CN112184781A - Method, device and equipment for registering ultrasonic image and CT image - Google Patents
Method, device and equipment for registering ultrasonic image and CT image Download PDFInfo
- Publication number
- CN112184781A CN112184781A CN202010961304.XA CN202010961304A CN112184781A CN 112184781 A CN112184781 A CN 112184781A CN 202010961304 A CN202010961304 A CN 202010961304A CN 112184781 A CN112184781 A CN 112184781A
- Authority
- CN
- China
- Prior art keywords
- image
- slice
- contour
- target object
- candidate
- 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
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000002604 ultrasonography Methods 0.000 claims description 107
- 238000001914 filtration Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 23
- 230000009466 transformation Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 15
- 230000001131 transforming effect Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 210000004204 blood vessel Anatomy 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 abstract description 6
- 238000002591 computed tomography Methods 0.000 description 201
- 230000008569 process Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 10
- 210000003734 kidney Anatomy 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 239000003550 marker Substances 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000009508 confectionery Nutrition 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012285 ultrasound imaging Methods 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 238000012795 verification Methods 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
- G06T7/30—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- 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
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/30084—Kidney; Renal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The application belongs to the field of image data processing, and provides a method, a device and equipment for registering an ultrasonic image and a CT image. The method comprises the following steps: acquiring an ultrasonic image of a target object, and extracting a first contour feature of the target object in the ultrasonic image; performing area matching on the first contour features and a plurality of preset second contour features, and determining at least one candidate CT slice; determining a target CT slice according to the similarity between the at least one candidate CT slice and the ultrasonic image; and determining the registration relation of the ultrasonic image and the CT image according to the spatial position of the target CT slice in the CT image. The registration relation between the CT image and the ultrasonic image is determined only by the candidate CT slices, so that the number of the CT slices needing registration calculation can be greatly reduced, the registration real-time performance is improved, the method is not limited to the rich part of the blood vessel, and the application range of the registration method can be improved.
Description
Technical Field
The application belongs to the field of image processing, and particularly relates to a registration method, a registration device and registration equipment of an ultrasonic image and a CT image.
Background
In recent years, because of the advantages of small creation, few complications, and kidney function preservation, the medical image-guided percutaneous renal surgery has gradually become an important means for establishing a surgical channel in percutaneous nephrolithotomy. The clear and real-time medical imaging technology can effectively improve the puncture precision in the operation and reduce the repeated puncture times. The ultrasound image has the characteristics of strong real-time performance, low inspection cost, low spatial resolution and small visual field, and the CT image has the characteristic of high resolution, so that the ultrasound image and the CT image are registered to form an important research direction for improving the image precision and the real-time performance.
The current registration methods of ultrasound images and CT images include an image registration method based on organ edge features and internal blood vessel features, and an image registration method based on depth learning. However, the image registration method based on the organ edge features and the internal blood vessel features is limited to the parts with rich blood vessel features, and the registration accuracy of the parts with sparse blood vessel features is not high. In the image registration method based on deep learning, the registration real-time performance is not high due to the iterative computation process.
Disclosure of Invention
In view of this, embodiments of the present application provide a method, an apparatus, and a device for registering an ultrasound image and a CT image, so as to solve the problems in the prior art that when registering an ultrasound image and a CT image, the ultrasound image and the CT image are limited to a portion with rich vascular features, and the real-time performance in the registration process is not high.
A first aspect of an embodiment of the present application provides a method for registering an ultrasound image and a CT image, where the method includes:
acquiring an ultrasonic image of a target object, and extracting a first contour feature of the target object in the ultrasonic image;
performing area matching on the first contour features and a plurality of preset second contour features to determine at least one candidate CT slice, wherein the plurality of second contour features are contour features of a plurality of preset CT slices in the CT image of the target object;
determining a target CT slice according to the similarity between the at least one candidate CT slice and the ultrasonic image;
and determining the registration relation of the ultrasonic image and the CT image according to the spatial position of the target CT slice in the CT image.
With reference to the first aspect, in a first possible implementation manner of the first aspect,
determining a target CT slice according to the similarity of the at least one candidate CT slice and the ultrasonic image respectively, wherein the method comprises the following steps:
obtaining a rigid transformation matrix between the ultrasound image and the candidate CT slices through iterative optimization;
transforming the candidate CT slices into images under a coordinate system of the ultrasonic image according to the rigid transformation matrix, and calculating the similarity between the images of the CT slices transformed by the coordinate system and the ultrasonic image;
and determining the target CT slice matched with the ultrasonic image according to the similarity.
Obtaining a rigid transformation matrix between the ultrasonic image and the candidate CT slices, and calculating the similarity between the image slices of the CT and the ultrasonic image after the image slices are transformed by a coordinate system
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, obtaining a rigid transformation matrix between the ultrasound image and the candidate CT slices through iterative optimization includes:
updating a rigid transformation matrix according to the gradient of the root-mean-square loss function of the pixel values by an optimizer based on gradient descent;
and when the loss function value is converged or the loss function reaches the maximum iteration times, obtaining a rigid transformation matrix between the ultrasonic image and the candidate CT slice.
With reference to the first possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the transforming the candidate CT slices into an image in a coordinate system of an ultrasound image according to the rigid transformation matrix, and calculating a similarity between an image slice of the CT transformed by the coordinate system and the ultrasound image includes:
transforming the candidate CT slices through a rigid transformation matrix to obtain transformed CT slices;
and calculating the similarity of the contour of the target object in the transformed CT slice and the ultrasonic image through the Dice coefficient.
With reference to the first aspect, in a fourth possible implementation manner of the first aspect, the extracting contour features of the target object in an ultrasound image includes:
extracting an interested area of a target object in an ultrasonic image;
removing noise in the region of interest by continuous median filtering;
extracting a contour edge line of the target object from the denoised image;
integrating the contour edge lines to obtain an integrated solid line, and connecting the disconnected solid line through a closing operation;
and binarizing the connected solid line to obtain the contour feature of the target object.
With reference to the fourth possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect, the removing, by continuous median filtering, noise in the region of interest includes:
filtering the whole noise of the image through a first size filtering kernel;
and filtering noise of the edge contour by a second size filtering kernel, wherein the size of the first size filtering kernel is smaller than that of the second size filtering kernel.
With reference to the first aspect, in a sixth possible implementation manner of the first aspect, before area-matching the contour features in the ultrasound image with the contour features of a CT slice in a preset CT image, the method includes:
extracting a region of interest of a target object in a CT slice;
performing Gaussian filtering on the extracted region of interest;
and carrying out binarization processing on the filtered region of interest to obtain the contour characteristics of the target object in the CT slice.
With reference to the first aspect, in a seventh possible implementation manner of the first aspect, performing area matching on the contour feature in the ultrasound image and the contour feature of a CT slice in a preset CT image to obtain a candidate CT slice matched with the contour feature in the ultrasound image includes:
determining the contour area of a target object in a CT slice to obtain a fitting curve of the serial number of the CT slice and the contour area of the target object;
acquiring the outline area of a target object in an ultrasonic image;
and searching the serial number of the CT slice matched with the contour area of the target object in the ultrasonic image in the fitting curve, and determining candidate CT slices according to the searched serial number of the slice.
A second aspect of an embodiment of the present application provides an apparatus for registering an ultrasound image and a CT image, the apparatus including:
the contour feature extraction unit is used for acquiring an ultrasonic image comprising a target object and extracting contour features of the target object in the ultrasonic image;
the candidate CT slice acquisition unit is used for performing area matching on the contour features in the ultrasonic image and the contour features of the CT slices in a preset CT image to obtain candidate CT slices matched with the contour features in the ultrasonic image;
and the registration relation determining unit is used for determining the registration relation between the ultrasonic image and the CT image according to the candidate CT slices.
A third aspect of embodiments of the present application provides an apparatus for registration of ultrasound and CT images, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of the first aspect when executing the computer program.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, performs the steps of the method according to any one of the first aspect.
Compared with the prior art, the embodiment of the application has the advantages that: the method comprises the steps of predetermining contour features of a plurality of CT slices in a CT image of a target object, namely predetermining a plurality of second contour features, screening at least one candidate CT slice from the plurality of CT slices acquired in advance in an area matching mode when the ultrasonic image is acquired, determining a target CT slice according to the similarity between the candidate CT slice and the ultrasonic image, and determining the registration relation between the ultrasonic image and the CT image according to the spatial position of the determined target CT slice in the CT image. The registration relation between the CT image and the ultrasonic image is determined only by the candidate CT slices, so that the number of the CT slices needing registration calculation can be greatly reduced, the registration real-time performance is improved, the method is not limited to the rich part of the blood vessel, and the application range of the registration method can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a frame diagram of the registration of ultrasound images and CT images provided by an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating an implementation of a registration method of an ultrasound image and a CT image according to an embodiment of the present application;
fig. 3 is a schematic outline acquisition process of an ultrasound image according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of contour acquisition of an ultrasound image provided by an embodiment of the present application;
FIG. 5 is a schematic diagram of contour acquisition of a CT slice according to an embodiment of the present disclosure;
FIG. 6 is a schematic view of a fitted curve of CT slice serial number and kidney contour area according to an embodiment of the present disclosure;
FIG. 7 is a table of registration data between ultrasound images and CT slices according to an embodiment of the present disclosure;
FIG. 8 is a schematic diagram of a CT slice and ultrasound image fusion provided by an embodiment of the present application;
fig. 9 is a schematic diagram illustrating a spatial position relationship between an ultrasound image and CT volume data according to an embodiment of the present application;
fig. 10 is a schematic view of an ultrasound image and CT image registration apparatus according to an embodiment of the present disclosure;
fig. 11 is a schematic diagram of a registration apparatus for ultrasound images and CT images provided by an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
Currently, medical imaging technologies for navigation in a puncture surgery mainly include an electronic Computed Tomography (CT) imaging technology and an ultrasound imaging technology. Puncture planning based on preoperative high resolution CT images is difficult to perform accurately intraoperatively due to breathing, tissue deformation, and uncertain factors during the puncture procedure. The ultrasound image becomes a common image guiding means in the operation due to the advantages of strong real-time performance, low examination cost and the like, but the ultrasound image has lower spatial resolution and narrower visual field, thereby greatly limiting the function of the ultrasound image in the target positioning.
In order to improve the real-time performance and accuracy of the puncture navigation, researchers have proposed various registration methods of two-dimensional ultrasound images and three-dimensional CT images.
The general registration method of the ultrasound image and the CT image comprises the following steps: firstly, establishing a matching relation between a two-dimensional ultrasonic image and a CT slice in a CT image, then registering the two-dimensional ultrasonic image to the CT slice, and finally determining the spatial position relation between the two-dimensional ultrasonic image and the three-dimensional CT image.
When the matching relationship between the ultrasonic image and the CT slice is determined, the matching relationship is initialized in a manual setting mode, in the process of acquiring the ultrasonic image, the movement of the ultrasonic probe is tracked based on the optical positioning sensor, and then the matching relationship is updated in real time through the coordinate conversion relationship between the physical space and the image space. The matching mode requires that no obstacle can be blocked between the positioning sensor and the ultrasonic probe, and the motion influence of the target object is not considered. For example, when the target object is an organ, the respiratory motion may affect the change of the position of the organ during the measurement process, so the registration accuracy between the ultrasound image and the CT image is not high due to the motion information of the target object or the obstruction factor between the ultrasound probe and the positioning sensor.
In order to reduce the influence of the motion information of the target object on the registration accuracy, a method for calculating the corresponding relation between a two-dimensional ultrasonic image and a CT image based on the edge direction characteristics of a blood vessel is provided. The method performs registration based on vessel structure features and gradient features. When the vessel features are clear enough, a better registration result can be obtained. However, this kind of registration is limited to the location with rich vessel features, which is not suitable for wide application.
At present, an image registration method based on deep learning gradually becomes a research hotspot in the registration field, and different deep learning frameworks are proposed, such as an unsupervised learning image registration framework, or a weakly supervised convolutional neural network framework of a multi-modal image. However, the existing deep learning registration framework still has difficulty in learning sparse image features, and the registration accuracy of the ultrasound image and the CT image still needs to be further improved.
Aiming at the defects existing in the current registration of the ultrasonic image and the CT image, the registration method of the ultrasonic image and the CT image, which is high in precision and good in real-time, is provided. Fig. 1 is a block diagram illustrating an implementation of a method for registering an ultrasound image and a CT image during a surgical operation according to an embodiment of the present application, as shown in fig. 1:
before operation, a three-dimensional CT image of the abdomen of the patient may be acquired, and CT feature masks, i.e., second contour features, of a plurality of CT slices of the target object are extracted therefrom. In operation, an ultrasound image is acquired in real time through an ultrasound acquisition device, and an ultrasound feature mask of a target object in the ultrasound image, namely a first contour feature, is extracted. And then, carrying out rough matching on the first contour feature and the second contour feature in an area matching mode to obtain a candidate CT slice matched with the first contour feature in area. Then, the similarity between the candidate CT slices and the ultrasonic image is calculated, the target CT slice is determined according to the image similarity, and the registration relation between the ultrasonic image and the CT image is determined according to the spatial position of the target CT slice in the CT image.
The registration method of the ultrasound image and the CT image provided by the present application is exemplarily described below with reference to specific embodiments.
As shown in fig. 2, the implementation process of the method of the present application includes:
s201, an ultrasonic image including a target object is obtained, and contour features of the target object in the ultrasonic image are extracted.
The target object in the embodiment of the present application may be a target portion of an operation, or a portion of a simulation operation. For example, the target object may be a percutaneously punctured kidney or the like.
In the real-time acquired ultrasound image, in order to quickly complete coarse matching with a CT slice in the CT image, as shown in fig. 1, the contour feature of the acquired two-dimensional ultrasound image may be extracted during an operation or a training process to obtain an ultrasound feature mask. An implementation flow for extracting contour features of an ultrasound image may be as shown in fig. 3, and includes:
s301, extracting the region of interest of the target object in the ultrasonic image.
The region of interest (ROI for short, and region of interest for all english) in the ultrasound image refers to a region where a target object in the ultrasound image is located.
The method for extracting the region of interest of the target object in the ultrasonic image can acquire the ROI in the ultrasonic image according to the characteristic information of the target object. The feature information of the target object includes, but is not limited to, a shape feature, a brightness feature, and the like.
For example, in the schematic diagram of the process of extracting the outline feature of the ultrasound image shown in fig. 4, the region of interest b in the scanned ultrasound image a may be obtained by scanning the shape feature.
And S302, removing noise in the region of interest through continuous median filtering.
As shown in fig. 4, the region of interest b obtained by the feature recognition mode includes more noise, and in order to obtain a clearer image, the obtained region of interest b may be subjected to denoising processing by a continuous median filtering mode, so as to obtain a filtered image c.
In a possible implementation, the continuous median filtering process may include:
filtering the noise of the image overall by a first size filtering kernel, and filtering the noise of the edge contour by a second size filtering kernel, wherein the size of the first size filtering kernel is smaller than that of the second size filtering kernel.
And filtering is carried out through a filtering kernel with a smaller size, so that the overall noise of the image can be removed, and the contour edge information can be kept as far as possible. And filtering is carried out through a filtering kernel with a larger size, so that the noise on the edge contour can be removed, and a denoised image c is obtained.
And S303, extracting the contour edge line of the target object from the denoised image.
And denoising the region of interest to obtain a denoised image. The extraction of the contour edge feature can be performed on the denoised image. For example, the Candy operator may be used to extract edge features of the contour, and an image d including the edge features is obtained.
And S304, integrating the contour edge lines to obtain an integrated solid line, and connecting the disconnected solid line through a closing operation.
After continuous median filtering, some noise still exists at the edges. Through edge contour feature extraction, the obtained edge often comprises various scattered lines, and the scattered edge lines can be integrated into a complete solid line. For example, the scattered edge lines can be integrated into a complete solid line by using the laplacian operator, and the disconnected part can be connected by using a closing operation.
And S305, binarizing the connected solid line to obtain the contour feature of the target object.
And carrying out binarization processing on the connected implementation to obtain a contour characteristic diagram e of the target object. As shown in fig. 1, the obtained contour feature is roughly matched with a CT slice in a preset (e.g., before operation or training) CT image to obtain a candidate CT slice. When the shape of the target object is not changed obviously, the contour features of the CT slices corresponding to the target object can be obtained in advance, so that rough matching with the ultrasonic image can be performed quickly.
As shown in fig. 5, an implementation process of obtaining a CT slice corresponding to a target object includes:
and S5.1, acquiring a CT slice in the CT image.
Wherein the CT image comprises a plurality of CT slices. For the same target object, the slice angle can be gradually changed through a preset angle amplitude value to obtain a slice group under each angle, one slice group comprises a plurality of CT slices, and a CT image of the target object can be obtained through the slice groups corresponding to the plurality of angles.
For example, in general, the shape of a general target object is stable, and only the rigid motion of the target object in free breathing can be considered without generating significant deformation such as expansion and contraction with breathing. The CT slice of the target object can be obtained from the three-dimensional CT image before image navigation.
S5.2, extracting the interested region of the target object in the CT slice.
The method for extracting the region of interest of the target object in the CT slice can acquire the ROI in the CT slice according to the characteristic information of the target object. The feature information of the target object includes, but is not limited to, a shape feature, a brightness feature, and the like.
And S5.3, performing Gaussian filtering on the extracted region of interest.
And the extracted region of interest, namely ROI, is subjected to Gaussian filtering, so that most of noise in the region of interest can be filtered, thereby facilitating subsequent binarization processing and obtaining more accurate contour characteristics.
And S5.4, carrying out binarization processing on the filtered region of interest to obtain the contour characteristics of the target object in the CT slice.
And carrying out binarization processing on the filtered ROI to obtain the contour characteristics of the target object in the CT slice.
S202, area matching is carried out on the contour features in the ultrasonic image and the contour features of the CT slices in the preset CT image, and candidate CT slices matched with the contour features in the ultrasonic image are obtained.
In order to quickly obtain a CT slice matched with an ultrasound image acquired in real time, a contour area corresponding to a contour feature of the obtained CT slice and a contour area corresponding to a contour feature of the ultrasound image may be calculated. And performing coarse matching in an area matching mode to obtain CT slices matched with the ultrasonic images, namely candidate CT slices.
In a possible implementation manner, the contour area corresponding to the contour feature of each CT slice may be calculated in advance, and a fitting curve of the serial number of the CT slice and the contour area is established. For example, in fig. 6, the kidney contour area corresponding to each CT slice number may be calculated to obtain a fitting curve of the CT slice number and the kidney contour area. In the matching process, the contour feature of the target object can be extracted from the real-time acquired ultrasonic image, and the contour area corresponding to the contour feature of the ultrasonic image can be calculated. And comparing the calculated outline area of the ultrasonic image with a pre-established fitted curve, so that the CT slices matched with the outline area of the acquired ultrasonic image can be determined, and one or more determinable CT slices are taken as candidate CT slices.
Through the area matching mode, the candidate CT slices corresponding to the ultrasonic images can be rapidly determined, and only the CT slices matched with the ultrasonic images need to be determined in the candidate CT slices, so that the calculation amount of registration can be greatly reduced, and the registration efficiency is improved. And the registration process is not limited to the vessel characteristics, which is beneficial to improving the adaptive range of registration.
S203, determining a target CT slice according to the similarity between the at least one candidate CT slice and the ultrasonic image.
After candidate CT slices corresponding to the acquired ultrasound image are determined, because CT slices having the same contour area may correspond to different detection angles corresponding to the target, CT slices similar to the detection angle of the ultrasound image need to be further selected from the candidate CT slices.
As shown in fig. 1, the candidate CT slices and the ultrasound image may be subjected to registration calculation, the similarity between the ultrasound image and the candidate CT slices is determined, and the candidate CT slice with the highest similarity is used as the target CT slice registered with the ultrasound image.
In a possible implementation manner, a rigid transformation matrix between the ultrasound image and the candidate CT slices can be obtained through an iterative optimization manner, the CT slices are transformed to an image in a coordinate system where the ultrasound image is located through the obtained rigid transformation matrix, the similarity of the profile features of the transformed image and the ultrasound image is calculated, and the candidate CT slice with the highest similarity is selected as the target CT slice.
Specifically, in determining the rigid transformation matrix of the ultrasound image and the candidate CT slice, the gradient of the root Mean Square (MSE) Loss function Loss may be continuously increased according to the gradient of a gradient descent optimizer, such as an Adams optimizerAnd newly allocating parameters until the loss function value converges to the minimum value, or the iteration times reach the maximum iteration times. For example, it can be represented by a formulaA rigid transformation matrix is determined between the ultrasound image and the candidate CT slice. Wherein,for a rigid transformation matrix between the ultrasound image and the candidate CT slice, IUSFor ultrasound images, ICTFor candidate CT slices, Loss is the pixel value root mean square Loss function.
After a rigid transformation matrix between a two-dimensional ultrasound image and a candidate CT slice is obtained through registration calculation, a B-spline interpolation method may be used to transform the candidate CT slice into an image under an ultrasound image coordinate system, a Dice Coefficient (entirely called Dice Coefficient, abbreviated as DC in english) may be used to calculate the similarity between the transformed candidate CT slice and the ultrasound image, and the calculation formula may be:
wherein,for a rigid transformation matrix between the ultrasound image and the candidate CT slice, IUSFor ultrasound images, ICTFor candidate CT slices, Dice is the Dice coefficient. The higher the Dice is, the higher the similarity between the Dice is. And selecting the candidate CT slice with the highest dice coefficient to be matched with the ultrasonic image to obtain the CT slice with the accurately matched ultrasonic image.
S204, determining the registration relation between the ultrasonic image and the CT image according to the space position of the target CT slice in the CT image.
According to the rigid transformation matrix, the spatial position of the target CT slice in the CT image can be determined, and the registration relation between the ultrasonic image and the CT image can be determined according to the spatial position, so that image fusion can be performed according to the registration relation, and a real-time and accurate navigation image can be obtained.
To verify the registration method described in this application, the coordinates of the ith marker point on the ultrasound imageCoordinates of the ith mark point on the CT slice after registration transformationThe distance between the two points is used as the Registration Error between the ultrasound image and the CT slice, that is, the Registration Error of the marker point (referred to as final Registration Error, FRE) can be calculated as:
wherein n is the number of the marked points.
In the registration experiment of the ultrasound image and the CT slice, the registration error between the CT slice and the ultrasound image is shown in fig. 7. In fig. 7, the registration method correctly calculates the CT slice matching relationship between the ultrasound image and the three-dimensional CT image, the average registration error between the ultrasound image and the marker point of the CT slice is 0.709mm, and the average registration operation time is 1.15 s.
In addition, through experimental verification, the registration method provided by the application can obtain better registration accuracy on kidney phantom data, obtain a fusion image shown in fig. 8, namely a fusion image of an ultrasound image and a CT slice, and obtain a spatial position relationship between the ultrasound image and CT volume data shown in fig. 9 according to the registered CT slice.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Fig. 10 is a schematic view of a registration apparatus for ultrasound images and CT images according to an embodiment of the present application, as shown in fig. 10, the registration apparatus includes:
a contour feature acquiring unit 1001 configured to acquire an ultrasound image of a target object and extract a first contour feature of the target object in the ultrasound image;
an area matching unit 1002, configured to perform area matching on the first contour feature and a plurality of preset second contour features, and determine at least one candidate CT slice, where the plurality of second contour features are contour features of a plurality of preset CT slices in a CT image of the target object;
a target CT slice determining unit 1003, configured to determine a target CT slice according to similarities between the at least one candidate CT slice and the ultrasound image, respectively;
a registration relation determining unit 1004, configured to determine a registration relation between the ultrasound image and the CT image according to a spatial position of the target CT slice in the CT image.
The registration apparatus shown in fig. 10 corresponds to the registration method shown in fig. 1.
Fig. 11 is a schematic diagram of a registration apparatus for ultrasound images and CT images according to an embodiment of the present application. As shown in fig. 11, the registration apparatus 11 of the ultrasound image and the CT image of the embodiment includes: a processor 110, a memory 111 and a computer program 112 stored in said memory 111 and executable on said processor 110, such as a registration program for ultrasound and CT images. The processor 110, when executing the computer program 112, implements the steps in the above-described embodiments of the method for registering ultrasound and CT images. Alternatively, the processor 110 implements the functions of the modules/units in the above-mentioned device embodiments when executing the computer program 112.
Illustratively, the computer program 112 may be partitioned into one or more modules/units that are stored in the memory 111 and executed by the processor 110 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 112 in the registration device 11 for ultrasound and CT images.
The registering device for the ultrasound image and the CT image may include, but is not limited to, a processor 110 and a memory 111. Those skilled in the art will appreciate that fig. 11 is only an example of the registration device 11 for the ultrasound image and the CT image, and does not constitute a limitation to the registration device 11 for the ultrasound image and the CT image, and may include more or less components than those shown, or combine some components, or different components, for example, the registration device for the ultrasound image and the CT image may further include an input/output device, a network access device, a bus, etc.
The Processor 110 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 111 may be an internal storage unit of the registration apparatus 11 for the ultrasound image and the CT image, such as a hard disk or a memory of the registration apparatus 11 for the ultrasound image and the CT image. The memory 111 may also be an external storage device of the ultrasound image and CT image registration device 11, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, which are equipped on the ultrasound image and CT image registration device 11. Further, the memory 111 may also include both an internal storage unit and an external storage device of the registration device 11 of the ultrasound image and the CT image. The memory 111 is used for storing the computer program and other programs and data required by the registration device of the ultrasound and CT images. The memory 111 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. . Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (11)
1. A method for registering an ultrasound image with a CT image, the method comprising:
acquiring an ultrasonic image of a target object, and extracting a first contour feature of the target object in the ultrasonic image;
performing area matching on the first contour features and a plurality of preset second contour features to determine at least one candidate CT slice, wherein the plurality of second contour features are contour features of a plurality of preset CT slices in the CT image of the target object;
determining a target CT slice according to the similarity between the at least one candidate CT slice and the ultrasonic image;
and determining the registration relation of the ultrasonic image and the CT image according to the spatial position of the target CT slice in the CT image.
2. The method of claim 1, wherein determining the target CT slice according to the similarity between the at least one candidate CT slice and the ultrasound image comprises:
obtaining a rigid transformation matrix between the ultrasound image and the candidate CT slices through iterative optimization;
transforming the candidate CT slices into images under a coordinate system of the ultrasonic image according to the rigid transformation matrix, and calculating the similarity between the images of the CT slices transformed by the coordinate system and the ultrasonic image;
and determining the target CT slice matched with the ultrasonic image according to the similarity.
3. The method of claim 2, wherein obtaining a rigid transformation matrix between the ultrasound image and the candidate CT slices by iterative optimization comprises:
updating a rigid transformation matrix according to the gradient of the root-mean-square loss function of the pixel values by an optimizer based on gradient descent;
and when the loss function value is converged or the loss function reaches the maximum iteration times, obtaining a rigid transformation matrix between the ultrasonic image and the candidate CT slice.
4. The method of claim 2, wherein transforming the candidate CT slices into an image in a coordinate system of an ultrasound image according to the rigid transformation matrix, and calculating the similarity between the image slices of the CT transformed by the coordinate system and the ultrasound image comprises:
transforming the candidate CT slices through a rigid transformation matrix to obtain transformed CT slices;
and calculating the similarity of the contour of the target object in the transformed CT slice and the ultrasonic image through the Dice coefficient.
5. The method of claim 1, wherein extracting contour features of the target object in an ultrasound image comprises:
extracting an interested area of a target object in an ultrasonic image;
removing noise in the region of interest by continuous median filtering;
extracting a contour edge line of the target object from the denoised image;
integrating the contour edge lines to obtain an integrated solid line, and connecting the disconnected solid line through a closing operation;
and binarizing the connected solid line to obtain the contour feature of the target object.
6. The method of claim 5, wherein removing noise in the region of interest by continuous median filtering comprises:
filtering the whole noise of the image through a first size filtering kernel;
and filtering noise of the edge contour by a second size filtering kernel, wherein the size of the first size filtering kernel is smaller than that of the second size filtering kernel.
7. The method of claim 1, wherein prior to area matching the contour features in the ultrasound image with the contour features of the CT slices in the pre-set CT image, the method comprises:
extracting a region of interest of a target object in a CT slice;
performing Gaussian filtering on the extracted region of interest;
and carrying out binarization processing on the filtered region of interest to obtain the contour characteristics of the target object in the CT slice.
8. The method of claim 1, wherein performing area matching on the contour feature in the ultrasound image and the contour feature of the CT slice in the preset CT image to obtain a candidate CT slice matched with the contour feature in the ultrasound image comprises:
determining the contour area of a target object in a CT slice to obtain a fitting curve of the serial number of the CT slice and the contour area of the target object;
acquiring the outline area of a target object in an ultrasonic image;
and searching the serial number of the CT slice matched with the contour area of the target object in the ultrasonic image in the fitting curve, and determining candidate CT slices according to the searched serial number of the slice.
9. An apparatus for registering an ultrasound image and a CT image, the apparatus comprising:
the contour feature acquisition unit is used for acquiring an ultrasonic image of a target object and extracting a first contour feature of the target object in the ultrasonic image;
the area matching unit is used for performing area matching on the first contour features and a plurality of preset second contour features to determine at least one candidate CT slice, wherein the plurality of second contour features are contour features of a plurality of preset CT slices in the CT image of the target object;
the target CT slice determining unit is used for determining a target CT slice according to the similarity between the at least one candidate CT slice and the ultrasonic image;
and the registration relation determining unit is used for determining the registration relation between the ultrasonic image and the CT image according to the spatial position of the target CT slice in the CT image.
10. An apparatus for registration of ultrasound and CT images, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor realizes the steps of the method according to any of claims 1 to 8 when executing the computer program.
11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010961304.XA CN112184781A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for registering ultrasonic image and CT image |
PCT/CN2020/129551 WO2022052303A1 (en) | 2020-09-14 | 2020-11-17 | Method, apparatus and device for registering ultrasound image and ct image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010961304.XA CN112184781A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for registering ultrasonic image and CT image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112184781A true CN112184781A (en) | 2021-01-05 |
Family
ID=73920898
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010961304.XA Pending CN112184781A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for registering ultrasonic image and CT image |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112184781A (en) |
WO (1) | WO2022052303A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112950623A (en) * | 2021-03-29 | 2021-06-11 | 云印技术(深圳)有限公司 | Mark identification method and system |
CN113096093A (en) * | 2021-04-12 | 2021-07-09 | 中山大学 | Method, system and device for calculating quantity and volume of calculi in CT (computed tomography) image |
CN113409371A (en) * | 2021-06-25 | 2021-09-17 | 浙江商汤科技开发有限公司 | Image registration method and related device and equipment |
CN113902927A (en) * | 2021-12-09 | 2022-01-07 | 北京车网科技发展有限公司 | Comprehensive information processing method fusing image and point cloud information |
CN114187338A (en) * | 2021-12-08 | 2022-03-15 | 卡本(深圳)医疗器械有限公司 | Organ deformation registration method based on estimated 2d displacement field |
CN115409835A (en) * | 2022-10-31 | 2022-11-29 | 成都浩目科技有限公司 | Three-dimensional imaging method, device, electronic equipment, system and readable storage medium |
CN116211353A (en) * | 2023-05-06 | 2023-06-06 | 北京大学第三医院(北京大学第三临床医学院) | Wearable ultrasonic bladder capacity measurement and multi-mode image morphology evaluation system |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114648477A (en) * | 2022-03-25 | 2022-06-21 | 南京北新智能科技有限公司 | Digital fusion matrix |
CN115147469A (en) * | 2022-05-10 | 2022-10-04 | 腾讯科技(深圳)有限公司 | Registration method, device, equipment and storage medium |
CN116236280B (en) * | 2023-02-02 | 2024-06-18 | 逸超医疗科技(北京)有限公司 | Interventional therapy guiding method and system based on multi-mode image fusion |
CN116402675B (en) * | 2023-03-23 | 2023-11-28 | 中国地质科学院地质力学研究所 | Image registration method based on shale component calibration |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090304252A1 (en) * | 2008-06-05 | 2009-12-10 | Dong Gyu Hyun | Non-Rigid Registration Between CT Images And Ultrasound Images |
US20090303252A1 (en) * | 2008-06-04 | 2009-12-10 | Dong Gyu Hyun | Registration Of CT Image Onto Ultrasound Images |
CN104463866A (en) * | 2014-12-04 | 2015-03-25 | 无锡日联科技有限公司 | Local shape matching method based on outline random sampling |
CN104574329A (en) * | 2013-10-09 | 2015-04-29 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic fusion imaging method and ultrasonic fusion imaging navigation system |
CN110930438A (en) * | 2019-11-22 | 2020-03-27 | 上海联影医疗科技有限公司 | Image registration method and device, electronic equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9877697B2 (en) * | 2014-04-30 | 2018-01-30 | Emory University | Systems, methods and computer readable storage media storing instructions for generating planning images based on HDR applicators |
US10991069B2 (en) * | 2014-10-08 | 2021-04-27 | Samsung Electronics Co., Ltd. | Method and apparatus for registration of medical images |
CN111091589B (en) * | 2019-11-25 | 2023-11-17 | 北京理工大学 | Ultrasonic and nuclear magnetic image registration method and device based on multi-scale supervised learning |
CN110838140A (en) * | 2019-11-27 | 2020-02-25 | 艾瑞迈迪科技石家庄有限公司 | Ultrasound and nuclear magnetic image registration fusion method and device based on hybrid supervised learning |
-
2020
- 2020-09-14 CN CN202010961304.XA patent/CN112184781A/en active Pending
- 2020-11-17 WO PCT/CN2020/129551 patent/WO2022052303A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090303252A1 (en) * | 2008-06-04 | 2009-12-10 | Dong Gyu Hyun | Registration Of CT Image Onto Ultrasound Images |
US20090304252A1 (en) * | 2008-06-05 | 2009-12-10 | Dong Gyu Hyun | Non-Rigid Registration Between CT Images And Ultrasound Images |
CN104574329A (en) * | 2013-10-09 | 2015-04-29 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic fusion imaging method and ultrasonic fusion imaging navigation system |
CN104463866A (en) * | 2014-12-04 | 2015-03-25 | 无锡日联科技有限公司 | Local shape matching method based on outline random sampling |
CN110930438A (en) * | 2019-11-22 | 2020-03-27 | 上海联影医疗科技有限公司 | Image registration method and device, electronic equipment and storage medium |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112950623A (en) * | 2021-03-29 | 2021-06-11 | 云印技术(深圳)有限公司 | Mark identification method and system |
CN113096093A (en) * | 2021-04-12 | 2021-07-09 | 中山大学 | Method, system and device for calculating quantity and volume of calculi in CT (computed tomography) image |
CN113096093B (en) * | 2021-04-12 | 2023-04-21 | 中山大学 | Calculation method, system and device for number and volume of CT image stones |
CN113409371A (en) * | 2021-06-25 | 2021-09-17 | 浙江商汤科技开发有限公司 | Image registration method and related device and equipment |
CN114187338A (en) * | 2021-12-08 | 2022-03-15 | 卡本(深圳)医疗器械有限公司 | Organ deformation registration method based on estimated 2d displacement field |
CN113902927A (en) * | 2021-12-09 | 2022-01-07 | 北京车网科技发展有限公司 | Comprehensive information processing method fusing image and point cloud information |
CN113902927B (en) * | 2021-12-09 | 2022-04-12 | 北京车网科技发展有限公司 | Comprehensive information processing method fusing image and point cloud information |
CN115409835A (en) * | 2022-10-31 | 2022-11-29 | 成都浩目科技有限公司 | Three-dimensional imaging method, device, electronic equipment, system and readable storage medium |
CN115409835B (en) * | 2022-10-31 | 2023-02-17 | 成都浩目科技有限公司 | Three-dimensional imaging method, device, electronic equipment, system and readable storage medium |
CN116211353A (en) * | 2023-05-06 | 2023-06-06 | 北京大学第三医院(北京大学第三临床医学院) | Wearable ultrasonic bladder capacity measurement and multi-mode image morphology evaluation system |
CN116211353B (en) * | 2023-05-06 | 2023-07-04 | 北京大学第三医院(北京大学第三临床医学院) | Wearable ultrasonic bladder capacity measurement and multi-mode image morphology evaluation system |
Also Published As
Publication number | Publication date |
---|---|
WO2022052303A1 (en) | 2022-03-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022052303A1 (en) | Method, apparatus and device for registering ultrasound image and ct image | |
US10242450B2 (en) | Coupled segmentation in 3D conventional ultrasound and contrast-enhanced ultrasound images | |
CN110338840B (en) | Three-dimensional imaging data display processing method and three-dimensional ultrasonic imaging method and system | |
CN106485695B (en) | Medical image Graph Cut dividing method based on statistical shape model | |
US8150132B2 (en) | Image analysis apparatus, image analysis method, and computer-readable recording medium storing image analysis program | |
CN103325143B (en) | Labelling point automatic registration method based on Model Matching | |
JP5584441B2 (en) | Association method between volume data | |
CN109124662B (en) | Rib center line detection device and method | |
CN111374712B (en) | Ultrasonic imaging method and ultrasonic imaging equipment | |
CN116580068B (en) | Multi-mode medical registration method based on point cloud registration | |
Jimenez-Carretero et al. | Optimal multiresolution 3D level-set method for liver segmentation incorporating local curvature constraints | |
CN108670301B (en) | Transverse process positioning method for vertebral column based on ultrasonic image | |
CN116363181A (en) | Feature-based CT image and ultrasonic image liver registration method | |
Hacihaliloglu et al. | Statistical shape model to 3D ultrasound registration for spine interventions using enhanced local phase features | |
Torres et al. | Kidney segmentation in 3-D ultrasound images using a fast phase-based approach | |
CN114494364A (en) | Liver three-dimensional ultrasonic and CT image registration initialization method and device and electronic equipment | |
CN117689697A (en) | US and CT image registration method based on point cloud registration and image feature registration | |
CN116309647B (en) | Method for constructing craniocerebral lesion image segmentation model, image segmentation method and device | |
CN112102327B (en) | Image processing method, device and computer readable storage medium | |
CN117115141A (en) | Incomplete medical image registration method and device, electronic equipment and medium | |
CN105956587B (en) | A kind of knee joint magnetic resonance image sequence meniscus extraction method based on shape constraining | |
CN116703882A (en) | Non-contact type heart three-dimensional mapping method and system | |
CN109816665B (en) | Rapid segmentation method and device for optical coherence tomography image | |
Alirr et al. | Automatic liver segmentation from ct scans using intensity analysis and level-set active contours | |
CN115239751A (en) | Postoperative image needle track extraction method |
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 |