CN111402305B - Medical image registration method, system and computer readable medium - Google Patents
Medical image registration method, system and computer readable medium Download PDFInfo
- Publication number
- CN111402305B CN111402305B CN202010503362.8A CN202010503362A CN111402305B CN 111402305 B CN111402305 B CN 111402305B CN 202010503362 A CN202010503362 A CN 202010503362A CN 111402305 B CN111402305 B CN 111402305B
- Authority
- CN
- China
- Prior art keywords
- image
- rigid
- registration
- pixel unit
- function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application provides a medical image registration method, a system and a computer readable medium, wherein the method comprises the following steps: acquiring a first image and a second image; extracting rigid organs in the first image and the second image; performing rigid registration on the rigid body organ according to the extraction result; and performing non-rigid registration of the target object according to the rigid registration result. According to the method, rigid registration and non-rigid registration are carried out on the medical image, so that the matching accuracy of the target object is greatly improved, and the accuracy of lesion progress evaluation during film reading is improved; by using the rigid organ to perform rigid registration, the matching accuracy of the target object is further improved, and the accuracy of lesion progress evaluation during radiographing is further improved.
Description
Technical Field
The present application relates generally to the field of medical image technology, and more particularly, to a medical image registration method, system and computer readable medium.
Background
In the current radiographing process, in a scene without intelligent comparison, radiographing experts need to compare baseline (first-time photographing) and visit (second-time photographing) images which are photographed by the same subject twice at different times in a visual observation mode, and repeatedly switch between two groups of images of three-dimensional multi-layer images to align and match focuses. Because the shooting posture (such as the lying position and angle) of the subject and the state (such as the difference between the stomach and the abdomen) of the subject are different on the two images of the same subject, the difficulty of identifying the lesion position and matching the two groups of images is greatly increased, the lesion matching error is easily caused, and the accuracy of lesion progress evaluation is seriously influenced.
Disclosure of Invention
The technical problem to be solved by the application is to provide a medical image registration method, a medical image registration system and a computer readable medium, which can improve the matching accuracy of medical images, so that the accuracy of lesion progress evaluation during reading is improved.
In order to solve the above technical problem, the present application provides a medical image registration method, including the following steps: acquiring a first image and a second image; extracting rigid organs in the first image and the second image; rigid registration is carried out on the rigid body organ according to the extraction result; and performing non-rigid registration of the target object according to the rigid registration result.
Optionally, the method further comprises: and obtaining a differential subtraction image of the first image and the second image according to the non-rigid registration result.
Optionally, the extraction algorithm for extracting the rigid body organ in the first image and the second image is:
where (x, y, z) is the coordinates of the pixels in the first image and the second image, and T1 is the predetermined density threshold.
Optionally, the extracting the rigid body organ in the first image and the second image further comprises: and optimizing the extraction result by using an image three-dimensional low-pass filtering algorithm.
Optionally, the rigid registration of the rigid body organ according to the extraction result comprises: acquiring a central operator, a standard central operator and a rotation, scaling and translation invariant operator according to the extraction result; and pairing the rigid body organs in the first image and the second image according to the coincidence center operator, the standard center operator, the rotation, scaling and translation invariant operator and a preset loss function.
Optionally, the non-rigid registration of the target object according to the rigid registration result includes: acquiring a motion function of each pixel unit according to the rigid registration result; determining a matching function according to the motion function of the pixel unit; determining a limiting function according to the motion function and the spatial texture feature of the pixel unit; and matching the target object according to the matching function and the limiting function.
Optionally, the first image and the second image are medical images of the same modality or different modalities.
Optionally, the method further comprises one or more of the following steps: measuring a change region of the target object according to the difference subtraction image; and saving the measurement results in the corresponding form.
The present application further provides a medical image registration system, comprising: a memory for storing instructions executable by the processor; and a processor for executing the instructions to implement the method as described above.
The present application also provides a computer readable medium having stored thereon computer program code which, when executed by a processor, implements a method as described above.
Compared with the prior art, the method has the following advantages:
rigid registration and non-rigid registration are carried out on the medical image, so that the matching accuracy of the target object is greatly improved, and the accuracy of lesion progress evaluation during film reading is improved; by using the rigid organ to perform rigid registration, the matching accuracy of the target object is further improved, and the accuracy of lesion progress evaluation during radiographing is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the principle of the application. In the drawings:
fig. 1 is a schematic flow chart of a medical image registration method according to an embodiment of the present application.
Fig. 2A and 2B are schematic rigid registration diagrams of a medical image registration method according to an embodiment of the present application.
Fig. 3A and 3B are schematic non-rigid registration diagrams of a medical image registration method according to an embodiment of the present application.
Fig. 4A-4D are schematic diagrams of a first image and a differential subtraction image of a medical image registration method according to an embodiment of the present application.
Fig. 5 is a schematic diagram illustrating measurement of a differential subtraction image according to an embodiment of the present application.
Fig. 6 is a table diagram illustrating measurement results of a difference subtraction image of a medical image registration method according to an embodiment of the present application.
Fig. 7 is a system block diagram of a medical image registration system according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.
As used in this application, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
The relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present application unless specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in reverse order or simultaneously. Meanwhile, other operations are added to or removed from these processes.
Fig. 1 shows a schematic flow diagram of a medical image registration method according to an embodiment of the present application. As shown in fig. 1, an embodiment of the present application provides a medical image registration method, including the following steps:
and 104, performing non-rigid registration of the target object according to the rigid registration result.
The following describes each step in the medical image registration method in further detail:
in step 101, a first image and a second image are acquired.
A medical image registration system acquires a first image and a second image. The first image and the second image are medical images from the same subject taken at different times. In one example, the first image may be a baseline image of the subject, i.e., an image taken for the first time; the second image may be an interview image of the subject, i.e., an image taken a second time.
Alternatively, the first image and the second image may be medical images of the same modality or different modalities.
Medical images of the same modality mean that the images are from the same sensor/imaging device, also known as a single modality. Medical images of different modalities refer to images from different sensors/imaging devices, also known as multiple modalities.
In step 102, a rigid body organ in the first image and the second image is extracted.
The medical image registration system extracts the rigid body organ in the first image and the second image. Rigid organs refer to organs which are difficult to form change in an adult human body and have the characteristic of no deformation when image acquisition is carried out at different time periods. Therefore, in medical imaging, rigid organs are suitable for rigid registration. The rigid body organ may be one or more, and the present invention is not limited thereto.
Preferably, the rigid body organ may be a bone. Adult bones have morphological invariance and, as high-density images in CT, have features that are easy to extract and edge-accurate, so bones are more suitable for rigid registration.
Optionally, the algorithm for extracting the rigid body organs in the first image and the second image is:
wherein (x, y, z) is the three-dimensional coordinates of the pixels in the first image and the second image; image (x, y, z) is a value of a pixel of the first Image and a pixel of the second Image; t1 is a preset density threshold, which can be set according to actual needs; OriMask (x, y, z) is a collection of high density pixels.
When Image (x, y, z) is greater than or equal to T1, the pixel is considered to be of high density, with a high probability of belonging to a rigid body organ region; when Image (x, y, z) is less than T1, the pixel is considered not to belong to a rigid organ region.
Optionally, extracting the rigid body organ in the first image and the second image may further include: and optimizing the extraction result by using an image three-dimensional low-pass filtering algorithm.
Because the medical image has the problems of space sampling rate and the like, such as noise, low resolution and CT diffraction ripple, the medical image registration system needs to optimize the extracted image boundary of the rigid body organ, so that the rigid body region is smooth and complete.
In one example, the three-dimensional low-pass filtering algorithm for the image may be a standard filtering function:
The Mask obtained at this time is the identified rigid body Region obtained by smoothing through the image three-dimensional low-pass filtering algorithm, and the problem of excessive ROI (Region of Interest) caused by resolution can be reduced.
In step 103, rigid registration is performed on the rigid body organ according to the extraction result.
Medical image registration is the process of performing one or a series of spatial transformations on two or more images of the same subject taken at different times, at different perspectives, or using different sensors, to achieve spatial correspondence between their corresponding points. Rigid registration refers to registration of objects without deformation, namely, the shapes of the objects on the two images are not changed, so that registration is performed only by translation, scaling and rotation, and the method is suitable for registration scenes of rigid organs and the like. The medical image registration system performs rigid registration on the rigid organ according to the extraction result, so that the rigid organ regions in the first image and the second image are consistent in space. By rigidly registering the rigid organs, non-rigid registration of other organs can be performed in a subsequent step based on the rigid registration result.
Fig. 2A and 2B are schematic rigid registration diagrams of a medical image registration method according to an embodiment of the present application. Fig. 2A is a first image, and fig. 2B is a second image. The medical image registration system rigidly registers the bones in fig. 2A and 2B. Using the spine of FIGS. 2A and 2B as an example, gross shifts in subject morphology can be seen. By pairing the spines in fig. 2A and 2B, each spine can be accurately mapped in the first image and the second image.
Optionally, rigidly registering the rigid body organ according to the extraction result may include: acquiring a central operator, a standard central operator and a rotation, scaling and translation invariant operator according to the extraction result; and pairing the rigid body organs in the first image and the second image according to the coincidence center operator, the standard center operator, the rotation, scaling and translation invariant operator and a preset loss function.
For the extraction result of the rigid body organ, the medical image registration system may compare the position parameter of the ROI with a corresponding iRST Operator (an irrational Rotation Scaling transformation Operator) and pair the position parameter with the iRST Operator. And the medical image registration system determines a loss function according to the difference value and the weight factor of the iRST operator, and realizes registration of each rigid body connected domain.
And the registration of each rigid body connected domain is realized by calculating the iRST invariance operator of each rigid body connected domain in the first image and the second image and comparing the iRST invariance operators between the two images. Because for the same organ, the difference between two sets of iRST operators calculated when the two images are used as rigid connected domains respectively should be small. Registration of the rigid body connected domain includes the following steps 1-4:
1. the medical image registration system first acquires a coincidence center operator. The algorithm for the coincident operator is as follows:
wherein p, q and r are ranks in three dimensional directions of an operator three-dimensional space respectively; m, N, K are the pixel numbers of the image in three-dimensional space in x, y, z independent orthogonal axes. Mask is connected region identification for
Which is an identification of the kth connected domain in three-dimensional space. When the spatial position coordinate (x, y, z) belongs to the kth connected domain,
the pixel value Image (x, y, z) corresponding to the coordinates representing the space position participates in the calculation; when the spatial position coordinate (x, y, z) does not belong to the kth connected component,
then go toThe product of the above formula is also 0, and the pixel value Image (x, y, z) corresponding to the coordinates of the spatial position does not participate in the calculation.
Wherein
3. iRST operator can be obtained based on standard central operator
The following were used:
the number of iRST operators can be set according to actual needs. Generally, the number of iRST operators may be 10-40, preferably 10.
4. A loss function of
Wherein
For the weighting factor of the corresponding ith iRST operator,
the ith iRST operator of the p-th rigid connected domain in the first image,
is the iRST operator of the s-th rigid connected domain in the second image,
the difference of the ith iRST operator of the ROI corresponding to the two images. In general, the earlier in-order iRST operator may be weighted more heavily.
In one example, when the absolute value difference between the rigid body connected domain operator in each first image and the rigid body connected domain operator in each second image is the smallest after subtraction, that is, when the above loss function reaches the minimum, the rigid body connected domain in the first image and the rigid body connected domain in the second image are considered to be the same rigid body connected domain. For example, there are A, B and C rigid body connected domains in the first image and D, E and F rigid body connected domains in the second image. Then the loss functions of three sets of connected components a and D, A and E, A and F, respectively, need to be calculated when finding the corresponding connected component a in the second image. If the loss function of A and E is the smallest of the three groups, then A and E are considered to be the mapping of the same region in different images.
In step 104, non-rigid registration of the target object is performed based on the rigid registration result.
And the medical image registration system performs non-rigid registration on the target object according to the rigid registration result. The non-rigid registration refers to the registration of objects with deformation, namely, the shape of the objects on the two images changes, and the registration needs to be carried out through translation, rotation, scaling and parameter weight distribution of the deformation of the objects, so that the non-rigid registration is suitable for registration scenes of soft non-rigid organs and the like. Due to the state of the subject in different time periods and the positioning error, the slice cutting angle at each time is not consistent with the last position angle, so that the shapes and the sizes of the cut planes are different due to the slice cutting angle. In addition, global effects can be caused by changes in the overall morphology of the human body, for example, a subject becoming fat or thin can cause the overall morphology of many non-rigid organs to become larger or smaller. The target object may be a lesion or a non-rigid body organ. The medical image registration system takes the rigid registration result as the reference of the positioning of the space region in the image, and then carries out non-rigid registration on the target object, thereby greatly improving the accuracy of the non-rigid registration of the target object.
Optionally, the non-rigid registration of the target object according to the rigid registration result may include: optionally, the non-rigid registration of the target object according to the rigid registration result includes: acquiring a motion function of each pixel unit according to the rigid registration result; determining a matching function according to the motion function of the pixel unit; determining a limiting function according to the motion function and the spatial texture feature of the pixel unit; and matching the target object according to the matching function and the limiting function.
The medical image registration system firstly establishes a space motion field according to a rigid registration result and estimates a motion function of each pixel unit. The pixel unit may be a pixel point or a pixel region. The motion function in pixel units is as follows:
the system determines a matching function from the motion function in pixel units. The matching function is as follows:
wherein
The medical image registration system determines a limit function according to the motion function and the spatial texture feature of the pixel unit. Taking the relative gray texture feature as an example of the spatial texture feature, a constraint function is set for the motion function and the relative gray texture feature based on each pixel unit to determine the motion trajectory of the non-rigid body.
The limiting function is
Wherein
Is a weight parameter;
is the pixel value for the current pixel location,
pixel values corresponding to approximate locations of the matched image.
And the medical image registration system matches the target object according to the matching function and the limiting function.
Finding the best matching point based on the above matching function and constraint function, the best matching point should satisfy the point as
Is the maximum value of, i.e. the matching point is satisfied
Fig. 3A and 3B are schematic non-rigid registration diagrams of a medical image registration method according to an embodiment of the present application. Fig. 3A is a first image, and fig. 3B is a second image. The medical image registration system performs rigid registration on the non-rigid target organ in fig. 3A and 3B. The target organ expansion as indicated by the arrows can be seen in fig. 3A and 3B. By pairing the target organs of fig. 3A and 3B, the pixel units of the target organs in the first and second images can be associated.
Optionally, the method may further include: and obtaining a differential subtraction image of the first image and the second image according to the non-rigid registration result.
The differential subtraction refers to a difference image of two images obtained by subtracting two registered images of the same subject. By subtracting the registered first image and second image, the medical image registration system may obtain a differential subtraction image of the first image and the second image. The medical image registration system can display the differential subtraction image to a reader through a screen and the like. The reader can clearly find the focus through the differential subtraction image, and the progress of the disease is evaluated according to the change area of the focus.
Fig. 4A-4D are schematic diagrams of a first image and a differential subtraction image of a medical image registration method according to an embodiment of the present application. Fig. 4A and 4B are two first images of different sources, respectively, fig. 4C is a differential subtraction image of the first image 4A and a corresponding second image (not shown), and fig. 4D is a differential subtraction image of the first image 4B and a corresponding second image (not shown). The white dots indicated by the arrows in fig. 4A-4D represent nodules of the target organ, which are the lesion objects to be observed in the medical image. In fig. 4A and 4B, it can be seen that, in addition to the nodule, white dots formed by blood vessels interfere with the judgment of the viewer on the nodule. However, after the differential subtraction processing, the white spot regions formed by the blood vessels in fig. 4C and 4D are greatly reduced, and the viewer can more clearly judge and see the progressing nodules.
Optionally, the method may further comprise one or more of the following steps: measuring a change region of the target object according to the difference subtraction image; and saving the measurement results in the corresponding form.
The medical image registration system may measure a region of change of the target object based on the differential subtraction image. By automatically measuring the change area of the target object, the progress of the focus area can be intelligently evaluated, the film reading efficiency is improved, and errors possibly caused by manual measurement are reduced. After the change area of the target object is measured, the medical image registration system can also store the measurement result in a corresponding form, so that the progress of the focus area can be intelligently evaluated, the film reading efficiency is improved, and errors possibly caused by manual measurement are reduced. Fig. 5 is a schematic diagram illustrating measurement of a differential subtraction image according to an embodiment of the present application. As shown in fig. 5, the system measures the lesion area (white dashed area in the figure) for the reader to assess tumor progression. Fig. 6 is a table diagram illustrating measurement results of a difference subtraction image of a medical image registration method according to an embodiment of the present application. As shown in fig. 6, the system saves the lesion measurements in a corresponding lesion form.
In summary, the medical image registration method of the embodiment of the application greatly improves the matching accuracy of the target object by performing rigid registration and then performing non-rigid registration on the medical image, thereby improving the accuracy of lesion progress evaluation during reading; by using the rigid organ to perform rigid registration, the matching accuracy of the target object is further improved, and the accuracy of lesion progress evaluation during radiographing is further improved.
The present application further provides a medical image registration system, comprising: a memory for storing instructions executable by the processor; and a processor for executing the instructions to implement the medical image registration method as described above.
Fig. 7 illustrates a system block diagram of a medical image registration system according to an embodiment of the present application. The medical image registration system 700 may include an internal communication bus 701, a Processor (Processor) 702, a Read Only Memory (ROM) 703, a Random Access Memory (RAM) 704, a communication port 705, and a hard disk 707. The internal communication bus 701 may enable data communication among the components of the medical image registration system 700. The processor 702 may make the determination and issue the prompt. In some embodiments, the processor 702 may be comprised of one or more processors. The communication port 705 can enable the medical image registration system 700 to communicate data with the outside. In some embodiments, the medical image registration system 700 may send and receive information and data from a network through the communication port 705. The medical image registration system 700 may also include various forms of program storage units and data storage units, such as a hard disk 707, Read Only Memory (ROM) 703 and Random Access Memory (RAM) 704, capable of storing various data files for computer processing and/or communication, and possibly program instructions for execution by the processor 702. The processor executes these instructions to implement the main parts of the method. The results processed by the processor are communicated to the user device through the communication port and displayed on the user interface.
The medical image registration method described above can be implemented as a computer program, stored in the hard disk 707, and can be recorded to the processor 702 for execution to implement the method of the present application.
The present application also provides a computer readable medium having stored thereon computer program code which, when executed by a processor, implements a medical image registration method as described above.
The medical image registration method, when implemented as a computer program, may also be stored as an article of manufacture in a computer-readable storage medium. For example, computer-readable storage media can include but are not limited to magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips), optical disks (e.g., Compact Disk (CD), Digital Versatile Disk (DVD)), smart cards, and flash memory devices (e.g., electrically Erasable Programmable Read Only Memory (EPROM), card, stick, key drive). In addition, various storage media described herein can represent one or more devices and/or other machine-readable media for storing information. The term "machine-readable medium" can include, without being limited to, wireless channels and various other media (and/or storage media) capable of storing, containing, and/or carrying code and/or instructions and/or data.
It should be understood that the above-described embodiments are illustrative only. The embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, and/or other electronic units designed to perform the functions described herein, or a combination thereof.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing disclosure is by way of example only, and is not intended to limit the present application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. The processor may be one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), digital signal processing devices (DAPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or a combination thereof. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips … …), optical disks (e.g., Compact Disk (CD), Digital Versatile Disk (DVD) … …), smart cards, and flash memory devices (e.g., card, stick, key drive … …).
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Although the present application has been described with reference to the present specific embodiments, it will be recognized by those skilled in the art that the foregoing embodiments are merely illustrative of the present application and that various changes and substitutions of equivalents may be made without departing from the spirit of the application, and therefore, it is intended that all changes and modifications to the above-described embodiments that come within the spirit of the application fall within the scope of the claims of the application.
Claims (9)
1. A medical image registration method, comprising the steps of:
acquiring a first image and a second image;
extracting rigid organs in the first image and the second image;
performing rigid registration on the rigid body organ according to the extraction result;
acquiring a motion function of each pixel unit according to the rigid registration result;
determining a matching function according to the motion function of the pixel unit, wherein the matching function is
Wherein
Is a weight coefficient; x, y and z are coordinates of the pixel unit in the first image on an x axis, a y axis and a z axis respectively; x ', y ', z ' are coordinates of an approximate pixel unit in the second image corresponding to the pixel unit on an x axis, a y axis and a z axis respectively; m, n and l are respectively a perception field range parameter;
the pixel value of the position of the pixel unit in the first image;
a pixel value that is an approximate pixel unit in the second picture corresponding to the pixel unit;
determining a limiting function according to the motion function and the spatial texture feature of the pixel unit, wherein the limiting function is
Wherein
Is a weight parameter; and
and matching the target object according to the matching function and the limiting function.
2. The method of claim 1, further comprising: and obtaining a differential subtraction image of the first image and the second image according to a non-rigid registration result.
3. The method of claim 1, wherein the extraction algorithm to extract the rigid body organ in the first image and the second image is:
wherein (x, y, z) is the coordinates of the pixels in the first image and the second image, and T1 is a predetermined density threshold; image (x, y, z) is a value of a pixel of the first Image and a pixel of the second Image; OriMask (x, y, z) is a collection of high density pixels.
4. The method of claim 3, wherein said extracting the rigid body organ in the first image and the second image further comprises:
and optimizing the extraction result by using an image three-dimensional low-pass filtering algorithm.
5. The method of claim 1, wherein said rigidly registering the rigid body organ according to the extraction results comprises:
acquiring a central operator, a standard central operator and a rotation, scaling and translation invariant operator according to the extraction result; and
and pairing the rigid body organs in the first image and the second image according to the coincidence center operator, the standard center operator, the rotation, scaling and translation invariant operator and a preset loss function.
6. The method of claim 1, wherein the first image and the second image are medical images of the same modality or different modalities.
7. The method of claim 2, further comprising one or more of the following steps:
measuring a change area of the target object according to the differential subtraction image; and
the measurement results are saved in the corresponding form.
8. A medical image registration system, comprising:
a memory for storing instructions executable by the processor; and
a processor for executing the instructions to implement the method of any one of claims 1-7.
9. A computer-readable medium having stored thereon computer program code which, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010503362.8A CN111402305B (en) | 2020-06-05 | 2020-06-05 | Medical image registration method, system and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010503362.8A CN111402305B (en) | 2020-06-05 | 2020-06-05 | Medical image registration method, system and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111402305A CN111402305A (en) | 2020-07-10 |
| CN111402305B true CN111402305B (en) | 2020-09-11 |
Family
ID=71414087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010503362.8A Active CN111402305B (en) | 2020-06-05 | 2020-06-05 | Medical image registration method, system and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111402305B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734710A (en) * | 2020-12-30 | 2021-04-30 | 上海睿刀医疗科技有限公司 | Device and system for constructing focus recognition model based on historical pathological information |
| CN112837226B (en) * | 2021-01-15 | 2023-11-07 | 深圳市铱硙医疗科技有限公司 | Morphology-based mid-brain sagittal plane extraction method, system, terminal and medium |
| CN112927274A (en) * | 2021-02-02 | 2021-06-08 | 深圳蓝韵医学影像有限公司 | Dual-energy subtraction image registration method, device and equipment and readable storage medium |
| CN115018795B (en) * | 2022-06-09 | 2023-04-07 | 北京医准智能科技有限公司 | Method, device and equipment for matching focus in medical image and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109074639A (en) * | 2015-10-19 | 2018-12-21 | 上海联影医疗科技有限公司 | Figure registration system and method in medical image system |
| CN110782428A (en) * | 2019-09-20 | 2020-02-11 | 浙江未来技术研究院(嘉兴) | Method and system for constructing clinical brain CT image ROI template |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886508B (en) * | 2017-11-23 | 2021-11-23 | 上海联影医疗科技股份有限公司 | Differential subtraction method and medical image processing method and system |
-
2020
- 2020-06-05 CN CN202010503362.8A patent/CN111402305B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109074639A (en) * | 2015-10-19 | 2018-12-21 | 上海联影医疗科技有限公司 | Figure registration system and method in medical image system |
| 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 |
| CN110782428A (en) * | 2019-09-20 | 2020-02-11 | 浙江未来技术研究院(嘉兴) | Method and system for constructing clinical brain CT image ROI template |
Non-Patent Citations (1)
| Title |
|---|
| 《Non-Rigid Registration of Images With Geometric and Photometric Deformation by Using Local Affine Fourier-Moment Matching》;Su Hong-Ren等;《Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition》;20151231;第2874-2882页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111402305A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111402305B (en) | Medical image registration method, system and computer readable medium | |
| JP6059261B2 (en) | Intelligent landmark selection to improve registration accuracy in multimodal image integration | |
| CN112967236B (en) | Image registration method, device, computer equipment and storage medium | |
| CN106340015B (en) | A kind of localization method and device of key point | |
| JP4640845B2 (en) | Image processing apparatus and program thereof | |
| CN106651827A (en) | Fundus image registering method based on SIFT characteristics | |
| JP2016531709A (en) | Image analysis technology for diagnosing disease | |
| EP1941453A2 (en) | Method of registering images, algorithm for carrying out the method of registering images, a program for registering images using the said algorithm and a method of treating biomedical images to reduce imaging artefacts caused by object movement | |
| CN112907642B (en) | Registration and superposition method, system, storage medium and equipment | |
| WO2007095165A1 (en) | System and method for image-based tree matching and registration | |
| Urschler et al. | SIFT and shape context for feature-based nonlinear registration of thoracic CT images | |
| WO2003046817A1 (en) | Detection and analysis of lesions in contact with a structural boundary | |
| KR20140114303A (en) | System and method for automatic planning of two-dimensional views in 3d medical images | |
| US20190392552A1 (en) | Spine image registration method | |
| EP4156096A1 (en) | Method, device and system for automated processing of medical images to output alerts for detected dissimilarities | |
| CN110782489A (en) | Image data matching method, device and equipment and computer readable storage medium | |
| CN111899850A (en) | Medical image information processing method, display method and readable storage medium | |
| JP5364009B2 (en) | Image generating apparatus, image generating method, and program thereof | |
| US11551371B2 (en) | Analyzing symmetry in image data | |
| Liu et al. | Automated binocular vision measurement of food dimensions and volume for dietary evaluation | |
| CN110136095A (en) | Liver three-dimensional CT image lesion region automatic extracting system and method | |
| WO2014106747A1 (en) | Methods and apparatus for image processing | |
| Urschler et al. | Assessing breathing motion by shape matching of lung and diaphragm surfaces | |
| CN115222878A (en) | Scene reconstruction method applied to lung bronchoscope surgical robot | |
| CN113658106A (en) | Liver focus automatic diagnosis system based on abdomen enhanced CT |
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 | ||
| CP03 | "change of name, title or address" |
Address after: 314000 3 storeys, Building 9, Intelligent Industry Innovation Park, 36 Changshengnan Road, Jiaxing Economic and Technological Development Zone, Zhejiang Province Patentee after: Zhejiang Taimei Medical Technology Co., Ltd Address before: 314001 3rd floor, building 9, smart industry innovation park, 36 Changsheng South Road, Jiaxing City, Zhejiang Province Patentee before: MOBILEMD SYSTEM (JIAXING) Co.,Ltd. |
|
| CP03 | "change of name, title or address" |