WO2015055599A2 - Registration of medical images - Google Patents
Registration of medical images Download PDFInfo
- Publication number
- WO2015055599A2 WO2015055599A2 PCT/EP2014/071934 EP2014071934W WO2015055599A2 WO 2015055599 A2 WO2015055599 A2 WO 2015055599A2 EP 2014071934 W EP2014071934 W EP 2014071934W WO 2015055599 A2 WO2015055599 A2 WO 2015055599A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- registration
- images
- local
- roi
- image
- Prior art date
Links
- 239000013598 vector Substances 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000002059 diagnostic imaging Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 15
- 239000000463 material Substances 0.000 claims description 9
- 210000000988 bone and bone Anatomy 0.000 claims description 8
- 238000002604 ultrasonography Methods 0.000 claims description 7
- 238000002595 magnetic resonance imaging Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000002603 single-photon emission computed tomography Methods 0.000 claims description 3
- 210000000056 organ Anatomy 0.000 claims 1
- 238000013459 approach Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 8
- 238000002591 computed tomography Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 5
- 210000001519 tissue Anatomy 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 210000004185 liver Anatomy 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000002600 positron emission tomography Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/037—Emission tomography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/46—Arrangements for interfacing with the operator or the patient
- A61B6/467—Arrangements for interfacing with the operator or the patient characterised by special input means
- A61B6/469—Arrangements for interfacing with the operator or the patient characterised by special input means for selecting a region of interest [ROI]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
- A61B6/5247—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image combining images from an ionising-radiation diagnostic technique and a non-ionising radiation diagnostic technique, e.g. X-ray and ultrasound
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/4808—Multimodal MR, e.g. MR combined with positron emission tomography [PET], MR combined with ultrasound or MR combined with computed tomography [CT]
- G01R33/4812—MR combined with X-ray or computed tomography [CT]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
- G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
- G01R33/5608—Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
- G06T2207/20012—Locally adaptive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
Definitions
- the invention relates to a method and an image processing device for the registration of at least two images of an object, for example of CT and/or MRI scans of the body of a patient.
- the US 2013/0182925 Al discloses a method of initially registering a first set of image data and a second set of image data. A further registration of the images is then performed in a region that is automatically or manually selected.
- the initial registration may for example be a free-form transformation, while the further registration is a rigid registration.
- the initial and the further registrations may be merged.
- the US 2005/065421 Al discloses a method in which first anatomical and functional images are co -registered, and second anatomical and functional images, acquired at a later stage, are co-registered.
- a global, rigid registration is performed on the first and second anatomical images.
- a volume of interest (ROI) is identified in the first co- registered composite image data set and a local, non-rigid registration is performed on this ROI and a corresponding ROI within the globally registered image data set.
- the WO 2007/066294 A2 discloses a procedure in which several registrations of a first image and a second image are displayed on a display during a medical intervention. A physician can then visually select one of the registrations for subsequent use.
- the WO 20121025855 Al discloses the registration of anatomical images and emission images.
- a global rigid registration is followed by a local non- rigid registration of a region of interest.
- an embodiment of the invention relates to an image processing device that can register at least two images of an object, said device comprising the following components:
- a first module that is called “global registration module” in the following and that serves for executing a registration (called “global registration”) of the at least two images using a given registration algorithm with a first parameter vector.
- selection module A second module that is called “selection module” in the following and that serves for the selection of a given region of interest, called “ROI”, in the images.
- a third module that is called “local registration module” in the following and that serves for executing at least one registration (called “local registration”) of the images within the selected ROI using the above-mentioned given registration algorithm with a parameter vector that is different from the first parameter vector.
- the aforementioned "different parameter vector" of the local registration is automatically determined for at least one local registration based on an automatic analysis of the ROI, wherein said analysis comprises at least one of the following items: the evaluation of intensity ranges, image edges, entropy measurements, intensity histograms, edge histograms, intensity range of residuum, and/or anatomical position.
- the image processing device may for example be realized by dedicated electronic hardware, digital data processing hardware with associated software, or a mixture of both.
- the images that are processed by the device are typically two-dimensional or three-dimensional images, for example obtained from a medical CT (Computed Tomography) or MRI (Magnetic Resonance Imaging) scanning procedure.
- the images are preferably encoded as digital data sets in which each element represents an image value (e.g. a gray value) at an associated point in space (represented e.g. by its x, y, z-coordinates in an associated coordinate system).
- the "registration" of two images of an object refers to the determination of a mapping between the two images that maps each image point of a first one of the images onto that image point of the second image which belongs to the same location or structure of the imaged object.
- a registration of images that have been generated with the same apparatus is usually necessary because of possible movements of the object (motion of a patient; heart beat; growth of a structure etc.). Registration of images that have been generated with different apparatuses/modalities is usually necessary because one and the same structure of the imaged object is represented differently in such images.
- images Prior to a registration, images may be preprocessed appropriately, for example by a filtering or by the removal of objects that are of no interest.
- the object that is depicted in the processed images may for example be (a part of) the body of a person or animal in medical examinations, a suitcase in baggage control, a piece of material in material sciences or the like.
- the attributes "global” and "local” shall indicate that the "global registration” extends to a larger part of the images than the "local registration", the latter being restricted to the selected ROI. It is however possible that the "global registration” does not cover the whole images, for example if structures of no interest are left out (e.g. the patient table).
- the "given registration algorithm” may be any algorithm that is appropriate for the desired registration of the images at hand.
- a variety of such registration algorithms are known in the art, for example rigid registrations, affine registrations, and non-rigid registrations (cf. US 2013/0182925 Al; J. Modersitzki, “Numerical Methods for Image Registration”. Oxford University Press, 2004; D. Rueckert, L. I. Sonoda, C. Hayes, D. L. G. Hill, M. O. Leach, and D. J. Hawkes, "Non-rigid registration using free-form deformations: Application to breast MR images", IEEE Transactions on Medical Imaging, 18(8):712— 721 , 1999). All that is assumed about the used registration algorithm is that it depends on N > 1 parameters, wherein these parameters can be arranged in a "parameter vector" of some N-dimensional parameter space.
- each of them will use a parameter vector that is different from both the first parameter vector and from the parameter vectors of the other local registrations.
- the selection of the ROI may be executed in any one of the original images, in both images simultaneously (with a later merging of the selections), and/or in the globally registered version of the images.
- the latter option is typically preferred as the globally registered images reveal those areas where the global registration may not yet be good enough such that these areas can be selected as ROI.
- the selection of a ROI and the corresponding determination of at least one local registration can optionally be repeated several times for different ROIs and/or be executed in parallel for different ROIs.
- an embodiment of the invention relates to a method for the registration of at least two images of an object, said method comprising the following steps that may be executed in the listed or any other order or in parallel, if appropriate:
- ROI a region of interest
- the aforementioned "different parameter vector" of the local registration is automatically determined for at least one local registration based on an automatic analysis of the ROI, wherein said analysis comprises at least one of the following items: the evaluation of intensity ranges, image edges, entropy measurements, intensity histograms, edge histograms, intensity range of residuum, and/or anatomical position.
- an embodiment of the invention relates to a medical imaging apparatus comprising the following components:
- At least one image generating device for generating images of an object.
- the image processing device will hence comprise a global registration module for executing a global registration of the images using a given registration algorithm with a first parameter vector, a selection module for the selection of a ROI in the images, and a local registration module for executing at least one local registration of the images within the selected ROI using the given registration algorithm with a different parameter vector.
- the image processing device, the method, and the medical imaging apparatus are based on the same concept that a global registration of two images is followed by at least one local registration with a different parameter vector in a selected region of interest.
- the image processing device, the method, and the medical imaging apparatus have the advantage that they allow for an effective improvement of the registration of two images that can readily be implemented. This is because a first registration, which would usually be taken as the final result, is locally refined in at least one selected region of interest by a local registration. As said local registration applies the same registration algorithm as the first registration, the refinement can be achieved without a need of implementing a completely different registration algorithm.
- At least two local registrations are executed with different parameter vectors (with respect to the image processing device, this means that the local registration module is designed to execute at least two registrations with different parameter vectors).
- the different parameter vectors may be given in advance, for example provided from a memory of the local registration module. Additionally or alternatively, they may be chosen or generated (i) at random, (ii) based on user inputs, and/or (iii) in dependence on the selected ROI and/or the type of the images to be registered.
- Calculation of two or more local registrations allows for a comparison of the results, for example with the help of some objective function that provides a numerical score for the results. The best of the local registrations can then be chosen for further usage.
- the results of the local registrations with different parameter vectors are displayed (e.g. on a monitor of the image processing device or the medical imaging apparatus), wherein a user can then select at least one of the displayed results for further usage.
- the selection may for example be done with the help of some input device such as a mouse, a trackball, a keyboard or the like (again, this may be a part of the image processing device and/or the medical imaging apparatus).
- some input device such as a mouse, a trackball, a keyboard or the like (again, this may be a part of the image processing device and/or the medical imaging apparatus).
- the user will select the local registration that appears to be the best, though other selection criteria are possible, too. Displaying of the result of a registration may be done in any appropriate way, for example by showing an overlay of the registered images.
- the selection of a result of a local registration is of course tantamount to the selection of a particular local registration and its parameter vector that has been used for achieving the selected result.
- the results of the local registrations may be displayed sequentially, perhaps with the additional option for the user to jump between the results. Most preferably, the results of the local registrations are displayed simultaneously such that the user can see them at a glance and compare them in parallel. Additionally or alternatively, the result of the global registration may be displayed in parallel, too.
- the aforementioned selection of a local registration is advantageous in that it allows for a refinement of the image registration by exploiting the user's capabilities of (intuitively) evaluating registrations.
- the image processing device is used for what it can do best, i.e. executing numerical calculations (for several local registrations) with high velocity. All the user has to do is to select, for example via a simple mouse click, that one of the local registrations that appears to him/her to be the best, wherein this selection will often be based on criteria that can hardly be formulated rigorously or be implemented in an algorithm.
- the user may optionally also select two or more results of the local registrations for further usage.
- the user may simultaneously provide a ranking of the selected registrations ("best", "second-best”, etc.).
- the parameter vectors of the selected registrations will then usually indicate a sub-region of the whole parameter space that can be searched with preference during a further optimization of the local registration. For example, the average of the selected parameter vectors (optionally weighted with their ranking) could be used to define a new local registration.
- this selected registration may optionally be refined in a further processing step (if several local registrations have been selected, each of them may be refined and/or a new local registration that is derived from them can be refined). Hence the optimum of this selected local registration can be taken as basis for a further usage.
- a refinement of a local registration may for example comprise a new calculation of said local registration with a change of one or more parameters (which may be components of the associated parameter vector or not) that are known to improve the accuracy of the registration.
- parameters may for example be related to the resolution of the processed images and/or the number of iterations that are performed with an iterative registration algorithm.
- sub-optimal values will be chosen for such parameters when several local registrations have to be calculated in order to limit the required runtime of the algorithm to reasonable values.
- the usage of sub-optimal, simplified local registrations is usually sufficient for the intended purpose of finding out which of the local registrations yield better results than the others.
- the selection of one or more displayed results from several local registrations by a user will typically take place again and again a lot of times with different input images (e.g. from different body regions and/or patients).
- the user's selections may optionally be evaluated with respect to possible preferences, i.e. with respect to deviations from a (blind or random) selection of registrations with equal probability. For example, if the user selects parameter vectors from some sub-region of parameter space more frequently than from other regions, this indicates a preference that may be detected qualitatively or even quantitatively. This information can preferably be exploited during future image registrations. Local registrations with parameter vectors that are preferred by the user may for example be presented as default selections.
- more local registrations can be computed in a region of parameter space that comprises preferred parameter vectors.
- regions of parameter space from which local registrations are seldom or never selected can be sampled more sparsely or be omitted altogether.
- the registration procedure can thus be provided with some kind of learning capability that provides for a continuous improvement over time. It should be noted that "the user" whose preferences are determined may of course also correspond to a group of several users.
- the "different parameter vector" of the local registration is automatically determined for at least one local registration based on an automatic analysis of the ROI.
- the user's input may be limited to the selection of the ROI (if this is not done automatically, too), and an automatic algorithm analyzes this ROI and determines some parameter vector for a local registration (e.g. according to some given criterion that is implemented in the algorithm). Due to the focusing on the ROI, the automatically determined parameter vector will usually yield better registration results (for the ROI) than the global registration which had to use the first parameter vector that was chosen in view of the WHOLE images.
- the aforementioned automatic analysis of the ROI comprises at least one of the following items: the evaluation of intensity ranges, image edges, entropy measurements, intensity histograms, edge histograms, intensity range of residuum, and/or anatomical position.
- the evaluation of intensity ranges for an underlying image can indicate which kind of anatomical content (for a CT image e.g. air within the lungs or bowel gas with very low HU values, liquids, non-dense or dense tissue with moderate HU values, bone structures with higher HU values) is present in the ROI and can therefore justify a certain parameter setting.
- the registration of bone structures will for example require a stiffer deformation while registration of tissue structures requires a moderate elasticity.
- the presence of air or gas can suggest a setting which allows for larger volume changes between the images to be compared.
- the evaluation of intensity histograms extends the evaluation of intensity ranges.
- a histogram analysis can be used to quantify the portions of certain intensity ranges (e.g. of bones and liquids).
- a parameter setting designed for the largest portion present in the ROI can then be chosen, or the parameter setting may be chosen sub-ROI-dependent or even voxel-dependent, e.g. if the ROI is composed of more than one material.
- the histogram analysis can be done separately on each image, which allows e.g. detection for contrast agent in one of the images. An adequate parameter setting for this scenario would be an elastic but volume-preserving deformation.
- image edges can be prominent (e.g. at the diaphragm) or small (e.g. at the intestine interface between liver and kidney). While prominent image edges are easy to match, edges of smaller strength may require a parameter setting with a decreased weight of the regularizer or with an increased weight of the similarity term or may require a pre-processing of the images in order to enhance the strength of the edge.
- edge histograms extends the evaluation of image edges.
- a histogram analysis can be used to quantify the amount of edges with a certain strength. Similar to the scenario where intensity histograms are evaluated, dedicated parameter settings for sub-ROIs may be chosen.
- the evaluation of the residuum image can be used.
- Non- aligned image edges will appear in the residuum image as a pair of line- like structures, one with positive intensities, the other with negative intensities.
- the occurrence of such a pair can be detected and indicates, e.g. an increased elasticity or a decreased weight of the regularizer or an increased weight of the similarity term or a pre-processing of the images.
- the anatomical position of the ROI can be used for parameter setting.
- an organ-specific or bone-specific parameter setting can be used.
- One or multiple of the aforementioned examples can be combined with an analysis on multiple resolution levels (or multiple scales). If a certain feature is not present after evaluation on a certain image resolution level but is present on a finer image resolution level, it is reasonable to choose a parameter setting which adds the finer resolution level to the registration.
- the selection of the ROI may be done manually by a user, for example with the help of a mouse or some other pointer with which the user can indicate boundaries of the desired ROI on a display of the images. In another embodiment, selection of the ROI may be done automatically, for example based on an algorithm that segments regions with particular features in a given image.
- the at least one local registration of the images within the selected ROI using the given registration algorithm with a different parameter vector can optionally be repeated at least once.
- One cycle of local registrations may for example allow for a selection of the best result by a user, and the following cycle of local registrations may be based on this selection, using for example parameter vectors close to the one that was selected in the previous cycle. Of course this process may be iterated several times.
- one local registration for the ROI may be considered as the final local registration (e.g. the local registration that has been selected as the best one by a user, or the local registration that is based on an automatically determined parameter vector).
- this final local registration is merged with the global registration.
- Such a merging may be achieved in various ways as long as it is provided that the final local registration dominates (or exclusively applies) within the ROI while the global registration dominates (or exclusively applies) outside the ROI.
- a transition region may be defined in which a continuous blending from the global registration to the local registration takes place (cf. US 2013/0182925 Al).
- the global registration and/or the local registration(s) may preferably be non-rigid registrations (or "free-form transformations").
- Non-rigid registrations can usually better map two images onto each other, particularly if they depict soft, deformable material such as body tissue.
- the associated parameter vectors may contain a variety of different types of parameters.
- the parameter vector comprises at least one parameter selected from the group consisting of: a material property, a weighting factor, a number of iterations, and an image resolution.
- a typical parameter vector may for example comprise several material properties (e.g. elasticity of bones and muscles), a weighting factor (e.g. of image similarity vs. regularization), a maximal number of iterations, and a (sub-optimal) resolution of the images used for the local registration.
- the images that are registered may for example be images generated by an X-ray device such as an X ray projection apparatus or a CT scanner.
- the images may have been generated by a PET (Positron Emission Tomography) or SPECT (Single Photon Emission Computed Tomography) device, a Magnetic Resonance Imaging (MRI) device, or an ultrasound (US) device.
- PET Positron Emission Tomography
- SPECT Single Photon Emission Computed Tomography
- MRI Magnetic Resonance Imaging
- US ultrasound
- the described method will typically be realized with the help of a computing device, e.g. a microprocessor or an FPGA in the image processing device. Accordingly, the present invention further includes a computer program product which provides the
- the present invention includes a data carrier, for example a floppy disk, a hard disk, an EPROM, a compact disc (CD-ROM), a digital versatile disc (DVD), or a USB stick which stores the computer product in a machine readable form and which executes at least one of the methods of the invention when the program stored on the data carrier is executed on a computing device.
- the data carrier may particularly be suited for storing the program of the computing device mentioned in the previous paragraph.
- Intranet for download hence the present invention also includes transmitting the computer product according to the present invention over a local or wide area network.
- Fig. 1 schematically shows a medical imaging apparatus according to an embodiment of the invention
- Fig. 2 shows an example of an input image
- Fig. 3 illustrates the selection of a ROI in two globally registered input images
- Fig. 4 illustrates the display of a global registration and a plurality of local registrations with different parameter vectors.
- Image registration is increasingly accepted as base technology to establish correspondences between images.
- the application range is broad, covering frequent applications such as dynamic contrast imaging and change quantification in follow-up studies.
- Rigid/affine registration is suited only for few applications, and the majority of applications requires non-rigid registration.
- FIG. 1 schematically illustrates a medical imaging apparatus 100 according to an embodiment of above approach.
- a central element of the imaging apparatus is an image processing device 50 that may for example be realized by a microcomputer with associated software.
- the boxes that are depicted within the image processing device 50 are rather meant to illustrate different processing steps than different hardware components. Typically, these boxes correspond to modules which are primarily implemented by associated software (sub-)routines.
- Input images ,h are supplied to the image processing device 50 that may in general originate from any appropriate image source, including a storage in which previously generated images are stored for later processing.
- a first image Ii (or a stream of images) is provided by an X-ray scanner 10 with an X-ray source 1 1 and a detector 12 that can rotate about a patient P on a patient table.
- a second image I 2 (or a stream of images) is provided by an MRI scanner 20 that can generate sectional images or 3D images of the body of a patient P located in the bore of the scanner.
- the first and second images Ii, I 2 are provided in this example by different imaging modalities.
- the dimensionality of the images (2D, 3D) may be the same or different.
- the same object for example the same part of the body of a patient P, will have to be depicted on the supplied images Ii, I 2 to allow for a reasonable registration.
- the two (or more) images Ii, I 2 provided by external means are first processed in a "global registration module" 51 (optional
- the global registration module 51 executes a global registration GR of the images Ii, I 2 using some given registration algorithm that makes use of a (given) first parameter vector o.
- the global registration usually provides a mapping f of the coordinates x,y,z of the first image Ii onto the coordinates x',y',z' of the second image I 2 .
- This mapping is such that, for example, a point x,y,z which corresponds to a particular location or structure in the first image Ii (e.g.
- a bifurcation of a vessel is mapped onto the point x',y',z' which corresponds to the same location or structure in the second image I 2 .
- this mapping is illustrated by a deformation of the x',y',z'-coordinate system of the second image I 2 (such that identical object
- the result of the global registration is next passed on to a "selection module" 52 that allows for the selection of a region of interest ("ROI") by a user.
- This step makes use of an external user interface 60 to display the globally registered images on a display or monitor 63 and to allow for the indication of the ROI by the user with the help of a keyboard 61 and a mouse 62.
- the selection may for example be based on one of the original images (or on both), or the selection may be done automatically by the processing device 50.
- LR1 After selection of the ROI, several local registrations LR1, ... LRs, ... LRn are executed within the ROI by a "local registration module" 53.
- Each of these local registrations applies the same registration algorithm that was used by the global registration module, but uses a different parameter vector i ⁇ p 2 ⁇ ... p s ⁇ ... p_n.
- the results of the aforementioned local registrations LR1, ... LRs, ... LRn are presented to the user on the monitor 63. Preferably, all results are shown in parallel and optionally together with the result of the global registration GR at the center.
- the user may then select one or more of these local registrations, for example the local registration LRs, that he/she considers to be the best.
- This selected local registration LRs may optionally be improved by a refinement, e.g. a calculation with higher resolution, before it is further processed.
- the local registration LRs selected by the user is forwarded to a "merging module" 54 in which it is merged with the global registration GR in an appropriate way to yield a final overall registration.
- the global registration GR may for example dominate the final overall registration outside the ROI, while the selected local registration LRs dominates inside the ROI with a continuous, soft transition from the inside to the outside of the ROI.
- the final overall registration is then typically made available for further processing, storage and/or evaluation.
- the ROI may automatically be analyzed to find a parameter vector p s for a subsequent local registration.
- the given registration algorithm that is applied in the global and the local registration modules 51, 53 may preferably be a non-rigid registration.
- a non-rigid image registration may be implemented as an iterative process in which an image similarity term is optimized, while an additional regularization term keeps the solution in some sense realistic (usually a certain smoothness of the resulting deformation field is wanted).
- a typical non- rigid registration scheme consists of the following ingredients:
- An objective function combining an image similarity term and a regularization term. Frequent choices for the similarity term are mutual information, sum of squared differences, or intensity correlation.
- the regularization term usually implies a certain degree of smoothness, by, e.g., penalizing first- and/or second-order derivatives of the mapping field. - Image similarity and regularization term are weighted depending on
- Weighting is usually fixed for the whole image.
- a set (or vector) of parameters used to steer the registration scheme e.g.
- An optimization scheme e.g., gradient descend, conjugate gradients, etc.
- the accuracy of the registration output depends on (i) the number of iterations spent, i.e. on the runtime, (ii) the parameter setting used for registration, and (iii) the anatomy of interest. Since for non-rigid image registration no automatic validation scheme exists, it cannot be automatically determined if a registration output fulfills the user specifications (e.g., "registration error below 2 mm"). Even for a large number of iterations it cannot be guaranteed that the user specifications are fulfilled for any anatomy of interest.
- Figure 2 shows for example an exemplary CT image in which high-contrasted image edges (e.g. the diaphragm) are easier to detect than low-contrasted image edges (e.g., the lower boundary of the liver).
- high-contrasted image edges e.g. the diaphragm
- low-contrasted image edges e.g., the lower boundary of the liver.
- bone structures may for example get unrealistically deformed when using a tissue-specific parameter setting and require a bone-specific setting of the modeled material properties.
- different application scenarios point tracking, change quantification in follow-up studies, perfusion studies, (dynamic) contrast imaging, etc. pose different requirements, and there does not exist a one-solves-it-all registration solution.
- the accuracy of the registration output can however be improved by means of minimal user input.
- FIG. 3 illustrates the display of the result of the global registration as residuum (i.e. subtraction of first image and deformed second image) in which a cuboid has been selected as ROI to indicate the region where the registration output needs to be improved (lower liver boundary is not aligned).
- Other possible forms of the ROI comprise for example a sphere, an ellipsoid, or an irregular shape.
- Multiple fast local registration refinements LR1 , . .. LRn are next computed for the ROI and presented to the user. As illustrated in Figure 4, this may for instance be done in the form of previews displayed around a representation of the global registration GR at the center. Following a what-you-see-is-what- you-get approach the user can then select the preview best satisfying his/her needs (and hereby selects a parameter setting). This may be followed by an accurate registration refinement with the new parameter setting. The only required user input thus is (i) selecting a region of interest, and (ii) selecting one of the (very fast) computed previews.
- GUI graphical user interface
- the global registration algorithm from step 2 is re-run with the input images ,h cropped by the user-defined ROI and with each of the new parameter settings Pi, ... p s , ... p_n.
- the registration algorithm can be initialized with the global deformation obtained in step 2.
- the execution of the local registration algorithm needs to be fast. This can be achieved by (i) restricting the registration domain to the ROI, and (ii) restricting the registration to coarse (i.e. downsampled) resolutions of the input images (the result is then interpreted as a preview of the precise registration output). For each parameter setting a deformation for the ROI is computed.
- Provision of a second GUI where again the first, global registration output as well as the collection of refined, local registration outputs (previews) are shown to the user and where the user can select the preview which best fulfills his/her needs. Due to the preview-state (i.e. the registration performed in a very fast mode) it might occur that the alignment is still non-perfect. However, it is only important to select the preview (with the corresponding parameter setting) which improves the global registration result (from step 2) in the expected way/direction.
- the selected parameter setting p s is then used to perform a refined registration, i.e. initialized by the global deformation obtained in step 2.
- a highly-accurate registration with the new parameter setting is executed for the ROI.
- appropriate boundary conditions have to be chosen for the refined registration.
- Output of the system are aligned images or deformation fields between some or all of the input images.
- Favorite selection(s) may then later be proposed to (i) reduce number of refinement steps and/or (ii) restrict the set of modified parameter settings.
- the user may select the second-best (third-best, etc.) preview as well.
- the search range may then be spanned by the parameter settings from the n best previews
- a GUI where the first global registration output is shown to the user (e.g., in terms of fused images, residuum, contour overlay) and where the user can select a position or a ROI (as above).
- An automatic analysis of the image content within the ROI determines a more suitable parameter setting from a range of stored setups.
- the automatic analysis could for example employ intensity ranges, image edges, entropy measurements, intensity histograms, edge histograms, intensity range of residuum, anatomical position (in combination with a prior segmentation).
- a low intensity range for example, will motivate histogram equalization in order to facilitate alignment of low-contrasted image structures.
- the presence of filigree structures in the ROI for example, calls for the usage of a higher image resolution than usually used.
- the modified parameter setting is used to perform a second-pass (local) registration, i.e. initialized by the global deformation obtained in step 2, a highly-accurate registration with the new parameter setting is executed for the ROI.
- a second-pass (local) registration i.e. initialized by the global deformation obtained in step 2
- a highly-accurate registration with the new parameter setting is executed for the ROI.
- appropriate boundary conditions have to be chosen for the refined registration.
- Output of the system are aligned images or deformation fields between some or all of the input images.
- a fully-automatic analysis is achieved that is driven by user guidance (single click on image region where registration accuracy needs to be improved).
- the analysis is based on (i) the image content of both input images, and (ii) a first-pass global registration result; it is performed within a region around a user-specified position.
- the fully- automatic analysis results in a modified parameter setting, which is then used for a second- pass registration.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- High Energy & Nuclear Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Quality & Reliability (AREA)
- Pulmonology (AREA)
- Human Computer Interaction (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Image Analysis (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR112015018561A BR112015018561A2 (en) | 2013-10-18 | 2014-10-14 | image processing device that can record at least two images of an object, method for recording at least two images of an object, and medical imaging equipment |
EP14784213.2A EP2932470A2 (en) | 2013-10-18 | 2014-10-14 | Registration of medical images |
RU2015138724A RU2677764C2 (en) | 2013-10-18 | 2014-10-14 | Registration of medical images |
US14/763,853 US9536307B2 (en) | 2013-10-18 | 2014-10-14 | Registration of medical images |
JP2015557486A JP6145178B2 (en) | 2013-10-18 | 2014-10-14 | Medical image alignment |
CN201480008133.1A CN105074775B (en) | 2013-10-18 | 2014-10-14 | The registration of medical image |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP13189219.2 | 2013-10-18 | ||
EP13189219 | 2013-10-18 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2015055599A2 true WO2015055599A2 (en) | 2015-04-23 |
WO2015055599A3 WO2015055599A3 (en) | 2015-07-16 |
Family
ID=49517253
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2014/071934 WO2015055599A2 (en) | 2013-10-18 | 2014-10-14 | Registration of medical images |
Country Status (7)
Country | Link |
---|---|
US (1) | US9536307B2 (en) |
EP (1) | EP2932470A2 (en) |
JP (1) | JP6145178B2 (en) |
CN (1) | CN105074775B (en) |
BR (1) | BR112015018561A2 (en) |
RU (1) | RU2677764C2 (en) |
WO (1) | WO2015055599A2 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105816192A (en) * | 2016-03-03 | 2016-08-03 | 王雪原 | Method for three-dimensional registration and brain tissue extraction of individual human brain multimodality medical images |
JP2018518213A (en) * | 2015-05-07 | 2018-07-12 | シロナ・デンタル・システムズ・ゲゼルシャフト・ミット・ベシュレンクテル・ハフツング | Method for image enhancement of image data in a dental image generation system |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11213220B2 (en) | 2014-08-11 | 2022-01-04 | Cubisme, Inc. | Method for determining in vivo tissue biomarker characteristics using multiparameter MRI matrix creation and big data analytics |
US9818048B2 (en) | 2015-01-19 | 2017-11-14 | Ebay Inc. | Fine-grained categorization |
US9905006B2 (en) * | 2015-02-12 | 2018-02-27 | Toshiba Medical Systems Corporation | Medical image processing apparatus, medical image processing method, and medical imaging system |
US9922433B2 (en) | 2015-05-29 | 2018-03-20 | Moira F. Schieke | Method and system for identifying biomarkers using a probability map |
US11538176B2 (en) * | 2015-12-15 | 2022-12-27 | Koninklijke Philips N.V. | Image processing systems and methods |
KR102656542B1 (en) * | 2015-12-22 | 2024-04-12 | 삼성메디슨 주식회사 | Method and apparatus for displaying ultrasound images |
EP3383259A1 (en) * | 2016-02-16 | 2018-10-10 | St. Jude Medical, Cardiology Division, Inc. | Methods and systems for electrophysiology mapping using medical images |
WO2018006058A1 (en) | 2016-07-01 | 2018-01-04 | Cubisme, Inc. | System and method for forming a super-resolution biomarker map image |
US10055842B2 (en) * | 2016-07-29 | 2018-08-21 | Case Western Reserve University | Entropy-based radiogenomic descriptions on magnetic resonance imaging (MRI) for molecular characterization of breast cancer |
JP6833533B2 (en) * | 2017-01-31 | 2021-02-24 | キヤノンメディカルシステムズ株式会社 | Ultrasonic diagnostic equipment and ultrasonic diagnostic support program |
JP6934734B2 (en) * | 2017-03-17 | 2021-09-15 | キヤノン株式会社 | Image processing device, control method and program of image processing device |
US11232853B2 (en) | 2017-04-21 | 2022-01-25 | Cubisme, Inc. | System and method for creating, querying, and displaying a MIBA master file |
CN107145910A (en) * | 2017-05-08 | 2017-09-08 | 京东方科技集团股份有限公司 | Performance generation system, its training method and the performance generation method of medical image |
GB2567636B (en) * | 2017-10-17 | 2021-11-10 | Perspectum Diagnostics Ltd | Method and apparatus for imaging an organ |
DE102017221924B3 (en) * | 2017-12-05 | 2019-05-02 | Siemens Healthcare Gmbh | Method for merging an analysis data set with an image data record, positioning device and computer program |
US20210012546A1 (en) * | 2018-03-26 | 2021-01-14 | Koninklijke Philips N.V. | Automatic fault detection in hybrid imaging |
CN110772280B (en) * | 2018-07-31 | 2023-05-23 | 佳能医疗系统株式会社 | Ultrasonic diagnostic apparatus and method, and image processing apparatus and method |
CN110893108A (en) * | 2018-09-13 | 2020-03-20 | 佳能医疗系统株式会社 | Medical image diagnosis apparatus, medical image diagnosis method, and ultrasonic diagnosis apparatus |
US20220156928A1 (en) * | 2020-11-19 | 2022-05-19 | Mazor Robotics Ltd. | Systems and methods for generating virtual images |
CN112419378B (en) * | 2020-11-20 | 2024-04-09 | 上海联影智能医疗科技有限公司 | Medical image registration method, electronic device and storage medium |
WO2022146996A1 (en) * | 2020-12-30 | 2022-07-07 | Intuitive Surgical Operations, Inc. | Systems for updating a graphical user interface based upon intraoperative imaging |
US11295460B1 (en) | 2021-01-04 | 2022-04-05 | Proprio, Inc. | Methods and systems for registering preoperative image data to intraoperative image data of a scene, such as a surgical scene |
EP4312729A1 (en) | 2021-04-02 | 2024-02-07 | Spintech, Inc. | Systems and methods for template-based automatic detection of anatomical structures |
US11533467B2 (en) | 2021-05-04 | 2022-12-20 | Dapper Labs, Inc. | System and method for creating, managing, and displaying 3D digital collectibles with overlay display elements and surrounding structure display elements |
CN117314985A (en) * | 2021-05-28 | 2023-12-29 | 上海联影医疗科技股份有限公司 | Image registration method, device, equipment and medium |
CN113628259A (en) * | 2021-06-09 | 2021-11-09 | 维沃移动通信(杭州)有限公司 | Image registration processing method and device |
CN113870331B (en) * | 2021-10-07 | 2024-07-26 | 浙江大学 | Chest CT and X-ray real-time registration algorithm based on deep learning |
CN114677421B (en) * | 2022-04-12 | 2023-03-28 | 卡本(深圳)医疗器械有限公司 | Method for estimating rigid/non-rigid registration of 2d organ |
CN117372317A (en) * | 2022-06-30 | 2024-01-09 | 武汉联影智融医疗科技有限公司 | Registration method, registration apparatus, computer device, and readable storage medium |
CN116382465B (en) * | 2023-02-17 | 2024-02-13 | 中国科学院自动化研究所 | Optical brain-computer interface system and method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050065421A1 (en) | 2003-09-19 | 2005-03-24 | Siemens Medical Solutions Usa, Inc. | System and method of measuring disease severity of a patient before, during and after treatment |
WO2007066294A2 (en) | 2005-12-08 | 2007-06-14 | Koninklijke Philips Electronics N.V. | System and method for enabling selection of an image registration transformation |
WO2012102585A2 (en) | 2011-01-27 | 2012-08-02 | 주식회사 엘지화학 | Electrode assembly body |
US20130182925A1 (en) | 2012-01-12 | 2013-07-18 | Marco Razeto | Method of registering image data |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2290599A1 (en) * | 1997-05-23 | 1998-11-26 | The Carolinas Heart Institute | Electromagnetical imaging and therapeutic (emit) systems |
JP4294881B2 (en) * | 2000-05-12 | 2009-07-15 | 富士フイルム株式会社 | Image registration method and apparatus |
AU2003286329A1 (en) | 2003-01-13 | 2004-08-10 | Koninklijke Philips Electronics N.V. | A method of image registration and medical image data processing apparatus |
AU2003903511A0 (en) * | 2003-07-08 | 2003-07-24 | Canon Kabushiki Kaisha | Image registration method improvement |
US7231076B2 (en) | 2004-06-30 | 2007-06-12 | Accuray, Inc. | ROI selection in image registration |
IL179582A0 (en) * | 2006-11-26 | 2007-05-15 | Algotec Systems Ltd | Comparison workflow automation by registration |
JP2012034069A (en) * | 2010-07-29 | 2012-02-16 | Nikon Corp | Image processor and image processing program |
WO2012025855A1 (en) * | 2010-08-25 | 2012-03-01 | Koninklijke Philips Electronics N.V. | Dual modality imaging including quality metrics |
US9384555B2 (en) | 2012-07-02 | 2016-07-05 | Kabushiki Kaisha Toshiba | Motion correction apparatus and method |
-
2014
- 2014-10-14 BR BR112015018561A patent/BR112015018561A2/en not_active Application Discontinuation
- 2014-10-14 CN CN201480008133.1A patent/CN105074775B/en active Active
- 2014-10-14 EP EP14784213.2A patent/EP2932470A2/en not_active Ceased
- 2014-10-14 WO PCT/EP2014/071934 patent/WO2015055599A2/en active Application Filing
- 2014-10-14 US US14/763,853 patent/US9536307B2/en active Active
- 2014-10-14 JP JP2015557486A patent/JP6145178B2/en active Active
- 2014-10-14 RU RU2015138724A patent/RU2677764C2/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050065421A1 (en) | 2003-09-19 | 2005-03-24 | Siemens Medical Solutions Usa, Inc. | System and method of measuring disease severity of a patient before, during and after treatment |
WO2007066294A2 (en) | 2005-12-08 | 2007-06-14 | Koninklijke Philips Electronics N.V. | System and method for enabling selection of an image registration transformation |
WO2012102585A2 (en) | 2011-01-27 | 2012-08-02 | 주식회사 엘지화학 | Electrode assembly body |
US20130182925A1 (en) | 2012-01-12 | 2013-07-18 | Marco Razeto | Method of registering image data |
Non-Patent Citations (3)
Title |
---|
D. RUECKERT; L. 1. SONODA; C. HAYES; D. L. G. HILL; M. O. LEACH; D. J. HAWKES: "Non-rigid registration using free-form deformations: Application to breast MR images", IEEE TRANSACTIONS ON MEDICAL IMAGING, vol. 18, no. 8, 1999, pages 712 - 721 |
J. MODERSITZKI: "Numerical Methods for Image Registration", 2004, OXFORD UNIVERSITY PRESS |
See also references of EP2932470A2 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018518213A (en) * | 2015-05-07 | 2018-07-12 | シロナ・デンタル・システムズ・ゲゼルシャフト・ミット・ベシュレンクテル・ハフツング | Method for image enhancement of image data in a dental image generation system |
CN105816192A (en) * | 2016-03-03 | 2016-08-03 | 王雪原 | Method for three-dimensional registration and brain tissue extraction of individual human brain multimodality medical images |
Also Published As
Publication number | Publication date |
---|---|
JP2016512977A (en) | 2016-05-12 |
BR112015018561A2 (en) | 2017-07-18 |
JP6145178B2 (en) | 2017-06-07 |
WO2015055599A3 (en) | 2015-07-16 |
RU2015138724A3 (en) | 2018-06-19 |
EP2932470A2 (en) | 2015-10-21 |
CN105074775A (en) | 2015-11-18 |
RU2015138724A (en) | 2017-03-15 |
RU2677764C2 (en) | 2019-01-21 |
CN105074775B (en) | 2019-09-10 |
US9536307B2 (en) | 2017-01-03 |
US20160217576A1 (en) | 2016-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9536307B2 (en) | Registration of medical images | |
Noothout et al. | Deep learning-based regression and classification for automatic landmark localization in medical images | |
US10643331B2 (en) | Multi-scale deep reinforcement machine learning for N-dimensional segmentation in medical imaging | |
US9818200B2 (en) | Apparatus and method for multi-atlas based segmentation of medical image data | |
US8675944B2 (en) | Method of registering image data | |
US8437521B2 (en) | Systems and methods for automatic vertebra edge detection, segmentation and identification in 3D imaging | |
US7995864B2 (en) | Method and system for performing image registration | |
US9218542B2 (en) | Localization of anatomical structures using learning-based regression and efficient searching or deformation strategy | |
US9741131B2 (en) | Anatomy aware articulated registration for image segmentation | |
US10417777B2 (en) | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium | |
CN106062782B (en) | Unsupervised training for atlas-based registration | |
EP3447733A1 (en) | Selective image reconstruction | |
CN107004305A (en) | Medical image editor | |
US7616783B2 (en) | System and method for quantifying motion artifacts in perfusion image sequences | |
JP6505078B2 (en) | Image registration | |
US20180064409A1 (en) | Simultaneously displaying medical images | |
US9053541B2 (en) | Image registration | |
EP4156096A1 (en) | Method, device and system for automated processing of medical images to output alerts for detected dissimilarities | |
US9286688B2 (en) | Automatic segmentation of articulated structures | |
CN115700740A (en) | Medical image processing method, apparatus, computer device and storage medium | |
JP2017189384A (en) | Image processor, image processing method and program | |
JP2017099721A (en) | Image processing device and image processing method | |
US10885643B2 (en) | Image processing apparatus, image processing method, and storage medium | |
Wang et al. | CT scan range estimation using multiple body parts detection: let PACS learn the CT image content | |
Chou | Regression learning for 2D/3D image registration |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201480008133.1 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14784213 Country of ref document: EP Kind code of ref document: A2 |
|
REEP | Request for entry into the european phase |
Ref document number: 2014784213 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014784213 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14763853 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2015557486 Country of ref document: JP Kind code of ref document: A |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112015018561 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 2015138724 Country of ref document: RU Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 112015018561 Country of ref document: BR Kind code of ref document: A2 Effective date: 20150803 |