Abdominal war wound video auxiliary planning and navigation system based on artificial intelligence

By using artificial intelligence-based abdominal war trauma video assisted planning and navigation system in battlefield environments, the problems of the existing technology in real-time processing and recognition accuracy are solved, efficient and accurate image processing and intelligent navigation are achieved, and the improvement of the Safety and efficiency of surgery.

CN118924427AInactive Publication Date: 2024-11-12HEFEI DEYI ELECTRONICS CO LTD +1

Patent Information

Application Number
CN202411314928.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-20
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to meet the needs of real-time processing and analysis of video streams in battlefield environments, and is susceptible to noise and artifacts, resulting in a decrease in recognition accuracy and cannot meet the real-time and efficient requirements during battlefield surgery.

Method used

Adopt artificial intelligence-based abdominal trauma video-assisted planning and navigation system, including endoscopic acquisition module, image processing module and algorithm terminal, to ensure image quality through denoising, contrast enhancement and artifact correction technologies, combining deep learning and artificial The potential field method performs real-time identification and path planning, providing high accuracy and intelligent navigation.

Benefits of technology

Significantly improve the speed and response time of information processing during the operation, improve the accuracy of detection and identification, realize intelligent path planning and navigation, reduce operation time and error, adaptability and portability, and enhance doctors' decision-making support. ability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118924427A_ABST
    Figure CN118924427A_ABST
Patent Text Reader

Abstract

The invention discloses an abdominal war wound video auxiliary planning and navigation system based on artificial intelligence, which relates to the technical field of medical treatment and comprises an endoscope acquisition module, an image processing module, an algorithm end and a user interface end, the endoscope acquisition module comprises a laparoscope image acquisition unit and an endoscope image acquisition unit, and the laparoscope image acquisition unit and the endoscope image acquisition unit are both used for acquiring image data in the operation process in real time; the image processing module is used for preprocessing the acquired image data, and the preprocessing modes comprise image denoising processing, contrast enhancement processing, artifact correction processing and data standardization processing. According to the method, a series of denoising, contrast enhancement and artifact correction technologies are adopted in image preprocessing, so that the image quality is ensured, the recognition accuracy is improved, and the error rate is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to an artificial intelligence-based visual-assisted planning and navigation system for abdominal combat trauma. Background Art

[0002] In modern warfare, abdominal trauma is a common and serious injury, and timely and accurate surgical treatment is crucial for the survival and recovery of the wounded. However, the battlefield environment is complex and changeable, and traditional medical imaging equipment and technology are difficult to meet the needs under battlefield conditions. Medical personnel need to face extremely urgent situations on site and make quick diagnosis and surgical decisions, which often requires a high degree of expertise and rich experience.

[0003] With the development of artificial intelligence technology, computer vision and deep learning have been widely used in medical image analysis. Currently, many studies have begun to explore the use of neural networks for automatic analysis of medical images to improve the accuracy and speed of diagnosis. For example, convolutional neural networks have been widely used in the classification, segmentation and detection of medical images, and have achieved remarkable results. In the field of surgical assistance, some systems have achieved the recognition of surgical instruments and anatomical structures through video analysis and image processing technology.

[0004] However, these existing technologies are mainly concentrated in laboratory environments or medical facilities with limited conditions, and lack application under actual battlefield conditions; there are bottlenecks in real-time processing and analysis of video streams, and they cannot meet the requirements for real-time and high efficiency during battlefield surgery; due to the variability and harshness of the battlefield environment, existing systems are susceptible to noise, artifacts, etc. when processing images collected on the battlefield, resulting in reduced recognition accuracy; therefore, there is room for improvement. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose an artificial intelligence-based abdominal combat trauma visual assisted planning and navigation system. Its advantages are that a series of denoising, contrast enhancement and artifact correction technologies are used in image preprocessing to ensure image quality, improve recognition accuracy and reduce error rate.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An AI-based abdominal combat trauma video-assisted planning and navigation system, including an endoscope acquisition module, an image processing module, an algorithm end, and a user interface end;

[0008] The endoscope acquisition module includes a laparoscopic image acquisition unit and an endoscopic image acquisition unit, and the laparoscopic image acquisition unit and the endoscopic image acquisition unit are both used to acquire image data during the operation in real time;

[0009] The image processing module is used to preprocess the acquired image data, and the preprocessing method includes image denoising processing, contrast enhancement processing, artifact correction processing and data standardization processing;

[0010] The algorithm end includes a neural algorithm network recognition module and a path algorithm planning module. The neural algorithm network recognition module is used to deeply learn the YOLO series algorithm to analyze the pre-processed images, detect and identify abdominal organs and surgical instruments; the path algorithm planning module uses the artificial potential field method to perform path planning to plan and guide the surgical process;

[0011] The user interface includes a plurality of display modules, which display real-time surgical images, recognition results and path planning information in the form of image overlay;

[0012] The present invention is further configured such that the data source of the neural algorithm network recognition module is 10,000 abdominal CT and MRI image data collected, which include various types of normal and pathological images and mark key anatomical structures.

[0013] The present invention is further configured such that the key anatomical structures include the liver, spleen, kidneys, blood vessels and nerves.

[0014] The present invention is further configured such that the neural algorithm network recognition module needs to perform standardization processing on the image, and the standardization processing method includes size adjustment and gray value normalization.

[0015] The present invention is further configured such that the neural algorithm network recognition module needs to label the image when processing data, uses Labelme software to segment and label 10,000 abdominal CT and MRI image data, and uses the Yolo series deep learning model to segment the image; the collected abdominal CT and MRI image data sets are divided into a training set, a validation set, and a test set in a ratio of 8:1:1.

[0016] The present invention is further configured such that the yolo series deep learning model adjusts hyperparameters through grid search or Bayesian optimization method, and the hyperparameters include learning rate and batch size; the model is trained on a high-performance GPU cluster using the framework PyTorch, and the training time is 70-72 hours.

[0017] The present invention is further configured such that the path algorithm planning module uses an artificial potential field method to construct a virtual potential field, calculates the movement direction of the surgical instrument based on gravity and repulsion, updates the potential field parameters in real time, and dynamically adjusts the path based on the progress of the operation.

[0018] The present invention is further configured such that the path algorithm planning module has a feedback mechanism, and the feedback mechanism is to display the spatial relationship between the position of the surgical instrument and the target lesion in real time through the HDMS device, and provide direction adjustment suggestions.

[0019] The present invention is further configured such that the path algorithm planning module has a warning mechanism, wherein when the surgical instrument approaches an important structure, the system issues a real-time warning to alert the doctor, and automatically corrects the path to guide the surgical instrument to avoid obstacles.

[0020] The present invention is further configured such that the path algorithm planning module can realize 4k visualization, mark the lesion location and resection range on HDMS during real-time surgery, and use color coding to distinguish different areas; according to the real-time surgical progress, the display of the lesion resection range is dynamically updated.

[0021] The beneficial effects of the present invention are:

[0022] 1. Real-time and high efficiency: The present invention uses deep learning technology and efficient image processing algorithms to process and analyze images during surgery in real time. Compared with the delays and processing bottlenecks of the prior art, the present system significantly improves the speed and response time of information processing during surgery.

[0023] 2. High accuracy and robustness: By using advanced neural network models, the present invention has higher accuracy in detecting and identifying abdominal organs and surgical instruments. The system has been trained and verified with a large amount of medical image data and can maintain high-precision recognition performance in complex and changing battlefield environments. The present invention uses a series of denoising, contrast enhancement and artifact correction techniques in image preprocessing to ensure image quality, improve recognition accuracy and reduce error rate.

[0024] 3. Intelligent path planning and navigation: The present invention introduces an intelligent path planning algorithm that can dynamically adjust the surgical path according to the real-time recognition results and provide the optimal surgical navigation solution. This not only improves the accuracy and safety of the surgery, but also effectively reduces the operation time. The system's real-time navigation function is presented through an intuitive user interface, helping doctors obtain clear operation guidance during the operation, reducing operational errors and dependence on surgical experience.

[0025] 4. Adaptability and portability: Existing technologies usually rely on complex equipment and environmental conditions, while the present invention designs a portable system that adapts to battlefield environments. The equipment is lightweight, shock-resistant, dustproof, and waterproof, and can work stably in harsh environments, greatly improving the applicability and reliability of the system. The system's hardware and software architecture has been optimized to operate efficiently in low-resource environments, ensuring the operability of battlefield first aid.

[0026] 5. Enhanced decision support: The present invention not only provides basic image recognition functions, but also conducts in-depth analysis of the recognition results through deep learning and data mining technology, providing rich background information and auxiliary decision-making suggestions. This greatly improves the decision-making and response capabilities of doctors in emergency situations. The system can promptly remind abnormal situations detected during the operation and provide corresponding treatment suggestions to ensure the smooth progress of the operation.

[0027] 6. Simplified user interface and interactive operation: The present invention specially designs a concise and intuitive user interface, which displays comprehensive information, including real-time images, recognition results, path planning and navigation guidance, to help doctors fully control the situation during the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a schematic diagram of the overall structure of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0029] Figure 2 This is a schematic diagram of the structure of the image processing module of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0030] Figure 3 A schematic diagram of the neural network algorithm structure of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0031] Figure 4 This is a schematic diagram of the path planning algorithm structure of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0032] Figure 5 A schematic diagram of the neural network algorithm training process of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0033] Figure 6 A schematic diagram of the model loading and use process of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0034] Figure 7 A schematic diagram of the Gaussian distribution algorithm of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0035] Figure 8 This is a schematic diagram of mean filtering of the artificial intelligence-based abdominal combat trauma visual-assisted planning and navigation system proposed by the present invention;

[0036] Fig. 9 A contrast diagram of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0037] Fig.10 A schematic diagram of the model training of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0038] Fig.11 A schematic diagram of the path planning of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed by the present invention;

[0039] Fig.12 A schematic diagram of the distribution of training labels for the AI-based abdominal combat trauma visual-assisted planning and navigation system proposed by the present invention;

[0040] Fig.13 This is a schematic diagram of the cross-validation recall rate of the artificial intelligence-based abdominal combat trauma video-assisted planning and navigation system proposed in the present invention. DETAILED DESCRIPTION

[0041] The technical solution of this patent is further described in detail below in conjunction with specific implementation methods.

[0042] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0043] Reference Figure 1-6 , an AI-based abdominal combat trauma visual-assisted planning and navigation system, including an endoscope acquisition module, an image processing module, an algorithm end, and a user interface end; the endoscope acquisition module includes a laparoscope image acquisition unit and an endoscope image acquisition unit, both of which are used to obtain image data during the operation in real time; the endoscope uses a high-resolution, high-definition 4k endoscope device, and the 4K'P-CAM series endoscope camera system is selected, which has the characteristics of dustproof, waterproof and impact-resistant to adapt to the complex environmental conditions of the battlefield. The device transmits real-time image data to the central processing unit through a wired connection for subsequent processing;

[0044] In order to cope with the harsh conditions of the battlefield environment, the endoscope equipment is designed with fully enclosed protection technology, which has excellent dustproof, waterproof and impact resistance, and meets military-grade standards. The equipment shell is made of high-strength alloy material and is equipped with a shockproof buffer system to effectively resist strong vibration and impact and ensure long-term stable working performance. In addition, the equipment also integrates an automatic cleaning function to cope with dust and liquid contamination in the battlefield environment.

[0045] Image data is transmitted to the central processing unit in real time through a high-speed wired interface, and with the help of advanced real-time data streaming protocols, low latency and high fidelity of image data are ensured. The central processing unit combines edge computing with deep learning algorithms for instant image processing, providing real-time image enhancement, three-dimensional reconstruction and intelligent analysis. The system can automatically identify and track the position of organs and surgical instruments, and generate accurate operational feedback to provide doctors with real-time surgical navigation support. Through efficient data processing and intelligent analysis, the system significantly improves the accuracy and safety of surgery, effectively reduces operation time and risks, and provides solid technical support for medical operations in complex combat trauma environments.

[0046] Reference Figure 7 and Figure 8 The image processing module is used to preprocess the acquired image data. The preprocessing methods include image denoising, contrast enhancement, artifact correction and data standardization. The filtering algorithms including Gaussian filtering and mean filtering are used to remove noise in the image and enhance the clarity of the image. The adaptive histogram equalization and other technologies are used to improve the contrast of the image and make the details clearer.

[0047] Reference Fig. 9 In terms of contrast enhancement, the module uses adaptive histogram equalization (AHE) technology to improve the global and local contrast of the image by dynamically adjusting the grayscale distribution of the image, making the details more prominent and the information richer. Combined with advanced image correction algorithms, the system can effectively correct artifacts, distortions and other visual interference in the image to ensure the authenticity and accuracy of the image data. In addition, the module also integrates a variety of image enhancement technologies, such as edge enhancement and sharpening processing, to ensure that images acquired in complex environments can clearly present key details and support subsequent intelligent analysis and decision support.

[0048] Reference Fig.10 The algorithm side includes a neural algorithm network recognition module and a path algorithm planning module. The neural algorithm network recognition module is used to deeply learn the YOLO series algorithm to analyze the pre-processed images, detect and identify abdominal organs and surgical instruments;

[0049] 1) Model training: A large number of annotated medical image datasets are used to train the neural network model. During the training process, data enhancement techniques (rotation, flipping, scaling) are used to improve the generalization ability of the model; the framework used, PyTorch, integrates multi-scale feature extraction and self-attention mechanisms to further enhance the model's ability to recognize subtle structures. In addition, a combination of transfer learning and self-supervised learning is used to effectively shorten the training time and improve the recognition accuracy of the model;

[0050] 2) Real-time recognition: During the operation, the trained model is used to analyze the real-time acquired images, identify and mark the key organs and instruments; by introducing innovative real-time image segmentation and instance separation technology, the system can accurately distinguish overlapping and similar organs and instruments. The recognition results are displayed on the image through intelligent color coding and dynamic selection, and combined with augmented reality (AR) technology, the real-time recognition information is presented in a three-dimensional overlay form, which is convenient for doctors to perform precise operations and rapid positioning. The system also integrates an anomaly detection module based on deep learning, which can identify and prompt potential instrument collisions or misoperations in real time, further improving the safety and accuracy of the operation.

[0051] Reference Fig.11 The path algorithm planning module uses the artificial potential field method to plan and guide the surgical process; ensure that the surgical instrument selects the optimal path during the operation, combines the neural network recognition module to detect and avoid important organs and blood vessels, and combines the predetermined path and real-time situation of the operation. The system updates the path planning in real time to provide the optimal surgical path, dynamically adjusts the surgical plan, and ensures the safety and efficiency of the operation.

[0052] In actual operation, the path algorithm planning module is closely integrated with the neural network recognition module to obtain and analyze the position data of organs and blood vessels in the surgical area in real time. By integrating real-time image data and surgical environment information, the system can update the path planning in real time and dynamically adjust the surgical path to cope with intraoperative changes. The module also combines intelligent path prediction technology to generate the optimal path strategy by simulating and rehearsing possible operation paths, and feeds back the updated path planning information to the doctor in real time with an intuitive interface.

[0053] In addition, to further improve the safety and efficiency of surgery, the module integrates an artificial intelligence-based anomaly detection and adaptive adjustment mechanism, which can monitor any deviation from the preset path during the operation in real time and automatically adjust the planning strategy to adapt to unexpected situations in complex surgical environments. The system not only provides intuitive path guidance, but also has an intelligent obstacle avoidance function, which ensures the safety and precision of surgical instruments by predicting potential obstacles and automatically adjusting the path.

[0054] The user interface includes multiple display modules, which display real-time surgical images, recognition results and path planning information in the form of image overlays; it is convenient for doctors to use during surgery; it helps doctors understand the progress of the surgery in real time and make decisions.

[0055] 1. Neural Network Algorithm

[0056] 1. Data Collection

[0057] Data source: 10,000 abdominal CT and MRI image data were collected, including various types of normal and pathological images, and key anatomical structures (such as liver, spleen, kidneys, major blood vessels and nerves) were marked.

[0058] Data preprocessing: Standardize the image, including resizing, grayscale normalization, etc. This process uses adaptive interpolation algorithms and multi-scale data recalibration technology to dynamically adjust the image size and grayscale distribution, so that the image data has the best visual characteristics and information density when entering the subsequent analysis stage. In addition, the image feature enhancement mechanism is introduced to adaptively adjust the image contrast and brightness through intelligent algorithms to optimize data quality, thereby improving the accuracy of subsequent processing and analysis.

[0059] 2. Image processing and annotation

[0060] Labeling tools: Use labelme software to segment and label 10,000 abdominal CT and MRI image data;

[0061] Reference Fig.12 ,Neural network model: The YOLO series deep learning model is used to segment the image. The collected abdominal CT and MRI image data sets are divided into training set, validation set and test set in a ratio of 8:1:1 to ensure that the performance of the model on different data is representative. The cross-validation method is used during the training process to improve the generalization ability of the model.

[0062] Hyperparameter optimization: Tune the model’s hyperparameters (such as learning rate, batch size, etc.) through grid search or Bayesian optimization methods to obtain the best model performance.

[0063] 3. Training Platform

[0064] Training the model on a high-performance GPU cluster using the PyTorch framework takes about 70-72 hours.

[0065] 4. Validate the model

[0066] Reference Fig.13 , K-fold cross validation is used to evaluate the model performance. In each validation, different folds are used as validation sets, and the rest are used as training sets. This cycle is repeated K times, and the average performance is finally taken as the evaluation standard of the model.

[0067] The performance of the neural network model of the present invention on the test set is as follows:

[0068] Organ and surgical instrument testing:

[0069] Accuracy: 96.5%

[0070] Recall: 94.8%

[0071] Precision: 95.2%

[0072] F1 Score: 95.0%

[0073] IoU (Intersection over Union): 87.5%.

[0074] 2. Path Planning Algorithm

[0075] 1. Path tracking and adjustment

[0076] Algorithm selection: The artificial potential field method (APF) is used to construct a virtual potential field and calculate the movement direction of the surgical instrument based on the attraction and repulsion.

[0077] Real-time adjustment: Update potential field parameters in real time, dynamically adjust the path according to the progress of the operation, and ensure that the surgical instruments move along the optimal path.

[0078] 2. Feedback Mechanism

[0079] Feedback method: HDMS equipment displays the spatial relationship between the position of surgical instruments and the target lesion in real time, and provides direction adjustment suggestions.

[0080] 3. Steps and details

[0081] 1) Path prediction and obstacle avoidance

[0082] Prediction algorithm: Through the above-mentioned neural network detection algorithm, the organs in the abdomen and the movement trajectory of the instrument are automatically identified and detected, and the organs that need to be avoided and the important structures that may be encountered during the operation are displayed in real time in an interactive manner.

[0083] Obstacle avoidance strategy: Combine surgical approaches and prediction models to plan obstacle avoidance paths and ensure that surgical instruments avoid important nerves and blood vessels.

[0084] 2) Warning mechanism

[0085] Real-time warning: When surgical instruments approach important structures, the system issues real-time warnings to alert doctors.

[0086] Path correction: Automatically correct the path to guide surgical instruments to avoid obstacles.

[0087] 4. Display the extent of lesion resection

[0088] 1) 4k visualization

[0089] Marking lesions: Mark the location of lesions and the extent of resection on HDMS during real-time surgery, and use color coding to distinguish different areas; assisting doctors in performing precise operations.

[0090] 2) Assisted resection of lesions

[0091] Dynamic update: The display of lesion resection range is dynamically updated according to the real-time surgical progress to ensure accurate operation.

[0092] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An artificial intelligence-based visual-assisted planning and navigation system for abdominal combat trauma, characterized in that: It includes an endoscope acquisition module, an image processing module, an algorithm end, and a user interface end; The endoscope acquisition module includes a laparoscopic image acquisition unit and an endoscopic image acquisition unit, and the laparoscopic image acquisition unit and the endoscopic image acquisition unit are both used to acquire image data during the operation in real time; The image processing module is used to preprocess the acquired image data, and the preprocessing method includes image denoising processing, contrast enhancement processing, artifact correction processing and data standardization processing; The algorithm end includes a neural algorithm network recognition module and a path algorithm planning module. The neural algorithm network recognition module is used to deeply learn the YOLO series algorithm to analyze the pre-processed images, detect and identify abdominal organs and surgical instruments; the path algorithm planning module uses the artificial potential field method to perform path planning to plan and guide the surgical process; The user interface includes a plurality of display modules, which display real-time surgical images, recognition results and path planning information in the form of image overlay.

2. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 1, characterized in that: The data source of the neural algorithm network recognition module is 10,000 abdominal CT and MRI image data, which include various types of normal and pathological images and mark key anatomical structures.

3. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 2, characterized in that: The key anatomical structures include the liver, spleen, kidneys, blood vessels and nerves.

4. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 3, characterized in that: The neural algorithm network recognition module needs to perform standardization processing on the image, and the standardization processing method includes size adjustment and gray value normalization.

5. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 4, characterized in that: The neural algorithm network recognition module needs to annotate the image when processing data. Labelme software is used to segment and annotate 10,000 abdominal CT and MRI image data, and the yolo series deep learning model is used to segment the image; the collected abdominal CT and MRI image data sets are divided into training set, validation set and test set in a ratio of 8:1:

1.

6. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 5, characterized in that: The Yolo series deep learning model uses grid search or Bayesian optimization methods to adjust hyperparameters, including learning rate and batch size; the model is trained on a high-performance GPU cluster using the PyTorch framework, and the training time is 70-72 hours.

7. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 1, characterized in that: The path algorithm planning module uses the artificial potential field method to construct a virtual potential field, calculates the movement direction of the surgical instrument based on gravity and repulsion, updates the potential field parameters in real time, and dynamically adjusts the path according to the progress of the operation.

8. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 7, characterized in that: The path algorithm planning module has a feedback mechanism, which displays the position of the surgical instrument and the spatial relationship between the target lesion in real time through the HDMS device, and provides direction adjustment suggestions.

9. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 8, characterized in that: The path algorithm planning module has a warning mechanism. When the surgical instrument approaches an important structure, the system issues a real-time warning to alert the doctor, automatically corrects the path, and guides the surgical instrument to avoid obstacles.

10. The AI-based abdominal combat trauma video-assisted planning and navigation system according to claim 9, characterized in that: The path algorithm planning module can achieve 4k visualization, mark the lesion location and resection range on HDMS during real-time surgery, and use color coding to distinguish different areas; according to the real-time surgical progress, the display of the lesion resection range is dynamically updated.

Citation Information

Patent Citations

  • Surgical auxiliary system and surgical path planning method

    CN114948199A

  • Image recognition method based on multi-fidelity Bayesian optimization

    CN115346061A

  • Surgical navigation system for prediction based on historical data analysis

    CN116935009A

  • Ultrasonic image abdominal organ and viscera detection method based on YOLOX

    CN117422701A

  • Method for analyzing endoscopic image and automatically generating diagnostic report

    CN117524402A

Cited By

  • Neurosurgical navigation acceleration processing method and system

    CN119600203A