CN114187338A - Organ deformation registration method based on estimated 2d displacement field - Google Patents
Organ deformation registration method based on estimated 2d displacement field Download PDFInfo
- Publication number
- CN114187338A CN114187338A CN202111494423.XA CN202111494423A CN114187338A CN 114187338 A CN114187338 A CN 114187338A CN 202111494423 A CN202111494423 A CN 202111494423A CN 114187338 A CN114187338 A CN 114187338A
- Authority
- CN
- China
- Prior art keywords
- image
- contour
- ultrasonic
- organ
- displacement field
- 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.)
- Granted
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06T2207/10132—Ultrasound image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses an organ deformation registration method based on an estimated 2d displacement field, which comprises the following steps of: s1, acquiring a CT image and an ultrasonic image, acquiring a CT image organ outline from the CT image, and acquiring an ultrasonic image organ outline from the ultrasonic image; s2, calculating a common roi area between the organ contour of the CT image and the organ contour of the ultrasonic image; s3, searching ultrasonic contour points in the organ contour of the ultrasonic image and CT contour points in the organ contour of the CT image, searching the corresponding position of each ultrasonic contour point in the CT contour points by using the minimum gradient difference principle, and calculating the displacement vectors (u, v) of the ultrasonic contour points; s4, taking the displacement vectors (u, v) of the ultrasonic contour points as boundary conditions, and obtaining a displacement field of a public roi area by calculating an Euler-Lagrangian equation; and S5, applying the deformation quantity of the displacement field to the CT image through the displacement field of the common roi area to obtain a deformation registration image.
Description
Technical Field
The invention relates to the field of image registration, in particular to an organ deformation registration method based on an estimated 2d displacement field.
Background
When medical image analysis is performed, several images of the same patient are often put together for analysis, so that comprehensive information of the patient in various aspects is obtained, and the medical diagnosis and treatment level is improved. Quantitative analysis is performed on several different images, and the problem of strict alignment of the several images is firstly solved, which is called image registration. Medical image registration refers to seeking a (or a series of) spatial transformation for one medical image to bring it into spatial correspondence with a corresponding point on another medical image. This coincidence means that the same anatomical point on the body has the same spatial position on the two matching images. The result of the registration should be such that all anatomical points, or at least all points of diagnostic significance and points of surgical interest, on both images are matched.
Medical image registration techniques are an important branch of medical image processing that developed only in the 90 s. Medical image registration techniques primarily discuss registration after data acquisition, also referred to as retrospective registration. At present, the existing image registration method is complex in operation, the accuracy of the registered image is low, the observation operation of a doctor on the image is influenced, and the working efficiency of the doctor is seriously reduced.
Disclosure of Invention
The invention aims to solve the problems and provides an organ deformation registration method based on an estimated 2d displacement field, which is simple to operate and higher in registration accuracy.
In order to achieve the purpose, the technical scheme of the invention is as follows:
an organ deformation registration method based on an estimated 2d displacement field comprises the following steps:
s1, acquiring a CT image and an ultrasonic image, acquiring a CT image organ outline from the CT image, and acquiring an ultrasonic image organ outline from the ultrasonic image;
s2, calculating a common roi area between the organ contour of the CT image and the organ contour of the ultrasonic image;
s3, searching ultrasonic contour points in the organ contour of the ultrasonic image and CT contour points in the organ contour of the CT image, searching the corresponding position of each ultrasonic contour point in the CT contour points by using the minimum gradient difference principle, and calculating the displacement vectors (u, v) of the ultrasonic contour points;
s4, taking the displacement vectors (u, v) of the ultrasonic contour points as boundary conditions, and obtaining a displacement field of a public roi area by calculating an Euler-Lagrangian equation;
and S5, applying the deformation quantity of the displacement field to the CT image through the displacement field of the common roi area to obtain a deformation registration image.
Further, in step S1, the findcontours function of opencv is used to obtain peripheral ordered contour points of the segmentation mask, and the CT image organ contour and the ultrasound image organ contour are obtained from the CT image and the ultrasound image respectively through the peripheral ordered contour points.
Further, in step S2, a union mask of the CT image mask and the ultrasound image mask is first obtained, and then the minimum circumscribed rectangle of the union mask is calculated; the length and the width of the public roi are respectively 1.2 times of the length and the width of the minimum circumscribed rectangle of the union mask.
Further, the step S3 specifically includes the following steps:
s31, sampling the CT contour points to make the number of the CT contour points in the organ contour of the CT image consistent with the number of the ultrasound contour points in the organ contour of the ultrasound image;
s32, establishing a coordinate system, and placing the CT contour points and the ultrasonic contour points in the coordinate system to obtain the coordinates of the CT contour points and the ultrasonic contour points;
s33, respectively taking the CT contour point coordinates and the ultrasonic contour point coordinates as two groups of periodic sequences, and calculating the coordinate gradient difference between the corresponding CT contour point coordinates and the corresponding ultrasonic contour point coordinates;
and S34, determining a new starting position and ending position by utilizing the periodic property of the CT contour points, and enabling the square sum of the coordinate gradient differences of all the CT contour point coordinates and all the ultrasonic contour point coordinates to be minimum, thereby calculating the displacement vector (u, v) of each ultrasonic contour point relative to the CT contour point.
Further, in step S4, the calculation formula of the euler-lagrange equation is:
and solving to obtain:
uxx+uyy+vxx+vyy＝0；
finally, obtaining a displacement field of the public roi;
wherein u isxDenotes the first order partial derivative of u over x, uyDenotes the 1 st order partial derivative, v, of u vs yxDenotes the first order partial derivative of v versus x, vyDenotes the first order partial derivative of v versus y, uxxDenotes the second order partial derivative of u over x, uyyDenotes the second order partial derivative of u over y, vxxDenotes the second order partial derivative of v vs. x, vyyRepresenting the second order partial derivative of v versus y.
Further, in the step S5, a remap function of opencv is called to apply a deformation amount of the common roi displacement field to the CT image to obtain a deformed registered image.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, the organ outline of the CT image and the organ outline of the ultrasonic image are firstly obtained from the CT image and the ultrasonic image, then the displacement field of the public roi area is obtained through the displacement change between the CT outline point and the ultrasonic outline point, and finally the deformation registration image is obtained, so that the operation is simple, convenient and fast, and the working efficiency of the image registration operation is effectively improved; in addition, the invention takes the global displacement field and the local deformation matching as specific research objects, and can quickly match the deformation area and solve the global displacement field, thereby realizing the global deformation registration from the CT image to the ultrasonic image, enabling doctors to see organs and surrounding tissues in the CT image under the ultrasonic environment, effectively improving the working efficiency of the doctors and guiding the direction for the future development of the medical image registration technology.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a block diagram of the framework of the present invention;
FIG. 2 is a schematic diagram of a common roi and two contours to be registered;
FIG. 3 is a schematic diagram of a displacement field color coding (left) and a displacement vector field (right);
FIG. 4 is a CT effect graph before registration;
fig. 5 is a CT effect graph after registration.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived from the embodiments of the present invention by a person skilled in the art without any creative effort, should be included in the protection scope of the present invention.
As shown in fig. 1 to 5, the present embodiment discloses an organ deformation registration (CT to ultrasound) method based on an estimated 2d displacement field, which is characterized by comprising the following steps:
s1, acquiring a CT image organ outline, an ultrasonic image organ outline, a CT image and an ultrasonic image;
the specific operation is as follows: the CT image and the ultrasound image utilize findcontours function of opencv to acquire peripheral ordered contour points (x1, x 2.. xn) of the segmentation mask, so as to obtain organ contours of the CT image and organ contours of the ultrasound image.
S2, calculating a public roi area based on the organ contour of the CT image and the organ contour of the ultrasonic image; as shown in fig. 2, the contour located on the outer side is a CT image contour, the contour located on the inner side is an ultrasound image contour, and a circle on the contour indicates a corresponding position obtained by the least sum of squares of the gradient differences;
the specific operation is as follows: solving a union set mask of the CT image mask and the ultrasonic image mask, and calculating a minimum external rectangle of the union set mask; the length and width of the roi is 1.2 times the length and width of the minimum bounding rectangle.
S3, searching the corresponding position of each ultrasonic contour point in the CT contour point (contour _ CT) by using a gradient difference minimum principle, and calculating a displacement vector (u, v) of the ultrasonic contour point;
step S31, sampling the CT contour points to make the number of the CT contour points (contour _ CT) consistent with the number of the ultrasound contour points (contour _ us);
step S32, establishing a coordinate system to obtain the coordinates of the CT contour points and the coordinates of the ultrasonic contour points, taking the two groups of the coordinates of the contour points as two groups of periodic sequences, and calculating the coordinate gradient difference between adjacent points;
step S33, determining a new initial position and an end position by using the periodic property of the CT contour points, and enabling the coordinate gradient difference square sum of the CT contour points and the ultrasonic contour points to be minimum, thereby calculating the displacement vector (u, v) of each ultrasonic contour point corresponding to the CT contour point;
s4, based on the step S3, taking the displacement vectors (u, v) of the ultrasonic contour points as boundary conditions, calculating an Euler-Lagrangian equation, and obtaining a displacement field of a public roi area;
s41, minimization of energy equation:
s42, the corresponding solution (Euler-Lagrange equation) of the energy equation is:
uxx+uyy+vxx+vyy＝0；
the displacement field of the whole public roi can be obtained by solving the sparse matrix;
and S5, based on the displacement field of the common roi, calling a remap function of opencv to apply warping of the displacement field to the CT image to obtain a deformation registration image (output).
According to the invention, the organ outline of the CT image and the organ outline of the ultrasonic image are firstly obtained from the CT image and the ultrasonic image, then the displacement field of the public roi area is obtained through the displacement change between the CT outline point and the ultrasonic outline point, and finally the deformation registration image is obtained, so that the operation is simple, convenient and fast, and the working efficiency of the image registration operation is effectively improved; in addition, the invention takes the global displacement field and the local deformation matching as specific research objects, and can quickly match the deformation area and solve the global displacement field, thereby realizing the global deformation registration from the CT image to the ultrasonic image, enabling doctors to see organs and surrounding tissues in the CT image under the ultrasonic environment, effectively improving the working efficiency of the doctors and guiding the direction for the future development of the medical image registration technology.
Claims (6)
1. An organ deformation registration method based on an estimated 2d displacement field is characterized in that: the method comprises the following steps:
s1, acquiring a CT image and an ultrasonic image, acquiring a CT image organ outline from the CT image, and acquiring an ultrasonic image organ outline from the ultrasonic image;
s2, calculating a common roi area between the organ contour of the CT image and the organ contour of the ultrasonic image;
s3, searching ultrasonic contour points in the organ contour of the ultrasonic image and CT contour points in the organ contour of the CT image, searching the corresponding position of each ultrasonic contour point in the CT contour points by using the minimum gradient difference principle, and calculating the displacement vectors (u, v) of the ultrasonic contour points;
s4, taking the displacement vectors (u, v) of the ultrasonic contour points as boundary conditions, and obtaining a displacement field of a public roi area by calculating an Euler-Lagrangian equation;
and S5, applying the deformation quantity of the displacement field to the CT image through the displacement field of the common roi area to obtain a deformation registration image.
2. The method of organ deformation registration based on an estimated 2d displacement field according to claim 1, wherein: in step S1, the findcontours function of opencv is used to obtain peripheral ordered contour points of the segmentation mask, and the CT image organ contour and the ultrasound image organ contour are obtained from the CT image and the ultrasound image respectively through the peripheral ordered contour points.
3. The method of organ deformation registration based on an estimated 2d displacement field according to claim 2, wherein: in step S2, a union mask of the CT image mask and the ultrasound image mask is first obtained, and then the minimum circumscribed rectangle of the union mask is calculated; the length and the width of the public roi are respectively 1.2 times of the length and the width of the minimum circumscribed rectangle of the union mask.
4. A method of registration of organ deformations based on estimation of 2d displacement field according to claim 3, characterized by: the step S3 specifically includes the following steps:
s31, sampling the CT contour points to make the number of the CT contour points in the organ contour of the CT image consistent with the number of the ultrasound contour points in the organ contour of the ultrasound image;
s32, establishing a coordinate system, and placing the CT contour points and the ultrasonic contour points in the coordinate system to obtain the coordinates of the CT contour points and the ultrasonic contour points;
s33, respectively taking the CT contour point coordinates and the ultrasonic contour point coordinates as two groups of periodic sequences, and calculating the coordinate gradient difference between the corresponding CT contour point coordinates and the corresponding ultrasonic contour point coordinates;
and S34, determining a new starting position and ending position by utilizing the periodic property of the CT contour points, and enabling the square sum of the coordinate gradient differences of all the CT contour point coordinates and all the ultrasonic contour point coordinates to be minimum, thereby calculating the displacement vector (u, v) of each ultrasonic contour point relative to the CT contour point.
5. The method of organ deformation registration based on an estimated 2d displacement field according to claim 4, wherein: in step S4, the calculation formula of the euler-lagrange equation is:
and solving to obtain:
uxx+uyy+vxx+vyy＝0；
finally, obtaining a displacement field of the public roi;
wherein u isxDenotes the first order partial derivative of u over x, uyDenotes the 1 st order partial derivative, v, of u vs yxDenotes the first order partial derivative of v versus x, vyDenotes the first order partial derivative of v versus y, uxxDenotes the second order partial derivative of u over x, uyyDenotes the second order partial derivative of u over y, vxxDenotes the second order partial derivative of v vs. x, vyyRepresenting the second order partial derivative of v versus y.
6. The method of organ deformation registration based on an estimated 2d displacement field according to claim 5, wherein: in step S5, a remap function of opencv is called to apply a deformation amount of the common roi displacement field to the CT image to obtain a deformed registered image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111494423.XA CN114187338B (en) | 2021-12-08 | 2021-12-08 | Organ deformation registration method based on estimated 2d displacement field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111494423.XA CN114187338B (en) | 2021-12-08 | 2021-12-08 | Organ deformation registration method based on estimated 2d displacement field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114187338A true CN114187338A (en) | 2022-03-15 |
| CN114187338B CN114187338B (en) | 2023-04-28 |
Family
ID=80542833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111494423.XA Active CN114187338B (en) | 2021-12-08 | 2021-12-08 | Organ deformation registration method based on estimated 2d displacement field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114187338B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114677421A (en) * | 2022-04-12 | 2022-06-28 | 卡本(深圳)医疗器械有限公司 | Method for estimating rigid/non-rigid registration of 2d organ |
| CN117058135A (en) * | 2023-10-11 | 2023-11-14 | 卡本(深圳)医疗器械有限公司 | Prostate system puncture point distribution method, equipment and medium based on system template |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101198981A (en) * | 2005-06-15 | 2008-06-11 | 皇家飞利浦电子股份有限公司 | Method of model-based elastic image registration for comparing a first and a second image |
| CN106204561A (en) * | 2016-07-04 | 2016-12-07 | 西安电子科技大学 | Prostate multi-modality images non-rigid registration method based on mixed model |
| JP2017127623A (en) * | 2016-01-15 | 2017-07-27 | キヤノン株式会社 | Image processor, image processing method, and program |
| CN112184781A (en) * | 2020-09-14 | 2021-01-05 | 中国科学院深圳先进技术研究院 | Method, device and equipment for registering ultrasonic image and CT image |
| CN113298855A (en) * | 2021-05-27 | 2021-08-24 | 广州柏视医疗科技有限公司 | Image registration method based on automatic delineation |
-
2021
- 2021-12-08 CN CN202111494423.XA patent/CN114187338B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101198981A (en) * | 2005-06-15 | 2008-06-11 | 皇家飞利浦电子股份有限公司 | Method of model-based elastic image registration for comparing a first and a second image |
| US20080205719A1 (en) * | 2005-06-15 | 2008-08-28 | Koninklijke Philips Electronics, N.V. | Method of Model-Based Elastic Image Registration For Comparing a First and a Second Image |
| JP2017127623A (en) * | 2016-01-15 | 2017-07-27 | キヤノン株式会社 | Image processor, image processing method, and program |
| CN106204561A (en) * | 2016-07-04 | 2016-12-07 | 西安电子科技大学 | Prostate multi-modality images non-rigid registration method based on mixed model |
| CN112184781A (en) * | 2020-09-14 | 2021-01-05 | 中国科学院深圳先进技术研究院 | Method, device and equipment for registering ultrasonic image and CT image |
| CN113298855A (en) * | 2021-05-27 | 2021-08-24 | 广州柏视医疗科技有限公司 | Image registration method based on automatic delineation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114677421A (en) * | 2022-04-12 | 2022-06-28 | 卡本(深圳)医疗器械有限公司 | Method for estimating rigid/non-rigid registration of 2d organ |
| CN114677421B (en) * | 2022-04-12 | 2023-03-28 | 卡本(深圳)医疗器械有限公司 | Method for estimating rigid/non-rigid registration of 2d organ |
| CN117058135A (en) * | 2023-10-11 | 2023-11-14 | 卡本(深圳)医疗器械有限公司 | Prostate system puncture point distribution method, equipment and medium based on system template |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114187338B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Perperidis et al. | Spatio-temporal free-form registration of cardiac MR image sequences | |
| Niethammer et al. | Geometric metamorphosis | |
| JP5592796B2 (en) | System and method for quantitative 3DCEUS analysis | |
| Cifor et al. | Hybrid feature-based diffeomorphic registration for tumor tracking in 2-D liver ultrasound images | |
| CN114187338B (en) | Organ deformation registration method based on estimated 2d displacement field | |
| CN112150524B (en) | Two-dimensional and three-dimensional medical image registration method and system based on deep learning | |
| JP2008546441A (en) | Elastic image registration method based on a model for comparing first and second images | |
| Chen et al. | An improved level set for liver segmentation and perfusion analysis in MRIs | |
| Jin et al. | Object recognition in medical images via anatomy-guided deep learning | |
| WO2007144620A2 (en) | Automatic quantification of changes in images | |
| Alam et al. | Evaluation of medical image registration techniques based on nature and domain of the transformation | |
| Liu et al. | Accuracy validation for medical image registration algorithms: a review | |
| Lu et al. | A hybrid multimodal non-rigid registration of MR images based on diffeomorphic demons | |
| Lee et al. | Multi-contrast computed tomography healthy kidney atlas | |
| Zheng | Cross-modality medical image detection and segmentation by transfer learning of shapel priors | |
| Lang et al. | Towards model-enhanced real-time ultrasound guided cardiac interventions | |
| Gupta et al. | Technology and research developments in carotid image registration | |
| Puyol-Anton et al. | Towards a multimodal cardiac motion atlas | |
| CN114677421B (en) | Method for estimating rigid/non-rigid registration of 2d organ | |
| Perperidis et al. | Spatio-temporal free-form registration of cardiac MR image sequences | |
| JP2022052210A (en) | Information processing device, information processing method, and program | |
| Marias et al. | Image analysis for assessing molecular activity changes in time-dependent geometries | |
| Prabu et al. | A statistical deformation model (SDM) based regularizer for non-rigid image registration: application to registration of multimodal prostate MRI and histology | |
| Roujol et al. | Real time constrained motion estimation for ECG-gated cardiac MRI | |
| Li et al. | A hybrid nonrigid medical image registration method on chest radiography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |