[0025] The filtered image includes any one of medical endoscope, ultrasound, X-ray machine, CT\ET original medical image data.

[0026] The camera refers to reading 1, 2, 4 or 6 resolution 4k, 60 frame rate medical image original data.

[0027] The method steps of medical image optimization are:

[0028] Step 1, set the filter in front of the photosensitive element to filter stray light and avoid image interference;

[0029] Step two, in order to realize the protection of image information integrity, high pixel, after the photosensitive element to collect the image will be parallel data, through the serial board for serial processing, realize high speed transmission;

[0030] Step three, using GMSL3 transmission mode, get 6Gbps transmission rate, the image to the deserial board, the serial signal into parallel signal; And the parallel signal transmission to the core board;

[0031] In this process, the gyro will photosensitive element position information real-time transmission to the core board, to correct the image;

[0032] Step four: the core board fusion algorithm module automatically identifies the number of connected camera and pixel, automatically matches the built-in image processing algorithm module, through the exposure algorithm module, denoising algorithm module, enhance the contrast algorithm module for pretreatment, color restoration, image fusion and other processing, get single or multiple images, as state 1;

[0033] Step five: extract the image features of state 1, automatically select single image algorithm module, or multi image fusion algorithm module, through the fusion algorithm module to get state 2;

[0034] Step six: the state 2 image is distributed, identified as single image or multiple images, and output the spectral filtered image and normal image after processing;

[0035] Step seven: image ISP processing module continues to process single image or multiple images;

[0036] Step eight: the core board transmits the processed image signal to the signal output port, and outputs the processed video signal to the display, and displays the camera image in real time;

[0037] Step nine: according to the instruction issued by the serial port control, the video signal processed by the core board can be stored on the hard disk or transmitted through the network port.

[0038] The definition and explanation of terms in this patent:

[0039] Optical hard mirror: referred to as lens, the lens used in endoscope has a kind of optical hard mirror. Optical hard mirror is a type of endoscope, its characteristics lies in that the optical components are made of columnar glass, and the outer tube is metal structure, and the outer tube is not flexible. It is mainly composed of mechanical system, optical system and light guide system.

[0040] Gyroscope: bmi088, clear photosensitive element position information.

[0041] GMSL3: high speed transmission data reaches 6Gbps.

[0042] MIPI (Mobile Industry Processor Interface) is a high-performance, low-power, and low-cost serial communication interface developed by the MIPI Alliance. Its purpose is to standardize internal device interfaces such as camera, display screen interface, and RF / baseband interface, thereby reducing the complexity of device design and increasing design flexibility.

[0043] Filter: used to filter stray light, ensuring that natural light 450-650nm enters the photosensitive element.

[0044] Serial board uses chip: MAX96789.

[0045] Deserializing board uses chip: MAX96752.

[0046] 4K medical endoscope: sensor collects image signals and outputs them to a 4K display in real time, providing an image system for medical personnel to watch during surgery.

[0047] Image ISP (Image Signal Processor) processing module is a dedicated processor or hardware module for real-time processing and optimization of image or video signals.

[0048] Sensor (Sensor): used to collect images, with a pixel reaching 4K.

[0049] Photosensitive element: a type of sensor, mainly used in endoscopes. The photosensitive element (such as a CCD or CMOS chip) is actually a special sensor designed to convert optical signals into electrical signals.

[0050] Sensor input: sensor collects image input into the ISP pipeline.

[0051] DPC (Dead Pixel Correction): image dead pixel detection: detects dead pixels in the sensor and corrects these dead pixels. Dead pixels are white pixels in the output image under a full black environment and black pixels in the output image under a high light environment.

[0052] BLC (Black Level Compensation): black level compensation: from the characteristics of the sensor, the lowest output voltage of the sensor is the black level voltage. By calibrating the black level size, the influence of the black level on the image is eliminated.

[0053] WB (White Balance): white balance: corrects color deviations in the sensor under different color temperatures. Through white card calculation of RGB three-channel gain value, white balance correction is completed.

[0054] Demosaic: Removes mosaic effects from images captured by a single CMOS sensor that contain only one color in the RGB spectrum. It restores the missing colors in the image through interpolation.

[0055] Gamma Correction, also known as gamma correction or gamma nonlinearity adjustment, is a nonlinear operation or inverse operation technique used to adjust image or video signals. It is used to encode and decode linear brightness or RGB values ​​to match the nonlinear characteristics of display devices. Furthermore, gamma correction can expand or compress the dynamic range of an image.

[0056] CCM (Color Correction Matrix): Due to the non-ideal nature of the sensor's spectral response and the different spectral distribution of the ambient light source, there will be a large color difference between the sensor image and the actual scene. By calculating the color correction matrix, the image color can be adjusted to make the image color closer to the actual color.

[0057] Contrast / Brightness Enhancement: By enhancing image contrast and brightness, it makes the brightness distribution of images under non-uniform lighting more uniform and enhances the image's transparency.

[0058] NR (Noise Reduction): Reduces image noise using low-pass filters such as Gaussian and median filters.

[0059] Edge Enhancement: This feature uses edge detection technology to extract image edges and enhance them, thereby improving image sharpness.

[0060] Output: Convert RGB image format to YUV420 output.

[0061] AE Stat: Automatic Exposure Information Statistics: Statistics on image brightness, variance, histogram, etc., used to assess whether the current image is underexposed or overexposed.

[0062] AE Control: Evaluates the current exposure based on exposure statistics, calculates the exposure parameters for the next frame, and transmits the exposure parameters of the next frame back to the sensor to complete automatic exposure control.

[0063] Contrast enhancement refers to adjusting the contrast of an image to make its details clearer and enhance its visual appeal. Contrast refers to the degree of difference between the brightest and darkest parts of an image; by increasing this difference, the details of the image can be made more prominent.

[0064] Brightness Enhancement is to adjust the brightness level of the image, making it brighter or darker. Brightness refers to the average light intensity of the image, by adjusting the brightness, you can change the light and dark degree of the image, so as to affect the visual effect.

[0065] CCD: Charge Coupled Device, is a kind of semiconductor device for image acquisition.

[0066] CMOS: is the abbreviation of Complementary Metal Oxide Semiconductor; it is an integrated technology that makes transistors, resistors, capacitors and diodes on the same silicon wafer with standard process. CMOS chip has the advantages of low power consumption, high integration, strong anti-interference ability, etc. It is widely used in microprocessors, digital signal processors, memories and image sensors.

[0067] GMSL3: is the third generation of Gigabit Multimedia Serial Link technology; high data transmission rate: GMSL3 supports up to 12Gbps data transmission rate, which can meet the bandwidth demand of high-definition camera and other high-speed data transmission equipment; low delay: realize low delay of video data transmission, ensure the real-time of system.

[0068] Core board: adopt custom NVIDIA AGX Orin 64G as core board, used for processing image information received by camera.

[0069] Table 1: core board technical parameter table

[0070]

[0071] The significant progress and creative technical features of the utility model are:

[0072] Technical route adopts: the interference of filter filters out the mixed color, only allows 400-650nm light to pass through and transmit to the photosensitive element; the photosensitive element transmits image data to the input interface of the camera host through the GMSL3 data line, and the gyroscope also transmits the state information to the rear end at high speed, the host integrates the gyroscope information, processes the image, and obtains the ideal medical image after fusion; other patents do not write the use of filter, which may cause the image quality to be affected by stray light;

[0073] Low-delay endoscope camera module: collect high-pixel images, reach 3840*2160@60Hz, and transmit the images to the backend without processing; the main purpose is to overcome the image information loss caused by image processing at the camera module end, and to overcome the problems that image processing at the camera module end may cause the temperature of the module to rise, damage components, affect imaging quality, etc.;

[0074] The technical purpose achieved: the main purpose is to meet the transmission of low delay and high pixels, and the image information is completely preserved, and the powerful host at the backend can better complete the processing of the image, so as to guarantee the final image quality. Other patents perform image processing at the front end of the camera, which may cause the loss of image information. The present patent adopts a backend processing method to save image information;

[0075] The technical effect achieved: the optimized image data is transmitted to the display screen for real-time display and play, for the medical staff to refer. The optimized image data can also be processed in the GPU chip processor, and the processed result can be superimposed on the optimized image data and transmitted to the display screen for real-time display. The optimized image data can also be copied to an external storage device, such as a U disk, for backup or network transmission to a remote end. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 It is a structural schematic diagram of the present application.

[0077] Figure 2 It is Figure 1 A local enlarged view of the A in the figure.

[0078] Figure 3 It is Figure 1 A local enlarged view of the B in the figure.

[0079] Figure 4 It is a structural schematic diagram of the optical hard mirror to the host in the present application.

[0080] Figure 5 It is a module structure schematic diagram in the present application.

[0081] Figure 6 It is a module flowchart schematic diagram in the present application.

[0082] Figure 7 It is a processing flowchart from image state 1 to image state 2 in the present application.

[0083] In the figure: 4K camera system 1, optical hard mirror 1-1, camera 1-2, optical bayonet 1-2-1, optical filter 1-2-2, photosensitive element 1-2-3, gyroscope 1-2-4, key plate 1-2-5, camera mainboard 1-2-6, serial board 1-2-7, camera cable 1-3, camera host 1-4, host mainboard 1-4-1, video output board 1-4-1-1, core board 1-4-1-2, hard disk 1-4-1-3, deserializing board 1-4-1-4, touch screen 1-4-2, host power supply 1-4-3, video expansion board 1-4-4, network port 1-4-5, USB port 1-4-6, RS232 port 1-4-7, signal output port 1-4-8, display 1-5, signal connection line 1-5-1, signal input interface 1-5-2. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the utility model will be clearly and completely described below with reference to the drawings in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, rather than all the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the utility model.

[0085] Embodiment one:

[0086] A medical image tuning device, comprising an illumination element, further comprising a camera front end, a camera host, and a rear end device.

[0087] The camera front end comprises an optical hard mirror 1-1, a camera 1-2, an optical bayonet 1-2-1, an optical filter 1-2-2, a photosensitive element 1-2-3, a gyroscope 1-2-4, a key plate 1-2-5, a camera mainboard 1-2-6, a serial board 1-2-7, and a camera cable 1-3.

[0088] The gyroscope 1-2-4 is connected to the key plate 1-2-5, and the key plate 1-2-5 is connected to the camera mainboard 1-2-6.

[0089] The optical filter 1-2-2 is arranged at the front end of the photosensitive element 1-2-3, and the gyroscope 1-2-4 is built-in on the key plate 1-2-5.

[0090] The optical filter 1-2-2 filters out the interference color, and transmits the filtered image to the photosensitive element 1-2-3.

[0091] The image data of the photosensitive element 1-2-3 is transmitted to the input interface of the camera host 1-4 through the camera cable 1-3, and the state information of the gyroscope 1-2-4 is also transmitted to the camera host 1-4, and the camera host 1-4 processes the image according to the information of the gyroscope 1-2-4;

[0092] The camera host 1-4 comprises a host mainboard 1-4-1, a video output board 1-4-1-1, a core board 1-4-1-2, a hard disk 1-4-1-3, a deserializing board 1-4-1-4, a touch screen 1-4-2, a host power supply 1-4-3, a fan, a video expansion board 1-4-4, a network port 1-4-5, a USB port 1-4-6, an RS232 port 1-4-7, a signal output port 1-4-8, a display 1-5, a signal connection line 1-5-1, and a signal input interface 1-5-2.

[0093] The camera cable 1-3 is a GMSL3 data line.

[0094] The photosensitive element 1-2-3 is used for collecting the image obtained by the camera 1-2.

[0095] The host mainboard 1-4-1 comprises a core board 1-4-1-2, and the core board 1-4-1-2 comprises a fusion algorithm module, the fusion algorithm module comprises an acquisition module, a DPC module, a BLC module, a WB module, a Demosaic module, a Gamma correct module, a CCM module, a Contrast / Brightness Enhancement module, an NR module, an Edge Enhancement module, an output module, an AE Stat module, and an AE Control module; the host mainboard 1-4-1 is connected with the touch screen 1-4-2, the host power supply 1-4-3, the fan, the video expansion board 1-4-4, the signal output interface 1-5-2, or other host interfaces.

[0096] The output module comprises the video output board 1-4-1-1, the video expansion board 1-4-4, and a signal output end; the signal output end comprises the signal output port 1-4-8, the network port 1-4-5, the USB port 1-4-6, and the RS232 port 1-4-7.

[0097] The rear-end device comprises the display 1-5 or a remote receiving device.

[0098] The hardware connection relationship of the medical image optimization device is: the lens of the optical hard mirror 1 / 1 collects image information of a target area, the optical hard mirror 1 / 1 is adaptively connected with the optical bayonet 1-2-1, the collected image information is optically transmitted to the optical filter 1-2-2, the photosensitive element 1-2-3 is connected with the camera mainboard 1-2-6; the gyroscope 1-2-4 is connected with the camera mainboard 1-2-6; the key plate 1-2-5 is connected with the camera mainboard 1-2-6; the camera mainboard 1-2-6 is connected with the serial board 1-2-7; the serial board 1-2-7 is connected with the deserializing board 1-2-7 through the camera cable 1-3, the deserializing board 1-2-7 is connected with the core board 1-4-1-2, the core board 1-4-1-2 is connected with the hard disk 1-4-1-3 and the video output board 1-4-1-1 at the same time; the video output board 1-4-1-1 is connected with the video expansion board 1-4-4, the video expansion board 1-4-4 is connected with the back-end device through wired or wireless network, and the display 1-5 in the back-end device displays the optimized medical image.

[0099] The image data transmission relationship of the medical image optimization device is: the camera 1-2 converts the collected optical signal into an electrical signal through the photosensitive element 1-2-3 and transmits it to the camera mainboard 1-2-6, the gyroscope 1-2-4 collects the state information of the photosensitive element 1-2-3 and outputs it to the camera mainboard 1-2-6, the serial board 1-2-7 converts the data of the camera mainboard into serial data and transmits it to the deserializing board 1-2-7 at high speed through the camera cable 1-3, the deserializing board 1-2-7 converts the serial data into parallel data and inputs it to the camera host 1-4.

[0100] The camera converts the collected image information into digital signals, and transmits the parallel signals to the serializer through the serial board 1-2-7; the gyroscope 1-2-4 collects the state information of the photosensitive element 1-2-3 and outputs it to the serial signal input port of the deserializing board 1-2-7; the serializer compiles the parallel signals into serial signals and transmits them to the deserializing board 1-2-7 at high speed; at the same time, the gyroscope 1-2-4 also transmits the state information to the input interface of the camera host 1-4, and the camera cable 1-3 transmits the image data to the input interface of the camera host 1-4; the camera host 1-4 processes the image based on the gyroscope 1-2-4 information; the core board 1-4-1-2 fusion algorithm module of the camera host 1-4 reads the number and pixels of the connected camera 1-2, automatically matches the built-in image processing algorithm module, pre-processes through the exposure algorithm module, the noise reduction algorithm module, and the contrast enhancement algorithm module to obtain a single or multiple images as state 1; the image features of state 1 are extracted, a single algorithm module or a multiple image fusion algorithm module is automatically selected, and state 2 is obtained through the fusion algorithm module; the state 2 image is distributed and recognized as a single image, and the processed spectral filtered image and normal image are output respectively, the camera host core board 1-4-1-2 is connected with the image ISP processing module, the ISP processing module is connected with the host mainboard 1-4-1, the host mainboard 1-4-1 is connected with the video output board 1-4-1-1, the video output board 1-4-1-1 is connected with the video expansion board 1-4-4, the video expansion board 1-4-4 is connected with the host signal output port 1-4-8, the host signal output port 1-4-8 is connected with the display 1-5, or the image after tuning is transmitted to a remote device through a wired or wireless network through a signal output interface, and the display 1-5 in the remote device displays the image.

[0101] The camera 1-2 collects single-channel, or double-channel, or 4-channel, or 6-channel camera images; single-channel camera 1-2 refers to one camera sensor chip; double-channel camera refers to double-channel camera sensor chip; 4-channel camera refers to 4-channel camera sensor chip; 6-channel camera refers to 6-channel sensor chip; the camera 1-2 is divided into a left camera and a right camera.

[0102] The filter 1-2-2 is used to filter stray light and only allow 400-650nm light to enter the photosensitive element 1-2-3.

[0103] The photosensitive element 1-2-3 is any one of CMOS, CCD, or infrared sensor chip.

[0104] The filtered image is the original data of the medical endoscope image.

[0105] The camera 1-2 is connected with the endoscope of the digestive tract.

[0106] The image information is medical endoscope medical image original data.

[0107] The camera 1-2 refers to reading 1-way resolution 4k, frame rate 60 frames of medical image original data.

[0108] Embodiment two:

[0109] The image information is ultrasonic medical image original data.

[0110] The camera 1-2 refers to reading 2-way resolution 4k, frame rate 60 frames of medical image original data.

[0111] The filtered image is ultrasonic image original data.

[0112] The rest is the same as above.

[0113] Embodiment three:

[0114] The image information is medical X-ray machine medical image original data.

[0115] The camera 1-2 refers to reading 4-way resolution 4k, frame rate 60 frames of medical image original data.

[0116] The filtered image is X-ray machine image original data.

[0117] The rest is the same as above.

[0118] Embodiment four:

[0119] The image information is medical CT\ET medical image original data.

[0120] The camera 1-2 refers to reading 6-way resolution 4k, frame rate 60 frames of medical image original data.

[0121] The filtered image is CT\ET image original data.

[0122] The rest is the same as above.

[0123] The specific embodiments of the utility model are described in detail above in combination with the drawings, but the utility model is not limited to the above-mentioned embodiments, and various changes can be made within the knowledge range possessed by those skilled in the art without departing from the purpose of the utility model.

Claims

1. A medical image tuning apparatus comprising an illumination element, characterized by: Also include camera front end, camera host, back-end device; The camera front end includes a camera, the camera includes: optical hard mirror, optical socket, optical filter, photosensitive element, gyroscope, key plate, camera mainboard, serial board, camera cable; The gyroscope is connected with the key plate; the key plate is connected with the camera mainboard; The optical filter is arranged at the front end of the photosensitive element; the gyroscope is built in the camera key plate; The optical filter filters out the interference color, and transmits the filtered image to the photosensitive element; The photosensitive element transmits image data to the input interface of the camera host through the camera cable, and the gyroscope also transmits state information to the camera host; the camera host comprehensively processes the gyroscope information and processes the image; The camera host includes: host mainboard, video output board, core board, hard disk, deserializing board, touch screen, host power supply, fan, video expansion board, network port, USB port, RS232 port, signal output port, display, signal connection line, signal input interface; The camera cable refers to GMSL3 data line; The photosensitive element is used for collecting the image obtained by the camera; The core board includes a fusion algorithm module, and the fusion algorithm module includes a collection module, a DPC module, a BLC module, a WB module, a Demosaic module, a Gamma correct module, a CCM module, a Contrast / Brightness Enhancement module, an NR module, an Edge Enhancement module, an output module, an AE Stat module and an AE Control module; the host mainboard is connected with the touch screen, the host power supply, the fan, the video expansion board, the signal output port or other host interfaces respectively; The output module includes the video output board, the video expansion board and the signal output end; The host mainboard is connected with the touch screen, the video expansion board and the signal output end respectively; the signal output end includes the signal output port, the network port, the USB port and the RS232 port; The back-end device includes: display, or remote receiving device; The hardware connection relationship of the medical image tuning device is as follows: the lens of the optical hard mirror collects image information of a target area, the optical hard mirror is connected with the optical socket in a matched mode, the collected image information is transmitted to the optical filter in an optical mode, the photosensitive element is connected with the camera mainboard; the gyroscope is connected with the key plate; the key plate is connected with the camera mainboard; the camera mainboard is connected with the serial board; the serial board is connected with the deserializing board through the camera cable; the deserializing board is connected with the core board; the core board is connected with the hard disk and the video output board simultaneously; the video output board is connected with the video expansion board; the video expansion board is connected with the signal output port; the signal input interface is connected with the display. ​ The image data transmission relationship of the medical image optimization device is: the camera converts the collected optical signal into an electrical signal through a photosensitive element and transmits it to the camera mainboard, the gyroscope collects the state information of the photosensitive element and outputs it to the camera mainboard, the serial board converts the data of the camera mainboard into serial data and transmits it to the deserializing board at high speed through the camera cable, the deserializing board converts the serial data into parallel data and inputs it to the camera host; the camera host core board fusion algorithm module reads the number of connected cameras and pixels; matches the built-in image processing algorithm module, pre-processes through the exposure algorithm module, the noise reduction algorithm module and the contrast enhancement algorithm module, obtains a single or multiple images as state 1; extracts the image features of state 1, automatically selects a single image algorithm module or a multiple image fusion algorithm module, and obtains state 2 through the fusion algorithm module; distribute the state 2 image, identify it as a single image, output the spectral filtered image and the normal image after processing respectively, the core board is connected with the image ISP processing module, the ISP processing module is connected with the host mainboard, the host mainboard outputs image data to the signal output port, the signal output port is output to the display, and the display displays the optimized image, or the signal output port is transmitted to the remote device through wired or wireless network.

2. The medical image tuning apparatus of claim 1, wherein: The camera collects single-channel, or double-channel, or 4-channel, or 6-channel camera images; the single-channel camera refers to a camera sensor chip; The double-channel camera refers to a double-channel camera sensor chip; The 4-channel camera refers to a 4-channel camera sensor chip; The 6-channel camera refers to a 6-channel sensor chip; The camera is divided into a left camera and a right camera.

3. The medical image tuning apparatus of claim 1, wherein: The filter is used to filter stray light and only allow 400-650nm light to enter the photosensitive element.

4. The medical image tuning apparatus of claim 1, wherein: The photosensitive element is any one of CMOS, CCD or infrared sensor chip.

5. The medical image tuning apparatus of claim 1, wherein: The filtered image includes any one of medical endoscope, ultrasound, X-ray machine, CT\ET original medical image data.

6. The medical image tuning apparatus of claim 1, wherein: The camera refers to reading 1-channel, or 2-channel, or 4-channel, or 6-channel resolution 4k, frame rate 60 frames of medical image original data.

Images