WO2020087257A1 - 图像引导方法及装置、医疗设备、计算机可读存储介质 - Google Patents
图像引导方法及装置、医疗设备、计算机可读存储介质 Download PDFInfo
- Publication number
- WO2020087257A1 WO2020087257A1 PCT/CN2018/112586 CN2018112586W WO2020087257A1 WO 2020087257 A1 WO2020087257 A1 WO 2020087257A1 CN 2018112586 W CN2018112586 W CN 2018112586W WO 2020087257 A1 WO2020087257 A1 WO 2020087257A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- dimensional
- registration
- magnetic resonance
- dimensional image
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/38—Registration of image sequences
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/1048—Monitoring, verifying, controlling systems and methods
- A61N5/1049—Monitoring, verifying, controlling systems and methods for verifying the position of the patient with respect to the radiation beam
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
Definitions
- the present disclosure relates to the field of medical imaging, and in particular to an image guidance method and device, medical equipment, and computer-readable storage media.
- the movement of the target area in the same treatment fraction will cause the focus position of the treatment beam to deviate from the treatment target area.
- the deviation between the focus position of the treatment beam and the target area can be determined based on the images collected in real time through image guidance technology, so that this deviation can be corrected.
- the images used to characterize the initial position state and current position state of the lesion generally require the same or similar imaging technology, such as X-ray transmission imaging technology and computer tomography based on X-ray irradiation Scanning (Computed Tomography, CT) imaging technology, so that accurate and fast image registration can be achieved, and the above-mentioned position deviation can be determined in time.
- imaging technology such as X-ray transmission imaging technology and computer tomography based on X-ray irradiation Scanning (Computed Tomography, CT) imaging technology
- the images obtained by Magnetic Resonance Imaging can more clearly represent the distribution of soft tissues, and are more conducive to the precise location of the lesions. Therefore, it has a good performance in the field of image guidance Application prospects.
- the digital projection images generated by MRI cannot be accurately and quickly registered with the X-ray transmission images taken in real time, so it is difficult to apply MRI technology to real-time During the image boot process.
- the present disclosure provides an image guidance method and apparatus, medical equipment, and computer-readable storage medium, which can implement real-time image guidance incorporating MRI.
- the present disclosure provides an image guidance method, the method including:
- the reference three-dimensional image is a computer tomography image after three-dimensional reconstruction
- Image guidance is performed on the basis of using the reference three-dimensional image to characterize the initial position state.
- the method before performing image guidance on the basis of using the reference three-dimensional image to represent the initial position state, the method further includes:
- the registration result of the three-dimensional to three-dimensional registration is output, so that the deviation of the positioning between the magnetic resonance image and the reference three-dimensional image is corrected.
- the method before outputting the registration result of the three-dimensional to three-dimensional registration, so that the positional deviation between the magnetic resonance image and the reference three-dimensional image is corrected, the method further includes:
- the reference three-dimensional image is a cone beam computed tomography image after three-dimensional reconstruction; three-dimensional three-dimensional registration is performed on the three-dimensional magnetic resonance image and the reference three-dimensional image to Before the marking of the area range of each object of interest in the reference three-dimensional image, the method further includes:
- the image guidance based on using the reference three-dimensional image to represent the initial position state includes:
- the registration result of the two-dimensional to three-dimensional registration is output, so that the relative position deviation between the target individual between the reference three-dimensional image and the X-ray transmission images collected at the two different angles is corrected.
- an image guidance device which includes:
- a first acquisition module configured to acquire a three-dimensional magnetic resonance image of the target individual, where the three-dimensional magnetic resonance image is marked with an area of at least one object of interest;
- a second acquisition module configured to acquire a reference three-dimensional image of the target individual, the reference three-dimensional image is a computed tomography image after three-dimensional reconstruction;
- a registration module configured to perform three-dimensional to three-dimensional registration on the three-dimensional magnetic resonance image and the reference three-dimensional image to complete the marking of the area range of each object of interest in the reference three-dimensional image;
- the image guidance module is configured to perform image guidance based on using the reference three-dimensional image to characterize the initial position state.
- the device further includes:
- An output module for outputting the registration result of the three-dimensional three-dimensional registration before image guidance based on using the reference three-dimensional image to represent the initial position state, so as to position the magnetic resonance image and the reference three-dimensional image The deviation is corrected.
- the second acquiring module is further configured to: before outputting the registration result of the three-dimensional to three-dimensional registration, re-acquire the registration result when the registration accuracy of the registration result does not meet the application conditions The reference three-dimensional image of the target individual.
- the reference three-dimensional image is a cone beam computed tomography image after three-dimensional reconstruction; the device further includes:
- the image processing module is configured to remove a part of the reference three-dimensional image where image artifacts exist before performing three-dimensional three-dimensional registration on the three-dimensional magnetic resonance image and the reference three-dimensional image.
- the image guidance module includes:
- An acquisition unit used to acquire X-ray transmission images collected at two different angles
- a registration unit configured to perform two-dimensional to three-dimensional registration on the reference three-dimensional image and the X-ray transmission images acquired at the two different angles;
- the output unit is used to output the registration result of the two-dimensional to three-dimensional registration, so that the relative position deviation of the target individual between the reference three-dimensional image and the X-ray transmission images collected at the two different angles is obtained Correction.
- the present disclosure also provides a medical device including a processor and a memory, the memory stores program instructions, and the processor is configured to call the program instructions in the memory to perform the above Any kind of image guidance method.
- the present disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, the program instructions being configured to be executed when executed by a processor
- the processor executes any of the above image guidance methods.
- the present disclosure can mark the area of the object of high accuracy in the magnetic resonance image in the reference three-dimensional image through three-dimensional to three-dimensional registration between the magnetic resonance image and the reference three-dimensional image, thereby
- the image guidance process that uses the reference three-dimensional image to characterize the initial position state can enjoy the benefits brought by the high soft tissue contrast resolution of MRI, that is, the introduction of MRI in real-time image guidance is realized, and the advantages of MRI technology can be used to better Conduct real-time image guidance.
- FIG. 1 is a schematic flowchart of an image guidance method provided by an embodiment of the present disclosure
- FIG. 2 is a schematic flowchart of an image guidance method provided by yet another embodiment of the present disclosure.
- FIG. 3 is a structural block diagram of an image guidance device provided by an embodiment of the present disclosure.
- FIG. 4 is a structural block diagram of a medical device provided by an embodiment of the present disclosure.
- FIG. 1 is a schematic flowchart of an image guidance method provided by an embodiment of the present disclosure. Referring to FIG. 1, in the image guidance method:
- step 101 a three-dimensional magnetic resonance image of a target individual is acquired.
- the three-dimensional magnetic resonance image at least one area of interest is marked.
- a reference three-dimensional image of the target individual is obtained.
- the reference three-dimensional image is a computed tomography image after three-dimensional reconstruction.
- step 103 three-dimensional to three-dimensional registration is performed on the three-dimensional magnetic resonance image and the reference three-dimensional image to complete the marking of the area range of each object of interest in the reference three-dimensional image.
- step 104 image guidance is performed on the basis of using the reference three-dimensional image to represent the initial position state.
- the method of the embodiment of the present disclosure can be applied to any medical activity including image guidance, such as image-guided radiotherapy (Image-Guided Radio Therapy, IGRT), intracranial tumor resection surgery, or other image guidance. Surgery, etc.
- image guidance such as image-guided radiotherapy (Image-Guided Radio Therapy, IGRT), intracranial tumor resection surgery, or other image guidance. Surgery, etc.
- the target individual refers to the object of implementation of these medical activities, for example, a patient who needs radiotherapy or surgery.
- the image guidance method may be installed on medical equipment (eg, radiotherapy equipment, image guidance medical equipment, operating table, etc.) in the form of software, so as to realize the image guidance process in medical activities.
- the three-dimensional Magnetic Resonance (MR) image may be a three-dimensional image obtained mainly by imaging the target individual using MRI technology, which may be obtained from the imaging device through the communication connection of the above medical device It may also be obtained by imaging the medical device itself; the reference three-dimensional image may be a three-dimensional image obtained by three-dimensional reconstruction after imaging the target individual using imaging techniques such as computer tomography (Computed Tomography, CT). It can be received by the medical device from the imaging device through the communication connection and processed, or it can be received from the image processing device through the communication connection, or it can be the medical device itself after imaging and processing owned.
- MRI Magnetic Resonance
- the computer tomography technology can be cone beam computer tomography (Cone beam CT, CBCT) technology, single-layer spiral computer tomography (SingleSliceheliealCT, SSCT) technology, multi-layer spiral computer tomography (MultiSliecsheliealCT) , MSCT) technology, etc.
- Cone beam CT cone beam computer tomography
- CBCT cone beam computer tomography
- SingleSliceheliealCT single-layer spiral computer tomography
- SSCT single-layer spiral computer tomography
- MultiSliecsheliealCT multi-layer spiral computer tomography
- MSCT multi-layer spiral computer tomography
- the area of the object of interest is manually selected by the user in the magnetic resonance image, for example, the area of the lesion in radiotherapy, the position of an anatomical point, or the tumor and its tumor during intracranial tumor resection The area of peripheral vascular tissue, etc.
- the medical device displays the three-dimensional magnetic resonance image and provides an area selection tool, so that the user selects each object of interest by operating on the medical device geographic range.
- the medical device described above receives a magnetic resonance image of the area range where each object of interest has been marked from the imaging device. Based on the magnetic resonance image that can clearly show the characteristics of the soft tissue distribution, the area of the target object marked in the magnetic resonance image can have higher accuracy than in other types of images.
- image registration refers to seeking an (or a series of) spatial transformations for one image so that it is spatially consistent with the corresponding point on another image. That is, the above three-dimensional to three-dimensional registration refers to seeking one or a series of spatial transformations so that the magnetic resonance image can coincide with the reference three-dimensional image through such spatial transformation. It should be noted that the 3D-3D registration can be performed only in the spatial region concerned by medical activities to save the algorithm cost; similarly, the magnetic resonance image and the reference 3D image can also be performed only in the spatial region concerned by medical activities Acquisition to shorten imaging time and reduce exposure dose.
- the result of image registration can be expressed as the relative position coordinates of the same positioning point (or the same name point, which can include, for example, anatomical points or image feature points) between images, or can be expressed as
- the transformation matrix can also be expressed as a correspondence table between each image region of the same name in the image, and may not be limited to this.
- the initial position state refers to the position of the target individual before or at the beginning of the treatment activity, and corresponds to the current position state of the target individual during the treatment activity (the two positions can be, for example, (The movable coordinates of the movable bed relative to the bottom support structure are represented).
- the acquired image can be compared with the reference three-dimensional image, thereby providing the information required for medical activities, such as the deviation between the focus position of the treatment beam and the target area position in radiotherapy, or Whether the part to be removed moves during surgery, etc.
- the embodiments of the present disclosure can mark the area of the object of interest in the magnetic resonance image with high accuracy in the reference three-dimensional image through three-dimensional to three-dimensional registration between the magnetic resonance image and the reference three-dimensional image, thereby
- the image guidance process that uses the reference three-dimensional image to characterize the initial position state can enjoy the benefits brought by the high soft tissue contrast resolution of MRI, that is, the introduction of MRI in real-time image guidance is realized, and the advantages of MRI technology can be used to better Conduct real-time image guidance.
- FIG. 2 is a schematic flowchart of an image-guided method provided by yet another embodiment of the present disclosure. Referring to Fig. 2, the method is performed by a radiotherapy device, in this method:
- step 201 a three-dimensional magnetic resonance image of the target individual is acquired.
- medical personnel before the start of radiotherapy, medical personnel operate an MRI device to perform three-dimensional imaging of the chest of the target individual (lung cancer patient) to obtain a three-dimensional magnetic resonance image of the chest of the target individual, and based on the connection between the devices Transfer the magnetic resonance image to the computer.
- the medical staff operates the computer to delineate each lesion area in the magnetic resonance image as the area range of at least one object of interest marked in the three-dimensional magnetic resonance image.
- the control system of the radiotherapy device receives the magnetic resonance images marked with each lesion area from the computer device, and completes the three-dimensional magnetic resonance image.
- step 202 a reference three-dimensional image of the target individual is obtained.
- medical personnel before the start of radiation therapy, medical personnel perform a pre-treatment position on the target individual, for example, change the posture and position of the target individual under the guidance of the laser line released by the radiotherapy device so that the laser line is aligned with the target individual's Corresponding parts.
- medical personnel operate the CBCT system in the radiotherapy equipment to perform CBCT imaging on the chest of the target individual.
- the control system of the radiotherapy device receives the obtained CBCT image data to obtain three-dimensional volume data of the chest of the target individual through three-dimensional reconstruction as the reference three-dimensional image.
- the radiotherapy device may output a prompt to the user to guide the removal of the region of interest (ROI) during the 3D reconstruction process
- ROI region of interest
- step 203 three-dimensional to three-dimensional registration is performed on the three-dimensional magnetic resonance image and the reference three-dimensional image to complete the marking of the area range of each object of interest in the reference three-dimensional image.
- the radiotherapy apparatus after acquiring the magnetic resonance image and the reference three-dimensional image, performs three-dimensional to three-dimensional image registration on the magnetic resonance image and the reference three-dimensional image.
- the above three-dimensional to three-dimensional image registration includes iteratively seeking the optimal transformation relationship between the magnetic resonance image and the reference three-dimensional image, and using the registration accuracy as a sign to indicate whether to continue the iteration.
- the registration accuracy reaches the specified level, the iteration is stopped, and the resulting transformation relationship is output as the registration result.
- the area range of each object of interest in the magnetic resonance image can be transformed into the area range of each object of interest in the reference three-dimensional image to complete the area of each object of interest in the Refer to the mark in the 3D image.
- step 204 when the registration accuracy of the registration result does not satisfy the application condition, the reference three-dimensional image of the target individual is newly acquired.
- the maximum number of iterations is set during the above iteration process.
- the iteration is stopped and the process returns to step 202 to reacquire the reference three-dimensional image.
- the above application conditions that is, "registration accuracy reaches a specified level”
- registration accuracy can be set according to actual application requirements. It should be understood that for the case where the number of iterations reaches the maximum number of iterations and the registration accuracy is still lower than the specified level, it can be considered that the difference between the reference 3D image and the magnetic resonance image is too large at this time to find a reasonable image Transformation relationship. Therefore, by reacquiring the reference three-dimensional image in this case and repeating the intermediate process, the accuracy of the area range of each object of interest in the reference three-dimensional image can be improved on the basis of ensuring registration accuracy.
- step 205 the registration result of the three-dimensional to three-dimensional registration is output, so that the deviation of the positioning between the magnetic resonance image and the reference three-dimensional image is corrected.
- the radiotherapy device may output the registration result to prompt the medical staff to move the bed, thereby correcting the positional deviation between the reference three-dimensional image and the magnetic resonance image.
- the magnetic resonance image is standardized, so the magnetic resonance image can represent the standard position of the swing. Therefore, in the case where the registration accuracy of the reference three-dimensional image and the magnetic resonance image satisfies the application conditions, it can be considered that the registration result represents the deviation between the current positioning position and the standard positioning position, which can be carried out accordingly Move the bed to reach the standard position. Based on the above process, it can help reduce the position deviation.
- Steps 206 to 208 are processes performed during the treatment of each target. In this process:
- step 206 X-ray transmission images acquired at two different angles are acquired.
- the radiotherapy device can perform X-ray transmission imaging at two different angles on the chest of the target individual under the operation of medical personnel (the two angles are called the first angle and the second angle, respectively) to obtain two A set of X-ray transmission images, the two sets of X-ray transmission images jointly characterize the current position status of the target individual.
- step 207 two-dimensional to three-dimensional registration is performed on the reference three-dimensional image and the X-ray transmission images acquired at the two different angles.
- the above 2D-3D registration process includes: using a ray casting algorithm to generate a digitally reconstructed image (Digitally Reconstructed Radiograph, DRR) based on the reference 3D image at a first angle and a second angle, respectively.
- DRR Digitally Reconstructed Radiograph
- the obtained two sets of digitally reconstructed images are compared with the above two sets of X-ray transmission images, and the spatially transformed parameters are optimized according to the comparison results, so that two sets of digital reconstructions are regenerated according to the optimized parameters Image and repeat the above process (iteration) until the termination condition is met and the optimized spatial transformation parameters are output as the registration result of the 2D-3D registration.
- step 208 the registration result of the two-dimensional to three-dimensional registration is output so that the relative position deviation between the target individual between the reference three-dimensional image and the X-ray transmission images collected at the two different angles is obtained Correction.
- the relative position deviation may be due to the overall movement of the target individual during the time period between taking the reference three-dimensional image and taking the two X-ray transmission images, or may be due to the relative internal organization of the target individual.
- the movement of the target individual may not be limited to this.
- the above-mentioned relative position deviation specifically refers to the deviation between the current target position and its reference position (that is, the target position determined according to the reference three-dimensional image).
- the above-mentioned relative position deviation may have different meanings, and the purpose of outputting the registration result of the above-mentioned 2D-3D registration may not be limited to correcting the above relative position deviation (it may also be, for example Track the movement of the object within the target individual, or obtain the actual removal of the part to be removed).
- the radiotherapy device may output the registration result of the two-dimensional to three-dimensional registration to the medical personnel to represent the deviation between the focus position of the treatment beam and the position of the target area at the current moment.
- the radiotherapy device can move the bed according to the registration result under the operation of medical personnel to correct this deviation; when this deviation is greater than or equal to the predetermined threshold , You can continue treatment without moving the bed.
- the predetermined threshold may be determined according to actual application scenarios and application requirements.
- the treatment process of each target can be completed in sequence, so as to finally complete the entire image guidance process.
- the embodiments of the present disclosure can mark the area of the object of interest in the magnetic resonance image with high accuracy in the reference three-dimensional image through three-dimensional to three-dimensional registration between the magnetic resonance image and the reference three-dimensional image, thereby
- the image guidance process that uses the reference three-dimensional image to characterize the initial position state can enjoy the benefits brought by the high soft tissue contrast resolution of MRI, that is, the introduction of MRI in real-time image guidance is realized, and the advantages of MRI technology can be used to better Conduct real-time image guidance.
- the above image guidance method skips the steps 201, 203, 204, and 205 on the basis of FIG. 2 and directly uses the reference three-dimensional image obtained by three-dimensional reconstruction of the CBCT image data for image guidance.
- the reference to the three-dimensional image may not accurately locate the area of each object of interest, which will bring certain difficulties and uncertainties to the radiotherapy; on the other hand, the initial positioning error will not be corrected, This may affect the accuracy of radiotherapy.
- the embodiments of the present disclosure can use magnetic resonance images to provide precise positioning of the area range of each object of interest, and can help correct initial positioning errors, so that radiation therapy can be more accurate and easy to perform.
- F is the conversion factor
- ⁇ is the attenuation coefficient of X-rays in the tissue
- ⁇ water is the attenuation coefficient of X-rays in water.
- I 0 is the initial intensity of X-ray
- ⁇ i is the linear attenuation coefficient of tissue i
- l i is the length of X-ray passing through tissue i
- I is the intensity of X-ray after passing through the three-dimensional volume data.
- MRI cannot generally be applied to real-time image guidance, and its high soft tissue contrast resolution cannot benefit the effect of image guidance.
- the embodiments of the present disclosure in turn utilize the 3D-3D registration between the magnetic resonance image and the reference 3D image, so that the advantages of MRI can be applied indirectly to the real-time image guidance through the reference 3D image, so that the real-time image guidance does not need to be repeated
- a large number of time-consuming imaging processes of MRI can also enjoy the benefits of the advantages of MRI, which helps to achieve real-time image guidance with better results.
- the image guiding device includes:
- the first acquiring module 31 is configured to acquire a three-dimensional magnetic resonance image of the target individual, and the three-dimensional magnetic resonance image is marked with an area of at least one object of interest;
- the second acquisition module 32 is used to acquire a reference three-dimensional image of the target individual, where the reference three-dimensional image is a computed tomography image after three-dimensional reconstruction;
- the registration module 33 is configured to perform three-dimensional to three-dimensional registration on the three-dimensional magnetic resonance image and the reference three-dimensional image to complete the marking of the area range of each object of interest in the reference three-dimensional image;
- the image guidance module 34 is configured to perform image guidance based on using the reference three-dimensional image to characterize the initial position state.
- the device further includes:
- An output module for outputting the registration result of the three-dimensional three-dimensional registration before image guidance based on using the reference three-dimensional image to represent the initial position state, so as to position the magnetic resonance image and the reference three-dimensional image The deviation is corrected.
- the second obtaining module 32 is further configured to: before outputting the registration result of the three-dimensional registration, when the registration accuracy of the registration result does not satisfy the application conditions, re-acquire all The reference three-dimensional image of the target individual.
- the reference three-dimensional image is a cone beam computed tomography image after three-dimensional reconstruction; the device further includes:
- the image processing module is configured to remove a part of the reference three-dimensional image where image artifacts exist before performing three-dimensional three-dimensional registration on the three-dimensional magnetic resonance image and the reference three-dimensional image.
- the image guidance module 34 includes:
- An acquisition unit used to acquire X-ray transmission images collected at two different angles
- a registration unit configured to perform two-dimensional to three-dimensional registration on the reference three-dimensional image and the X-ray transmission images acquired at the two different angles;
- the output unit is used to output the registration result of the two-dimensional to three-dimensional registration, so that the relative position deviation of the target individual between the reference three-dimensional image and the X-ray transmission images collected at the two different angles is obtained Correction.
- the image guidance apparatus may implement any one of the above image guidance methods through corresponding configurations and configurations, and specific details are not described in detail.
- the image guidance device is presented in the form of a functional unit / functional module.
- "Unit / module” here may refer to an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a processor and memory that execute one or more software or firmware programs, integrated logic circuits, and / or others that can provide the above functions Device.
- ASIC Application Specific Integrated Circuit
- the processor may execute one or more software or firmware programs, integrated logic circuits, and / or others that can provide the above functions Device.
- at least part of the functions of at least one of the mentioned units and modules may be implemented by the processor executing the program code stored in the memory.
- the medical device includes a processor 41 and a memory 42.
- the memory 42 stores program instructions.
- the processor 41 is configured to call the program instructions in the memory 42 to perform any of the above image guidance. method.
- the processor 41 may include a central processing unit (CPU, single-core or multi-core), a graphics processor (GPU), a microprocessor, an application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC), a digital signal processor (DSP), Digital signal processing equipment (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, or multiple integrated circuits for controlling program execution.
- CPU central processing unit
- GPU graphics processor
- microprocessor an application-specific integrated circuit
- ASIC Application-Specific Integrated Circuit
- DSP digital signal processor
- DSPD Digital signal processing equipment
- PLD programmable logic device
- FPGA field programmable gate array
- controller microcontroller, or multiple integrated circuits for controlling program execution.
- the memory 42 may include read-only memory (Read-Only Memory, ROM) or other types of static storage devices that can store static information and instructions, random access memory (Random Access, Memory, RAM), or other types that can store information and instructions
- the dynamic storage device may also include electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), read-only disc (Compact Disc Read-Only Memory, CD-ROM) or other disc storage, disc storage (Including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or can be used to carry or store desired program code in the form of instructions or data structures and can be used by a computer Access to any other media, but not limited to this.
- the memory can be set independently or integrated with the processor.
- the processor 41 may include one or more CPUs.
- the above medical device may include multiple processors.
- Each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor.
- the processor here may refer to one or more devices, circuits, and / or processing cores for processing data (eg, computer program instructions).
- the above medical equipment may include a general-purpose computer equipment or a special-purpose computer equipment.
- the medical device may be any electronic device that requires medical image registration, such as a radiotherapy device, an image-guided medical device, or an operating table.
- the computer device may be a desktop computer, a portable computer, a network server, or a palmtop computer. (Personal Digital Assistant, PDA), mobile phones, tablet computers, wireless terminal equipment, communication equipment, embedded equipment or similar structured equipment.
- PDA Personal Digital Assistant
- An embodiment of the present disclosure also provides a computer storage medium for storing a computer program used in any one of the image guiding methods described above, where the computer program includes program instructions. By executing the stored program, any of the above image guidance methods provided by the present disclosure can be realized.
- the embodiments of the present disclosure may be provided as a method, an apparatus (device), or a computer program product. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.
- the computer program is stored / distributed in a suitable medium, provided with other hardware or as a part of the hardware, and may also adopt other distribution forms, such as through the Internet or other wired or wireless telecommunication systems.
- These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processing machine, or other programmable data processing device to produce a machine that enables the generation of instructions executed by the processor of the computer or other programmable data processing device
- These computer program instructions may also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, the instructions The device implements the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and / or block diagrams.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operating steps are performed on the computer or other programmable device to produce computer-implemented processing, which is executed on the computer or other programmable device
- the instructions provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and / or block diagrams.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Graphics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Radiology & Medical Imaging (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Pathology (AREA)
- Human Computer Interaction (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
一种图像引导方法及装置、医疗设备、计算机可读存储介质。所述图像引导方法包括:获取目标个体的三维的磁共振图像(101),所述三维的磁共振图像中标记有至少一个关注对象的区域范围;获取所述目标个体的参考三维图像(102),所述参考三维图像是三维重建后的计算机断层扫描图像;对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记(103);在采用所述参考三维图像表征初始位置状态的基础上进行图像引导(104)。可以实现实时图像引导中MRI的引入,并可以借助MRI技术的优势来更好地进行实时图像引导。
Description
本公开涉及医学影像领域,特别涉及一种图像引导方法及装置、医疗设备、计算机可读存储介质。
在放射治疗过程中,同一治疗分次中靶区运动会导致治疗射束聚焦位置偏离治疗靶区。针对这一问题,可以通过图像引导技术来基于实时采集的图像确定治疗射束聚焦位置与靶区位置之间的偏差,使得这一偏差能够得到校正。
在实时的图像引导过程中,用于表征病灶的初始位置状态和当前位置状态的图像一般都要求是类型相同或相近的成像技术,例如均是基于X射线照射的X光透射成像技术和计算机断层扫描(Computed Tomography,CT)成像技术,如此才能实现精确而快速的图像配准,以及时确定上述位置偏差。
相比于其他成像技术,磁共振成像(Magnetic Resonance Imaging)技术所得到的图像能够更清晰地表示软组织的分布情况,更有利于精确定位病灶的位置,因此其在图像引导领域中有着很好的应用前景。但是,由于MRI的成像过程比较耗时,并且其成像原理导致由MRI生成的数字投影图像不能与实时拍摄的X光透射图像进行精确而快速的图像配准,因此MRI技术很难实际应用到实时的图像引导过程中。
发明内容
本公开提供一种图像引导方法及装置、医疗设备、计算机可读存储介质,可以实现引入了MRI的实时图像引导。
第一方面,本公开提供了一种图像引导方法,所述方法包括:
获取目标个体的三维的磁共振图像,所述三维的磁共振图像中标记有至少一个关注对象的区域范围;
获取所述目标个体的参考三维图像,所述参考三维图像是三维重建后的计 算机断层扫描图像;
对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记;
在采用所述参考三维图像表征初始位置状态的基础上进行图像引导。
在一种可能的实现方式中,在采用所述参考三维图像表征初始位置状态的基础上进行图像引导之前,还包括:
输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正。
在一种可能的实现方式中,在输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正之前,还包括:
在配准结果的配准精度不满足应用条件时,重新获取所述目标个体的所述参考三维图像。
在一种可能的实现方式中,所述参考三维图像是三维重建后的锥形束计算机断层扫描图像;在对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记之前,所述方法还包括:
去除所述参考三维图像中存在图像伪影的部分。
在一种可能的实现方式中,所述在采用所述参考三维图像表征初始位置状态的基础上进行图像引导,包括:
获取两个不同角度下采集的X光透射图像;
对所述参考三维图像与所述两个不同角度下采集的X光透射图像进行二维-三维配准;
输出二维-三维配准的配准结果,以使所述目标个体在所述参考三维图像与所述两个不同角度下采集的X光透射图像之间的相对位置偏差得到校正。
第二方面,本公开还提供了一种图像引导装置,该装置包括:
第一获取模块,用于获取目标个体的三维的磁共振图像,所述三维的磁共振图像中标记有至少一个关注对象的区域范围;
第二获取模块,用于获取所述目标个体的参考三维图像,所述参考三维图像是三维重建后的计算机断层扫描图像;
配准模块,用于对所述三维的磁共振图像与所述参考三维图像进行三维-三 维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记;
图像引导模块,被配置为在采用所述参考三维图像表征初始位置状态的基础上进行图像引导。
在一种可能的实现方式中,所述装置还包括:
输出模块,用于在采用所述参考三维图像表征初始位置状态的基础上进行图像引导之前输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正。
在一种可能的实现方式中,所述第二获取模块还用于:在输出三维-三维配准的配准结果之前,在配准结果的配准精度不满足应用条件时,重新获取所述目标个体的所述参考三维图像。
在一种可能的实现方式中,所述参考三维图像是三维重建后的锥形束计算机断层扫描图像;所述装置还包括:
图像处理模块,用于在对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准之前去除所述参考三维图像中存在图像伪影的部分。
在一种可能的实现方式中,所述图像引导模块包括:
获取单元,用于获取两个不同角度下采集的X光透射图像;
配准单元,用于对所述参考三维图像与所述两个不同角度下采集的X光透射图像进行二维-三维配准;
输出单元,用于输出二维-三维配准的配准结果,以使所述目标个体在所述参考三维图像与所述两个不同角度下采集的X光透射图像之间的相对位置偏差得到校正。
第三方面,本公开还提供了一种医疗设备,所述医疗设备包括处理器和存储器,所述存储器中存储有程序指令,所述处理器配置为调用所述存储器中的程序指令以执行上述任意一种图像引导方法。
第四方面,本公开还提供了一种计算机可读存储介质,所述计算机存储介质存储有计算机程序,所述计算机程序包括程序指令,所述程序指令被配置为在被处理器执行时使所述处理器执行上述任意一种图像引导方法。
由上述技术方案可知,本公开可以通过磁共振图像与参考三维图像之间的三维-三维配准,来将磁共振图像中精确度很高的关注对象的区域范围标记在参考三维图像当中,从而采用该参考三维图像表征初始位置状态的图像引导过程 可以享受到MRI的高软组织对比分辨率所带来的好处,即实现了实时图像引导中MRI的引入,可以借助MRI技术的优势来更好地进行实时图像引导。
图1是本公开一个实施例提供的图像引导方法的流程示意图;
图2是本公开又一实施例提供的图像引导方法的流程示意图;
图3是本公开一个实施例提供的图像引导装置的结构框图;
图4是本公开一个实施例提供的医疗设备的结构框图。
为使本公开的原理和优点更加清楚,下面将结合附图对本公开实施方式作进一步地详细描述。显然,所描述的实施例是本公开的一部分实施例,而不是全部的实施例。除非另外定义,本公开使用的技术术语或者科学术语应当为本公开所属领域内具有一般技能的人士所理解的通常意义。本公开中使用的“第一”、“第二”以及类似的词语并不表示任何顺序、数量或者重要性,而只是用来区分不同的组成部分。
图1是本公开一个实施例提供的图像引导方法的流程示意图。参见图1,所述图像引导方法中:
在步骤101中,获取目标个体的三维的磁共振图像。其中,所述三维的磁共振图像中标记有至少一个关注对象的区域范围。
在步骤102中,获取所述目标个体的参考三维图像。其中,所述参考三维图像是三维重建后的计算机断层扫描图像。
在步骤103中,对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记。
在步骤104中,在采用所述参考三维图像表征初始位置状态的基础上进行图像引导。
需要说明的是,本公开实施例的方法可以应用于任意一种包括图像引导的医疗活动中,例如图像引导放射治疗(Image-Guided Radio Therapy,IGRT)、颅内肿瘤切除手术或者其他涉及图像引导的外科手术等。应理解的是,所述目标个体指的是这些医疗活动的实施对象,例如需要进行放射治疗或外科手术的病 人。在一个示例中,所述图像引导方法可以采用软件的形式安装在医疗设备(例如放疗设备、图像引导医疗设备、手术台等)上,从而实现医疗活动中的图像引导过程。在此基础上,所述三维的磁共振(Magnetic Resonance,MR)图像可以是主要利用MRI技术对目标个体成像后所得到的三维的图像,其可以是上述医疗设备通过通信连接从成像设备处获取得到的,也可以是该医疗设备自身成像得到的;所述参考三维图像可以是利用计算机断层扫描(Computed Tomography,CT)类的成像技术对目标个体成像后经过三维重建所得到的三维的图像,其可以是上述医疗设备通过通信连接从成像设备处接收并经过处理后得到的,也可以是上述医疗设备通过通信连接从图像处理设备处接收得到的,还可以是该医疗设备自身成像并处理后得到的。其中,计算机断层扫描类的技术可以是锥形束计算机断层扫描(Cone beam CT,CBCT)技术、单层螺旋计算机断层扫描(SingleSlice helieal CT,SSCT)技术、多层螺旋计算机断层扫描(MultiSliecs helieal CT,MSCT)技术等。
应理解的是,所述关注对象的区域范围是由用户在磁共振图像中人为选取的,例如放射治疗中病灶的区域范围、某个解剖点的位置,或者颅内肿瘤切除手术中肿瘤及其周边血管组织的区域范围,等等。在一个示例中,上述医疗设备在接收到三维的磁共振图像之后,通过显示所述三维的磁共振图像并提供区域选取工具,使得用户通过在所述医疗设备上的操作选取每个关注对象的区域范围。在又一示例中,上述医疗设备从成像设备处接收已标记每个关注对象的区域范围的磁共振图像。基于磁共振图像能够清晰表示出软组织分布的特点,上述在磁共振图像中标记出来的关注对象的区域范围相比于在其他类型的影像中可具有更高的精确度。
还应理解的是,图像配准是指对于一幅图像寻求一种(或一系列的)空间变换,使它与另一幅图像上的对应点达到空间上的一致。即,上述三维-三维配准指的是寻求一种或一系列的空间变换,使得所述磁共振图像能够通过这种空间变换与所述参考三维图像重合。需要说明的是,三维-三维配准可以仅在医疗活动所关心的空间区域内进行,以节省算法开支;类似地,磁共振图像和参考三维图像也可以仅针对医疗活动所关心的空间区域进行采集,以缩短成像时间并减少曝光剂量。还需要说明的是,图像配准的结果可以表示为同一定位点(或称同名点,可以例如包括解剖点或图像特征点)在图像之间的相对位置坐标, 也可以表示为图像之间的变换矩阵,还可以表示为图像中每个同名图像区域之间的对应关系表,并可以不仅限于此。基于所述三维-三维配准的配准结果,磁共振图像中的至少一个关注对象的区域范围可以在参考三维图像中得到标记。可理解的是,即便参考三维图像中表示出的关注对象不清晰或者根本没有表示出关注对象,只要配准精度满足应用需求,都可以基于配准结果完成每个关注对象的区域范围在参考三维图像的标记。
还应理解的是,所述初始位置状态指的是目标个体在治疗活动之前或开始时所处的位置,与治疗活动过程中目标个体所处的当前位置状态彼此对应(两个位置可以例如采用可移动病床相对于底部支撑结构的移动坐标来表示)。在图像引导过程中,可以将实施采集的图像与参考三维图像进行比较,由此提供进行医疗活动所需要的信息,比如放射治疗中治疗射束聚焦位置与靶区位置之间的偏差,或是外科手术中待切除部分是否发生移动,等等。
可以看出,本公开实施例可以通过磁共振图像与参考三维图像之间的三维-三维配准,来将磁共振图像中精确度很高的关注对象的区域范围标记在参考三维图像当中,从而采用该参考三维图像表征初始位置状态的图像引导过程可以享受到MRI的高软组织对比分辨率所带来的好处,即实现了实时图像引导中MRI的引入,可以借助MRI技术的优势来更好地进行实时图像引导。
以肺癌的图像引导放射治疗为例,图2是本公开又一实施例提供的图像引导方法的流程示意图。参见图2,该方法由放疗设备执行,在该方法中:
在步骤201中,获取目标个体的三维的磁共振图像。
在一个示例中,在放射治疗开始之前,医疗人员操作MRI设备对目标个体(肺癌患者)的胸部进行三维成像,以得到目标个体的胸部的三维的磁共振图像之后,并基于设备之间的连接将该磁共振图像传输到计算机中。此后,医疗人员通过操作计算机在该磁共振图像中勾画各个病灶区,作为上述三维的磁共振图像中标记的至少一个关注对象的区域范围。在步骤201中,基于设备之间的连接,放疗设备的控制系统从计算机设备处接收标记有各个病灶区的磁共振图像,完成所述三维的磁共振图像。
在步骤202中,获取所述目标个体的参考三维图像。
在一个示例中,在放射治疗开始之前,医疗人员对目标个体进行治疗前的摆位,例如在放疗设备释放出的激光线的引导下改变目标个体的姿势和位置使 得激光线对准目标个体的相应部位。在摆位完成之后,医疗人员操作放疗设备中的CBCT系统,以对目标个体的胸部进行CBCT成像。在步骤202中,在成像完成之后,放疗设备的控制系统接收所得到的CBCT图像数据,以通过三维重建,得到目标个体的胸部的三维体数据,作为上述参考三维图像。应理解的是,由于CBCT图像的三维重建可能存在锥束伪影,因此在三维重建过程中的选择感兴趣区域(Region Of Interest,ROI)的环节,放疗设备可以向用户输出提示以引导其去除所述参考三维图像中存在图像伪影的部分(例如CBCT图像的开始和结束部分),从而帮助提升CBCT图像的准确程度。
在步骤203中,对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记。
在一个示例中,放疗设备在获取得到所述磁共振图像和所述参考三维图像之后,对所述磁共振图像和所述参考三维图像进行三维-三维图像配准。在一个示例中,上述三维-三维图像配准包括通过迭代的方式寻求磁共振图像和参考三维图像之间的最佳变换关系,并以配准精度作为指示是否继续迭代的标志。在配准精度达到指定水平时,停止迭代,输出所得到的变换关系为配准结果。依照配准结果的变换关系,可以将磁共振图像中每个关注对象的区域范围变换为参考三维图像中的每个关注对象的区域范围,以完成每个所述关注对象的区域范围在所述参考三维图像中的标记。
在步骤204中,在配准结果的配准精度不满足应用条件时,重新获取所述目标个体的所述参考三维图像。
在一个示例中,在上述迭代过程中设定最大迭代次数,当迭代次数达到最大迭代次数而配准精度仍低于指定水平时,停止迭代并返回步骤202之前以重新获取所述参考三维图像。在该示例中,上述应用条件即“配准精度达到指定水平”,可以依照实际的应用需求进行设定。应理解的是,对于迭代次数达到最大迭代次数而配准精度仍低于指定水平的情形来说,可以认为此时的参考三维图像与磁共振图像之间的差异过大而难以找到合理的图像变换关系。由此,通过在此情形下重新获取参考三维图像并重复中间过程的方式,可以在保证配准精度的基础上提升参考三维图像中每个关注对象的区域范围的准确程度。
在步骤205中,输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正。
在一个示例中,在配准精度满足应用条件的情况下,放疗设备可以输出配准结果,以提示医疗人员进行移床,进而校正参考三维图像与磁共振图像之间的摆位偏差。一般情况下,可以认为磁共振图像是经过标准化处理的,因此磁共振图像可以代表标准的摆位位置。由此,在参考三维图像与磁共振图像的配准精度满足应用条件的情况下,可以认为配准结果代表了当前的摆位位置与标准的摆位位置之间的偏差,从而可以依此进行移床以达到标准的摆位位置。基于上述过程,可以帮助减小摆位偏差。
经过上述过程,即完成了放射治疗前的准备,可以开始依次对每一个靶点进行治疗。步骤206至步骤208是在对每一个靶点进行治疗的过程中所执行的过程,在这一过程中:
在步骤206中,获取两个不同角度下采集的X光透射图像。
在一个示例中,放疗设备可以在医疗人员的操作下对目标个体的胸部进行两个不同角度下的X光透射成像(两个角度分别称为第一角度和第二角度),以得到两个一组的X光透射图像,该两个一组的X光透射图像共同表征目标个体的当前位置状态。
在步骤207中,对所述参考三维图像与所述两个不同角度下采集的X光透射图像进行二维-三维配准。
在一个示例中,上述二维-三维配准的过程包括:分别在第一角度和第二角度下,采用光线投射算法基于所述参考三维图像生成数字重建影像(Digitally Reconstructed Radiograph,DRR),将得到的两个一组的数字重建影像与上述两个一组的X光透射图像进行比较,按照比较结果对空间变换的参数进行优化,从而依照优化后的参数重新生成两个一组的数字重建影像并重复上述过程(迭代),直到满足终止条件时输出优化后的空间变换的参数,以作为所述二维-三维配准的配准结果。
在步骤208中,输出二维-三维配准的配准结果,以使所述目标个体在所述参考三维图像与所述两个不同角度下采集的X光透射图像之间的相对位置偏差得到校正。
应理解的是,所述相对位置偏差可能来源于目标个体在拍摄参考三维图像与拍摄两个X光透射图像之间的时间段内所发生的整体移动,也可能来源于目标个体的内部组织相对于目标个体所发生的移动,并可以不仅限于此。对于上 述放射治疗这一应用场景而言,上述相对位置偏差具体指的是当前的靶区位置相对于其参考位置(即根据参考三维图像所确定的靶区位置)之间的偏差。当然,对于放射治疗以外的其他应用场景,上述相对位置偏差可以具有不同的含义,而且输出上述二维-三维配准的配准结果的目的也可以不仅限于校正上述相对位置偏差(还可以例如是跟踪物体在目标个体内的移动,或是获得所要切除的部分的实际切除情况)。
在一个示例中,放疗设备可以向医疗人员输出所述二维-三维配准的配准结果,以代表当前时刻治疗射束聚焦位置与靶区位置之间的偏差。在此基础之上,当这一偏差大于预定的阈值时,放疗设备可以在医疗人员的操作下依照配准结果进行移床以校正这一偏差;当这一偏差大于或等于该预定的阈值时,则可以不进行移床而继续进行治疗。应理解的是,所述预定的阈值可以依照实际应用场景和应用需求进行确定。
依照步骤206至步骤208的过程,可以依次完成每一个靶点的治疗过程,从而最终完成整个图像引导的过程。可以看出,本公开实施例可以通过磁共振图像与参考三维图像之间的三维-三维配准,来将磁共振图像中精确度很高的关注对象的区域范围标记在参考三维图像当中,从而采用该参考三维图像表征初始位置状态的图像引导过程可以享受到MRI的高软组织对比分辨率所带来的好处,即实现了实时图像引导中MRI的引入,可以借助MRI技术的优势来更好地进行实时图像引导。
在一个对比示例中,上述图像引导方法在图2的基础上跳过步骤201、203、204和205的过程,而直接采用CBCT图像数据经过三维重建得到的参考三维图像进行图像引导。可以看出,一方面参考三维图像中可能无法准确定位出各个关注对象的区域范围,这会给放射治疗带来一定的困难和不确定性;另一方面初始的摆位误差将不能得到校正,从而可能影响放射治疗的精确程度。对此,本公开实施例可以利用磁共振图像提供各个关注对象的区域范围的精确定位,并可以帮助校正初始的摆位误差,使得放射治疗能够更加精确而容易进行。
此外,需要说明的是,在上述任一示例的基础上,直接采用磁共振图像代替CBCT图像来作为参考三维图像是不可行的。其原因主要在于,上述光线透射算法可以在基于CBCT得到的三维体数据的基础上模拟X光线穿透人体不同组织器官时的衰减和曝光过程。所得到的CT值由X光线对组织的衰减与对水 的衰减的比值表示:
μ=(CT/1000+1)·μ
water·F
式中,F为转换因子,μ为X光线在组织中的衰减系数,μ
water为X光线在水中的衰减系数。在此基础之上,基于X光线穿过不同CT值组成的三维体数据,可以计算每条光线穿过三维体数据后的累积衰减参数:
式中,I
0为X射线的初始强度,μ
i是组织i的线性衰减系数,l
i是X射线穿过组织i的长度,I为X射线穿过三维体数据后的强度。基于上述关系,通过将上述I变换为图像灰度值,即可将经过三维重建的CBCT图像变换为二维的数字重建影像。然而,对于磁共振图像来说,其反映的是人体不同组织的氢含量,图像的MRI值与组织的衰减系数之间并不存在类似于上述CT值与组织的衰减系数之间的关系。即便模拟光线穿过MRI值组成的三维体数据,按上述累计衰减参数的计算方法计算每条光线累积衰减参数,得到的值也不能正确的反映不同组织的密度衰减信息,磁共振图像也与无法与实时采集的X光透射图像进行精确配准。
基于上述理由,MRI一般无法应用到实时图像引导中来,其所具有的高软组织对比分辨率也无法有益于图像引导的效果上。然而,本公开实施例则反过来利用磁共振图像与参考三维图像之间的三维-三维配准,使得MRI的优势能够通过参考三维图像间接应用于实时图像引导,使得实时图像引导既不需要重复大量进行MRI的耗时的成像过程,同时也能享受到MRI的优势所带来的好处,有助于实现具有更优效果的实时图像引导。
图3是本公开一个实施例提供的图像引导装置的结构框图。参见图3,该图像引导装置包括:
第一获取模块31,用于获取目标个体的三维的磁共振图像,所述三维的磁共振图像中标记有至少一个关注对象的区域范围;
第二获取模块32,用于获取所述目标个体的参考三维图像,所述参考三维图像是三维重建后的计算机断层扫描图像;
配准模块33,用于对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记;
图像引导模块34,被配置为在采用所述参考三维图像表征初始位置状态的 基础上进行图像引导。
在一种可能的实现方式中,所述装置还包括:
输出模块,用于在采用所述参考三维图像表征初始位置状态的基础上进行图像引导之前输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正。
在一种可能的实现方式中,所述第二获取模块32还用于:在输出三维-三维配准的配准结果之前,在配准结果的配准精度不满足应用条件时,重新获取所述目标个体的所述参考三维图像。
在一种可能的实现方式中,所述参考三维图像是三维重建后的锥形束计算机断层扫描图像;所述装置还包括:
图像处理模块,用于在对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准之前去除所述参考三维图像中存在图像伪影的部分。
在一种可能的实现方式中,所述图像引导模块34包括:
获取单元,用于获取两个不同角度下采集的X光透射图像;
配准单元,用于对所述参考三维图像与所述两个不同角度下采集的X光透射图像进行二维-三维配准;
输出单元,用于输出二维-三维配准的配准结果,以使所述目标个体在所述参考三维图像与所述两个不同角度下采集的X光透射图像之间的相对位置偏差得到校正。
应理解的是,根据上文所描述的图像引导方法的可选实现方式,该图像引导装置可以通过相对应的构造和配置实现上述任意一种的图像引导方法,具体细节不再赘述。
在图3对应的示例中,图像引导装置是以功能单元/功能模块的形式来呈现的。这里的“单元/模块”可以指特定应用集成电路(Application Specific Integrated Circuit,ASIC),执行一个或多个软件或固件程序的处理器和存储器,集成逻辑电路,和/或其他可以提供上述功能的器件。示例性的,所述及的单元和模块中的至少一个的至少部分功能可以通过由处理器来执行存储器中存储的程序代码来实现。
图4是本公开一个实施例提供的医疗设备的结构框图。参见图4,所述医疗设备包括处理器41和存储器42,所述存储器42中存储有程序指令,所述处理 器41配置为调用所述存储器42中的程序指令以执行上述任意一种图像引导方法。
处理器41可以包括中央处理器(CPU,单核或者多核),图形处理器(GPU),微处理器,特定应用集成电路(Application-Specific Integrated Circuit,ASIC),数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器,或者多个用于控制程序执行的集成电路。
存储器42可以包括只读存储器(Read-Only Memory,ROM)或可存储静态信息和指令的其他类型的静态存储设备,随机存取存储器(Random Access Memory,RAM)或者可存储信息和指令的其他类型的动态存储设备,也可以包括电可擦可编程只读存储器(Electrically Erasable Programmable Read-Only Memory,EEPROM)、只读光盘(Compact Disc Read-Only Memory,CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质,但不限于此。存储器可以是独立设置的,也可以和处理器集成在一起。
在具体实现中,作为一种实施例,处理器41可以包括一个或多个CPU。在具体实现中,作为一种实施例,上述医疗设备可以包括多个处理器。这些处理器中的每一个可以是一个单核(single-CPU)处理器,也可以是一个多核(multi-CPU)处理器。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
上述医疗设备可以包括一个通用计算机设备或者一个专用计算机设备。在具体实现中,医疗设备可以例如是放疗设备、图像引导医疗设备或者手术台等任意一种需要进行医学影像图像配准的电子设备,计算机设备可以是台式机、便携式电脑、网络服务器、掌上电脑(Personal Digital Assistant,PDA)、移动手机、平板电脑、无线终端设备、通信设备、嵌入式设备或类似结构的设备。
本公开的实施例还提供了一种计算机存储介质,用于储存为上述任意一种图像引导方法所用的计算机程序,所述计算机程序包括程序指令。通过执行存储的程序,可以实现本公开提供的上述任意一种图像引导方法。
本领域技术人员应明白,本公开的实施例可提供为方法、装置(设备)、或计 算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。计算机程序存储/分布在合适的介质中,与其它硬件一起提供或作为硬件的一部分,也可以采用其他分布形式,如通过因特网或其它有线或无线电信系统。
本申请是参照本公开的实施例的方法、装置(设备)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述仅为本公开的实施例,并不用以限制本公开,凡在本公开的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本公开的权利要求的保护范围之内。
Claims (12)
- 一种图像引导方法,包括:获取目标个体的三维的磁共振图像,所述三维的磁共振图像中标记有至少一个关注对象的区域范围;获取所述目标个体的参考三维图像,所述参考三维图像是三维重建后的计算机断层扫描图像;对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记;在采用所述参考三维图像表征初始位置状态的基础上进行图像引导。
- 根据权利要求1所述的方法,其中在采用所述参考三维图像表征初始位置状态的基础上进行图像引导之前,还包括:输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正。
- 根据权利要求2所述的方法,其中在输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正之前,还包括:在配准结果的配准精度不满足应用条件时,重新获取所述目标个体的所述参考三维图像。
- 根据权利要求1所述的方法,其中所述参考三维图像是三维重建后的锥形束计算机断层扫描图像;在对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记之前,所述方法还包括:去除所述参考三维图像中存在图像伪影的部分。
- 根据权利要求1至4中任一项所述的方法,其中所述在采用所述参考三维图像表征初始位置状态的基础上进行图像引导,包括:获取两个不同角度下采集的X光透射图像;对所述参考三维图像与所述两个不同角度下采集的X光透射图像进行二维-三维配准;输出二维-三维配准的配准结果,以使所述目标个体在所述参考三维图像与所述两个不同角度下采集的X光透射图像之间的相对位置偏差得到校正。
- 一种图像引导装置,包括:第一获取模块,用于获取目标个体的三维的磁共振图像,所述三维的磁共振图像中标记有至少一个关注对象的区域范围;第二获取模块,用于获取所述目标个体的参考三维图像,所述参考三维图像是三维重建后的计算机断层扫描图像;配准模块,用于对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准,以在所述参考三维图像中完成每个所述关注对象的区域范围的标记;图像引导模块,被配置为在采用所述参考三维图像表征初始位置状态的基础上进行图像引导。
- 根据权利要求6所述的装置,还包括:输出模块,用于在采用所述参考三维图像表征初始位置状态的基础上进行图像引导之前输出三维-三维配准的配准结果,以使所述磁共振图像与参考三维图像之间的摆位偏差得到校正。
- 根据权利要求7所述的装置,其中所述第二获取模块还用于:在输出三维-三维配准的配准结果之前,在配准结果的配准精度不满足应用条件时,重新获取所述目标个体的所述参考三维图像。
- 根据权利要求6所述的装置,其中所述参考三维图像是三维重建后的锥形束计算机断层扫描图像;所述装置还包括:图像处理模块,用于在对所述三维的磁共振图像与所述参考三维图像进行三维-三维配准之前去除所述参考三维图像中存在图像伪影的部分。
- 根据权利要求6至9中任一项所述的装置,其中所述图像引导模块包 括:获取单元,用于获取两个不同角度下采集的X光透射图像;配准单元,用于对所述参考三维图像与所述两个不同角度下采集的X光透射图像进行二维-三维配准;输出单元,用于输出二维-三维配准的配准结果,以使所述目标个体在所述参考三维图像与所述两个不同角度下采集的X光透射图像之间的相对位置偏差得到校正。
- 一种医疗设备,其中,所述医疗设备包括处理器和存储器,所述存储器中存储有程序指令,所述处理器配置为调用所述存储器中的程序指令以执行如权利要求1至5中任一所述的方法。
- 一种计算机可读存储介质,其特征在于,所述计算机存储介质存储有计算机程序,所述计算机程序包括程序指令,所述程序指令被配置为在被处理器执行时使所述处理器执行如权利要求1至5中任一项所述的方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/290,715 US11961245B2 (en) | 2018-10-30 | 2018-10-30 | Method and apparatus for performing image guidance, medical equipment, and computer-readable storage medium |
CN201880031818.6A CN111386555B (zh) | 2018-10-30 | 2018-10-30 | 图像引导方法及装置、医疗设备、计算机可读存储介质 |
PCT/CN2018/112586 WO2020087257A1 (zh) | 2018-10-30 | 2018-10-30 | 图像引导方法及装置、医疗设备、计算机可读存储介质 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2018/112586 WO2020087257A1 (zh) | 2018-10-30 | 2018-10-30 | 图像引导方法及装置、医疗设备、计算机可读存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020087257A1 true WO2020087257A1 (zh) | 2020-05-07 |
Family
ID=70463308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/112586 WO2020087257A1 (zh) | 2018-10-30 | 2018-10-30 | 图像引导方法及装置、医疗设备、计算机可读存储介质 |
Country Status (3)
Country | Link |
---|---|
US (1) | US11961245B2 (zh) |
CN (1) | CN111386555B (zh) |
WO (1) | WO2020087257A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022120716A1 (zh) * | 2020-12-10 | 2022-06-16 | 西安大医集团股份有限公司 | 实时图像引导方法、装置及系统、放射治疗系统 |
WO2022120707A1 (zh) * | 2020-12-10 | 2022-06-16 | 西安大医集团股份有限公司 | 实时图像引导方法、装置及系统、放射治疗系统 |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR3091348A1 (fr) * | 2018-12-27 | 2020-07-03 | Universite de Bordeaux | Méthode de prédiction du risque de récidive après un traitement d’une tumeur par rayonnement |
WO2020185015A1 (ko) * | 2019-03-12 | 2020-09-17 | 주식회사 메디트 | 치아 보철 제조를 위한 3차원 스캔 데이터 처리 방법 |
US11547323B2 (en) * | 2020-02-14 | 2023-01-10 | Siemens Healthcare Gmbh | Patient model estimation from camera stream in medicine |
CN113017833A (zh) * | 2021-02-25 | 2021-06-25 | 南方科技大学 | 脏器定位方法、装置、计算机设备及存储介质 |
WO2024160375A1 (en) * | 2023-02-03 | 2024-08-08 | Brainlab Ag | Computing a hybrid surface from medical image data using trusted regions and a plausibility check |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105139442A (zh) * | 2015-07-23 | 2015-12-09 | 昆明医科大学第一附属医院 | 一种结合ct和mri二维图像建立人体膝关节三维仿真模型的方法 |
CN106934807A (zh) * | 2015-12-31 | 2017-07-07 | 深圳迈瑞生物医疗电子股份有限公司 | 一种医学影像分析方法、系统及医疗设备 |
CN108701220A (zh) * | 2016-02-05 | 2018-10-23 | 索尼公司 | 用于处理多模态图像的系统和方法 |
Family Cites Families (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100581479C (zh) * | 2007-01-10 | 2010-01-20 | 华中科技大学 | 三维超声影像的重建方法 |
CN100579449C (zh) * | 2007-01-30 | 2010-01-13 | 西门子(中国)有限公司 | 磁共振引导的治疗仪器的位置校正装置 |
DE102007010806B4 (de) * | 2007-03-02 | 2010-05-12 | Siemens Ag | Verfahren zum Schaffen erweiterter Möglichkeiten bei der Verwendung von für den Einsatz von Registrierungsverfahren ungeeigneten Bilddaten eines Patienten und Röntgenangiographiesystem |
CN101959454B (zh) | 2008-03-07 | 2013-11-20 | 皇家飞利浦电子股份有限公司 | 通过磁共振图像的自动分割进行ct替代 |
CN102232835A (zh) | 2010-04-21 | 2011-11-09 | 清华大学 | 一种影像引导放射治疗的定位方法 |
EP2691898A2 (en) * | 2011-03-29 | 2014-02-05 | Boston Scientific Neuromodulation Corporation | System and method for atlas registration |
US20130235969A1 (en) * | 2012-03-01 | 2013-09-12 | Imris Inc. | Patient Alignment in MRI Guided Radiation Therapy |
EP2877089B1 (en) * | 2012-07-27 | 2022-05-18 | University Health Network | Radiotherapy system integrating a radiation source with a magnetic resonance imaging apparatus with movable magnet components |
KR101932721B1 (ko) * | 2012-09-07 | 2018-12-26 | 삼성전자주식회사 | 의료 영상들의 정합 방법 및 장치 |
ITTO20130527A1 (it) * | 2013-06-26 | 2014-12-27 | Masmec S P A | Sistema di navigazione ecografica assistita da calcolatore, in particolare per fornire assistenza al personale medico durante interventi diagnostici e/o terapeutici. |
CN103932796A (zh) * | 2014-04-13 | 2014-07-23 | 北京师范大学 | 一种基于多模态医学影像数据融合的颅内电极个体化定位的方法 |
CN106462971B (zh) * | 2014-06-25 | 2021-01-26 | 皇家飞利浦有限公司 | 用于配准不同成像模态的成像设备 |
CN104637061A (zh) | 2015-01-30 | 2015-05-20 | 中国科学院自动化研究所 | 一种二维三维医学图像配准方法 |
EP3245532B1 (en) | 2015-01-30 | 2018-06-20 | Koninklijke Philips N.V. | Automated scan planning for follow-up magnetic resonance imaging |
CN106611411B (zh) * | 2015-10-19 | 2020-06-26 | 上海联影医疗科技有限公司 | 一种医学图像中肋骨分割的方法及医学图像处理装置 |
CN105488804B (zh) | 2015-12-14 | 2018-06-12 | 上海交通大学 | 脑部asl、spect和mri图像配准融合联合分析的方法及系统 |
JP6727319B2 (ja) * | 2016-03-10 | 2020-07-22 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | Synthetic CTイメージング |
US10748296B2 (en) * | 2018-01-18 | 2020-08-18 | Elekta, Inc. | Methods and devices for surface motion tracking |
CN108711187B (zh) * | 2018-08-03 | 2021-12-31 | 华侨大学 | 配准融合ct和mri信号建立人体腰椎三维仿真模型的方法 |
US20220015686A1 (en) * | 2018-12-11 | 2022-01-20 | Brown University | Neural biomarkers of parkinson's disease |
US11806084B2 (en) * | 2019-03-22 | 2023-11-07 | Globus Medical, Inc. | System for neuronavigation registration and robotic trajectory guidance, and related methods and devices |
-
2018
- 2018-10-30 US US17/290,715 patent/US11961245B2/en active Active
- 2018-10-30 WO PCT/CN2018/112586 patent/WO2020087257A1/zh active Application Filing
- 2018-10-30 CN CN201880031818.6A patent/CN111386555B/zh active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105139442A (zh) * | 2015-07-23 | 2015-12-09 | 昆明医科大学第一附属医院 | 一种结合ct和mri二维图像建立人体膝关节三维仿真模型的方法 |
CN106934807A (zh) * | 2015-12-31 | 2017-07-07 | 深圳迈瑞生物医疗电子股份有限公司 | 一种医学影像分析方法、系统及医疗设备 |
CN108701220A (zh) * | 2016-02-05 | 2018-10-23 | 索尼公司 | 用于处理多模态图像的系统和方法 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022120716A1 (zh) * | 2020-12-10 | 2022-06-16 | 西安大医集团股份有限公司 | 实时图像引导方法、装置及系统、放射治疗系统 |
WO2022120707A1 (zh) * | 2020-12-10 | 2022-06-16 | 西安大医集团股份有限公司 | 实时图像引导方法、装置及系统、放射治疗系统 |
Also Published As
Publication number | Publication date |
---|---|
US11961245B2 (en) | 2024-04-16 |
CN111386555A (zh) | 2020-07-07 |
CN111386555B (zh) | 2024-03-29 |
US20220020164A1 (en) | 2022-01-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020087257A1 (zh) | 图像引导方法及装置、医疗设备、计算机可读存储介质 | |
JP6894987B2 (ja) | 適応型放射線療法に対する3次元位置特定及び追跡 | |
US10791958B2 (en) | Magnetic resonance projection imaging | |
JP6624695B2 (ja) | 適応型放射線療法に対する移動する標的の3次元位置特定 | |
JP6886565B2 (ja) | 表面の動きを追跡する方法及び装置 | |
JP6053792B2 (ja) | 可変画像レジストレーションのワークフローにおけるユーザー入力と変形ベクトル場の修正との統合 | |
CN107206252B (zh) | 核磁共振引导直线加速器中的运动管理 | |
JP5330992B2 (ja) | 生物学に導かれた適応的な治療計画 | |
AU2018266458B2 (en) | Systems and methods of accounting for shape change during radiotherapy | |
US20120022845A1 (en) | Monitoring of the radiation dose accumulated by a body | |
US10614598B2 (en) | Systems and methods for generating 2D projection from previously generated 3D dataset | |
WO2020237537A1 (zh) | 图像引导方法及装置、医疗设备、计算机可读存储介质 | |
CN115526929A (zh) | 基于图像的配准方法和装置 | |
WO2022198553A1 (zh) | 三维图像引导摆位的方法、系统及存储介质 | |
US20060058620A1 (en) | Setting a relative position of a radiation device and a patient | |
CN110322426B (zh) | 基于可变人体模型的肿瘤靶区勾画方法、设备和存储介质 | |
US20210295542A1 (en) | Method, radiotherapy device, and computer-readable storage medium for image registration | |
Shepard | An ultrasound-based motion management system utilizing 2D/3D real-time tracking for use in radiotherapy | |
CN116091517A (zh) | 医学影像处理方法、装置、存储介质和计算机程序产品 | |
JP2015000092A (ja) | 患者位置決めシステム、および患者位置決め方法。 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18938301 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18938301 Country of ref document: EP Kind code of ref document: A1 |