Search

CN-122002140-A - Method, device and system for automatically adjusting video brightness of endoscope

CN122002140ACN 122002140 ACN122002140 ACN 122002140ACN-122002140-A

Abstract

The invention discloses an endoscope imaging system and a method for automatically adjusting image exposure parameters, which belong to the technical field of image processing, wherein the method comprises the steps of collecting a first endoscope image and performing resolution reduction processing to obtain a second endoscope image; identifying effective operation area of surgery and calculating the overexposure degree of the area, and self-adaptively adjusting the video brightness of the endoscope based on the overexposure degree. The effective operation area identification and overexposure degree calculation can be realized by adopting a deep learning model or a traditional image processing method. And the brightness adjustment judges whether overexposure is carried out according to the overexposure degree, namely, if the overexposure is not carried out, the automatic exposure is kept, and if the overexposure is carried out, the automatic exposure is switched to an intelligent light measuring exposure mode, the brightness of a light source is reduced, the Gamma curve is adjusted, and the exposure brightness is reduced, so that the overexposure is eliminated, and the image detail is restored. The system comprises a light source device, a camera device, a brightness adjusting device, a storage device and a display device, and can automatically detect overexposure and prompt a user to realize intelligent adjustment of the brightness of the endoscope image.

Inventors

  • NIE LINCHUAN
  • WANG GUOXIN
  • LI XIANLONG

Assignees

  • 青岛海泰新光科技股份有限公司

Dates

Publication Date
20260508
Application Date
20260206

Claims (10)

  1. 1. A method for automatically adjusting the brightness of an endoscopic video, comprising: acquiring a first endoscopic image based on an automatic exposure mode; performing resolution reduction processing based on the first endoscope image to obtain a second endoscope image; identifying an effective operation area of the operation based on the second endoscope image, and calculating an area overexposure degree value; And performing feedback adjustment based on comparison between the overexposure degree value of the effective operation area and a preset overexposure threshold value, and gradually adjusting overexposure inhibition until the overexposure inhibition function is closed.
  2. 2. The method of claim 1, wherein the identifying the effective operation area of the surgery based on the second endoscope image, calculating the area overexposure value, and using a deep learning model comprises: Identifying an effective operation area of a surgery by adopting a network framework based on U-Net++, wherein the network framework of U-Net++ comprises a feature extraction module, a multi-scale feature fusion module and an area segmentation module; And constructing a detection model based on the densely connected convolutional neural network, calculating the regional overexposure degree, capturing overexposed regions with different sizes through the multi-scale receptive field, and outputting two detection results, namely a binary mask of the overexposed region and an overexposed degree value by the model.
  3. 3. The method of automatically adjusting endoscope video brightness according to claim 1, wherein said identifying an effective operative region of surgery and calculating a region overexposure based on said second endoscope image is accomplished using conventional image processing methods comprising: generating an effective operation area with a preset size by taking a centroid point of the second endoscope image as a center; Acquiring the brightness value information of the image of the effective operation area; Acquiring a brightness distribution map according to the image brightness value information; and acquiring the regional overexposure degree according to the brightness distribution diagram.
  4. 4. The method of claim 1, wherein the step of adjusting the overexposure suppression step by step until the overexposure suppression function is turned off comprises performing feedback adjustment based on a comparison of the effective operating region overexposure magnitude value and a preset overexposure threshold value: the overexposure degree value is larger than or equal to a preset overexposure threshold, the overexposure phenomenon exists in the current scene, an overexposure suppression function is started, and the brightness of the endoscope image is adjusted.
  5. 5. The method for automatically adjusting the brightness of an endoscopic video according to claim 4, wherein the current scene has an overexposure phenomenon, an overexposure suppression function is started, and the brightness of an endoscopic image is adjusted, comprising: Changing the exposure mode from automatic exposure to intelligent photometry; acquiring a third endoscope image after changing the exposure mode, and acquiring an overexposure degree value; Judging that the current scene has overexposure phenomenon according to the overexposure degree value, and reducing the brightness of the illumination light source to the first light source brightness according to the preset light source brightness step; acquiring a fourth endoscope image after the brightness of the illumination light source is changed, and acquiring an overexposure degree value; Judging that the current scene has overexposure phenomenon according to the overexposure degree value, adjusting the original Gamma1 curve to the Gamma2 curve, changing the Gamma curve so as to better compress the brightness of the image at the highlight overexposure position and improve the detail texture at the dark position; Acquiring a fifth endoscope image after the Gamma curve is changed, and acquiring an overexposure degree value; judging that the current scene has overexposure phenomenon according to the overexposure degree value, and reducing the exposure brightness according to a preset exposure brightness step; Repeating the steps until the overexposure inhibition function is closed, and changing the exposure mode from intelligent photometry to automatic exposure to obtain the endoscope video.
  6. 6. The method according to claim 5, wherein after the step of adjusting the overexposure inhibition is performed, it is determined that the current scene is not overexposed according to the acquired new endoscopic image, and the current exposure mode, the illumination light source brightness, the Gamma curve and the exposure brightness combination are continuously used to acquire the endoscopic video.
  7. 7. The method of claim 1, wherein the step of adjusting the overexposure suppression step by step until the overexposure suppression function is turned off comprises performing feedback adjustment based on a comparison of the effective operating region overexposure magnitude value and a preset overexposure threshold value: The overexposure degree value is smaller than a preset overexposure threshold value, the overexposure phenomenon does not exist in the current scene, and the automatic exposure mode is continuously adopted to acquire the endoscope video.
  8. 8. An endoscope video brightness adjustment device, a method for automatically adjusting the endoscope video brightness using the method of claims 1 to 7, comprising: the image acquisition unit is used for acquiring an endoscope video image; the image resolution reduction unit is used for carrying out sub-sampling processing on the endoscope image; An effective operation region identification unit for identifying a critical anatomical region in which a surgeon is concerned and directly performs an instrument operation at a current operation stage; The area overexposure degree quantization unit is used for quantizing the overexposure degree of the image output by the effective operation area identification unit; the overexposure suppression enabling unit is used for starting and closing the overexposure suppression function, and the brightness adjusting unit can adjust the brightness according to the overexposure degree value during starting; The brightness adjusting unit is used for adaptively adjusting the exposure light measuring area, the illumination light source brightness, the Gamma curve processing effect and the exposure brightness of the system according to the quantized overexposure degree value and the overexposure inhibition switch, so as to achieve the purposes of removing the overexposure condition in the effective operation area and recovering the image texture details; and the OSD prompting unit is used for displaying the current image brightness adjusting mode at the display end.
  9. 9. The apparatus according to claim 8, wherein the overexposure suppression enabling unit turns on and off an overexposure suppression function, comprising: The automatic opening is carried out according to the result calculated by the regional overexposure degree quantization unit, or the manual key is opened when the operator judges that the overexposure phenomenon exists; the manual key is turned off when the operator judges the operation condition.
  10. 10. An endoscopic imaging system for automatically adjusting the brightness of an endoscopic video, a method of applying the automatic adjustment of the brightness of an endoscopic video of claims 1-7, comprising: The light source device is used for adjusting the brightness of the illumination light source according to the brightness value of the light source provided by the endoscope video brightness adjusting device; an imaging device comprising an image sensor for acquiring image data of biological tissue under illumination by an illumination light source to generate an endoscopic video; The endoscope brightness adjusting device is used for detecting an effective operation area according to the endoscope video acquired by the image pickup system and adjusting the image brightness according to the overexposure degree of the effective operation area; The storage device is used for storing the execution instruction, and the storage instruction is used for realizing the method for automatically adjusting the video brightness of the endoscope when being executed by the processor; and the display device is used for displaying the endoscope video and the OSD prompt.

Description

Method, device and system for automatically adjusting video brightness of endoscope Technical Field The invention relates to the field of image processing, in particular to a method, a device and a system for automatically adjusting the brightness of an endoscope video. Background In endoscopic surgery, high-definition, stable video imaging is a key precondition for accurate operation by doctors. The endoscope system provides the surgeon with a surgical field of view by transmitting in vivo tissue images to a display. However, due to the complexity of the anatomy in the body and the dynamic changes in the surgical procedure, there are often dramatic changes in the imaging environment, which pose a serious challenge to the stability of the image brightness. When a surgical instrument or tissue area (such as fat, serosa or some white tissue) enters the field of view and occupies a large proportion of the image, the automatic exposure control module of the endoscope camera system can make an excessive reaction due to the high surface reflectivity, and the brightness of the whole image is dramatically improved to balance the photometry. This global brightness increase results in other important anatomical structures, particularly areas of vascular texture where contrast is not high enough, losing detail from overexposure (overexposure), and the contours, strike, and boundaries with surrounding tissue becoming obscured or even completely invisible. Under the circumstance, a doctor cannot clearly identify the position of the blood vessel, so that the risk of misoperation (such as accidental injury of the blood vessel, penetration of a natural cavity channel and the like) is increased, and the operation time can be prolonged due to incapability of accurately judging the anatomical hierarchy, so that the safety and the efficiency of the operation are directly influenced. Currently, conventional automatic exposure control algorithms commonly employed in endoscopic systems can be considered the closest prior art to the present invention. Embodiments of this technique are typically based on feedback control of luminance statistics (e.g., average luminance or luminance histogram) for the entire frame of image or for the center region. However, the scheme has blindness of global adjustment, namely the technology only focuses on the overall brightness level of the image, and semantic content of different areas in the picture cannot be distinguished. When smaller light-reflecting tissues appear in the operation area of the instrument, the exposure control system usually weakens or ignores the influence of the area to ensure the brightness uniformity of the overall picture, so that the area is over-exposed strongly, and the texture details are lost. Accordingly, there is a strong need in the art for an endoscopic image processing method that overcomes the above-described shortcomings, effectively recognizes local highlighting of the instrument's operative field, and restores to some extent the vascular texture details masked by the overexposed field, thereby providing a consistent, detailed surgical field of view to the surgeon. Disclosure of Invention In view of the above, the present invention aims to provide a method, an apparatus and a system for automatically adjusting the video brightness of an endoscope, which can effectively overcome the defect of global adjustment blindness existing in the traditional automatic exposure control algorithm, and can specifically perform brightness adjustment on a local highlight region by intelligently identifying and distinguishing an instrument operation region and a key anatomical structure in an image, effectively inhibit the local overexposure phenomenon caused by easily reflective tissues, and recover important tissue information such as vascular textures and the like in which the overexposed region is covered on the basis, so as to provide a surgery field with stable brightness and clear details for a surgeon, thereby guaranteeing the safety and efficiency of surgery. According to a first aspect of the present disclosure, there is provided a method of automatically adjusting endoscope video brightness, comprising: acquiring a first endoscopic image based on an automatic exposure mode; performing resolution reduction processing based on the first endoscope image to obtain a second endoscope image; identifying an effective operation area of the operation based on the second endoscope image, and calculating an area overexposure degree value; And performing feedback adjustment based on comparison between the overexposure degree value of the effective operation area and a preset overexposure threshold value, and gradually adjusting overexposure inhibition until the overexposure inhibition function is closed. A method for automatically adjusting endoscope video brightness according to at least one embodiment of the present disclosure, the identifying an effective operation region of