CN113284082A - Intelligent planning method and device for hand bone fracture treatment nail channel - Google Patents
Intelligent planning method and device for hand bone fracture treatment nail channel Download PDFInfo
- Publication number
- CN113284082A CN113284082A CN202010099627.2A CN202010099627A CN113284082A CN 113284082 A CN113284082 A CN 113284082A CN 202010099627 A CN202010099627 A CN 202010099627A CN 113284082 A CN113284082 A CN 113284082A
- Authority
- CN
- China
- Prior art keywords
- channel
- target
- nail
- bone
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 208000010392 Bone Fractures Diseases 0.000 title claims abstract description 82
- 210000002411 hand bone Anatomy 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 33
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 105
- 230000003628 erosive effect Effects 0.000 claims abstract description 11
- 238000010586 diagram Methods 0.000 claims description 67
- 206010017076 Fracture Diseases 0.000 claims description 53
- 230000004927 fusion Effects 0.000 claims description 13
- 238000004040 coloring Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 10
- 210000004204 blood vessel Anatomy 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 description 8
- 238000002591 computed tomography Methods 0.000 description 8
- 229910000831 Steel Inorganic materials 0.000 description 7
- 239000010959 steel Substances 0.000 description 7
- 230000001427 coherent effect Effects 0.000 description 4
- 241001270131 Agaricus moelleri Species 0.000 description 2
- 208000028389 Nerve injury Diseases 0.000 description 2
- 230000035876 healing Effects 0.000 description 2
- 210000003041 ligament Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000008764 nerve damage Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 208000024248 Vascular System injury Diseases 0.000 description 1
- 208000012339 Vascular injury Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- A61B2034/101—Computer-aided simulation of surgical operations
- A61B2034/105—Modelling of the patient, e.g. for ligaments or bones
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/10116—X-ray 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30008—Bone
-
- 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
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Computational Linguistics (AREA)
- Heart & Thoracic Surgery (AREA)
- Radiology & Medical Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Robotics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Surgical Instruments (AREA)
Abstract
The present disclosure relates to an intelligent planning method and device for hand bone fracture treatment nail channel, which comprises the steps of obtaining a target image of a fractured hand bone; receiving a fractured bone region designated in the target image by a user; subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions; determining a strategy to-be-positioned nail channel through a preset channel according to the two island-shaped areas; and determining a target nail placing channel from the nail placing channels to be positioned. Therefore, by acquiring the target image of the fractured hand bone, determining the to-be-positioned nail channel through the preset channel strategy and determining the target nail placing channel from the to-be-positioned nail channel, the nail placing channel can be accurately determined on the premise of taking image data as a basis, the intelligent planning of the nail placing channel is realized, the reliability of the planning of the nail placing channel can be improved, the risk coefficient of manually determining the nail placing channel is reduced, and the excessive dependence on the experience of a doctor can be avoided.
Description
Technical Field
The present disclosure relates to medical technology, and in particular, to an intelligent planning method and device for a hand bone fracture treatment nail channel.
Background
The steel nail is used for fixing the fracture block after fracture, which is a common treatment means in modern medicine, and the fracture block can be prevented from shifting due to the traction of other muscle tissues or ligaments by fixing the fracture block through the steel nail, so that the fractured bone is ensured to be in the correct position and healed in the proper posture. However, if the position of the nail placing channel is determined incorrectly, the broken bone cannot be fixed completely, or the position is inaccurate, a certain influence may be caused to the fracture patient, for example, the broken bone heals at an improper position, which causes inconvenience in movement of the patient after healing, pain endured for a long time or more severely, unconsciousness of nerve injury part region, blood vessel injury, and the like. However, currently, the doctor usually plans the position of the nail placing channel by clinical experience, and manually specifies the nail placing channel according to the specific bone fracture condition, so that the accuracy of the determined nail placing channel completely depends on the experience of the doctor, the reliable data basis is lacked, the reliability is low, and the risk coefficient is higher for the position of the nail placing channel determined by the doctor with clinical experience which is not particularly rich.
Disclosure of Invention
The invention aims to provide an intelligent planning method and device for a nail placing channel for hand bone fracture treatment, which are used for solving the technical problems that the existing manual nail placing channel is completely determined by experience, lacks of data basis, and is low in reliability and high in risk.
In order to achieve the above object, a first aspect of the present disclosure provides a method for intelligently planning nail placement channels for fracture of hand bones, the method comprising:
acquiring a target image of a fractured hand bone;
receiving a fractured bone region designated in the target image by a user;
subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions;
determining a strategy to-be-positioned nail channel through a preset channel according to the two island-shaped regions;
and determining a target nail placing channel from the nail placing channels to be positioned.
Optionally, the preset channel determination policy includes one or more of the following policies:
acquiring a centroid connecting line of the two island-shaped areas, acquiring a target connecting line of the central position of a fractured hand bone and the surface of the bone, determining a first target included angle between the centroid connecting line and the target connecting line, and taking an area, in the fractured bone area, of which the first target included angle is smaller than or equal to a first preset angle threshold value as the to-be-positioned nail channel;
generating a fracture line according to the mass centers of the two island-shaped regions by a preset fracture line generation algorithm, acquiring a target connecting line between the center position of a fractured hand bone and the surface of the bone, determining a second target included angle between the fracture line and the target connecting line, and taking a region, in the fractured bone region, of which the second target included angle is smaller than or equal to a second preset angle threshold value as a to-be-positioned nail channel;
and taking the region except the bone blood vessel in the fractured bone region as the to-be-positioned nail channel.
Optionally, in a case that the channel determination strategy includes one strategy, the determining a target staple placement channel from the staple to be placed channels includes: and taking the nail placing channel to be positioned as the target nail placing channel.
Optionally, in a case that the channel determination strategy includes a plurality of strategies, the determining a target staple placement channel from the staple to be placed channel includes:
coloring and marking the region outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy to obtain a fractured bone image with color marks;
acquiring a Movield projection image corresponding to each broken bone image;
acquiring a weight coefficient corresponding to each nail channel to be positioned;
and fusing the Movield projection diagrams corresponding to the strategies according to the weight coefficient to obtain a fused projection diagram, and determining a target nail placing channel from the fused projection diagram.
Optionally, the obtaining a weight coefficient corresponding to each to-be-positioned nail channel includes:
and taking the Movier projection diagrams under a plurality of strategies as the input of a pre-trained target neural network model, and calculating to obtain the weight coefficient.
Optionally, the fusing the morveland projection diagrams corresponding to the multiple strategies according to the weight coefficient to obtain a fused projection diagram, and determining the target nail placement channel from the fused projection diagram includes:
acquiring a color value corresponding to each pixel in the Movield projection diagram under each strategy;
weighting the color values at the same position in a plurality of different Movield projection diagrams according to the weight coefficient to obtain a target color value at each position;
obtaining the fusion projection drawing according to the target color numerical value at each position;
and determining the region of the fusion projection image in which the target color numerical value is in a preset range as the target nail placing channel.
In a second aspect of the present disclosure, there is provided an intelligent planning device for nail passage for fracture treatment of hand bones, the device comprising:
the acquisition module is used for acquiring a target image of the fractured hand bone;
the receiving module is used for receiving a fractured bone region designated by a user in the target image;
a processing module for subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions;
the first determining module is used for determining a channel of the nail to be positioned according to the two island-shaped regions through a preset channel determining strategy;
and the second determination module is used for determining a target nail placing channel from the nail placing channels to be positioned.
Optionally, the preset channel determination policy includes one or more of the following policies:
acquiring a centroid connecting line of the two island-shaped areas, acquiring a target connecting line of the central position of a fractured hand bone and the surface of the bone, determining a first target included angle between the centroid connecting line and the target connecting line, and taking an area, in the fractured bone area, of which the first target included angle is smaller than or equal to a first preset angle threshold value as the to-be-positioned nail channel;
generating a fracture line according to the mass centers of the two island-shaped regions by a preset fracture line generation algorithm, acquiring a target connecting line between the center position of a fractured hand bone and the surface of the bone, determining a second target included angle between the fracture line and the target connecting line, and taking a region, in the fractured bone region, of which the second target included angle is smaller than or equal to a second preset angle threshold value as a to-be-positioned nail channel;
and taking the region except the bone blood vessel in the fractured bone region as the to-be-positioned nail channel.
Optionally, in a case that the channel determination policy includes one policy, the second determination module is configured to:
and taking the nail placing channel to be positioned as the target nail placing channel.
Optionally, in a case that the channel determination policy includes a plurality of policies, the second determination module includes:
the coloring submodule is used for coloring and marking the areas outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy so as to obtain a fractured bone image with color marks;
the first acquisition submodule is used for acquiring a Motveld projection diagram corresponding to each fractured bone image;
the second acquisition submodule is used for acquiring a weight coefficient corresponding to each nail channel to be positioned;
and the determining submodule is used for fusing the Movield projection diagrams corresponding to the strategies according to the weight coefficient to obtain a fused projection diagram, and determining a target nail placing channel from the fused projection diagram.
Optionally, the second obtaining sub-module is configured to:
and taking the Movier projection diagrams under a plurality of strategies as the input of a pre-trained target neural network model, and calculating to obtain the weight coefficient.
Optionally, the determining sub-module is configured to:
acquiring a color value corresponding to each pixel in the Movield projection diagram under each strategy;
weighting the color values at the same position in a plurality of different Movield projection diagrams according to the weight coefficient to obtain a target color value at each position;
obtaining the fusion projection drawing according to the target color numerical value at each position;
and determining the region of the fusion projection image in which the target color numerical value is in a preset range as the target nail placing channel.
According to the technical scheme, the target image of the fractured hand bone is obtained; receiving a fractured bone region designated in the target image by a user; subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions; determining a strategy to-be-positioned nail channel through a preset channel according to the two island-shaped regions; and determining a target nail placing channel from the nail placing channels to be positioned. Therefore, by acquiring the target image of the fractured hand bone, determining the to-be-positioned nail channel through the preset channel strategy and determining the target nail-placing channel from the to-be-positioned nail channel, the nail-placing channel can be accurately determined on the premise of taking image data as a basis, the intelligent planning of the nail-placing channel is realized, the planning reliability of the nail-placing channel can be improved, and the risk coefficient of manually determining the nail-placing channel is reduced.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a flow chart illustrating a method for intelligently planning a hand bone fracture treatment nail channel according to an exemplary embodiment of the present disclosure;
FIG. 2 is a schematic view of a fracture line on a fracture analysis surface shown in an exemplary embodiment of the present disclosure;
FIG. 3 is a flow chart of a method for intelligently planning a nail passage for treating a fracture of a hand bone according to the embodiment shown in FIG. 1;
fig. 4 is a block diagram of an intelligent planning device for a hand bone fracture treatment nail channel according to an exemplary embodiment of the present disclosure;
fig. 5 is a block diagram of an intelligent planning device for a hand bone fracture treatment nail channel according to the embodiment shown in fig. 4.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
Before describing the specific embodiments of the present disclosure, a brief description will be given of a specific application scenario of the present disclosure, and the present disclosure can be applied to a medical clinical procedure requiring the placement of a steel nail at a fractured bone of a fractured patient. The steel nail is used for fixing the fracture block, so that the fracture block can be prevented from being displaced due to the traction of other muscle tissues or ligaments, and the fractured bone is ensured to be in the correct position and healed in the proper posture. The position of the nail placing channel is determined to be particularly critical, the accurate nail placing channel position is very favorable for bone recovery of a patient, if the position of the nail placing channel is determined to be wrong or inaccurate, certain influence can be caused on a fracture patient, for example, fractured bones heal at improper positions, the patient is inconvenient to move after healing, the patient suffers from long time or severe pain, and nerve injury parts lose consciousness, vascular injury and the like in tolerance areas. In the prior art, a doctor plans the position of the nail placing channel, usually through clinical experience, and manually specifies the nail placing channel according to a specific bone fracture condition, so that the accuracy of the determined nail placing channel completely depends on the experience of the doctor, reliable data basis is lacked, the reliability is low, and the risk coefficient is higher for the position of the nail placing channel determined by the doctor with not particularly rich clinical experience.
In order to solve the technical problem, the present disclosure provides an intelligent planning method and device for a nail placing channel for hand bone fracture treatment, the method includes acquiring a target image of a fractured hand bone; receiving a fractured bone region designated in the target image by a user; subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions; determining a strategy to-be-positioned nail channel through a preset channel according to the two island-shaped areas; and determining a target nail placing channel from the nail placing channels to be positioned. Therefore, by acquiring the target image of the fractured hand bone, determining the to-be-positioned nail channel through the preset channel strategy and determining the target nail placing channel from the to-be-positioned nail channel, the nail placing channel can be accurately determined on the premise of taking image data as a basis, the intelligent planning of the nail placing channel is realized, the reliability of the planning of the nail placing channel can be improved, the risk coefficient of manually determining the nail placing channel is reduced, and the excessive dependence on the experience of a doctor can be avoided.
Fig. 1 is a flow chart illustrating a method for intelligently planning a hand bone fracture treatment nail channel according to an exemplary embodiment of the present disclosure; referring to fig. 1, the method may include the steps of:
The target image may be an X-ray film, a CT (Computed Tomography) film, or a nuclear magnetic resonance film.
For example, if a hand bone of a patient is fractured, a CT image of the hand bone of the patient may be obtained, and a specific fractured bone may be determined from the CT image of the hand bone.
One possible implementation manner in this step is: based on the GraphCut-3D algorithm, each independent bone can be separated in a manual/automatic segmentation mode.
For example, each coherent bone region in the target image is identified based on the GraphCut-3D algorithm, the target image is divided into a plurality of coherent bone regions, and for a fractured bone, if the connection area is greater than a preset area threshold, two fractures in the fractured bone may be segmented into one coherent bone region, in which case, the user may select the coherent bone region as the fractured bone region; if the consecutive area is smaller than or equal to the predetermined area for the fractured region, two fractured fragments of the fractured bone can be respectively divided into a consecutive bone region, in which case the user can select the two consecutive bone regions to be determined as the fractured bone region.
Wherein the expansion process is used for filling out the pits at the edge and the inner part of each fracture block in the fractured bone area. And (3) corrosion treatment for kicking off the edge burrs of each fracture block in the fractured bone area. Multiple erosions and expansions may be used to smooth the surface of each fracture in the fractured bone region.
In this step, after the image of the fractured bone region is subjected to expansion and erosion treatment, two fracture blocks connected by blood and flesh are completely separated, so that an island-shaped region is formed by the image corresponding to each fracture block, and finally two island-shaped regions are obtained.
And 104, determining a channel to be positioned according to the two island-shaped areas through a preset channel determination strategy.
Wherein the preset channel determination policy may include one or more of the following policies:
the first strategy is to obtain a centroid connecting line of the two island-shaped areas, obtain a target connecting line of the central position of the fractured hand bone and the surface of the bone, determine a first target included angle between the centroid connecting line and the target connecting line, and use an area, in the fractured bone area, of which the first target included angle is smaller than or equal to a first preset angle threshold value as the to-be-positioned nail channel.
It should be noted that the centroid connecting line is a connecting line between centroid positions of two island-shaped areas, coordinates of a position where each point is located in the island-shaped area in the target image are determined, and when the coordinate position of each point on an object is determined, a centroid position coordinate (X) can be obtained through the following centroid position calculation formulac,Yc,Zc)：
Wherein G represents the mass corresponding to each particle in the material system; x, Y, Z represent the coordinates of each particle, respectively.
In addition, it should be further noted that the first preset angle may be set to 5 degrees, and a region, in the fractured bone region, in which the first target included angle is greater than a first preset angle threshold is used as a non-to-be-positioned nail channel; the non-pending region may be subdivided into a forbidden region and an unknown propriety region. A third preset angle threshold value can be set, and the area of which the first target included angle is larger than the first preset angle threshold value and smaller than the second preset angle threshold value is determined as an unknown area; and determining the area of which the first target included angle is greater than the second preset angle threshold as a forbidden area, wherein the third preset angle threshold is greater than the first preset angle threshold.
And a second strategy is that a fracture line is generated according to the mass centers of the two island-shaped areas through a preset fracture line generation algorithm, a target connecting line between the center position of the fractured hand bone and the surface of the bone is obtained, a second target included angle between the fracture line and the target connecting line is determined, and an area, in the fractured bone area, of which the second target included angle is smaller than or equal to a second preset angle threshold value is used as the to-be-positioned nail channel.
Wherein the fracture line is a projection of a fracture section between two island-shaped areas on a fracture analysis surface. The fracture analysis surface is an image presented after cutting of the fractured bone region in the long axis direction (longitudinal direction). When determining the fracture line, the fracture analysis surface may be obtained (see fig. 2, fig. 2 is a schematic diagram of the fracture line on the fracture analysis surface shown in an exemplary embodiment of the present disclosure, which includes a first cut surface 201 of one island region on the fracture analysis surface, a second cut surface 202 of the other island region on the fracture analysis surface, and a fracture line 203), and then the positions of the centroids of the two island regions on the fracture analysis surface are determined, and the fracture line automatically calculated by a 2D graph-cut algorithm is determined according to the positions of the two centroids.
It should be noted that the second preset angle threshold may be the same as or different from the first preset angle threshold. Taking the area, in the fractured bone area, of which the second target included angle is larger than a second preset angle threshold value as a non-to-be-positioned nail channel; the non-pending region may be subdivided into a forbidden region and an unknown propriety region. A fourth preset angle threshold value can be set, and the area where the second target included angle is larger than the second preset angle threshold value and smaller than the fourth preset angle threshold value is determined as an unknown area; and determining the area of which the second target included angle is greater than the fourth preset angle threshold as a forbidden area, wherein the fourth preset angle threshold is greater than the second preset angle threshold.
And thirdly, taking the region except the bone blood vessel in the fractured bone region as the to-be-positioned nail channel.
It should be noted that the bone blood vessels and the corresponding image gray scales of other regions except the bone blood vessels on the CT image are different, so that the to-be-positioned nail channel can be determined according to the difference of the image gray scales.
And 105, determining a target nail placing channel from the nail placing channels to be positioned.
Wherein, in case the channel determination strategy comprises a strategy, the channel to be positioned can be taken as the target nail positioning channel. In the case where the channel determination strategy includes multiple strategies, a target staple placement channel may be determined from the staple-to-be-positioned channels by:
coloring and marking the region outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy to obtain a fractured bone image with color marks; acquiring a Motveld projection image corresponding to each broken bone image; acquiring a weight coefficient corresponding to each nail channel to be positioned; and fusing the Movield projection diagrams corresponding to the strategies according to the weight coefficient to obtain a fused projection diagram, and determining a target nail placing channel from the fused projection diagram.
It should be noted that the to-be-positioned nail channel determined by each strategy can be used as a target nail placement channel, but generally, in order to ensure that an optimal target nail placement channel is obtained, the nail placement channels obtained under each strategy can be integrated, so that the target nail placement channel with the minimum risk can be determined. The weight coefficient may be preset, or may be calculated by using the morveld projection plots under multiple strategies as an input of a pre-trained target neural network model. The target neural network model can be obtained by training in the following way:
acquiring a first Movide projection diagram, a second Movide projection diagram and a third Movide projection diagram corresponding to a plurality of target hand bones which are already planned by the hand bone fracture nail placing channel within historical time, and establishing a hand bone fracture nail placing channel planning data set; and performing machine learning on the hand bone fracture nail placing channel planning data set to obtain the target neural network model, wherein the target neural network model can be the first Movide projection diagram, the second Movide projection diagram and the second Movide projection diagram as inputs, the weight coefficient is an output, and the target neural network model is used for determining the proportion of the color value at each position in the Movide projection diagram determined under each strategy in the final color value corresponding to the corresponding position in the fusion projection diagram.
In the above training mode, the first morvede projection diagram may be a morvede projection diagram obtained by performing morvede projection equal-area projection on a first broken bone image, which is obtained by performing morvede projection equal-area projection on a first broken bone image, by performing color marking on the to-be-positioned target channel and a region other than the to-be-positioned nail channel obtained under the strategy after determining the to-be-positioned nail channel from the CT image of the target hand bone for which the hand bone fracture nail channel planning has been completed within the historical time. The second morveld projection graph can be a morveld projection graph obtained by performing morveld projection equal-area projection on the first fractured bone image, wherein the second morveld projection graph is obtained by performing morveld projection equal-area projection on a second fractured bone image with color marks after the CT image of the target hand bone for planning the hand bone fracture nail placing channel in the historical time determines the channel to be placed through the second strategy and then performing coloring marking on the channel to be placed and the region outside the channel to be placed, which is obtained under the second strategy. The third morveld projection diagram may be a morveld projection diagram obtained by performing morveld projection equal-area projection on a third fractured bone image, which is obtained by performing morveld projection equal-area projection on a region except the to-be-positioned nail channel and the to-be-positioned nail channel obtained under the third strategy after determining the to-be-positioned nail channel on the CT image of the target hand bone for which the hand bone fracture nail channel planning has been completed within the historical time through the third strategy.
According to the technical scheme, the target image of the fractured hand bone is obtained, the to-be-positioned nail channel is determined through the preset channel strategy, the target nail placing channel is determined from the to-be-positioned nail channel, the nail placing channel can be accurately determined on the premise of taking image data as a basis, the intelligent planning of the nail placing channel is realized, the planning reliability of the nail placing channel can be improved, and the risk coefficient of manually determining the nail placing channel is reduced.
FIG. 3 is a flow chart of a method for intelligently planning a nail passage for treating a fracture of a hand bone according to the embodiment shown in FIG. 1; in case the channel determination policy comprises a plurality of policies, this step 105 may be implemented by the following method illustrated in fig. 3, see fig. 3, this step 105 may comprise the following steps:
and 1051, coloring and marking the areas outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy to obtain a fractured bone image with color marks.
The to-be-positioned nail channel and the area except the to-be-positioned nail channel can be respectively dyed with different colors, so that the to-be-positioned nail channel and other areas can be obviously distinguished.
Illustratively, if the area of the channel of the nail to be positioned obtained under each strategy is dyed with green, the forbidden area is dyed with red, and the unknown area is dyed with yellow, three images of the fractured bone with red, yellow and green marks are obtained.
Exemplarily, after the channel to be positioned, which is determined by the first strategy, is dyed with green, the area which is not known to be possible to be dyed with yellow is dyed, and the area which is forbidden to be dyed with red is dyed, the obtained first target fractured bone image is subjected to Movidet equal-area projection to obtain a first target Movidet projection diagram, and the green area on the first target Movidet projection diagram is the channel to be positioned. Similarly, a first target morvede projection diagram corresponding to the second strategy and a first target morvede projection diagram corresponding to the second strategy can be obtained.
And 1053, acquiring a weight coefficient corresponding to each nail channel to be set.
The weight coefficient is used to represent the weight of the color in the morvede projection diagram obtained under each strategy in the color of the final fusion projection diagram, and the weight coefficient may be a preset parameter or may be calculated by using the morvede projection diagrams under a plurality of strategies as the input of a pre-trained target neural network model.
Illustratively, the color value at the pixel a in the first morvedimensional projection graph obtained by the above strategy one is the hexadecimal data CD0000, the color value at the pixel a in the second morvedimensional projection graph obtained by the above strategy two is the hexadecimal data 9ACD32, and the color value at the pixel a in the third morvedimensional projection graph obtained by the above strategy three is the hexadecimal data EEE 00.
Illustratively, the weight coefficient occupied by the color value in the first morbidir projection diagram in the corresponding target color value in the fused projection diagram is 0.4, the weight coefficient occupied by the color value in the second morbidir projection diagram in the corresponding target color value in the fused projection diagram is 0.4, the weight coefficient occupied by the color value in the third morbidir projection diagram in the corresponding target color value in the fused projection diagram is 0.2, and the target color value is, again taking the pixel a as an example:
CD0000×0.4+9ACD32×0.4+EEE00×0.2。
One possible implementation manner in this step is: and displaying the corresponding target color value at each position, so that the fused projection drawing can be obtained.
The preset range can be determined according to the diameter of a standby steel nail, the standby steel nail is a device to be placed in the nail placing channel for fixing the fracture block, and the larger the diameter of the standby steel nail is, the more the preset range is.
According to the technical scheme, the color numerical values at the same position in a plurality of different Movield projection diagrams are weighted according to the weighting coefficient to obtain the target color numerical value at each position, the fusion projection diagram is obtained according to the target color numerical value at each position, the region, in the fusion projection diagram, of which the target color numerical value is in the preset range is determined as the target nail placing channel, the nail placing channel can be accurately determined on the premise of taking image data as a basis, the intelligent planning of the nail placing channel is realized, the reliability of the nail placing channel planning can be improved, and the risk coefficient for manually determining the nail placing channel is reduced.
Fig. 4 is a block diagram of an intelligent planning device for a hand bone fracture treatment nail channel according to an exemplary embodiment of the present disclosure; referring to fig. 4, the apparatus includes:
an obtaining module 401, configured to obtain a target image of a fractured hand bone;
a receiving module 402, configured to receive a fractured bone region specified in the target image by a user;
a processing module 403 for performing an expansion and erosion process on the fractured bone region to separate the fractured bone region into two island-shaped regions;
a first determining module 404, configured to determine, according to the two island-shaped regions, a channel to be positioned through a preset channel determination strategy;
and a second determining module 405, configured to determine a target staple placing channel from the staple placing channels to be placed.
According to the technical scheme, the target image of the fractured hand bone is obtained through the obtaining module 401, the to-be-positioned nail channel is determined through the first determining module 404 according to the preset channel strategy, the target nail-placing channel is determined from the to-be-positioned nail channel through the second determining module 405, the nail-placing channel can be accurately determined on the premise of taking image data as a basis, intelligent planning of the nail-placing channel is achieved, the planning reliability of the nail-placing channel can be improved, and the risk coefficient of manually determining the nail-placing channel is reduced.
Optionally, the preset channel determination policy includes one or more of the following policies:
acquiring a centroid connecting line of the two island-shaped areas, acquiring a target connecting line of the central position of the fractured hand bone and the surface of the bone, determining a first target included angle between the centroid connecting line and the target connecting line, and taking an area, in the fractured bone area, of which the first target included angle is smaller than or equal to a first preset angle threshold value as the to-be-positioned nail channel;
generating a fracture line according to the mass centers of the two island-shaped areas through a preset fracture line generation algorithm, acquiring a target connecting line between the center position of the fracture hand bone and the surface of the bone, determining a second target included angle between the fracture line and the target connecting line, and taking an area, in the fractured bone area, of which the second target included angle is smaller than or equal to a second preset angle threshold value as the to-be-positioned nail channel;
and taking the area except the bone blood vessel in the broken bone area as the to-be-positioned nail channel.
Optionally, in a case that the channel determination policy includes a policy, the second determination module 405 is configured to:
and taking the nail placing channel to be positioned as the target nail placing channel.
FIG. 5 is a block diagram of an intelligent planning device for a hand bone fracture treatment nail channel according to the embodiment shown in FIG. 4; referring to fig. 5, in the case where the channel determination policy includes a plurality of policies, the second determination module 405 includes:
the coloring submodule 4051 is used for coloring and marking the areas outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy so as to obtain a fractured bone image with color marks;
a first obtaining sub-module 4052, configured to obtain a morvegder projection map corresponding to each fractured bone image;
a second obtaining submodule 4053, configured to obtain a weight coefficient corresponding to each to-be-positioned nail channel;
the determining sub-module 4054 is configured to fuse the morvede projection diagrams corresponding to the multiple strategies according to the weight coefficient to obtain a fused projection diagram, and determine the target staple placing channel from the fused projection diagram.
Optionally, the second obtaining sub-module 4053 is configured to:
and taking the Movield projection diagrams under a plurality of strategies as the input of a pre-trained target neural network model, and calculating to obtain the weight coefficient.
Optionally, the determining sub-module 4054 is configured to:
acquiring a color value corresponding to each pixel in the Movield projection diagram under each strategy;
weighting the color values at the same position in a plurality of different Movield projection graphs according to the weight coefficient to obtain a target color value at each position;
obtaining the fusion projection image according to the target color value at each position;
and determining the region of the fused projection image with the target color value in a preset range as the target nail placing channel.
According to the technical scheme, the color numerical values at the same position in a plurality of different Movield projection drawings are subjected to weighting processing by the determining submodule according to the weighting coefficient to obtain the target color numerical value at each position, the fusion projection drawing is obtained according to the target color numerical value at each position, the area, in the fusion projection drawing, of which the target color numerical value is in the preset range is determined as the target nail placing channel, the nail placing channel can be accurately determined on the premise of taking image data as a basis, the intelligent planning of the nail placing channel is realized, the reliability of the nail placing channel planning can be improved, and the risk coefficient of manually determining the nail placing channel is reduced.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. An intelligent planning method for a hand bone fracture treatment nail channel is characterized by comprising the following steps:
acquiring a target image of a fractured hand bone;
receiving a fractured bone region designated in the target image by a user;
subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions;
determining a strategy to-be-positioned nail channel through a preset channel according to the two island-shaped regions;
and determining a target nail placing channel from the nail placing channels to be positioned.
2. The method of claim 1, wherein the preset channel determination policy comprises one or more of the following policies:
acquiring a centroid connecting line of the two island-shaped areas, acquiring a target connecting line of the central position of a fractured hand bone and the surface of the bone, determining a first target included angle between the centroid connecting line and the target connecting line, and taking an area, in the fractured bone area, of which the first target included angle is smaller than or equal to a first preset angle threshold value as the to-be-positioned nail channel;
generating a fracture line according to the mass centers of the two island-shaped regions by a preset fracture line generation algorithm, acquiring a target connecting line between the center position of a fractured hand bone and the surface of the bone, determining a second target included angle between the fracture line and the target connecting line, and taking a region, in the fractured bone region, of which the second target included angle is smaller than or equal to a second preset angle threshold value as a to-be-positioned nail channel;
and taking the region except the bone blood vessel in the fractured bone region as the to-be-positioned nail channel.
3. The method of claim 2, wherein in the event that the channel determination strategy comprises one strategy, said determining a target staple placement channel from the staple-to-be-positioned channels comprises: and taking the nail placing channel to be positioned as the target nail placing channel.
4. The method of claim 2, wherein, where the channel determination strategy comprises a plurality of strategies, the determining a target staple placement channel from the staple to be placed channel comprises:
coloring and marking the region outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy to obtain a fractured bone image with color marks;
acquiring a Movield projection image corresponding to each broken bone image;
acquiring a weight coefficient corresponding to each nail channel to be positioned;
and fusing the Movield projection diagrams corresponding to the strategies according to the weight coefficient to obtain a fused projection diagram, and determining a target nail placing channel from the fused projection diagram.
5. The method according to claim 4, wherein the obtaining a weight coefficient corresponding to each staple channel to be positioned comprises:
and taking the Movier projection diagrams under a plurality of strategies as the input of a pre-trained target neural network model, and calculating to obtain the weight coefficient.
6. The method according to claim 4, wherein the fusing the Movield projection graphs corresponding to the plurality of strategies according to the weight coefficients to obtain a fused projection graph, and determining the target nail placement channel from the fused projection graph comprises:
acquiring a color value corresponding to each pixel in the Movield projection diagram under each strategy;
weighting the color values at the same position in a plurality of different Movield projection diagrams according to the weight coefficient to obtain a target color value at each position;
obtaining the fusion projection drawing according to the target color numerical value at each position;
and determining the region of the fusion projection image in which the target color numerical value is in a preset range as the target nail placing channel.
7. An intelligent planning device for a hand bone fracture treatment nail channel, the device comprising:
the acquisition module is used for acquiring a target image of the fractured hand bone;
the receiving module is used for receiving a fractured bone region designated by a user in the target image;
a processing module for subjecting the fractured bone region to an expansion and erosion process to separate the fractured bone region into two island regions;
the first determining module is used for determining a channel of the nail to be positioned according to the two island-shaped regions through a preset channel determining strategy;
and the second determination module is used for determining a target nail placing channel from the nail placing channels to be positioned.
8. The apparatus of claim 7, wherein the predetermined channel determination policy comprises one or more of the following policies:
acquiring a centroid connecting line of the two island-shaped areas, acquiring a target connecting line of the central position of a fractured hand bone and the surface of the bone, determining a first target included angle between the centroid connecting line and the target connecting line, and taking an area, in the fractured bone area, of which the first target included angle is smaller than or equal to a first preset angle threshold value as the to-be-positioned nail channel;
generating a fracture line according to the mass centers of the two island-shaped regions by a preset fracture line generation algorithm, acquiring a target connecting line between the center position of a fractured hand bone and the surface of the bone, determining a second target included angle between the fracture line and the target connecting line, and taking a region, in the fractured bone region, of which the second target included angle is smaller than or equal to a second preset angle threshold value as a to-be-positioned nail channel;
and taking the region except the bone blood vessel in the fractured bone region as the to-be-positioned nail channel.
9. The apparatus of claim 8, wherein in the case that the channel determination policy comprises one policy, the second determination module is configured to:
and taking the nail placing channel to be positioned as the target nail placing channel.
10. The apparatus of claim 8, wherein in the case that the channel determination policy comprises a plurality of policies, the second determination module comprises:
the coloring submodule is used for coloring and marking the areas outside the to-be-positioned target channel and the to-be-positioned nail channel obtained under each strategy so as to obtain a fractured bone image with color marks;
the first acquisition submodule is used for acquiring a Motveld projection diagram corresponding to each fractured bone image;
the second acquisition submodule is used for acquiring a weight coefficient corresponding to each nail channel to be positioned;
and the determining submodule is used for fusing the Movield projection diagrams corresponding to the strategies according to the weight coefficient to obtain a fused projection diagram, and determining a target nail placing channel from the fused projection diagram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010099627.2A CN113284082A (en) | 2020-02-18 | 2020-02-18 | Intelligent planning method and device for hand bone fracture treatment nail channel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010099627.2A CN113284082A (en) | 2020-02-18 | 2020-02-18 | Intelligent planning method and device for hand bone fracture treatment nail channel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113284082A true CN113284082A (en) | 2021-08-20 |
Family
ID=77274865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010099627.2A Pending CN113284082A (en) | 2020-02-18 | 2020-02-18 | Intelligent planning method and device for hand bone fracture treatment nail channel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113284082A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150100067A1 (en) * | 2013-10-08 | 2015-04-09 | University Of Washington Through Its Center For Commercialization | Methods and systems for computer-guided placement of bone implants |
| CN107913101A (en) * | 2017-12-21 | 2018-04-17 | 成都真实维度科技有限公司 | Based on virtual image and the fracture of neck of femur surgical planning method and system for combining tantalum nail |
| CN108257118A (en) * | 2018-01-08 | 2018-07-06 | 浙江大学 | A kind of fracture adhesion dividing method based on normal direction corrosion and random walk |
| CN108852511A (en) * | 2018-04-26 | 2018-11-23 | 北京罗森博特科技有限公司 | The automatic planning and device of implant for into bones optimal location |
| CN110738681A (en) * | 2019-10-11 | 2020-01-31 | 北京航空航天大学 | automatic pedicle screw operation path planning method based on deep learning network |
-
2020
- 2020-02-18 CN CN202010099627.2A patent/CN113284082A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150100067A1 (en) * | 2013-10-08 | 2015-04-09 | University Of Washington Through Its Center For Commercialization | Methods and systems for computer-guided placement of bone implants |
| CN107913101A (en) * | 2017-12-21 | 2018-04-17 | 成都真实维度科技有限公司 | Based on virtual image and the fracture of neck of femur surgical planning method and system for combining tantalum nail |
| CN108257118A (en) * | 2018-01-08 | 2018-07-06 | 浙江大学 | A kind of fracture adhesion dividing method based on normal direction corrosion and random walk |
| CN108852511A (en) * | 2018-04-26 | 2018-11-23 | 北京罗森博特科技有限公司 | The automatic planning and device of implant for into bones optimal location |
| CN110738681A (en) * | 2019-10-11 | 2020-01-31 | 北京航空航天大学 | automatic pedicle screw operation path planning method based on deep learning network |
Non-Patent Citations (1)
| Title |
|---|
| GIOVANNI F. SOLITRO等: "Innovative approach in the development of computer assisted algorithm for spine pedicle screw placement", MEDICAL ENGINEERING AND PHYSICS, 31 December 2016 (2016-12-31), pages 354 - 365 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6178345B1 (en) | Method for detecting the exact contour of targeted treatment areas, in particular, the external contour | |
| US20220233159A1 (en) | Medical image processing method and device using machine learning | |
| US20230008386A1 (en) | Method for automatically planning a trajectory for a medical intervention | |
| US7340082B2 (en) | Method and medical imaging apparatus for determining a slice in an examination volume for data acquisition in the slice | |
| CN112263236B (en) | System and method for intelligent evaluation of whole-body tumor MRI | |
| JP2002159478A (en) | Method of detecting anatomical landmark automatically in radiographic image and program storage device read by device | |
| CN110946652B (en) | Method and device for planning screw path of bone screw | |
| CN109907827B (en) | Operation navigation system for mandibular angle osteotomy | |
| CN108367161A (en) | Radiotherapy system, data processing method and storage medium | |
| US9980783B2 (en) | Bone repositioning based on an automated assignment | |
| KR20200056105A (en) | Method and apparatus for calculating coronary artery calcium scoring | |
| US20230177681A1 (en) | Method for determining an ablation region based on deep learning | |
| CN113077499A (en) | Pelvis registration method, pelvis registration device and pelvis registration system | |
| CN113284082A (en) | Intelligent planning method and device for hand bone fracture treatment nail channel | |
| CN112053346A (en) | Method and system for determining operation guide information | |
| CN112991333B (en) | Image processing method and system based on voice analysis in endoscopic surgery | |
| US20230172535A1 (en) | Method for predicting the recurrence of a lesion by image analysis | |
| CN105678738B (en) | The localization method and its device of datum mark in medical image | |
| CN108852287A (en) | A method of the selection symmetrical region of interest of brain | |
| CN111227933B (en) | Prediction and real-time rendering system for mandibular angle osteotomy | |
| CN104200196B (en) | Guide pin position automatic identifying method in a kind of radioscopy image | |
| CN115607286B (en) | Knee joint replacement surgery navigation method, system and equipment based on binocular calibration | |
| US10806467B2 (en) | Method of locating center position and axial direction of distal locking hole of intramedullary nail | |
| Millan-Arias et al. | General Cephalometric Landmark Detection for Different Source of X-Ray Images | |
| CN110772278A (en) | Implant body postoperative verification method, device and terminal |
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 |