CN117017486B - Lung nodule puncture path planning method based on medical image - Google Patents
Lung nodule puncture path planning method based on medical image Download PDFInfo
- Publication number
- CN117017486B CN117017486B CN202311266649.3A CN202311266649A CN117017486B CN 117017486 B CN117017486 B CN 117017486B CN 202311266649 A CN202311266649 A CN 202311266649A CN 117017486 B CN117017486 B CN 117017486B
- Authority
- CN
- China
- Prior art keywords
- puncture
- area
- virtual
- channel
- planning
- 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.)
- Active
Links
- 206010056342 Pulmonary mass Diseases 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005070 sampling Methods 0.000 claims abstract description 55
- 238000012216 screening Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000011156 evaluation Methods 0.000 claims description 34
- 238000013210 evaluation model Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 16
- 238000013145 classification model Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003211 malignant effect Effects 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 claims description 3
- 230000035515 penetration Effects 0.000 claims description 3
- 210000004072 lung Anatomy 0.000 abstract description 6
- 210000000056 organ Anatomy 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000002059 diagnostic imaging Methods 0.000 description 7
- 210000001519 tissue Anatomy 0.000 description 6
- 206010028980 Neoplasm Diseases 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000036210 malignancy Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007920 subcutaneous administration Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- A61B2034/107—Visualisation of planned trajectories or target regions
-
- 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
- A61B2034/108—Computer aided selection or customisation of medical implants or cutting guides
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
- G06T2207/30064—Lung nodule
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Surgery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Geometry (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Robotics (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention belongs to the technical field of medical detection, and particularly relates to a lung nodule puncture path planning method based on medical images. According to the invention, the lung nodule puncture path can be screened and planned based on the medical image, after the image information of the lung nodule region is obtained, the offset processing can be carried out based on the edge curve of the lung nodule region, so that a safe sampling region can be obtained, the puncture needle is prevented from damaging the normal lung region in the sampling process, meanwhile, the safe puncture path can be determined through screening of the virtual puncture channel, the execution priority of each puncture channel is determined according to the finally obtained planning score, other tissues and organs in a patient can be avoided when the puncture needle is guided, and the phenomenon of secondary damage to the patient in the puncture needle guiding process is avoided.
Description
Technical Field
The invention belongs to the technical field of medical detection, and particularly relates to a lung nodule puncture path planning method based on medical images.
Background
The lung nodule is a common lung lesion, diagnosis and treatment of the lung nodule are carried out through medical images, common medical image technologies comprise X-rays, CT, MRI and the like, in a lung nodule puncture operation, information such as the position, the size, the shape and the like of the nodule are acquired through the medical image technology, and an optimal puncture path is planned so as to ensure the success and the safety of the operation, so that research on a lung nodule puncture path planning method based on the medical images has important practical significance.
In the prior art, although medical imaging is assisted, the medical personnel still need to execute the puncturing operation by virtue of subjective judgment, and as a certain distance exists between a puncturing area and a puncturing point, other tissues or organs exist in the puncturing area, and further, in the process of guiding the puncturing needle, the puncturing area is easy to touch other tissues or organs, and the patient is easily damaged secondarily, therefore, the scheme provides a method for screening and planning a pulmonary nodule puncturing path based on medical imaging.
Disclosure of Invention
The invention aims to provide a lung nodule puncture path planning method based on medical images, which can screen and plan a lung nodule puncture path based on the medical images and is used for providing a reference scheme for a doctor before operation, so that the puncture path can avoid other tissues and organs in a patient, and the phenomenon of secondary damage to the patient in the process of guiding a puncture needle is avoided.
The technical scheme adopted by the invention is as follows:
a lung nodule puncture path planning method based on medical imaging, comprising:
acquiring a target area and image information of the target area, wherein the image information of the target area comprises a first feature and a second feature;
inputting the first features into an evaluation model to obtain image distribution areas of the first features, and calibrating corresponding areas as areas to be sampled;
acquiring a puncture area and image information between the puncture area and an area to be sampled, and calibrating the puncture area and the area to be sampled as an interference image;
setting a plurality of sampling nodes in the region to be sampled, and constructing a plurality of virtual puncture channels to the puncture region by taking the sampling nodes as starting nodes;
constructing a virtual coordinate system according to the interference image, the area to be sampled and the puncture area, determining a node where the virtual puncture channel intersects with the puncture area as a starting coordinate, and calibrating the node where the virtual puncture channel intersects with the area to be sampled as a target coordinate;
acquiring interference features and edge coordinates of the interference features from the interference images, calibrating the interference features as interference coordinates, and judging whether the virtual puncture channel passes through the interference coordinates or not;
if yes, screening out the virtual puncture channel;
if not, calibrating the virtual puncture channel as a channel to be evaluated, and summarizing the channel to be evaluated into a data set to be evaluated;
inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths;
inputting the puncture paths into a planning model, obtaining a planning score of each puncture path, and determining the execution priority of each puncture path according to the planning score.
In a preferred embodiment, the step of inputting the first feature into an evaluation model to obtain an image distribution area of the first feature includes:
acquiring edge inflection point coordinates of the first feature, and calibrating the coordinates as reference parameters;
invoking an evaluation function from the evaluation model;
and inputting the reference parameters into an evaluation function, and calibrating the output result as the image distribution area of the first feature.
In a preferred embodiment, after the image distribution area of the first feature is determined, the image distribution area is input into an evaluation model, and the evaluation process is as follows:
acquiring an image distribution area of the first feature, and calibrating the image distribution area as a parameter to be evaluated;
acquiring evaluation intervals from the evaluation model, wherein a plurality of evaluation intervals are arranged, and each evaluation interval corresponds to one evaluation score;
and comparing the parameter to be evaluated with an evaluation interval to obtain an evaluation score of the parameter to be evaluated, and determining the benign and malignant degree of the lung nodule in the area to be sampled according to the evaluation score of the parameter to be evaluated.
In a preferred embodiment, the step of disposing a plurality of sampling nodes in the area to be sampled includes:
acquiring an edge inflection point of the region to be sampled, and connecting adjacent edge inflection points to obtain an edge curve of the region to be sampled;
acquiring the diameter of the puncture needle and calibrating the diameter as an offset parameter;
inwardly shifting the edge curve of the area to be sampled according to the shifting parameter to obtain the edge curve of the sampling area;
obtaining a standard function, and inputting the coordinates of the inflection points of the edges of the sampling area into the standard function to obtain the central coordinates of the sampling area;
and shifting the central coordinate of the sampling area according to the shifting parameter, and determining the shifting result as a sampling node.
In a preferred embodiment, the step of constructing a plurality of virtual puncture channels to the puncture area with the sampling node as a start node includes:
acquiring a puncture area and constructing a plurality of puncture points in the puncture area;
connecting all the sampling nodes with a plurality of puncture points respectively to obtain a plurality of virtual paths;
and offsetting the virtual path according to the offset parameter, and calibrating an offset result as a virtual puncture channel.
In a preferred scheme, after the virtual puncture channels are determined, puncture angles of all the virtual puncture channels are obtained and calibrated as parameters to be verified;
acquiring a checking interval and comparing the checking interval with the parameter to be checked;
if the parameter to be checked is in the check interval, reserving the virtual puncture channel;
if the parameter to be checked is not in the check interval, the virtual puncture channel is marked as a non-executable puncture channel, and the virtual puncture channel is synchronously screened out.
In a preferred embodiment, the step of inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths includes:
obtaining all the channels to be evaluated with consistent target coordinates, and calibrating the channels to be evaluated as parameters to be classified;
obtaining the shortest distance between the channel to be evaluated with the consistent target coordinates and the interference coordinates, and calibrating the shortest distance as a parameter to be classified;
obtaining a classification threshold value from the classification model and comparing the classification threshold value with the parameters to be classified;
if the parameters to be classified are smaller than the classification threshold, screening out the corresponding channels to be evaluated;
and if the parameter to be classified is greater than or equal to the classification threshold, determining the corresponding channel to be evaluated as a puncture path.
In a preferred embodiment, the step of inputting the puncture paths into a planning model to obtain a planning score for each puncture path includes:
acquiring a puncture path and corresponding parameters to be classified;
calling a planning interval from the planning model;
comparing the parameters to be classified with the planning interval to obtain a planning score;
arranging the puncture paths according to the values of the planning scores from large to small to obtain the execution priority of each puncture path;
the execution priority of the puncture path is consistent with the arrangement order of the corresponding planning score.
The invention also provides a lung nodule puncture path planning system based on the medical image, which is applied to the lung nodule puncture path planning method based on the medical image, and comprises the following steps:
the device comprises a first acquisition module, a second acquisition module and a first processing module, wherein the first acquisition module is used for acquiring a target area and image information of the target area, and the image information of the target area comprises a target first feature and a target second feature;
the evaluation module is used for inputting the first feature into an evaluation model, obtaining the image distribution area of the first feature, and calibrating the corresponding area as an area to be sampled;
the second acquisition module is used for acquiring the puncture area and the image information between the puncture area and the area to be sampled and calibrating the puncture area and the area to be sampled as an interference image;
the first construction module is used for setting a plurality of sampling nodes in the area to be sampled, and constructing a plurality of virtual puncture channels to the puncture area by taking the sampling nodes as starting nodes;
the second construction module is used for constructing a virtual coordinate system according to the interference image, the region to be sampled and the puncture region, determining a node where the virtual puncture channel intersects with the puncture region as an initial coordinate, and calibrating the node where the virtual puncture channel intersects with the region to be sampled as a target coordinate;
the judging module is used for acquiring interference features from the interference images, calibrating the edge coordinates of the interference features as interference coordinates and judging whether the virtual puncture channel passes through the interference coordinates or not;
if yes, screening out the virtual puncture channel;
if not, calibrating the virtual puncture channel as a channel to be evaluated, and summarizing the channel to be evaluated into a data set to be evaluated;
the classification module is used for inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with the repeated target coordinates to obtain a plurality of puncture paths;
the planning module is used for inputting the puncture paths into a planning model, obtaining the planning score of each puncture path, and determining the execution priority of each puncture path according to the planning score.
And, a lung nodule puncture path planning terminal based on medical images, comprising:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the above-described medical image-based lung nodule penetration path planning method.
The invention has the technical effects that:
according to the invention, the lung nodule puncture path can be screened and planned based on the medical image, after the image information of the lung nodule region is obtained, the offset processing can be carried out based on the edge curve of the lung nodule region, so that a safe sampling region can be obtained, the puncture needle is prevented from damaging the normal lung region in the sampling process, meanwhile, the safe puncture path can be determined through screening of the virtual puncture channel, the execution priority of each puncture channel is determined according to the finally obtained planning score, other tissues and organs in a patient can be avoided when the puncture needle is guided, and the phenomenon of secondary damage to the patient in the puncture needle guiding process is avoided.
Drawings
FIG. 1 is a flow chart of a method provided by the present invention;
fig. 2 is a block diagram of a system provided by the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one preferred embodiment" 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.
Referring to fig. 1 and 2, the present invention provides a lung nodule puncture path planning method based on medical images, comprising:
s1, acquiring a target area and image information of the target area, wherein the image information of the target area comprises a first feature and a second feature;
s2, inputting the first features into an evaluation model to obtain image distribution areas of the first features, and calibrating the corresponding areas as areas to be sampled;
s3, acquiring a puncture area and image information between the puncture area and an area to be sampled, and calibrating the puncture area and the area to be sampled as an interference image;
s4, setting a plurality of sampling nodes in the area to be sampled, and constructing a plurality of virtual puncture channels to the puncture area by taking the sampling nodes as initial nodes;
s5, constructing a virtual coordinate system according to the interference image, the area to be sampled and the puncture area, determining a node where the virtual puncture channel intersects with the puncture area as a starting coordinate, and calibrating the node where the virtual puncture channel intersects with the area to be sampled as a target coordinate;
s6, acquiring interference features and edge coordinates of the interference features from the interference images, calibrating the interference features as interference coordinates, and judging whether the virtual puncture channel passes through the interference coordinates;
if yes, screening out the virtual puncture channel;
if not, calibrating the virtual puncture channel as a channel to be evaluated, and summarizing the channel to be evaluated into a data set to be evaluated;
s7, inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths;
s8, inputting the puncture paths into a planning model, obtaining a planning score of each puncture path, and determining the execution priority of each puncture path according to the planning score.
As described in the above steps S1-S8, the lung nodule is a common lung lesion, the diagnosis and treatment of which are performed by medical imaging, the common medical imaging techniques include X-ray, CT, MRI, etc., in the lung nodule puncture operation, the position, size, form, etc. information of the nodule are acquired by medical imaging techniques, so as to plan an optimal puncture path, so as to ensure the success and safety of the operation, therefore, the lung nodule puncture path planning method based on medical imaging is studied to have important practical significance, in this embodiment, the image information of the lung region is firstly acquired, and then classified into the first feature and the second feature, the first feature corresponds to the lung nodule region, the second feature is the healthy region, and then the first feature is input into the evaluation model, so as to calculate the distribution area, and the benign malignancy of the lung nodule can be primarily determined according to the distribution area, then determining the distribution area as an area to be sampled, and before sampling, determining the puncture area, wherein the puncture area is distributed on the epidermis of a patient, then acquiring image information between the puncture area and the area to be sampled, and calibrating the image information as an interference image, wherein tissues or organs such as capillary vessels or subcutaneous bones which are used for interfering with the execution of the puncture needle exist in the interference image, then setting a plurality of sampling nodes based on the area to be sampled, and constructing a virtual puncture channel by taking the sampling nodes as initial nodes, wherein the virtual puncture channel can be realized by using a three-dimensional reconstruction technology, which is a common medical auxiliary means, without excessive redundancy, then determining initial coordinates and target coordinates of the virtual puncture channel by constructing a virtual coordinate system, and simultaneously determining the target and distant coordinates of interference features in the interference image, and determining whether the virtual puncture channel coincides with the interference feature or not according to the virtual puncture channel, screening out the coincident virtual puncture channel, determining a channel to be evaluated, inputting the channel to be evaluated into a classification model for secondary screening, determining puncture paths, inputting the puncture paths into a planning model, determining planning scores of all puncture paths, and determining execution priorities of all puncture paths according to the planning scores.
In a preferred embodiment, the step of inputting the first feature into the evaluation model to obtain the image distribution area of the first feature includes:
s201, acquiring edge inflection point coordinates of a first feature, and calibrating the coordinates as reference parameters;
s202, calling an evaluation function from an evaluation model;
s203, inputting the reference parameters into the evaluation function, and calibrating the output result as the image distribution area of the first feature.
As described in the above steps S201 to S201, after the first feature is determined, the coordinates of the inflection points of the edges are obtained, and in this embodiment, the coordinates are calibrated as reference parameters, and then input into an evaluation function to obtain the image distribution area of the first feature, where the expression of the evaluation function is:wherein->Image distribution area representing a first feature +.>Represents the number of edge inflection points, +.>Number indicating coordinates of inflection point>Represents the abscissa of inflection point, ++>And the ordinate of the inflection point is represented, and based on the inflection point, after the image distribution area of the first characteristic is obtained, the benign and malignant degree of the lung nodule of the patient can be determined by combining the evaluation model.
In a preferred embodiment, after the image distribution area of the first feature is determined, it is input into an evaluation model, and the evaluation process is as follows:
stp1, acquiring an image distribution area of a first feature, and calibrating the image distribution area as a parameter to be evaluated;
stp2, obtaining evaluation intervals from an evaluation model, wherein a plurality of evaluation intervals are arranged, and each evaluation interval corresponds to one evaluation score;
stp3, comparing the parameter to be evaluated with the evaluation interval to obtain an evaluation score of the parameter to be evaluated, and determining the benign and malignant degree of the lung nodule in the area to be sampled according to the evaluation score of the parameter to be evaluated.
As described in the above steps Stp1 to Stp3, after the image distribution area of the first feature is determined, the image distribution area is further evaluated, the nodules below 4 mm are benign, the probability of malignancy is only 1% for the nodules between 4 and 7 mm, the probability of malignancy is increased to 15% for the nodules above 8 mm, and 75% for the nodules above two cm.
In a preferred embodiment, the step of disposing a plurality of sampling nodes in the area to be sampled includes:
s401, acquiring edge inflection points of a region to be sampled, and connecting adjacent edge inflection points to obtain an edge curve of the region to be sampled;
s402, acquiring the diameter of the puncture needle and calibrating the diameter as an offset parameter;
s403, inwards shifting the edge curve of the area to be sampled according to the shifting parameter to obtain the edge curve of the sampling area;
s404, acquiring a standard function, and inputting the coordinates of the inflection points of the edge of the sampling area into the standard function to obtain the central coordinates of the sampling area;
s405, offsetting the central coordinate of the sampling area according to the offset parameter, and determining an offset result as a sampling node.
As described in the above steps S401 to S405, after the area to be sampled is determined, the area to be sampled is shifted based on the inflection point of the edge, so as to obtain a safe sampling area, in this embodiment, the area to be sampled is determined as a sampling area, and the shift distance is determined according to the diameter of the puncture needle, so as to ensure that normal tissue in the lung area is not damaged in the process of performing puncture, after the area to be sampled is determined, the image distribution area combined with the first feature is input into a standard function, the center coordinate of the area to be sampled is calculated, and a shift basis is provided for the sampling node to be determined subsequently, wherein the expression of the standard function is as followsWherein->And the central coordinates of the sampling area are represented, and offset processing is carried out according to the central coordinates, so that a plurality of sampling nodes can be obtained, the offset distances of the sampling nodes can be determined by historical experience of medical staff, and the purpose of taking lung nodule samples at different positions is achieved.
In a preferred embodiment, the step of constructing a plurality of virtual puncture channels to the puncture area using the sampling node as a starting node includes:
s406, acquiring a puncture area, and constructing a plurality of puncture points in the puncture area;
s407, respectively connecting all the sampling nodes with a plurality of puncture points to obtain a plurality of virtual paths;
s408, the virtual path is offset according to the offset parameter, and the offset result is calibrated as a virtual puncture channel.
As described in the above steps S406-S408, after the sampling node is determined, a virtual puncture channel can be constructed by using the sampling node as a starting node, in the process of constructing the virtual puncture channel, a plurality of executable puncture points are determined in the puncture area, then the puncture points are connected with the sampling node, so as to obtain virtual paths, and the virtual paths are offset to obtain a plurality of virtual puncture channels, and then the virtual puncture channels are screened to determine the final puncture path.
In a preferred embodiment, after the virtual puncture channels are determined, puncture angles of all the virtual puncture channels are obtained and calibrated as parameters to be checked;
acquiring a checking interval and comparing the checking interval with parameters to be checked;
if the parameter to be checked is in the check interval, reserving the virtual puncture channel;
if the parameter to be checked is not in the checking interval, the virtual puncture channel is marked as a non-executable puncture channel, and the virtual puncture channel is synchronously screened out.
In this embodiment, after the virtual puncture channel is determined, the puncture angle of the virtual puncture channel needs to be determined, the virtual puncture channel is determined as a parameter to be checked, in order to ensure the puncture success degree, a corresponding check interval is set according to the operation habit of medical staff, the check interval is compared with the parameter to be checked in real time, the virtual puncture channel which is not in the check interval is determined as a non-executable puncture channel, the virtual puncture channel which is not in the check interval is synchronously screened out, and the virtual puncture channel which is in the check interval is reserved.
In a preferred embodiment, the step of inputting the channel to be evaluated into the classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths includes:
s701, acquiring all channels to be evaluated with consistent target coordinates, and calibrating the channels to be evaluated as parameters to be classified;
s702, acquiring the shortest distance between the channel to be evaluated with consistent target coordinates and the interference coordinates, and calibrating the shortest distance as a parameter to be classified;
s703, acquiring a classification threshold value from the classification model and comparing the classification threshold value with parameters to be classified;
if the parameters to be classified are smaller than the classification threshold, screening out the corresponding channels to be evaluated;
if the parameter to be classified is greater than or equal to the classification threshold, determining the corresponding channel to be evaluated as a puncture path.
As described in the above steps S701-S703, after the channels to be evaluated are determined, the channels to be evaluated with the same objective coordinates are classified as a group, the classification result includes a puncture path and a screened channel to be evaluated, the classification is based on the shortest distance between the channel to be evaluated and the interference coordinates, generally speaking, the smaller the shortest distance between the channel to be evaluated and the interference coordinates is, the greater the execution process of the puncture difficulty is, the higher the operability requirement for the medical staff is, based on this, the screening process is executed on the channels to be evaluated by setting the classification threshold, and then the puncture paths can be screened out from a plurality of channels to be evaluated, and then the execution priority of the puncture paths can be determined according to the setting of the planning model.
In a preferred embodiment, the step of inputting the puncture paths into the planning model to obtain a planning score for each puncture path includes:
s801, acquiring a puncture path and corresponding parameters to be classified;
s802, calling a planning interval from a planning model;
s803, comparing the parameters to be classified with the planning interval to obtain a planning score;
s804, arranging puncture paths according to the value of the planning score from large to small to obtain the execution priority of each puncture path;
wherein, the execution priority of the puncture path is consistent with the arrangement order of the corresponding planning score.
As described in the above steps S801-S804, after the puncture paths are determined, the corresponding parameters to be classified are obtained, and then the planning intervals are called from the planning model, the planning intervals are provided with a plurality of planning intervals, the planning intervals are determined according to the actual operation success degree of the medical staff, the determination is not limited explicitly, each planning interval corresponds to a planning score, after the planning score of each puncture path is determined, the planning scores are arranged according to the order from large to small, and accordingly, the arrangement results also correspond to the execution priority of each puncture path, so as to provide a good preoperative plan for the medical staff.
The invention also provides a lung nodule puncture path planning system based on the medical image, which is applied to the lung nodule puncture path planning method based on the medical image, and comprises the following steps:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a target area and image information of the target area, and the image information of the target area comprises a target first feature and a target second feature;
the evaluation module is used for inputting the first features into the evaluation model, obtaining the image distribution area of the first features, and calibrating the corresponding areas as areas to be sampled;
the second acquisition module is used for acquiring the puncture area and the image information between the puncture area and the area to be sampled and calibrating the puncture area and the area to be sampled as an interference image;
the first construction module is used for setting a plurality of sampling nodes in the area to be sampled, and constructing a plurality of virtual puncture channels to the puncture area by taking the sampling nodes as starting nodes;
the second construction module is used for constructing a virtual coordinate system according to the interference image, the area to be sampled and the puncture area, determining a node where the virtual puncture channel intersects with the puncture area as an initial coordinate, and calibrating the node where the virtual puncture channel intersects with the area to be sampled as a target coordinate;
the judging module is used for acquiring interference features from the interference image, calibrating the edge coordinates of the interference features as interference coordinates, and judging whether the virtual puncture channel passes through the interference coordinates or not;
if yes, screening out the virtual puncture channel;
if not, calibrating the virtual puncture channel as a channel to be evaluated, and summarizing the channel to be evaluated into a data set to be evaluated;
the classification module is used for inputting the channel to be evaluated into the classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths;
the planning module is used for inputting the puncture paths into the planning model, obtaining the planning score of each puncture path, and determining the execution priority of each puncture path according to the planning score.
When the planning system is executed, the first acquisition module is used for acquiring the image information of the target area, the image information comprises a first feature and a second feature, the first feature is a lung nodule area, the second feature is a normal area, the evaluation module is used for calculating the image distribution area of the first feature and synchronously determining the area to be sampled, the second acquisition module is used for acquiring the puncture area and acquiring the image information between the puncture area and the area to be sampled, the first acquisition module is used for calibrating the puncture area to be an interference image, the first construction module is used for setting a plurality of sampling nodes in the area to be sampled, the sampling nodes are used as initial nodes, a plurality of virtual puncture channels are constructed to the puncture area, the second construction module is used for determining the initial coordinates and the target coordinates of the virtual puncture channels, meanwhile, the interference coordinates of the interference image can be determined, the judgment module is used for comparing the interference coordinates with the passing points of the virtual puncture channels, so that the virtual puncture channels can be screened, a plurality of channels to be evaluated can be obtained, the second screening of the channels to be processed by the evaluation module can be finally executed, the puncture channels to be processed by the sampling channels can be accurately screened, the first construction module is used for determining the puncture paths to be planned by the planning system, the planned puncture paths, the puncture paths can be provided by the planned puncture paths, the planned puncture paths can be accurately arranged according to the success rates, and the success rates can be determined by the planned puncture paths are provided by the success rates are arranged, and the success rates are calculated by the planned puncture paths are calculated, and the success rates can be planned by the puncture paths can be planned and have the success rates.
And, a lung nodule puncture path planning terminal based on medical images, comprising:
at least one processor;
and a memory communicatively coupled to the at least one processor;
the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the lung nodule penetration path planning method based on medical images.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention. Structures, devices and methods of operation not specifically described and illustrated herein, unless otherwise indicated and limited, are implemented according to conventional means in the art.
Claims (10)
1. A lung nodule puncture path planning method based on medical images is characterized in that: comprising the following steps:
acquiring a target area and image information of the target area, wherein the image information of the target area comprises a first feature and a second feature;
inputting the first features into an evaluation model to obtain image distribution areas of the first features, and calibrating corresponding areas as areas to be sampled;
acquiring a puncture area and image information between the puncture area and an area to be sampled, and calibrating the puncture area and the area to be sampled as an interference image;
setting a plurality of sampling nodes in the region to be sampled, and constructing a plurality of virtual puncture channels to the puncture region by taking the sampling nodes as starting nodes;
constructing a virtual coordinate system according to the interference image, the area to be sampled and the puncture area, determining a node where the virtual puncture channel intersects with the puncture area as a starting coordinate, and calibrating the node where the virtual puncture channel intersects with the area to be sampled as a target coordinate;
acquiring interference features and edge coordinates of the interference features from the interference images, calibrating the interference features as interference coordinates, and judging whether the virtual puncture channel passes through the interference coordinates or not;
if yes, screening out the virtual puncture channel;
if not, calibrating the virtual puncture channel as a channel to be evaluated, and summarizing the channel to be evaluated into a data set to be evaluated;
inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths;
inputting the puncture paths into a planning model, obtaining a planning score of each puncture path, and determining the execution priority of each puncture path according to the planning score.
2. The lung nodule puncture path planning method based on medical images of claim 1, wherein: the step of inputting the first feature into an evaluation model to obtain an image distribution area of the first feature includes:
acquiring edge inflection point coordinates of the first feature, and calibrating the coordinates as reference parameters;
invoking an evaluation function from the evaluation model;
and inputting the reference parameters into an evaluation function, and calibrating the output result as the image distribution area of the first feature.
3. The lung nodule puncture path planning method based on medical images of claim 1, wherein: after the image distribution area of the first feature is determined, the image distribution area of the first feature is input into an evaluation model, and the evaluation process is as follows:
acquiring an image distribution area of the first feature, and calibrating the image distribution area as a parameter to be evaluated;
acquiring evaluation intervals from the evaluation model, wherein a plurality of evaluation intervals are arranged, and each evaluation interval corresponds to one evaluation score;
and comparing the parameter to be evaluated with an evaluation interval to obtain an evaluation score of the parameter to be evaluated, and determining the benign and malignant degree of the lung nodule in the area to be sampled according to the evaluation score of the parameter to be evaluated.
4. The lung nodule puncture path planning method based on medical images of claim 1, wherein: the step of setting a plurality of sampling nodes in the area to be sampled comprises the following steps:
acquiring an edge inflection point of the region to be sampled, and connecting adjacent edge inflection points to obtain an edge curve of the region to be sampled;
acquiring the diameter of the puncture needle and calibrating the diameter as an offset parameter;
inwardly shifting the edge curve of the area to be sampled according to the shifting parameter to obtain the edge curve of the sampling area;
obtaining a standard function, and inputting the coordinates of the inflection points of the edges of the sampling area into the standard function to obtain the central coordinates of the sampling area;
and shifting the central coordinate of the sampling area according to the shifting parameter, and determining the shifting result as a sampling node.
5. The method for planning a lung nodule puncture path based on medical images according to claim 4, wherein: the step of constructing a plurality of virtual puncture channels to the puncture area by taking the sampling node as an initial node comprises the following steps:
acquiring a puncture area and constructing a plurality of puncture points in the puncture area;
connecting all the sampling nodes with a plurality of puncture points respectively to obtain a plurality of virtual paths;
and offsetting the virtual path according to the offset parameter, and calibrating an offset result as a virtual puncture channel.
6. The lung nodule puncture path planning method based on medical images of claim 1, wherein: after the virtual puncture channels are determined, puncture angles of all the virtual puncture channels are obtained and calibrated as parameters to be verified;
acquiring a checking interval and comparing the checking interval with the parameter to be checked;
if the parameter to be checked is in the check interval, reserving the virtual puncture channel;
if the parameter to be checked is not in the check interval, the virtual puncture channel is marked as a non-executable puncture channel, and the virtual puncture channel is synchronously screened out.
7. The lung nodule puncture path planning method based on medical images of claim 1, wherein: inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with repeated target coordinates to obtain a plurality of puncture paths, wherein the method comprises the following steps:
obtaining all the channels to be evaluated with consistent target coordinates, and calibrating the channels to be evaluated as parameters to be classified;
obtaining the shortest distance between the channel to be evaluated with the consistent target coordinates and the interference coordinates, and calibrating the shortest distance as a parameter to be classified;
obtaining a classification threshold value from the classification model and comparing the classification threshold value with the parameters to be classified;
if the parameters to be classified are smaller than the classification threshold, screening out the corresponding channels to be evaluated;
and if the parameter to be classified is greater than or equal to the classification threshold, determining the corresponding channel to be evaluated as a puncture path.
8. The lung nodule puncture path planning method based on medical images of claim 1, wherein: the step of inputting the puncture paths into a planning model to obtain a planning score of each puncture path comprises the following steps:
acquiring a puncture path and corresponding parameters to be classified;
calling a planning interval from the planning model;
comparing the parameters to be classified with the planning interval to obtain a planning score;
arranging the puncture paths according to the values of the planning scores from large to small to obtain the execution priority of each puncture path;
the execution priority of the puncture path is consistent with the arrangement order of the corresponding planning score.
9. A lung nodule puncture path planning system based on medical images, applied to the lung nodule puncture path planning method based on medical images as claimed in any one of claims 1 to 8, characterized in that: comprising the following steps:
the device comprises a first acquisition module, a second acquisition module and a first processing module, wherein the first acquisition module is used for acquiring a target area and image information of the target area, and the image information of the target area comprises a target first feature and a target second feature;
the evaluation module is used for inputting the first feature into an evaluation model, obtaining the image distribution area of the first feature, and calibrating the corresponding area as an area to be sampled;
the second acquisition module is used for acquiring the puncture area and the image information between the puncture area and the area to be sampled and calibrating the puncture area and the area to be sampled as an interference image;
the first construction module is used for setting a plurality of sampling nodes in the area to be sampled, and constructing a plurality of virtual puncture channels to the puncture area by taking the sampling nodes as starting nodes;
the second construction module is used for constructing a virtual coordinate system according to the interference image, the region to be sampled and the puncture region, determining a node where the virtual puncture channel intersects with the puncture region as an initial coordinate, and calibrating the node where the virtual puncture channel intersects with the region to be sampled as a target coordinate;
the judging module is used for acquiring interference features from the interference images, calibrating the edge coordinates of the interference features as interference coordinates and judging whether the virtual puncture channel passes through the interference coordinates or not;
if yes, screening out the virtual puncture channel;
if not, calibrating the virtual puncture channel as a channel to be evaluated, and summarizing the channel to be evaluated into a data set to be evaluated;
the classification module is used for inputting the channel to be evaluated into a classification model, and screening the virtual puncture channels with the repeated target coordinates to obtain a plurality of puncture paths;
the planning module is used for inputting the puncture paths into a planning model, obtaining the planning score of each puncture path, and determining the execution priority of each puncture path according to the planning score.
10. Lung nodule puncture path planning terminal based on medical image, its characterized in that: comprising the following steps:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the medical image-based lung nodule penetration path planning method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311266649.3A CN117017486B (en) | 2023-09-28 | 2023-09-28 | Lung nodule puncture path planning method based on medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311266649.3A CN117017486B (en) | 2023-09-28 | 2023-09-28 | Lung nodule puncture path planning method based on medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117017486A CN117017486A (en) | 2023-11-10 |
| CN117017486B true CN117017486B (en) | 2024-03-29 |
Family
ID=88637663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311266649.3A Active CN117017486B (en) | 2023-09-28 | 2023-09-28 | Lung nodule puncture path planning method based on medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117017486B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107296645A (en) * | 2017-08-03 | 2017-10-27 | 东北大学 | Lung puncture operation optimum path planning method and lung puncture operation guiding system |
| JP2019107298A (en) * | 2017-12-19 | 2019-07-04 | 賢一郎 蓮見 | Puncture path setting device, puncture control amount setting device and puncture system |
| CN113100935A (en) * | 2021-04-13 | 2021-07-13 | 上海大学 | Preoperative puncture path planning method and training system for lung puncture operation |
| CN115590623A (en) * | 2022-12-15 | 2023-01-13 | 苏州国科康成医疗科技有限公司（Cn） | Puncture path planning method and system |
| CN116012452A (en) * | 2023-03-28 | 2023-04-25 | 天津舞影猫科技有限公司 | Puncture navigation system and method for positioning target object based on ultrasonic image |
| CN116712167A (en) * | 2023-06-13 | 2023-09-08 | 上海联影智能医疗科技有限公司 | Navigation method and system for pulmonary nodule operation |
| CN116778138A (en) * | 2023-06-27 | 2023-09-19 | 中国人民解放军陆军军医大学第二附属医院 | Pulmonary nodule positioning system |
-
2023
- 2023-09-28 CN CN202311266649.3A patent/CN117017486B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107296645A (en) * | 2017-08-03 | 2017-10-27 | 东北大学 | Lung puncture operation optimum path planning method and lung puncture operation guiding system |
| JP2019107298A (en) * | 2017-12-19 | 2019-07-04 | 賢一郎 蓮見 | Puncture path setting device, puncture control amount setting device and puncture system |
| CN113100935A (en) * | 2021-04-13 | 2021-07-13 | 上海大学 | Preoperative puncture path planning method and training system for lung puncture operation |
| CN115590623A (en) * | 2022-12-15 | 2023-01-13 | 苏州国科康成医疗科技有限公司（Cn） | Puncture path planning method and system |
| CN116012452A (en) * | 2023-03-28 | 2023-04-25 | 天津舞影猫科技有限公司 | Puncture navigation system and method for positioning target object based on ultrasonic image |
| CN116712167A (en) * | 2023-06-13 | 2023-09-08 | 上海联影智能医疗科技有限公司 | Navigation method and system for pulmonary nodule operation |
| CN116778138A (en) * | 2023-06-27 | 2023-09-19 | 中国人民解放军陆军军医大学第二附属医院 | Pulmonary nodule positioning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117017486A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11931139B2 (en) | System and method for lung visualization using ultrasound | |
| US11864835B2 (en) | Puncture support device for determining safe linear puncture routes by puncture region classification and superimposing of images | |
| CN111161241B (en) | Liver image identification method, electronic equipment and storage medium | |
| US20220366562A1 (en) | Medical image analysis apparatus and method, and medical image visualization apparatus and method | |
| CN113610845A (en) | Tumor local control prediction model construction method, prediction method and electronic equipment | |
| CN111325759A (en) | Blood vessel segmentation method, device, computer equipment and readable storage medium | |
| CN113516623A (en) | Puncture path checking method and device, computer equipment and readable storage medium | |
| CN110473226B (en) | Training method of image processing network, computer device and readable storage medium | |
| EP3855396A2 (en) | Orientation detection in fluoroscopic images | |
| CN113662594B (en) | Mammary gland puncture positioning/biopsy method, device, computer equipment and storage medium | |
| CN114532965A (en) | Real-time lung cancer focus recognition system under thoracoscope | |
| CN114224471A (en) | Electrode needle distribution correction device and method, electronic device and storage medium | |
| CN107845106B (en) | Utilize the medical image registration method of improved NNDR strategy | |
| CN117017486B (en) | Lung nodule puncture path planning method based on medical image | |
| CN107392976A (en) | Data processing method, device and equipment | |
| KR20170128975A (en) | Vessel segmentation device and vessel segmentation method thereof | |
| CN109685796A (en) | Medical image processing method, device, equipment and storage medium | |
| CN113705807B (en) | Neural network training device and method, ablation needle arrangement planning device and method | |
| JP5491237B2 (en) | Medical image display device and medical image display method | |
| KR102322995B1 (en) | Method for artificial intelligence nodule segmentation based on dynamic window and apparatus thereof | |
| EP4318393A1 (en) | Surgical path processing system, method, apparatus and device, and storage medium | |
| CN108022234A (en) | Medical image-processing apparatus and medical image processing method | |
| CN114742979A (en) | Position identification method and device based on positioning patch, storage medium and equipment | |
| CN114201459A (en) | Improved radiotherapy structure standardized naming method and device and storage medium | |
| CN117064552A (en) | Auxiliary planning system for preoperative self-adaptive matching of tumor morphology |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |