CN111815644A - Method and device for extracting skin face data of patient in medical image - Google Patents
Method and device for extracting skin face data of patient in medical image Download PDFInfo
- Publication number
- CN111815644A CN111815644A CN202010437790.5A CN202010437790A CN111815644A CN 111815644 A CN111815644 A CN 111815644A CN 202010437790 A CN202010437790 A CN 202010437790A CN 111815644 A CN111815644 A CN 111815644A
- Authority
- CN
- China
- Prior art keywords
- skin
- facial
- patient
- medical image
- template
- 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
Images
Classifications
-
- 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
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Abstract
The method and the device for extracting the skin face data of the patient in the medical image can automatically extract the skin face data of the patient in the medical image, greatly save time consumed by a doctor in a cutting process, and provide an accurate registration area for a point marking and fetching process. The method comprises the following steps: (1) reconstructing skin data of a patient by using a medical image three-dimensional reconstruction method through CT/MR images; (2) registering the facial T-shaped template to the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and calculating coordinate transformation from the facial T-shaped template to the facial skin of the patient so that the registered template is basically superposed with the eyebrow bone and the nose tip of the reconstructed skin; (3) extracting an approximate corresponding region on the skin of the face of the patient through the distance mapping from the T-shaped template of the face to the skin; (4) and trimming the approximately corresponding area to obtain accurate face data.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a method for extracting skin facial data of a patient in a medical image, and further relates to a device for extracting skin facial data of the patient in the medical image, which is mainly suitable for the field of image-guided surgery navigation.
Background
An image-guided surgery navigation system provides important navigation information such as relative position relation of surgical instruments and focus areas for doctors based on medical images such as Computed Tomography (CT) images and Magnetic Resonance Images (MRI) and augmented reality and tracking registration technologies, and assists the doctors in efficiently and safely completing surgery. The operation navigation can help a doctor to position the surgical instrument in the operation process, and the corresponding position of the surgical instrument in the CT/MR image of the patient is obtained in real time, so that the operation safety is ensured.
In head and neck surgical navigation, a doctor uses a probe scribing point registration method to scribe point clouds required for registration in a T-shaped region of the face of a patient from an eyebrow to a nose tip, and performs point cloud registration with the point clouds of the skin of the face of the patient extracted from a medical image. The consistency of the facial skin point cloud and the extracted point cloud is a key influencing the registration accuracy of a navigation system, and the extracted facial data range is too large, too small or misplaced, which can cause the extracted point to be registered incorrectly. Although manual cutting of the skin point cloud can control the accuracy of the facial data range, the required cutting time is too long, the time of a doctor is greatly occupied, and the normal surgical operation of the doctor is influenced.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the method for extracting the skin face data of the patient in the medical image, which can realize the automatic extraction of the skin face data of the patient in the medical image, greatly save the time consumed by a doctor in the cutting process and provide an accurate registration area for the point marking process.
The technical scheme of the invention is as follows: the method for extracting the facial data of the skin of the patient in the medical image comprises the following steps:
(1) reconstructing skin data of a patient by using a medical image three-dimensional reconstruction method through CT/MR images;
(2) registering the facial T-shaped template to the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and calculating coordinate transformation from the facial T-shaped template to the facial skin of the patient so that the registered template is basically superposed with the eyebrow bone and the nose tip of the reconstructed skin;
(3) extracting an approximate corresponding region on the skin of the face of the patient through the distance mapping from the T-shaped template of the face to the skin;
(4) and trimming the approximately corresponding area to obtain accurate face data.
The invention reconstructs the skin data of the patient by using a medical image three-dimensional reconstruction method; calculating a coordinate transformation from the template to the facial skin of the patient based on a point cloud registration method and a pre-stored facial T-shaped template; extracting an approximate corresponding region on the facial skin of the patient through the distance mapping from the template to the skin; trimming the corresponding area to obtain accurate face data; therefore, the facial data of the skin of the patient in the medical image can be automatically extracted, the time consumed by a doctor in the cutting process is greatly saved, and an accurate registration area can be provided for the point marking process.
There is also provided an apparatus for extracting facial data of a skin of a patient in a medical image, comprising:
a reconstruction module configured to reconstruct skin data of a patient using a medical image three-dimensional reconstruction method through a CT/MR image;
a registration module configured to register the facial T-shaped template onto the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and to calculate a coordinate transformation from the facial T-shaped template to the facial skin of the patient such that the registered template substantially coincides with the brow bone and the nose tip of the reconstructed skin;
an extraction module configured to extract a substantially corresponding region on the skin of the face of the patient by distance mapping of the facial T-shaped template to the skin;
a cropping module configured to crop the substantially corresponding region to obtain accurate facial data.
Drawings
Fig. 1 is a flowchart of a method for extracting facial data of a patient's skin in a medical image according to the present invention.
FIG. 2 is a schematic diagram of a facial T-shaped template according to the present invention.
Fig. 3 is a schematic view of the registration region of the template map according to the present invention.
Detailed Description
As shown in fig. 1, the method for extracting facial data of skin of a patient in a medical image includes the following steps:
(1) reconstructing skin data of a patient by using a medical image three-dimensional reconstruction method through CT/MR images;
(2) registering the facial T-shaped template to the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and calculating coordinate transformation from the facial T-shaped template to the facial skin of the patient so that the registered template is basically superposed with the eyebrow bone and the nose tip of the reconstructed skin;
(3) extracting an approximate corresponding region on the skin of the face of the patient through the distance mapping from the T-shaped template of the face to the skin;
(4) and trimming the approximately corresponding area to obtain accurate face data.
The invention reconstructs the skin data of the patient by using a medical image three-dimensional reconstruction method; calculating a coordinate transformation from the template to the facial skin of the patient based on a point cloud registration method and a pre-stored facial T-shaped template; extracting an approximate corresponding region on the facial skin of the patient through the distance mapping from the template to the skin; trimming the corresponding area to obtain accurate face data; therefore, the facial data of the skin of the patient in the medical image can be automatically extracted, the time consumed by a doctor in the cutting process is greatly saved, and an accurate registration area can be provided for the point marking process.
Preferably, in the step (1), the medical image three-dimensional reconstruction method is a moving cube algorithm, an average value of pixels of air and skin is given as a pixel threshold, each pixel cube with the size of 2 × 2 of the image is traversed, whether pixel values of each adjacent vertex of the cube are distributed on two sides of the threshold is judged, if yes, an isosurface corresponding to the threshold in the cube is estimated through a linear interpolation method, a skin surface is generated by connecting the isosurfaces in each cube, a reconstruction result is stored in a three-dimensional grid structure form, and a preview effect is displayed in a window.
Preferably, in the step (2), a pre-stored T-shaped facial template is cut from the average human face model, and includes a region from the eyebrow to the tip of the nose.
Preferably, in the step (3), each point of the face T-shaped template is used as a center to generate a spherical area with a radius of d mm, and a union of all spheres is taken as a neighborhood of the template; and traversing each point in the skin point cloud, judging whether the points are in the neighborhood, and only keeping all the points in the neighborhood to obtain a mapping area of the skin in the close range d mm of the facial T-shaped template.
Preferably, in the step (4), the area is expanded by d mm outwards relative to the original template, and a trimming operation is required to be performed: and extracting the boundary of the mapping area, and corroding d mm inwards by taking the boundary as a starting point to obtain the trimmed mapping area.
It will be understood by those skilled in the art that all or part of the steps in the method of the above embodiments may be implemented by hardware instructions related to a program, the program may be stored in a computer-readable storage medium, and when executed, the program includes the steps of the method of the above embodiments, and the storage medium may be: ROM/RAM, magnetic disks, optical disks, memory cards, and the like. Therefore, corresponding to the method of the present invention, the present invention also includes an apparatus for extracting facial data of a patient's skin in a medical image, which is generally represented in the form of functional modules corresponding to the steps of the method. The device includes:
a reconstruction module configured to reconstruct skin data of a patient using a medical image three-dimensional reconstruction method through a CT/MR image;
a registration module configured to register the facial T-shaped template onto the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and to calculate a coordinate transformation from the facial T-shaped template to the facial skin of the patient such that the registered template substantially coincides with the brow bone and the nose tip of the reconstructed skin;
an extraction module configured to extract a substantially corresponding region on the skin of the face of the patient by distance mapping of the facial T-shaped template to the skin;
a cropping module configured to crop the substantially corresponding region to obtain accurate facial data.
Preferably, in the reconstruction module, the medical image three-dimensional reconstruction method is a moving cube algorithm, the reconstruction result is stored in a three-dimensional grid structure form, and a preview effect is displayed in a window.
Preferably, in the registration module, a pre-stored facial T-shaped template is cut from the human face average model, and includes an area from the eyebrow to the tip of the nose.
Preferably, in the extraction module, each point of the face T-shaped template is used as a center to generate a spherical area with a radius of d mm, and a union of all spheres is taken as a neighborhood of the template; and (4) clipping the reconstructed skin point cloud by using the neighborhood to obtain a mapping area of the skin in a close distance d mm near the facial T-shaped template.
Preferably, in the trimming module, the area is expanded by d mm outwards relative to the original template, and the trimming operation is required to be carried out: and extracting the boundary of the mapping area, and corroding d mm inwards by taking the boundary as a starting point to obtain the trimmed mapping area.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent variations and modifications made to the above embodiment according to the technical spirit of the present invention still belong to the protection scope of the technical solution of the present invention.
Claims (10)
1. A method for extracting facial data of a patient's skin in a medical image is characterized in that: which comprises the following steps:
(1) reconstructing skin data of a patient by using a medical image three-dimensional reconstruction method through CT/MR images;
(2) registering the facial T-shaped template to the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and calculating coordinate transformation from the facial T-shaped template to the facial skin of the patient so that the registered template is basically superposed with the eyebrow bone and the nose tip of the reconstructed skin;
(3) extracting an approximate corresponding region on the skin of the face of the patient through the distance mapping from the T-shaped template of the face to the skin;
(4) and trimming the approximately corresponding area to obtain accurate face data.
2. The method for extracting facial data of skin of a patient in a medical image as claimed in claim 1, wherein: in the step (1), the medical image three-dimensional reconstruction method is a moving cube algorithm, the reconstruction result is stored in a three-dimensional grid structure form, and a preview effect is displayed in a window.
3. The method of claim 2, wherein the facial data of the skin of the patient in the medical image is extracted by: in the step (2), the pre-stored face T-shaped template is obtained by cutting the face average model and comprises an area from the eyebrow to the nose tip.
4. The method of claim 3, wherein the facial data of the skin of the patient in the medical image is extracted by: in the step (3), each point of the face T-shaped template is taken as a center, a spherical area with the radius of d mm is generated, and a union of all spheres is taken as a neighborhood of the template; and (4) clipping the reconstructed skin point cloud by using the neighborhood to obtain a mapping area of the skin in a close distance d mm near the facial T-shaped template.
5. The method of claim 4, wherein the facial data of the skin of the patient in the medical image is extracted by: in the step (4), the area is expanded by d mm outwards relative to the original template, and the trimming operation is required to be carried out: and extracting the boundary of the mapping area, and corroding d mm inwards by taking the boundary as a starting point to obtain the trimmed mapping area.
6. An extraction device of the facial data of the skin of a patient in a medical image is characterized in that: it includes:
a reconstruction module configured to reconstruct skin data of a patient using a medical image three-dimensional reconstruction method through a CT/MR image;
a registration module configured to register the facial T-shaped template onto the three-dimensional reconstructed skin by a point cloud registration method based on a pre-stored facial T-shaped template, and to calculate a coordinate transformation from the facial T-shaped template to the facial skin of the patient such that the registered template substantially coincides with the brow bone and the nose tip of the reconstructed skin;
an extraction module configured to extract a substantially corresponding region on the skin of the face of the patient by distance mapping of the facial T-shaped template to the skin;
a cropping module configured to crop the substantially corresponding region to obtain accurate facial data.
7. The apparatus for extracting facial data of skin of a patient in medical image as claimed in claim 6, wherein: in the reconstruction module, the medical image three-dimensional reconstruction method is a moving cube algorithm, the reconstruction result is stored in a three-dimensional grid structure form, and a preview effect is displayed in a window.
8. The apparatus for extracting facial data of skin of a patient in medical image as claimed in claim 7, wherein: in the registration module, a pre-stored facial T-shaped template is obtained by cutting a human face average model and comprises an area from an eyebrow to a nose tip.
9. The apparatus for extracting facial data of skin of a patient in medical image as claimed in claim 8, wherein: in the extraction module, each point of a T-shaped facial template is taken as a center to generate a spherical area with the radius of d mm, and the union of all spheres is taken as a neighborhood of the template; and (4) clipping the reconstructed skin point cloud by using the neighborhood to obtain a mapping area of the skin in a close distance d mm near the facial T-shaped template.
10. The apparatus for extracting facial data of skin of a patient in medical image as claimed in claim 9, wherein: in the trimming module, the area is expanded by d mm outwards relative to the original template, and trimming operation is required to be carried out: and extracting the boundary of the mapping area, and corroding d mm inwards by taking the boundary as a starting point to obtain the trimmed mapping area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010437790.5A CN111815644A (en) | 2020-05-21 | 2020-05-21 | Method and device for extracting skin face data of patient in medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010437790.5A CN111815644A (en) | 2020-05-21 | 2020-05-21 | Method and device for extracting skin face data of patient in medical image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111815644A true CN111815644A (en) | 2020-10-23 |
Family
ID=72848118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010437790.5A Pending CN111815644A (en) | 2020-05-21 | 2020-05-21 | Method and device for extracting skin face data of patient in medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815644A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110054300A1 (en) * | 2006-02-09 | 2011-03-03 | National University Corporation Hamamatsu University School Of Medicine | Surgery support device, surgery support method, and computer readable recording medium storing surgery support program |
| CN103544711A (en) * | 2013-11-08 | 2014-01-29 | 国家测绘地理信息局卫星测绘应用中心 | Automatic registering method of remote-sensing image |
| CN105761236A (en) * | 2015-11-16 | 2016-07-13 | 乐视致新电子科技（天津）有限公司 | Image preprocessing method and apparatus for image registering |
| CN106447780A (en) * | 2015-08-06 | 2017-02-22 | 柯惠有限合伙公司 | System and method for local three dimensional volume reconstruction using a standard fluoroscope |
| CN108932495A (en) * | 2018-07-02 | 2018-12-04 | 大连理工大学 | A kind of automobile front face parameterized model automatic Generation |
| CN109166177A (en) * | 2018-08-27 | 2019-01-08 | 清华大学 | Air navigation aid in a kind of art of craniomaxillofacial surgery |
| CN109464196A (en) * | 2019-01-07 | 2019-03-15 | 北京和华瑞博科技有限公司 | Using the operation guiding system and registration signal acquisition method of structure light Image registration |
| CN110459301A (en) * | 2019-07-29 | 2019-11-15 | 清华大学 | Brain neuroblastoma surgical navigation method for registering based on thermodynamic chart and facial key point |
-
2020
- 2020-05-21 CN CN202010437790.5A patent/CN111815644A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110054300A1 (en) * | 2006-02-09 | 2011-03-03 | National University Corporation Hamamatsu University School Of Medicine | Surgery support device, surgery support method, and computer readable recording medium storing surgery support program |
| CN103544711A (en) * | 2013-11-08 | 2014-01-29 | 国家测绘地理信息局卫星测绘应用中心 | Automatic registering method of remote-sensing image |
| CN106447780A (en) * | 2015-08-06 | 2017-02-22 | 柯惠有限合伙公司 | System and method for local three dimensional volume reconstruction using a standard fluoroscope |
| CN105761236A (en) * | 2015-11-16 | 2016-07-13 | 乐视致新电子科技（天津）有限公司 | Image preprocessing method and apparatus for image registering |
| CN108932495A (en) * | 2018-07-02 | 2018-12-04 | 大连理工大学 | A kind of automobile front face parameterized model automatic Generation |
| CN109166177A (en) * | 2018-08-27 | 2019-01-08 | 清华大学 | Air navigation aid in a kind of art of craniomaxillofacial surgery |
| CN109464196A (en) * | 2019-01-07 | 2019-03-15 | 北京和华瑞博科技有限公司 | Using the operation guiding system and registration signal acquisition method of structure light Image registration |
| CN110459301A (en) * | 2019-07-29 | 2019-11-15 | 清华大学 | Brain neuroblastoma surgical navigation method for registering based on thermodynamic chart and facial key point |
Non-Patent Citations (2)
| Title |
|---|
| ZIELINSKI B A等: "Network-level structural covariance in the developing brain", 《PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES》, vol. 107, no. 42, pages 18191 - 18196 * |
| 刘小丹等: "中心扩散法局部区域纹理映射", 《计算机工程与设计》, vol. 31, no. 17, pages 3852 - 3855 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956635B (en) | Lung segment segmentation method, device, equipment and storage medium | |
| CN107067398B (en) | Completion method and device for missing blood vessels in three-dimensional medical model | |
| CN109767841B (en) | Similar model retrieval method and device based on craniomaxillofacial three-dimensional morphological database | |
| US20190046272A1 (en) | ENT Image Registration | |
| US20170340390A1 (en) | Computer-Assisted Osteocutaneous Free Flap Reconstruction | |
| CN108765483B (en) | Method and system for determining mid-sagittal plane from brain CT image | |
| KR20210051141A (en) | Method, apparatus and computer program for providing augmented reality based medical information of patient | |
| CN103251457A (en) | Head and facial marker semiautomatic calibration method for neurosurgical stereotactic surgery | |
| CN111462055B (en) | Skull detection method and device | |
| Shan et al. | Augmented reality based brain tumor 3D visualization | |
| CN113643790A (en) | Replacement modeling method and system for spine | |
| CN114903590B (en) | Morse microsurgery mark information processing method, morse microsurgery mark information processing system and storage medium | |
| CN114404039B (en) | Tissue drift correction method and device for three-dimensional model, electronic equipment and storage medium | |
| KR102433473B1 (en) | Method, apparatus and computer program for providing augmented reality based medical information of patient | |
| CN113469935B (en) | Automatic detection and positioning method for posterior superior iliac spine based on CT image | |
| CN113274130A (en) | Markless surgery registration method for optical surgery navigation system | |
| CN107993277B (en) | priori knowledge-based reconstruction method of artificial bone repair model of damaged part | |
| EP3292835B1 (en) | Ent image registration | |
| CN111728695B (en) | Light beam auxiliary positioning system for craniotomy | |
| KR102302483B1 (en) | Method for fine face registration for 3d surgical navigation system, recording medium and device for performing the method | |
| CN111815644A (en) | Method and device for extracting skin face data of patient in medical image | |
| CN115063607B (en) | Method, device and equipment for determining cutting contour and storage medium | |
| CN114463557B (en) | Contour marking method, device, equipment, storage medium and system | |
| CN111402277B (en) | Object outline segmentation method and device for medical image | |
| CN114283179A (en) | Real-time fracture far-near end space pose acquisition and registration system based on ultrasonic images |
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 |