NL2032742B1 - A surgical navigation system based on artificial intelligence and graph theory algorithm - Google Patents
A surgical navigation system based on artificial intelligence and graph theory algorithm Download PDFInfo
- Publication number
- NL2032742B1 NL2032742B1 NL2032742A NL2032742A NL2032742B1 NL 2032742 B1 NL2032742 B1 NL 2032742B1 NL 2032742 A NL2032742 A NL 2032742A NL 2032742 A NL2032742 A NL 2032742A NL 2032742 B1 NL2032742 B1 NL 2032742B1
- Authority
- NL
- Netherlands
- Prior art keywords
- image
- module
- artificial intelligence
- graph theory
- system based
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/20—Surgical navigation systems; Devices for tracking or guiding surgical instruments, e.g. for frameless stereotaxis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/20—Surgical navigation systems; Devices for tracking or guiding surgical instruments, e.g. for frameless stereotaxis
- A61B2034/2046—Tracking techniques
- A61B2034/2065—Tracking using image or pattern recognition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
- A61B90/36—Image-producing devices or illumination devices not otherwise provided for
- A61B90/37—Surgical systems with images on a monitor during operation
- A61B2090/376—Surgical systems with images on a monitor during operation using X-rays, e.g. fluoroscopy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Epidemiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Databases & Information Systems (AREA)
- Robotics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Urology & Nephrology (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a surgery navigation auxiliary system based on artificial intelligence and graph theory algorithm in the field of artificial intelligence, A calibration and positioning module for extracting a target area of a surgery so as to generate a central surgery point, a graph conversion module for vectorizing the target area of the surgery according to a CT image, a conversion module taking a cutting position in the surgery area as a node, and a path generation module for connecting the central surgery point and the node, wherein the graph theory algorithm module generates a weighted graph between the central surgery point and the node. According to the technical scheme, the imaging of the surgical region is combined with the path generation module, so that the optimal surgical path is converted.
Description
P1538/NLpd
A SURGICAL NAVIGATION SYSTEM BASED ON ARTIFICIAL INTELLIGENCE AND
GRAPH THEORY ALGORITHM
The invention belongs to the field of artificial intelli- gence, and particularly relates to a surgical navigation auxiliary system based on artificial intelligence and a graph theory algo- rithm.
Background Technology
Traumatic surgery, as its name implies, is the operation of minor trauma. It refers to the use of laparoscopy, thoracoscopy and other modern medical devices and related equipment for sur- gery. The advantages of minimally invasive surgery are less trau- ma, less pain and faster recovery. It is the dream of every pa- tient who needs surgery. Minimally invasive surgery makes this dream come true. Early minimally invasive surgery refers to a new technology of performing surgery in the human body through lapa- roscopy, thoracoscopy and other endoscopes.
However, in minimally invasive surgery, due to the small opening area, the opening position will gradually lead to blood exudation in the process of surgery, which often blurs the visual field of the endoscope, and after the blood cover is removed, the shaking of the probe will lead to the deviation of the visual field, which makes the chief surgeon lose direction. Therefore, there is an urgent need for a surgical navigation assistant system to overcome the defect of path loss in minimally invasive surgery.
In order to solve the above problems, the object of the pre- sent invention is to provide a surgical navigation assistance sys- tem based on artificial intelligence and graph theory algorithm.
In order to realize the purpose, the technical scheme of the invention is as follows: the surgery navigation auxiliary system based on artificial intelligence and graph theory algorithm com- prises a graph theory algorithm module and an image module used for storing a human body image and a surgery track image, A cali-
bration and positioning module for extracting a target area of a surgery so as to generate a central surgery point, a graph conver- sion module for vectorizing the target area of the surgery accord- ing to a CT image, a conversion module taking a cutting position in the surgery area as a node, and a path generation module for connecting the central surgery point and the node, wherein the graph theory algorithm module generates a weighted graph between the central surgery point and the node.
Furthermore, the system also comprises an identification mod- ule, wherein the identification module divides the weighted graph into a plurality of dendrograms, and then the identification mod- ule finds a minimum spanning tree through the dendrogram as a sur- gical navigation path.
Furthermore, the system also comprises a comparison module, wherein the comparison module uses the minimum spanning tree to compare the CT image and the human body image, at this time, the node connecting line between the minimum spanning trees and the human body image are identified, and if the node connecting line passes through an aorta vessel, the comparison module gives an alarm to determine the minimum spanning tree.
Furthermore, the dendrograms close to the minimum spanning tree are compared one by one by the comparison module so as to plan the optimal dendrogram.
Furthermore, the discrimination module adopts a deep full convolution neural network structure U-Net.
Further, the image module includes placing the preoperative 3D image data and the intraoperative 2D image data in the same co- ordinate system, performing image registration, and providing im- age guidance during the operation.
Further, before 2D/3D registration, the image module needs to perform spatial transformation on the preoperative CT images to obtain DRR images at different angles, construct an objective function by calculating the similarity measure values of the DRR images and the intraoperative X-ray images, and optimize the ob- jective function to obtain the optimal spatial transformation pa- rameters. O that the similarity measure of the image to be regis- tered reaches an extreme value.
Further, the image registration includes performing coarse registration by using a deep learning network, and then performing fine registration by using a parameter optimization method.
Furthermore, the similarity measure between the segmented floating image and the reference image is calculated, and the pa- rameters are updated by Adam parameter optimization algorithm to complete the single-block registration.
By adopting the scheme, the invention realizes the following beneficial effects that: 1, in the technical scheme, the imaging of the operation area is combined with the path generation module so as to be converted into an optimal operation path. 2. Let G be a connected graph with n vertices, then starting from any vertex of G (the central surgery vertex), a depth-first search or breadth-first search can visit all n vertices of G, and then from a visited vertex to an unvisited adjacent vertex, an edge of G must be passed through. While the two methods for the
Each of the n vertices is visited only once, so except for the in- itial starting point, the remaining n-1 vertices are visited through a total of n-1 edges in G, thus connecting all the nodes. 3. Compared with the prior art for connecting all nodes, in the technical scheme, a weighted graph is divided into a plurality of dendrograms by using an identification module, and a minimum span- ning tree is used as a surgical navigation path. 4, Compared with the prior art for generating a surgical navi- gation path, in the technical scheme, the node connecting lines among the minimum spanning trees are identified from the human body image, and if the node connecting lines pass through an aor- tic blood vessel, the comparison module gives an alarm to deter- mine the minimum spanning tree. 5. According to the technical scheme, a 2D/3DCT hierarchical registration method based on a convolutional neural network is in- troduced by using an image module, and technical support is pro- vided for navigation problems in surgery.
Fig. 1 is a system flow chart of an embodiment of the present invention.
The following is a further detailed description of specific embodiments:
The embodiment is basically as shown in Figure 1: a surgical navigation auxiliary system based on artificial intelligence and graph theory algorithm comprises a graph theory algorithm module and an image module for storing human body images and surgical trajectory images. A calibration and positioning module for ex- tracting a target area of a surgery so as to generate a central surgery point, a graphic conversion module for vectorizing the target area of the surgery according to a CT image, a conversion module taking a cutting position in the surgery area as a node, and a path generation module for connecting the central surgery point and the node, wherein the graph theory algorithm module gen- erates a weighted graph between the central surgery point and the node.
The identification module divides the weighted graph into a plurality of dendrograms, and then the identification module looks for the minimum spanning tree as a surgery navigation path through the dendrogram; and the comparison module compares the minimum spanning tree with the CT image and the human body image, and identifies a node connecting line between the minimum spanning trees and the human body image, If the node connection line passes through the aorta vessel, the comparison module sends an alarm to determine the minimum spanning tree.
The dendrograms close to the minimum spanning tree are com- pared one by one by the comparison module so as to plan the opti- mal dendrogram, and the discrimination module adopts a deep full convolution neural network structure U-Net.
The specific implementation process is as follows: firstly, a
CT image map and a human body structure simulation map are sub- jected to convolution operation, preoperative 3D image data and intracperative 2D image data are placed in the same coordinate system, image registration is carried out, image guidance can be provided during the operation, and then an image module and an im- age module need to carry out space transformation on a preopera- tive CT image before 2D/3D registration, DRR images at different angles are obtained, an objective function is constructed by cal- culating the similarity measure values of the DRR images and the intraoperative X-ray images, and the objective function is opti- mized to obtain the optimal spatial transformation parameters, so 5 that the similarity measure values of the images to be registered reach an extreme value, and image registration comprises rough registration by using a deep learning network. Secondly, the pa- rameter optimization method is used for fine registration, and the similarity measure between the segmented floating image and the reference image is calculated. The Adam parameter optimization al- gorithm is used to update the parameters and complete the single block registration.
Subsequently, a weighted graph is generated between a central operation point and a node, subsequently, the weighted graph is divided into a plurality of dendrograms, subsequently, an identi- fication module finds a minimum spanning tree as an operation nav- igation path through the dendrogram, the spanning tree definition of the weighted graph sets the graph to be a connected graph with n vertexes, then starting from any vertex of G (the central opera- tion point), By making a depth-first search or breadth-first search, all n vertices in G can be visited, and then from a visit- ed vertex to an unvisited adjacent vertex, an edge in G must be traversed. Each of the n vertices is visited only once, so except for the initial starting point, the remaining n-1 vertices are visited through a total of n-1 edges in G, thus connecting all the nodes.
A minimum spanning tree is generated from the dendrogram, node connecting lines among the minimum spanning trees are identi- fied from the human body image, and if the node connecting lines pass through an aortic vessel, a comparison module gives an alarm to judge whether the minimum spanning tree meets the operation re- quirement, If the minimum spanning tree is negated, the dendro- grams close to the minimum spanning tree are compared one by one by the comparison module so as to plan the optimal dendrogram.
It is noted that relational terms such as first and second and the like may be used herein only to distinguish one entity or operation from another entity or operation without necessarily re-
quiring or implying any such actual relationship or order between such entities or operations. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cov- er a non-exclusive inclusion, such that a process, method, arti- cle, or apparatus that comprises a list of elements does not in- clude only those elements but may include other elements not ex- pressly listed or inherent to such process, method, article, or apparatus.
The above is only an embodiment of the present invention, and the general knowledge such as the specific structure and charac- teristics known in the scheme is not described too much here.
Those of ordinary skill in the art know all the general technical knowledge of the technical field to which the invention belongs before the application date or the priority date, can learn all the prior art in this field, and have the ability to apply the conventional experimental means before this date. Those of ordi- nary skill in the art may perfect and implement the present solu- tion in combination with their own capabilities under the inspira- tion given by the present application, and some typical known structures or known methods shall not be an obstacle for those of ordinary skill in the art to implement the present application. It should be noted that for those skilled in the art, several modifi- cations and improvements can be made without departing from the structure of the present invention, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the invention and the utility of the patent. The scope of protection claimed in this application shall be subject to the content of the claims, and the specific implementation mode and other records in the de- scription may be used to interpret the content of the claims.
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NL2032742A NL2032742B1 (en) | 2022-08-12 | 2022-08-12 | A surgical navigation system based on artificial intelligence and graph theory algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NL2032742A NL2032742B1 (en) | 2022-08-12 | 2022-08-12 | A surgical navigation system based on artificial intelligence and graph theory algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
NL2032742A NL2032742A (en) | 2022-09-20 |
NL2032742B1 true NL2032742B1 (en) | 2023-04-06 |
Family
ID=83744621
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
NL2032742A NL2032742B1 (en) | 2022-08-12 | 2022-08-12 | A surgical navigation system based on artificial intelligence and graph theory algorithm |
Country Status (1)
Country | Link |
---|---|
NL (1) | NL2032742B1 (en) |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109567942B (en) * | 2018-10-31 | 2020-04-14 | 上海盼研机器人科技有限公司 | Craniomaxillofacial surgical robot auxiliary system adopting artificial intelligence technology |
CN110840561A (en) * | 2019-11-11 | 2020-02-28 | 郑健青 | Operation navigation auxiliary system based on artificial intelligence and graph theory algorithm |
FR3104934B1 (en) * | 2019-12-18 | 2023-04-07 | Quantum Surgical | Method for automatic planning of a trajectory for a medical intervention |
-
2022
- 2022-08-12 NL NL2032742A patent/NL2032742B1/en active
Also Published As
Publication number | Publication date |
---|---|
NL2032742A (en) | 2022-09-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102014359B1 (en) | Method and apparatus for providing camera location using surgical video | |
CN110049742B (en) | Image-guided motion scaling for robot control | |
US20200323593A1 (en) | Methods and Apparatus for Surgical Planning | |
US20110306985A1 (en) | Surgical Assistance System | |
CN114129240B (en) | Method, system and device for generating guide information and electronic equipment | |
JP2013517909A (en) | Image-based global registration applied to bronchoscopy guidance | |
JPWO2020056086A5 (en) | ||
CN110033465A (en) | A kind of real-time three-dimensional method for reconstructing applied to binocular endoscope medical image | |
CN107292928A (en) | A kind of method and device of blood vessel positioning | |
Caborni et al. | Risk-based path planning for a steerable flexible probe for neurosurgical intervention | |
JP4596759B2 (en) | Image diagnostic apparatus and method of operating image diagnostic apparatus | |
Gao et al. | Three-dimensional path planning and guidance of leg vascular based on improved ant colony algorithm in augmented reality | |
JP4321121B2 (en) | Method for tracking movement of biological tissue in diagnostic image and diagnostic imaging apparatus using the method | |
Granna et al. | A 3-D volume coverage path planning algorithm with application to intracerebral hemorrhage evacuation | |
CN111260704B (en) | Vascular structure 3D/2D rigid registration method and device based on heuristic tree search | |
JP2004313736A (en) | Apparatus, method and program for medical image processing | |
Mourgues et al. | Interactive guidance by image overlay in robot assisted coronary artery bypass | |
NL2032742B1 (en) | A surgical navigation system based on artificial intelligence and graph theory algorithm | |
JP2000113086A (en) | Operation route setting device and recording medium recording operation route setting processing program | |
CN113876420B (en) | Path planning method, system, device and medium for planning surgical path | |
CN113081257A (en) | Automatic planning method for operation path | |
Andrea et al. | Validation of stereo vision based liver surface reconstruction for image guided surgery | |
JP7182126B2 (en) | Robotic surgery support device, robotic surgery support method, and program | |
CN116157088A (en) | System for planning and executing biopsy procedures and related methods | |
CN115294079A (en) | Operation navigation auxiliary system based on artificial intelligence and graph theory algorithm |