CN120259203A - A 3D laparoscopic surgery data processing method, device, equipment and storage medium - Google Patents

A 3D laparoscopic surgery data processing method, device, equipment and storage medium Download PDF

Info

Publication number
CN120259203A
CN120259203A CN202510301799.6A CN202510301799A CN120259203A CN 120259203 A CN120259203 A CN 120259203A CN 202510301799 A CN202510301799 A CN 202510301799A CN 120259203 A CN120259203 A CN 120259203A
Authority
CN
China
Prior art keywords
image
laparoscopic
image sequence
pixel
segmentation
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
Application number
CN202510301799.6A
Other languages
Chinese (zh)
Inventor
连若琪
贾富仓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to CN202510301799.6A priority Critical patent/CN120259203A/en
Publication of CN120259203A publication Critical patent/CN120259203A/en
Pending legal-status Critical Current

Links

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
    • A61B1/00002—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
    • A61B1/00163—Optical arrangements
    • A61B1/00195—Optical arrangements with eyepieces
    • A61B1/00197—Optical arrangements with eyepieces characterised by multiple eyepieces
    • 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
    • A61B1/313—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 for introducing through surgical openings, e.g. laparoscopes
    • A61B1/3132—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 for introducing through surgical openings, e.g. laparoscopes for laparoscopy
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/60—Image enhancement or restoration using machine learning, e.g. neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/77—Retouching; Inpainting; Scratch removal
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/80—Geometric correction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Surgery (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Optics & Photonics (AREA)
  • Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Endoscopes (AREA)

Abstract

本申请涉及一种3D腹腔镜手术数据处理方法、装置、设备以及存储介质。所述方法包括：采用视频处理技术对原始手术数据视频流进行分帧，得到双目腹腔镜系统左右摄像头对应的腹腔镜图像序列；基于相机参数对所述腹腔镜图像序列进行校准，得到消除图像畸变的腹腔镜图像序列；分别采用基于暗通道先验算法的烟雾去除技术以及基于DeepLabv3+架构的手术器械分割算法对校准后的腹腔镜图像序列进行烟雾去除和手术器械分割，生成无烟雾干扰和器械遮挡的腹腔镜图像序列。本申请通过结合暗通道先验算法和DeepLabv3+架构对腹腔镜手术图像进行预处理，能够同时解决腹腔镜图像中的烟雾干扰和器械遮挡问题，提升图像质量和后续任务的性能。

The present application relates to a 3D laparoscopic surgery data processing method, device, equipment and storage medium. The method comprises: using video processing technology to frame the original surgical data video stream to obtain a laparoscopic image sequence corresponding to the left and right cameras of the binocular laparoscope system; calibrating the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence that eliminates image distortion; using a smoke removal technology based on a dark channel prior algorithm and a surgical instrument segmentation algorithm based on the DeepLabv3+ architecture to perform smoke removal and surgical instrument segmentation on the calibrated laparoscopic image sequence, respectively, to generate a laparoscopic image sequence without smoke interference and instrument occlusion. The present application pre-processes laparoscopic surgical images by combining the dark channel prior algorithm and the DeepLabv3+ architecture, which can simultaneously solve the problems of smoke interference and instrument occlusion in laparoscopic images, and improve image quality and the performance of subsequent tasks.

Description

3D laparoscopic surgery data processing method, device, equipment and storage medium
Technical Field
The application belongs to the technical field of medical image processing, and particularly relates to a 3D laparoscopic surgery data processing method, device and equipment and a storage medium.
Background
Laparoscopic surgery is a minimally invasive surgical technique in which a patient's abdomen is provided with several small incisions, a laparoscope with a miniature camera and related surgical instruments are inserted, images in the abdominal cavity are transmitted to a monitor, and a doctor performs a surgical operation by observing the images on a screen. The operation mode has the advantages of small wound, quick recovery, light postoperative pain, short hospitalization time and the like. In recent years, 3D laparoscopic surgery further improves the accuracy and efficiency of the surgery as 3D imaging technology is applied. Compared with the traditional laparoscopic surgery, the three-dimensional image is captured by the 3D laparoscopic surgery through the double-camera system, the advantages of depth perception and space positioning are provided, and the surgery accuracy and safety are greatly improved.
In general, in the 3D laparoscopic surgery, a great amount of smoke is generated due to the electrocautery, laser ablation and other surgical operations, and the smoke can seriously reduce the quality of an endoscopic image, so that the surgical field is blurred, the visual judgment of a doctor is directly affected, the surgical risk is increased, and the subsequent image processing task is negatively affected. Meanwhile, the surgical instrument can frequently shield the operation area in the operation process, so that the observation of a doctor on a key anatomical structure is affected, and the processing of surgical data is interfered. During surgery, a large amount of image, video and sensor data is generated, which are in various formats and sources, and which require efficient data preprocessing to integrate and manage the surgical data. At present, the existing operation data preprocessing method mainly comprises the following aspects:
(1) The method has the advantages that the method is simple in image calibration and normalization, and most of the prior art only carries out simple zooming, normalization and other processes on images, and although the image format can be adjusted preliminarily, an effective processing mechanism is lacked for smoke, shielding and other interference factors in a complex operation scene.
(2) And partial researches utilize a deep learning technology to detect and segment the surgical instruments. The existing method mainly focuses on instrument detection and lacks treatment on interference factors such as smoke and the like.
(3) Some studies have attempted to remove smoke by image enhancement algorithms, but these methods are mostly independent of instrument mask generation, lacking comprehensive consideration of the combination of both.
(4) In recent years, a multi-modal learning technology is introduced into operation data analysis, and the understanding of a model on a complex operation scene is improved by fusing multi-modal data such as images, texts and the like. However, existing methods still rely on simple data calibration during the preprocessing stage, failing to fully mine the inherent complexity of the surgical data.
Disclosure of Invention
The application provides a 3D laparoscopic surgery data processing method, a device, equipment and a storage medium, which aim to solve one of the technical problems in the prior art at least to a certain extent.
In order to solve the problems, the application provides the following technical scheme:
A 3D laparoscopic surgical data processing method, comprising:
Framing an original operation data video stream by adopting a video processing technology to obtain a laparoscope image sequence corresponding to left and right cameras of a binocular laparoscope system;
calibrating the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence for eliminating image distortion;
And respectively adopting a smoke removal technology based on a dark channel priori algorithm and a surgical instrument segmentation algorithm based on DeepLabv & lt3+ & gt architecture to remove smoke and segment surgical instruments on the calibrated laparoscopic image sequence, so as to generate a laparoscopic image sequence without smoke interference and instrument shielding.
The technical scheme adopted by the embodiment of the application also comprises the steps that the video processing technology is adopted to frame the original operation data video stream to obtain a laparoscope image sequence corresponding to the left camera and the right camera of the binocular laparoscope system, and the method specifically comprises the following steps:
And acquiring each frame of image in the original operation data video stream, respectively dividing each frame of image into a left part and a right part along the horizontal direction, and respectively corresponding to the laparoscopic images of the left camera and the right camera of the binocular laparoscopic system.
The technical scheme adopted by the embodiment of the application also comprises the steps of calibrating the laparoscopic image sequence based on camera parameters to obtain the laparoscopic image sequence for eliminating image distortion, and specifically comprises the following steps:
Shooting an N Zhang Qipan-grid image by using a camera;
detecting corner points of the checkerboard image, and calculating an internal reference matrix and a distortion coefficient of a camera according to 3D world coordinates and 2D image coordinates of the checkerboard image by using a calibration function of OpenCV, wherein the internal reference matrix of the camera comprises a focal length or a principal point position, and the distortion coefficient comprises barrel-shaped or pillow-shaped distortion;
and performing de-distortion treatment on the framing laparoscopic image sequence by using the calculated internal reference matrix and the distortion coefficient, and recovering the real geometric shape of the laparoscopic image sequence.
The technical scheme adopted by the embodiment of the application further comprises that the smoke removal technology based on the dark channel prior algorithm and the surgical instrument segmentation algorithm based on DeepLabv3+ architecture are adopted to remove smoke and segment surgical instruments of the calibrated laparoscopic image sequence respectively, and the method comprises the following steps:
Calculating the minimum value of each pixel point from RGB channels of each frame of laparoscope image to form a dark channel image, and reversely calculating a transmittance map caused by atmospheric scattering according to the relationship between the dark channel image and the calibrated laparoscope image on the assumption that the dark channel image represents the minimum light intensity under the condition of no fog, wherein the transmittance calculation formula is as follows:
Wherein t represents a transmittance map, I represents a calibrated laparoscopic image, a represents an atmospheric light intensity, ω is an adjustment parameter for controlling defogging intensity;
Globally analyzing the dark channel image, selecting the brightest pixel with a set proportion in the dark channel image as the atmospheric light intensity, combining the transmissivity image and the atmospheric light intensity, and calculating a defogged laparoscope image by using an image restoration formula as follows:
wherein J represents the defogged laparoscopic image.
The technical scheme adopted by the embodiment of the application further comprises that the smoke removal technology based on the dark channel prior algorithm and the surgical instrument segmentation algorithm based on DeepLabv3+ architecture are adopted to remove smoke and segment surgical instruments from the calibrated laparoscopic image sequence, and the method further comprises the following steps:
Inputting the calibrated laparoscopic image into a DeepLabv & lt3+ & gt model, wherein the DeepLabv & lt3+ & gt model comprises an encoder and a decoder, the encoder is based on a modified ResNet architecture and is used for extracting an advanced semantic feature map of the laparoscopic image through hole volume and multi-scale feature fusion, the decoder is used for carrying out pixel-by-pixel upsampling operation on the feature map output by the encoder, restoring the low-resolution feature map to the same size as the input image and outputting a segmentation probability map, the segmentation probability map is a multi-channel image, each channel corresponds to one class probability distribution, pixel-by-pixel analysis is carried out on the segmentation probability map, class probability of each pixel is mapped into a specific class label, and a final surgical instrument segmentation mask is generated.
The technical scheme adopted by the embodiment of the application further comprises the steps of carrying out pixel-by-pixel analysis on the segmentation probability map, mapping the class probability of each pixel into a specific class label, and generating a final surgical instrument segmentation mask, wherein the specific steps are as follows:
The surgical instrument segmentation mask is represented in the form of a binary image, wherein a surgical instrument region is labeled as foreground and a background region is labeled as background.
The embodiment of the application adopts another technical scheme that a 3D laparoscopic surgery data processing device comprises:
The image framing module is used for framing the original operation data video stream by adopting a video processing technology to obtain a laparoscope image sequence corresponding to the left camera and the right camera of the binocular laparoscope system;
the image calibration module is used for calibrating the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence for eliminating image distortion;
The image preprocessing module is used for respectively adopting a smoke removal technology based on a dark channel priori algorithm and a surgical instrument segmentation algorithm based on DeepLabv & lt3+ & gt architecture to remove smoke and segment surgical instruments on the calibrated laparoscopic image sequence, so as to generate a laparoscopic image sequence without smoke interference and instrument shielding.
The technical scheme adopted by the embodiment of the application further comprises that the image preprocessing module respectively adopts a smoke removal technology based on a dark channel priori algorithm and a surgical instrument segmentation algorithm based on DeepLabv & lt3+ & gt architecture to remove smoke and segment surgical instruments of the calibrated laparoscopic image sequence, and specifically comprises the following steps:
Calculating the minimum value of each pixel point from RGB channels of each frame of laparoscope image to form a dark channel image, and reversely calculating a transmittance map caused by atmospheric scattering according to the relationship between the dark channel image and the calibrated laparoscope image on the assumption that the dark channel image represents the minimum light intensity under the condition of no fog, wherein the transmittance calculation formula is as follows:
Wherein t represents a transmittance map, I represents a calibrated laparoscopic image, a represents an atmospheric light intensity, ω is an adjustment parameter for controlling defogging intensity;
Globally analyzing the dark channel image, selecting the brightest pixel with a set proportion in the dark channel image as the atmospheric light intensity, combining the transmissivity image and the atmospheric light intensity, and calculating a defogged laparoscope image by using an image restoration formula as follows:
wherein J represents the defogged laparoscopic image;
Inputting the calibrated laparoscopic image into a DeepLabv & lt3+ & gt model, wherein the DeepLabv & lt3+ & gt model comprises an encoder and a decoder, the encoder is based on a modified ResNet architecture and is used for extracting an advanced semantic feature map of the laparoscopic image through hole volume and multi-scale feature fusion, the decoder is used for carrying out pixel-by-pixel upsampling operation on the feature map output by the encoder, restoring the low-resolution feature map to the same size as the input image and outputting a segmentation probability map, the segmentation probability map is a multi-channel image, each channel corresponds to one class probability distribution, pixel-by-pixel analysis is carried out on the segmentation probability map, class probability of each pixel is mapped into a specific class label, and a final surgical instrument segmentation mask is generated.
The embodiment of the application adopts a further technical scheme that the device comprises a processor and a memory coupled with the processor, wherein,
The memory stores program instructions for implementing the 3D laparoscopic surgical data processing method;
The processor is configured to execute the program instructions stored by the memory to control a 3D laparoscopic surgical data processing method.
According to another technical scheme adopted by the embodiment of the application, a storage medium is used for storing program instructions which can be operated by a processor, and the program instructions are used for executing the 3D laparoscopic surgery data processing method.
Compared with the prior art, the 3D laparoscopic surgery data processing method, device and equipment and the storage medium have the advantages that the laparoscopic surgery image is preprocessed by combining the dark channel prior algorithm and the DeepLabv3+ framework, smoke is quickly removed by the dark channel prior algorithm, the DeepLabv3+ framework is utilized to ensure high precision of segmentation of surgical instrument masks, reliable support is provided for real-time decision in the surgery process, the problems of smoke interference and instrument shielding in the laparoscopic image can be simultaneously solved, balance between instantaneity and high precision is achieved, the image quality and performance of subsequent tasks are remarkably improved, the preprocessed image data can be directly applied to surgery navigation and instrument detection tasks, the surgery accuracy and safety are improved, additional adaptation is not needed, and the method has good expandability and wide application prospect.
Drawings
FIG. 1 is a flow chart of a 3D laparoscopic surgical data processing method according to an embodiment of the present application;
FIG. 2 is a schematic diagram showing smoke removal effect according to an embodiment of the present application;
FIG. 3 is a schematic view of a surgical instrument segmentation effect according to an embodiment of the present application;
FIG. 4 is a schematic structural view of a 3D laparoscopic surgery data processing device according to an embodiment of the present application;
FIG. 5 is a schematic view of a device structure according to an embodiment of the present application;
Fig. 6 is a schematic structural diagram of a storage medium according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," "third," and the like in this disclosure are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", and "a third" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise. All directional indications (such as up, down, left, right, front, rear) in embodiments of the present application are merely used to explain the relative positional relationship, movement, etc. between the components in a particular pose (as shown in the drawings), and if the particular pose changes, the directional indication changes accordingly. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Specifically, please refer to fig. 1, which is a flowchart of a 3D laparoscopic surgery data processing method according to an embodiment of the present application. The 3D laparoscopic surgery data processing method provided by the embodiment of the application comprises the following steps:
S100, acquiring an original operation data video stream from a binocular laparoscope system;
In this step, the binocular laparoscopic system includes left and right cameras respectively used for capturing laparoscopic images of an operation area during an operation process, and generating an original operation data video stream of the 3D laparoscopic operation.
S110, framing an original operation data video stream by adopting a video processing technology, and separating a laparoscope image sequence corresponding to each of the left camera and the right camera;
In this step, since the original surgical data video stream is acquired by the left and right cameras, in the 3D laparoscopic surgical data processing process, the original surgical data video stream needs to be framed first to separate the laparoscopic image sequences corresponding to the left and right cameras. The specific framing mode is that each frame of image in the original operation data video stream is acquired, each frame of image is respectively divided into a left part and a right part along the horizontal direction, and the left part and the right part correspond to the laparoscope images of the left camera and the right camera respectively.
S120, calibrating the framing laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence for eliminating image distortion;
In this step, the calibration process is based on camera parameters, and uses a checkerboard as a calibration tool to calibrate the framed laparoscopic image sequence, and the specific calibration process includes:
s121, shooting N Zhang Qipan grids of images by using a camera, wherein the shooting quantity N of the grid images can be set according to actual application scenes;
S122, detecting corner points of the checkerboard image, calculating an internal reference matrix and a distortion coefficient of the camera according to 3D world coordinates of the checkerboard and the detected 2D image coordinates by using a calibration function of OpenCV, and optimizing camera parameters to minimize a re-projection error, wherein the internal reference matrix of the camera comprises a focal length, a principal point position and the like, and the distortion coefficient comprises barrel-shaped distortion, pillow-shaped distortion and the like;
S123, performing de-distortion processing on the framing laparoscopic image sequence by using the calculated internal reference matrix and the distortion coefficient, and recovering the real geometric shape of the laparoscopic image sequence.
It can be appreciated that the above framing and calibration process enables the laparoscopic image sequence to have higher quality and consistency, providing a reliable basis for surgical navigation and instrument detection tasks.
S130, respectively adopting a smoke removal technology based on a dark channel prior algorithm and a surgical instrument segmentation algorithm based on DeepLabv & lt3+ & gt architecture to remove smoke and segment surgical instruments on the calibrated laparoscopic image sequence, so as to generate a laparoscopic image sequence without smoke interference and instrument shielding;
In the step, through combining a dark channel prior algorithm with a DeepLabv3+ framework, firstly, adopting a smoke removal technology based on the dark channel prior algorithm to analyze the dark channel characteristics of a laparoscopic image, rapidly removing the interference of smoke on the laparoscopic image so as to recover a clear operation visual field, and then using the DeepLabv3+ framework to carry out operation instrument mask segmentation on the laparoscopic image, the problems of smoke interference and instrument shielding in the laparoscopic image can be simultaneously solved, the balance between instantaneity and high precision is realized, the image quality and the performance of subsequent tasks are obviously improved, and reliable support is provided for real-time decision in the operation process. Fig. 2 is a schematic view of smoke removal effect according to an embodiment of the present application, and fig. 3 is a schematic view of surgical instrument segmentation effect according to an embodiment of the present application.
Further, aiming at the image data with smoke, the application adopts a smoke removing technology based on a dark channel prior algorithm to remove the smoke. The specific smoke removal process includes first calculating the minimum value of each pixel point from the RGB channels of each frame of laparoscopic image, forming a dark channel image. Dark channel a priori theory holds that in a localized region of the haze-free image, the pixel values of at least one color channel approach zero. The details of the dark channels are further enhanced by morphological erosion operations, providing a basis for subsequent transmittance estimation. Assuming that the dark channel image represents the minimum light intensity under the haze-free condition, the transmittance map caused by atmospheric scattering is reversely calculated according to the relation between the dark channel image and the original laparoscopic image (namely, the calibrated laparoscopic image), wherein the transmittance calculation formula is as follows:
where t represents the transmittance map, I represents the original laparoscopic image, a represents the atmospheric light intensity, ω is an adjustment parameter for controlling the defogging intensity.
By globally analyzing the dark channel image, the brightest pixel with a set proportion in the dark channel image is selected as the atmospheric light intensity, wherein the atmospheric light is a part with uniformly weakened illumination in the atomization process, and the value of the atmospheric light is usually close to the RGB value of white light. The setting proportion of the brightest pixel in the embodiment of the application is 0.1%, and the setting can be specifically performed according to an actual application scene.
Combining the transmissivity graph and the atmospheric light intensity, and calculating a defogged laparoscope image by using an image restoration formula as follows:
wherein J represents the defogged laparoscopic image.
Through the operation, the smoke interference in the laparoscopic image can be effectively removed, the clear operation visual field is recovered, and high-quality image support is provided for subsequent operation navigation and instrument detection tasks.
Further, aiming at the laparoscopic image with instrument shielding, the application adopts a DeepLabv3+ architecture-based surgical instrument segmentation algorithm to segment the surgical instrument. The specific segmentation process includes first inputting the calibrated laparoscopic image into a DeepLabv < 3+ > model, deepLabv < 3+ > model including an encoder and a decoder, wherein the encoder is based on a modified ResNet architecture for extracting high-level semantic feature maps of the laparoscopic image through a hole volume and multi-scale feature fusion, thereby capturing key information of the surgical instrument while preserving sufficient context information to support accurate segmentation. Subsequently, the feature map output from the encoder is subjected to a pixel-by-pixel up-sampling operation by the decoder section, the low-resolution feature map is restored to the same size as the input image, and a segmentation probability map is output. The segmentation probability map is a multi-channel image, with each channel corresponding to a probability distribution of a class. In the post-processing stage, the segmentation probability map is analyzed pixel by pixel, the class probability of each pixel is mapped to a specific class label by thresholding or maximum indexing operations, ensuring that each pixel is assigned to the most likely class, thereby generating the final surgical instrument segmentation mask.
Specifically, the finally generated surgical instrument segmentation mask is represented in the form of a binary image, wherein a surgical instrument area is marked as a foreground (for example, the value is 1), a background area is marked as a background (for example, the value is 0), and the generated surgical instrument segmentation mask is directly applied to a surgical navigation or instrument detection task, so that the accuracy and safety of a surgery can be greatly improved.
Based on the above, the 3D laparoscopic surgery data processing method of the embodiment of the present application performs preprocessing on the laparoscopic surgery image by combining the dark channel prior algorithm and DeepLabv3+ architecture, rapidly removes smoke by using the dark channel prior algorithm, ensures high precision of surgical instrument mask segmentation by using DeepLabv3+ architecture, provides reliable support for real-time decision in the surgery process, can simultaneously solve the problems of smoke interference and instrument shielding in the laparoscopic image, achieves balance between instantaneity and high precision, significantly improves the image quality and performance of subsequent tasks, and the preprocessed image data can be directly applied to surgical navigation and instrument detection tasks, improves the accuracy and safety of surgery, and has good expandability and wide application prospects without additional adaptation.
Referring to fig. 4, a schematic structural diagram of a 3D laparoscopic surgery data processing device according to an embodiment of the application is shown. The 3D laparoscopic surgery data processing method device 40 of the embodiment of the present application includes:
The image framing module 41 is used for framing the original operation data video stream by adopting a video processing technology to obtain a laparoscope image sequence corresponding to the left camera and the right camera of the binocular laparoscope system;
an image calibration module 42, configured to calibrate the laparoscopic image sequence based on camera parameters, so as to obtain a laparoscopic image sequence with image distortion removed;
The image preprocessing module 43 is configured to perform smoke removal and surgical instrument segmentation on the calibrated laparoscopic image sequence by using a smoke removal technology based on a dark channel prior algorithm and a surgical instrument segmentation algorithm based on DeepLabv3+ architecture, so as to generate a laparoscopic image sequence without smoke interference and instrument shielding.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.
The device provided by the embodiment of the present application may be applied to the foregoing method embodiment, and details refer to the description of the foregoing method embodiment, which is not repeated herein.
Fig. 5 is a schematic diagram of an apparatus structure according to an embodiment of the application. The apparatus 50 comprises:
a memory 51 storing executable program instructions;
A processor 52 connected to the memory 51;
The processor 52 is configured to invoke executable program instructions stored in the memory 51 and perform the steps of framing an original surgical data video stream by using a video processing technique to obtain a laparoscopic image sequence corresponding to left and right cameras of the binocular laparoscopic system, calibrating the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence for eliminating image distortion, and performing smoke removal and surgical instrument segmentation on the calibrated laparoscopic image sequence by using a smoke removal technique based on a dark channel prior algorithm and a surgical instrument segmentation algorithm based on DeepLabv3+ architecture, respectively, so as to generate a laparoscopic image sequence without smoke interference and instrument occlusion.
The processor 52 may also be referred to as a CPU (Central Processing Unit ). The processor 52 may be an integrated circuit chip having signal processing capabilities. Processor 52 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Fig. 6 is a schematic structural diagram of a storage medium according to an embodiment of the application. The storage medium of the embodiment of the application stores program instructions 61 capable of realizing the steps of framing an original operation data video stream by adopting a video processing technology to obtain a laparoscopic image sequence corresponding to left and right cameras of a binocular laparoscopic system, calibrating the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence for eliminating image distortion, and respectively adopting a smoke removal technology based on a dark channel priori algorithm and a surgical instrument segmentation algorithm based on DeepLabv & lt+ & gt architecture to remove smoke and segment surgical instruments on the calibrated laparoscopic image sequence to generate a laparoscopic image sequence without smoke interference and instrument shielding. The program instructions 61 may be stored in the storage medium as a software product, and include instructions for causing a device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods according to the embodiments of the present application. The storage medium includes a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program instructions, or a terminal device such as a computer, a server, a mobile phone, a tablet, etc. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the partitioning of elements is merely a logical functional partitioning, and there may be additional partitioning in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not implemented. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. The foregoing is only the embodiments of the present application, and therefore, the patent scope of the application is not limited thereto, and all equivalent structures or equivalent processes using the descriptions of the present application and the accompanying drawings, or direct or indirect application in other related technical fields, are included in the scope of the application.

Claims (10)

1.一种3D腹腔镜手术数据处理方法，其特征在于，包括：1. A 3D laparoscopic surgery data processing method, comprising: 采用视频处理技术对原始手术数据视频流进行分帧，得到双目腹腔镜系统左右摄像头对应的腹腔镜图像序列；The original surgical data video stream is framed using video processing technology to obtain the laparoscopic image sequence corresponding to the left and right cameras of the binocular laparoscopic system; 基于相机参数对所述腹腔镜图像序列进行校准，得到消除图像畸变的腹腔镜图像序列；Calibrate the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence that eliminates image distortion; 分别采用基于暗通道先验算法的烟雾去除技术以及基于DeepLabv3+架构的手术器械分割算法对校准后的腹腔镜图像序列进行烟雾去除和手术器械分割，生成无烟雾干扰和器械遮挡的腹腔镜图像序列。The smoke removal technology based on the dark channel prior algorithm and the surgical instrument segmentation algorithm based on the DeepLabv3+ architecture were used to remove smoke and segment surgical instruments from the calibrated laparoscopic image sequence, respectively, to generate a laparoscopic image sequence without smoke interference and instrument occlusion. 2.根据权利要求1所述的3D腹腔镜手术数据处理方法，其特征在于，所述采用视频处理技术对原始手术数据视频流进行分帧，得到双目腹腔镜系统左右摄像头对应的腹腔镜图像序列，具体为：2. The 3D laparoscopic surgery data processing method according to claim 1 is characterized in that the video processing technology is used to frame the original surgery data video stream to obtain the laparoscopic image sequence corresponding to the left and right cameras of the binocular laparoscope system, specifically: 获取所述原始手术数据视频流中的每帧图像，分别将每帧图像沿水平方向分割为左右两部分，分别对应双目腹腔镜系统左摄像头和右摄像头的腹腔镜图像。Each frame of the image in the original surgical data video stream is obtained, and each frame of the image is divided into two parts in the horizontal direction, which correspond to the laparoscopic images of the left camera and the right camera of the binocular laparoscope system respectively. 3.根据权利要求2所述的3D腹腔镜手术数据处理方法，其特征在于，所述基于相机参数对所述腹腔镜图像序列进行校准，得到消除图像畸变的腹腔镜图像序列，具体为：3. The 3D laparoscopic surgery data processing method according to claim 2, characterized in that the laparoscopic image sequence is calibrated based on camera parameters to obtain a laparoscopic image sequence that eliminates image distortion, specifically: 利用相机拍摄N张棋盘格图像；Use a camera to take N chessboard images; 检测所述棋盘格图像的角点，利用OpenCV的校准函数，根据棋盘格的3D世界坐标和2D图像坐标计算相机的内参矩阵和畸变系数；其中，所述相机的内参矩阵包括焦距或主点位置，所述畸变系数包括桶形或枕形畸变；Detect the corner points of the chessboard image, and use the calibration function of OpenCV to calculate the intrinsic parameter matrix and distortion coefficient of the camera according to the 3D world coordinates and 2D image coordinates of the chessboard; wherein the intrinsic parameter matrix of the camera includes the focal length or the principal point position, and the distortion coefficient includes barrel or pincushion distortion; 使用计算到的内参矩阵和畸变系数对分帧后的腹腔镜图像序列进行去畸变处理，恢复腹腔镜图像序列的真实几何形状。The calculated internal parameter matrix and distortion coefficients are used to dedistort the framed laparoscopic image sequence to restore the true geometric shape of the laparoscopic image sequence. 4.根据权利要求1至3任一项所述的3D腹腔镜手术数据处理方法，其特征在于，所述分别采用基于暗通道先验算法的烟雾去除技术以及基于DeepLabv3+架构的手术器械分割算法对校准后的腹腔镜图像序列进行烟雾去除和手术器械分割，包括：4. The 3D laparoscopic surgery data processing method according to any one of claims 1 to 3, characterized in that the smoke removal technology based on the dark channel prior algorithm and the surgical instrument segmentation algorithm based on the DeepLabv3+ architecture are used to perform smoke removal and surgical instrument segmentation on the calibrated laparoscopic image sequence, respectively, comprising: 从每帧腹腔镜图像的RGB通道中计算出每个像素点的最小值，形成暗通道图像；假设所述暗通道图像代表无雾条件下的最小光强，根据暗通道图像与校准后的腹腔镜图像的关系反向推算大气散射导致的透射率图，其中透射率计算公式为：The minimum value of each pixel is calculated from the RGB channels of each frame of the laparoscopic image to form a dark channel image. Assuming that the dark channel image represents the minimum light intensity under fog-free conditions, the transmittance map caused by atmospheric scattering is reversely calculated based on the relationship between the dark channel image and the calibrated laparoscopic image, where the transmittance calculation formula is: 其中，t表示透射率图，I表示校准后的腹腔镜图像，A表示大气光强度，ω是一个调节参数，用于控制去雾强度；Where t represents the transmittance map, I represents the calibrated laparoscope image, A represents the atmospheric light intensity, and ω is an adjustment parameter used to control the defogging intensity; 全局分析所述暗通道图像，选取所述暗通道图像中设定比例的最亮像素作为大气光强度，结合所述透射率图和大气光强度，应用图像复原公式计算出去雾后的腹腔镜图像为：The dark channel image is globally analyzed, and the brightest pixels with a set proportion in the dark channel image are selected as the atmospheric light intensity. The defogging laparoscope image is calculated by combining the transmittance map and the atmospheric light intensity using the image restoration formula: 其中，J表示去雾后的腹腔镜图像。Wherein, J represents the defogging laparoscopic image. 5.根据权利要求1所述的3D腹腔镜手术数据处理方法，其特征在于，所述分别采用基于暗通道先验算法的烟雾去除技术以及基于DeepLabv3+架构的手术器械分割算法对校准后的腹腔镜图像序列进行烟雾去除和手术器械分割，还包括：5. The 3D laparoscopic surgery data processing method according to claim 1, characterized in that the smoke removal technology based on the dark channel prior algorithm and the surgical instrument segmentation algorithm based on the DeepLabv3+ architecture are used to perform smoke removal and surgical instrument segmentation on the calibrated laparoscopic image sequence, and further comprising: 将所述校准后的腹腔镜图像输入DeepLabv3+模型，所述DeepLabv3+模型包括编码器和解码器，所述编码器基于改进的ResNet架构，用于通过空洞卷和多尺度特征融合提取所述腹腔镜图像的高级语义特征图；所述解码器用于对编码器输出的特征图进行逐像素的上采样操作，将低分辨率的特征图恢复到与输入图像相同的尺寸，并输出分割概率图；其中所述分割概率图是一个多通道图像，每个通道对应一个类别的概率分布；对所述分割概率图进行逐像素分析，将每个像素的类别概率映射为具体的类别标签，生成最终的手术器械分割掩码。The calibrated laparoscopic image is input into the DeepLabv3+ model, which includes an encoder and a decoder. The encoder is based on an improved ResNet architecture and is used to extract high-level semantic feature maps of the laparoscopic image through void volumes and multi-scale feature fusion; the decoder is used to perform pixel-by-pixel upsampling operations on the feature maps output by the encoder, restore the low-resolution feature maps to the same size as the input image, and output a segmentation probability map; wherein the segmentation probability map is a multi-channel image, and each channel corresponds to the probability distribution of a category; the segmentation probability map is analyzed pixel by pixel, and the category probability of each pixel is mapped to a specific category label to generate a final surgical instrument segmentation mask. 6.根据权利要求5所述的3D腹腔镜手术数据处理方法，其特征在于，所述对所述分割概率图进行逐像素分析，将每个像素的类别概率映射为具体的类别标签，生成最终的手术器械分割掩码，具体为：6. The 3D laparoscopic surgery data processing method according to claim 5 is characterized in that the segmentation probability map is analyzed pixel by pixel, the category probability of each pixel is mapped to a specific category label, and the final surgical instrument segmentation mask is generated, specifically: 所述手术器械分割掩码以二值图像的形式表示，其中手术器械区域被标记为前景，背景区域被标记为背景。The surgical instrument segmentation mask is represented in the form of a binary image, in which the surgical instrument area is marked as foreground and the background area is marked as background. 7.一种3D腹腔镜手术数据处理装置，其特征在于，包括：7. A 3D laparoscopic surgery data processing device, comprising: 图像分帧模块：用于采用视频处理技术对原始手术数据视频流进行分帧，得到双目腹腔镜系统左右摄像头对应的腹腔镜图像序列；Image framing module: used to frame the original surgical data video stream using video processing technology to obtain the laparoscopic image sequence corresponding to the left and right cameras of the binocular laparoscopic system; 图像校准模块：用于基于相机参数对所述腹腔镜图像序列进行校准，得到消除图像畸变的腹腔镜图像序列；Image calibration module: used for calibrating the laparoscopic image sequence based on camera parameters to obtain a laparoscopic image sequence with image distortion eliminated; 图像预处理模块：用于分别采用基于暗通道先验算法的烟雾去除技术以及基于DeepLabv3+架构的手术器械分割算法对校准后的腹腔镜图像序列进行烟雾去除和手术器械分割，生成无烟雾干扰和器械遮挡的腹腔镜图像序列。Image preprocessing module: It is used to remove smoke and segment surgical instruments from the calibrated laparoscopic image sequence using the smoke removal technology based on the dark channel prior algorithm and the surgical instrument segmentation algorithm based on the DeepLabv3+ architecture, respectively, to generate a laparoscopic image sequence without smoke interference and instrument occlusion. 8.根据权利要求7所述的3D腹腔镜手术数据处理装置，其特征在于，所述图像预处理模块分别采用基于暗通道先验算法的烟雾去除技术以及基于DeepLabv3+架构的手术器械分割算法对校准后的腹腔镜图像序列进行烟雾去除和手术器械分割，具体为：8. The 3D laparoscopic surgery data processing device according to claim 7 is characterized in that the image preprocessing module uses a smoke removal technology based on a dark channel priori algorithm and a surgical instrument segmentation algorithm based on the DeepLabv3+ architecture to perform smoke removal and surgical instrument segmentation on the calibrated laparoscopic image sequence, specifically: 从每帧腹腔镜图像的RGB通道中计算出每个像素点的最小值，形成暗通道图像；假设所述暗通道图像代表无雾条件下的最小光强，根据暗通道图像与校准后的腹腔镜图像的关系反向推算大气散射导致的透射率图，其中透射率计算公式为：The minimum value of each pixel is calculated from the RGB channels of each frame of the laparoscopic image to form a dark channel image. Assuming that the dark channel image represents the minimum light intensity under fog-free conditions, the transmittance map caused by atmospheric scattering is reversely calculated based on the relationship between the dark channel image and the calibrated laparoscopic image, where the transmittance calculation formula is: 其中，t表示透射率图，I表示校准后的腹腔镜图像，A表示大气光强度，ω是一个调节参数，用于控制去雾强度；Where t represents the transmittance map, I represents the calibrated laparoscope image, A represents the atmospheric light intensity, and ω is an adjustment parameter used to control the defogging intensity; 全局分析所述暗通道图像，选取所述暗通道图像中设定比例的最亮像素作为大气光强度，结合所述透射率图和大气光强度，应用图像复原公式计算出去雾后的腹腔镜图像为：The dark channel image is globally analyzed, and the brightest pixels with a set proportion in the dark channel image are selected as the atmospheric light intensity. The defogging laparoscope image is calculated by combining the transmittance map and the atmospheric light intensity using the image restoration formula: 其中，J表示去雾后的腹腔镜图像；Where, J represents the defogging laparoscopic image; 将所述校准后的腹腔镜图像输入DeepLabv3+模型，所述DeepLabv3+模型包括编码器和解码器，所述编码器基于改进的ResNet架构，用于通过空洞卷和多尺度特征融合提取所述腹腔镜图像的高级语义特征图；所述解码器用于对编码器输出的特征图进行逐像素的上采样操作，将低分辨率的特征图恢复到与输入图像相同的尺寸，并输出分割概率图；其中所述分割概率图是一个多通道图像，每个通道对应一个类别的概率分布；对所述分割概率图进行逐像素分析，将每个像素的类别概率映射为具体的类别标签，生成最终的手术器械分割掩码。The calibrated laparoscopic image is input into the DeepLabv3+ model, which includes an encoder and a decoder. The encoder is based on an improved ResNet architecture and is used to extract high-level semantic feature maps of the laparoscopic image through void volumes and multi-scale feature fusion; the decoder is used to perform pixel-by-pixel upsampling operations on the feature maps output by the encoder, restore the low-resolution feature maps to the same size as the input image, and output a segmentation probability map; wherein the segmentation probability map is a multi-channel image, and each channel corresponds to the probability distribution of a category; the segmentation probability map is analyzed pixel by pixel, and the category probability of each pixel is mapped to a specific category label to generate a final surgical instrument segmentation mask. 9.一种设备，其特征在于，所述设备包括处理器、与所述处理器耦接的存储器，其中，9. A device, characterized in that the device comprises a processor and a memory coupled to the processor, wherein: 所述存储器存储有用于实现权利要求1-6任一项所述的3D腹腔镜手术数据处理方法的程序指令；The memory stores program instructions for implementing the 3D laparoscopic surgery data processing method according to any one of claims 1 to 6; 所述处理器用于执行所述存储器存储的所述程序指令以控制3D腹腔镜手术数据处理方法。The processor is used to execute the program instructions stored in the memory to control the 3D laparoscopic surgery data processing method. 10.一种存储介质，其特征在于，存储有处理器可运行的程序指令，所述程序指令用于执行权利要求1至6任一项所述3D腹腔镜手术数据处理方法。10. A storage medium, characterized in that it stores program instructions executable by a processor, wherein the program instructions are used to execute the 3D laparoscopic surgery data processing method according to any one of claims 1 to 6.
CN202510301799.6A 2025-03-14 2025-03-14 A 3D laparoscopic surgery data processing method, device, equipment and storage medium Pending CN120259203A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510301799.6A CN120259203A (en) 2025-03-14 2025-03-14 A 3D laparoscopic surgery data processing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510301799.6A CN120259203A (en) 2025-03-14 2025-03-14 A 3D laparoscopic surgery data processing method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN120259203A true CN120259203A (en) 2025-07-04

Family

ID=96197810

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510301799.6A Pending CN120259203A (en) 2025-03-14 2025-03-14 A 3D laparoscopic surgery data processing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN120259203A (en)

Similar Documents

Publication Publication Date Title
Liu et al. Knowledge-driven deep unrolling for robust image layer separation
CN106056562B (en) A face image processing method, device and electronic device
Gallo et al. Artifact-free high dynamic range imaging
CN111047709B (en) Binocular vision naked eye 3D image generation method
CN107798702B (en) Real-time image superposition method and device for augmented reality
CN120075619B (en) Intelligent jitter recognition and compensation method and system for endoscopic surgery image
CN107798704B (en) Real-time image superposition method and device for augmented reality
CN119741196B (en) High-robustness image stitching method
CN108230384A (en) Picture depth computational methods, device, storage medium and electronic equipment
CN114663575A (en) Method, apparatus and computer-readable storage medium for image processing
CN109241898B (en) Target positioning method and system and storage medium for endoscopic imaging
CN115965603A (en) Image processing method, device, terminal and readable storage medium for endoscope image
CN110046555A (en) Endoscopic system video image stabilization method and device
CN119168994A (en) A method for processing endoscope images and endoscope system thereof
Li et al. Collaborative surgical instrument segmentation for monocular depth estimation in minimally invasive surgery
Floor et al. 3D reconstruction of the human colon from capsule endoscope video
CN111612792A (en) Ai endoscopic analysis method and product of vein based on VRDS 4D medical image
WO2025214308A1 (en) Digestive cavity inner wall three-dimensional model reconstruction method and apparatus, device, and medium
CN111524075B (en) Depth image filtering method, image synthesis method, device, equipment and medium
CN120259203A (en) A 3D laparoscopic surgery data processing method, device, equipment and storage medium
CN117456098A (en) Three-dimensional model reconstruction method and device for target object
CN113989473B (en) A method and apparatus for relighting
CN114463236A (en) Monocular endoscope three-dimensional image display method and system
CN113469903A (en) Image processing method and device, electronic equipment and readable storage medium
CN115601233B (en) Method for converting 2D (two-dimensional) image into 3D (three-dimensional) image of medical image

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