10 results about "Fluorescence endoscopy" patented technology

The present invention relates to a fluorescence endoscope system, including a light source module, a camera module, a main control module, and a display module. The light source module is configured to emit an illumination beam, the camera module includes an endoscope configured to propagate the illumination beam and its reflected beam, and an operation unit configured to collect the reflected beam and convert the collected reflected beam into video data therefrom. The main control module includes a control unit configured to drive the light source module to emit a first illumination beam or a second illumination beam, and an image processing unit configured to process the video data frame by frame. The display module is configured to play the video data. The present invention can provide at least two operation modes including a white light mode and a fluorescence mode, and a first button of the operation unit can switch between the white light mode and the fluorescence mode, and has the advantage that the fluorescence imaging can provide a fluorescence image of tissue below the tissue surface, and can visualize and accurately identify lesions that are difficult to observe or early lesions, thereby improving the safety of surgery.

The utility model relates to a device for testing the imaging performance of a fluorescent endoscope, which comprises a mounting frame, and a clamp assembly, a container placing disc and an integrating sphere which are sequentially distributed on the mounting frame from top to bottom, and a lighting device arranged on one side of the integrating sphere, and exciting light of the lighting device illuminates the container placing disc through the integrating sphere. The container placing disc is provided with observation holes which are distributed in a circumferential mode, the clamp assembly comprises a double-screw clamp used for fixing the fluorescent endoscope and an adjusting frame used for adjusting the irradiation angle of the fluorescent endoscope, and the main purpose of the utility model is to enable a light source in the container placing disc to be more uniform through the reflection effect of an integrating sphere; according to the fluorescent endoscope, the sensitivity and definition of the fluorescent endoscope are improved, three important indexes including the radiance response characteristic, the fluorescent signal-to-noise ratio and the fluorescent static image latitude of the fluorescent endoscope are analyzed through real-time data of a fluorescent image collected by the fluorescent endoscope, and important parameters are provided for judging the imaging performance of the fluorescent endoscope.

The present disclosure relates to a fluorescence endoscope system. The fluorescence endoscope system comprises a light source module, a camera module, a main control module and a display module. The light source module is configured to emit illumination beams. The camera module comprises an endoscope and an operation portion. The endoscope is configured to propagate the illumination beams and reflected beams thereof. The operation portion is configured to receive the reflected beams and convert the reflected beams into video data. The main control module comprises a control unit and an image processing unit. The control unit is configured to control the light source module to emit a first illumination beam or a second illumination beam. The image processing unit is configured to process the video data frame by frame. The display module is configured to play the video data. The present disclosure can provide a white-light mode and a fluorescence mode, and switch between the white-light mode and the fluorescence mode by a first button on an operation portion. A fluorescence image of a tissue under a tissue surface is provided by means of fluorescence imaging, such that inconspicuous lesions and early lesions can be visually and precisely identified, thereby improving the safety of surgery.

The invention relates to the technical field of medical image processing, in particular to an image processing system for a fluorescent endoscope, the system comprises a control layer, an equipment layer and a database layer, the equipment layer comprises a camera group, a display and an illumination light source, the camera group is used for collecting visible light images and fluorescent light images, and the display is used for displaying the visible light images and the fluorescent light images; the illumination light source comprises a white light source, a fluorescence excitation light source and a light splitting filtering assembly, the database layer is used for storing data collected by the system, the control layer comprises a CPU, an image processing module, a calculation module and an image output module, the CPU is used for managing and controlling operation of the system, and the image output module is used for outputting the image. The image processing module is used for fusing the visible light image and the fluorescence image to generate a visible light fusion image which only emits fluorescence by the diseased tissue; and the image output module is used for connecting the host with a display to output the visible light fusion image which only emits fluorescence by the diseased tissue in real time.

The invention discloses an automatic exposure method of a fluorescent endoscope for an endoscope shooting object based on deep reinforcement learning and a self-group iteration upgrading device. Comprising the following steps: establishing an information acquisition device of the fluorescent endoscope camera system; dividing an observation area; collecting fluorescence image data as the state of the reinforcement learning environment, and inputting the fluorescence image data into an intelligent agent to obtain the exposure time of a fluorescence image; the fluorescence image of each spectral band is collected again, and the observation area is divided again; and collecting visible light image data as the state of the reinforcement learning environment, inputting the visible light image data into the intelligent agent to obtain the exposure time of the visible light image, and achieving automatic image exposure processing based on the fluorescent object. The system is suitable for narrow space imaging under the endoscope, and a good multi-spectral endoscope automatic exposure imaging result can be obtained. According to the self-group iteration upgrading device, model training iteration upgrading can be carried out in multiple modes, and the performance of the device is continuously improved.

A fluorescence endoscope device (1) comprises: a WLI light source (31) that emits WLI light; excitation light sources (32, 33) that emit excitation light for exciting a fluorescent reagent; a first imaging element (522) that images return light, which is the WLI light from an object being observed; a second imaging element (523) that images fluorescence emitted from the fluorescent reagent contained in the object being observed; and a processor (93). The processor (93) can switch between a superimposed fluorescence mode for outputting a superimposed image in which a fluorescence image obtained through imaging by the second imaging element (523) is superimposed on a WLI light image obtained through imaging by the first imaging element (522), and a single fluorescence mode for only outputting the fluorescence image. The processor (93) sets the amount of WLI light that is emitted by the WLI light source (31) for each exposure time per frame in the second imaging element (523) to be smaller in the single fluorescence mode than in the superimposed fluorescence mode.

The invention provides a compensation method for fluorescence signal uniformity in a fluorescence endoscope system deployed to an FPGA (Field Programmable Gate Array) based on deep reinforcement learning and a self-group iteration upgrading device. The compensation method comprises the following steps: dividing an imaging visual field of a fluorescence camera into a plurality of rectangular areas with the same size; a fluorescent contrast agent with a certain concentration is selected and placed in the center of each rectangular area successively, and images are collected; respectively calculating an average gray value in each rectangular region; and constructing and training a gray scale compensation multi-agent of the fluorescence imaging system by using a PPO algorithm, wherein the gray scale compensation agent outputs a compensation value of each pixel for performing compensation transformation on a gray scale value of the acquired fluorescence image. According to the method, the trouble caused by unreasonable change of the gray value of the fluorescence image in the operation process can be solved, and the defects which are difficult to solve in the hardware structure are overcome from the perspective of a software algorithm. According to the self-group iteration upgrading device, model training iteration upgrading can be carried out in multiple modes, and the performance of the device is continuously improved.

The application relates to a fluorescent image processing method and a fluorescent endoscope system. In a fluorescent mode, a detected object marked by a fluorescent agent is illuminated based on detection light, the detection light comprising white light and excitation light emitted in a set light emission mode; light signals from the detected object are collected based on a collection mode corresponding to the light emission mode, a first image is obtained based on first waveband light signals, and a second image is obtained based on second waveband light signals; the first waveband is set based on a spectral range of fluorescent light excited by the excitation light, and the second waveband is set based on a spectral range of the white light; the first image and the second image are fused to obtain a fluorescent detection image of the detected object, thereby solving the problem of unclear imaging of a fluorescent marking peripheral region and improving overall imaging effect.

This invention relates to a focal plane consistency coefficient testing device for a fluorescence endoscopy system. It includes a fixed plate, a worktable mounted on the fixed plate, and a transmission light box. An endoscope with a camera is mounted on the worktable via a connector. The camera is secured to the endoscope with a clip. A focusing knob is provided on the camera for adjusting image sharpness. The endoscope is positioned directly opposite the transmission light box, and a test card is mounted above the transmission light box. This invention provides a focal plane consistency coefficient testing device for a fluorescence endoscopy system, which boasts advantages such as simple and reasonable structure, practicality, and convenience.

The invention discloses an automatic exposure method for an endoscope shooting object by combining software and hardware with a fluorescent endoscope and a self-iteration upgrading device. The method mainly comprises the following steps: constructing an information acquisition device of the fluorescent endoscope camera system; collecting fluorescence image data as the state of the reinforcement learning environment, inputting the fluorescence image data into a deep noise reduction convolutional neural network, and then inputting the fluorescence image data into an intelligent agent to obtain the exposure time of a fluorescence image; the fluorescence image of each spectral band is collected again, and the observation area is divided again; and collecting visible light image data as the state of the reinforcement learning environment, inputting the visible light image data into the deep noise reduction convolutional neural network, and then inputting the visible light image data into the intelligent agent to obtain the exposure time of the visible light image so as to achieve automatic image exposure processing based on the fluorescent object. The system is suitable for a narrow space under the endoscope, and a good multi-spectral endoscope automatic exposure imaging result can be obtained.