WO2016110463A1 - Ultrasound imaging apparatus and method for segmenting anatomical objects - Google Patents

Ultrasound imaging apparatus and method for segmenting anatomical objects Download PDF

Info

Publication number
WO2016110463A1
WO2016110463A1 PCT/EP2016/050021 EP2016050021W WO2016110463A1 WO 2016110463 A1 WO2016110463 A1 WO 2016110463A1 EP 2016050021 W EP2016050021 W EP 2016050021W WO 2016110463 A1 WO2016110463 A1 WO 2016110463A1
Authority
WO
WIPO (PCT)
Prior art keywords
dimensional
ultrasound
segmentation
data
segmentation model
Prior art date
Application number
PCT/EP2016/050021
Other languages
French (fr)
Inventor
Jochen Peters
Amir Mohammad TAHMASEBI MARAGHOOSH
Juergen Weese
Christian Buerger
Original Assignee
Koninklijke Philips N.V.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Koninklijke Philips N.V. filed Critical Koninklijke Philips N.V.
Priority to JP2017535670A priority Critical patent/JP6644795B2/en
Priority to CN201680005093.4A priority patent/CN107106128B/en
Priority to US15/540,297 priority patent/US10667786B2/en
Priority to EP16700010.8A priority patent/EP3242602B1/en
Publication of WO2016110463A1 publication Critical patent/WO2016110463A1/en

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/13—Tomography
    • A61B8/14—Echo-tomography
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
    • 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
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
    • A61B8/467—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient characterised by special input means
    • A61B8/468—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient characterised by special input means allowing annotation or message recording
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G06T2207/10136—3D ultrasound image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20128—Atlas-based segmentation
    • 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
    • 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
    • G06T2207/30244—Camera pose
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/004—Annotating, labelling

Definitions

  • the present invention relates to an ultrasound imaging apparatus for segmenting anatomical objects in a field of view of an ultrasound acquisition unit.
  • the present invention further relates to a method for segmenting an anatomical object in a field of view of an ultrasound acquisition unit.
  • the present invention relates to image processing and segmentation of anatomical objects in a scanned volume of a patient.
  • the present invention further relates to a computer program comprising program code means for causing a computer to carry out the steps of the method according to the invention when said computer program is carried out on a computer.
  • ultrasound systems which combine ultrasound images with pre-operative image data of a patient derived from different imaging systems.
  • Ultrasound imaging systems can further combine predefined models of the anatomical structure scanned by the ultrasound probe or segmentation data with the images derived from the acquired ultrasound data in order to provide segmented images on the basis of the anatomical model and the ultrasound image data.
  • a corresponding system is e.g.
  • a real-time image and a corresponding real-time segmentation of anatomical objects i.e. a definition of a volume or a surface of an anatomical object in the field of view of the ultrasound probe can provide several advantages.
  • anatomical segmentation techniques require a clear contrast between different tissues visible in the provided image data such as magnet resonance tomography (MRT) or computer tomography (CT).
  • MRT magnet resonance tomography
  • CT computer tomography
  • a majority of the known segmentation techniques have a reduced performance for ultrasound imaging systems, since the segmentation model cannot properly be aligned to the ultrasound images which have a poor signal-to-noise ratio.
  • a prior information about the shape of the anatomical structure to be segmented can improve the segmentation of the anatomical structures in the ultrasound images and these techniques are typically applied to three-dimensional data which require a large computation effort so that these techniques are typically expensive and cannot be applied to real-time applications.
  • two- dimensional image data is acquired and on the basis of a position sensor reconstructed into a regular three-dimensional voxel array which is used for segmentation of anatomical objects.
  • the disadvantage of the known techniques for segmenting anatomical objects in ultrasound image data is that the previously determined three-dimensional segmentation models do not consider deformation of the anatomical objects during the analysis.
  • the computational effort for aligning the segmentation model to real-time three-dimensional ultrasound image data makes three-dimensional segmentation in real-time during the intervention difficult.
  • acquiring three-dimensional data during the intervention is complex so that typically only two-dimensional data is acquired during the intervention.
  • an ultrasound imaging apparatus for segmenting an anatomical object in a field of view of an ultrasound acquisition unit, comprising:
  • a data interface configured to receive two-dimensional ultrasound data of the object in the field of view in an image plane from the ultrasound acquisition unit and to receive a three-dimensional segmentation model as a three-dimensional representation of the object from a segmentation unit
  • an image processor configured to determine a two-dimensional segmentation model on the basis of the three-dimensional segmentation model and a segmentation plane, wherein the segmentation plane and an image plane of the two-dimensional ultrasound data correspond to each other, and
  • the image processor is configured to deformably adapt a contour of the two-dimensional segmentation model to the two-dimensional ultrasound data on the basis of pattern detection and wherein the image processor is configured to provide annotated two- dimensional image data on the basis of the two-dimensional ultrasound data and the segmentation model adapted to the two-dimensional ultrasound data.
  • a computer program comprising program code means for causing a computer to carry out the steps of the method according to the invention when said computer program is carried out on a computer.
  • a storing medium for storing the computer program according to the present invention.
  • the present invention is based on the idea to derive a two-dimensional segmentation model of an anatomical object from a three-dimensional segmentation model and a segmentation plane which corresponds to a cutting plane or an intersecting plane of the three-dimensional representation of the segmentation model, wherein an image plane of the acquired ultrasound data corresponds to the segmentation plane so that the corresponding two-dimensional segmentation model can be adapted to the two-dimensional ultrasound data with low computational effort and within a reduced time frame.
  • the two-dimensional segmentation model is further adapted to the two-dimensional ultrasound data by deforming a contour on the basis of pattern detected in the ultrasound data.
  • annotated two-dimensional image can be provided.
  • different image portions like different pixels are annotated or labeled as different anatomical features on the basis of the two dimensional segmentation model.
  • the surface pixels of the anatomical object can be annotated to provide a contour for visual display.
  • the anatomical object can be segmented in the ultrasound data received from the ultrasound acquisition unit with low computational effort within a short time frame and with high precision.
  • the adaptation of a segmentation model and ultrasound data segmentation of the anatomical object can in particular be provided for a live image stream of the ultrasound data so that the imaging apparatus and the imaging method can, e.g., be used for biopsy or branchytherapy operations or other image-guided interventions.
  • the segmentation unit comprises a data interface configured to receive three-dimensional medical image data of the object, and wherein the segmentation unit is configured to adapt a predefined three-dimensional segmentation model of the anatomical object on the basis of the three-dimensional medical image data prior to the two-dimensional imaging procedure.
  • a predefined three-dimensional segmentation model is a patient specifically adapted three-dimensional representation of the anatomical object and forms the three-dimensional segmentation.
  • the predefined three-dimensional segmentation model and a patient specific three-dimensional segmentation is used in the following during processing of the two- dimensional segmentation.
  • the segmentation unit is configured to provide the adapted three-dimensional segmentation model to the data interface.
  • the three-dimensional segmentation model and/or the two-dimensional segmentation model include a plurality of model elements forming a representation of the anatomical object and wherein anatomical information and/or pattern information are assigned to the model elements.
  • the model elements preferably form line elements or surface elements of the two-dimensional segmentation model or the three- dimensional segmentation model. This is a possibility to improve the adaptation of the contour of the two-dimensional segmentation model and to improve the information provided in the annotated image data, since the segmentation model includes more information than the mere outer shape so that the probability of a misalignment or a wrong segmentation can be reduced.
  • the image processor is configured to deformably adapt a contour of the two-dimensional segmentation model to the ultrasound data on the basis of the anatomical information and/or the pattern information.
  • This is a further possibility to improve the precision of the identification and the alignment, since the additional information like the anatomical information and/or the pattern information can be utilized in addition to the shape of the three-dimensional representation of the anatomical object.
  • the model elements may comprise a pattern information so that the respective elements can be aligned to correspondingly formed pattern in the ultrasound image data, wherein not only edges are detected in the ultrasound image data but also local image intensities or other image patterns are taken into account.
  • the pattern information comprise ultrasound data intensity information of the object, wherein the image processor is configured to adapt a contour of the two-dimensional segmentation model to corresponding patterns in the two- dimensional ultrasound data. This is a possibility to improve the alignment of the
  • the pattern information comprises intensity values and/or intensity gradients to which the model elements are aligned. This is a possibility to further improve the adaptation or the deformation of the shape of the two-dimensional segmentation model since further intensity or contrast information in the ultrasound data can be utilized to segment the anatomical object in the field of view.
  • the intensity information may be an intensity on one or the two opposite sides of the model elements to which the model elements should be aligned so that not only the edge detection is utilized but also the intensity information of the adjacent tissue.
  • the image processor is configured to display the anatomical information in the annotated image data. This is a possibility to further improve the reliability of the object segmentation, since the user can check whether the respective anatomical feature of the segmentation is properly aligned to the anatomical features in the ultrasound image.
  • the ultrasound imaging apparatus further comprises a position determining unit for determining a position and a viewing direction of the ultrasound acquisition unit and for determining the image plane of the two-dimensional ultrasound data, wherein the image processor is configured to determine the segmentation plane corresponding to the determined image plane.
  • a position determining unit for determining a position and a viewing direction of the ultrasound acquisition unit and for determining the image plane of the two-dimensional ultrasound data
  • the image processor is configured to determine the segmentation plane corresponding to the determined image plane.
  • the image plane is determined by the position determining unit and on the basis of the so determined image plane, the segmentation plane is determined so that the three-dimensional segmentation model can be reduced to the corresponding two-dimensional segmentation model in the segmentation plane and the two-dimensional segmentation model can be applied to the ultrasound image in the image plane.
  • the segmentation plane is predefined in relation to the three-dimensional segmentation and the image plane is adapted to the predefined segmentation plane. This is a possibility to determine the plane in which the ultrasound image should be acquired and to adapt the respective image plane to the so-defined segmentation plane so that a user can define the image to be captured prior to the imaging procedure.
  • the ultrasound imaging apparatus comprises a user interface, wherein the segmentation plane is predefined by the user via the user interface in relation to the three-dimensional segmentation model. This is a possibility to select the segmentation plane prior to the imaging and to adapt the image plane to the preselected segmentation plane. This allows to select the segmentation plane without the need of acquiring and segmenting a three-dimensional image before the start of two-dimensional imaging.
  • the data interface is configured to receive the two-dimensional ultrasound data of the anatomical object in the field of view from the ultrasound acquisition unit as a continuous data stream. This is a possibility to utilize live images of the anatomical object which are received in a continuous data stream so that a biopsy or a branchytherapy or some other intervention can be performed on the basis of the respective segmentation of the anatomical object.
  • the present invention provides a possibility to reduce the computational effort and the necessary time frame for segmenting an anatomical object. This is enabled by using two-dimensional instead of three-dimensional ultrasound data, since the two-dimensional segmentation model is determined on the basis of a three-dimensional segmentation model that is cut or intersected along the segmentation plane which
  • the precision of the alignment can be improved since the shape of the so determined two-dimensional segmentation model can be deformably adapted to the ultrasound data on the basis of pattern detection in the ultrasound data.
  • a coarse alignment is achieved by the correlation of the respective segmentation plane and the image plane and a fine correlation or adaptation is achieved by the adaptation of the shape of the segmentation model so that also a deformation of the anatomical object during the analysis can be considered.
  • the present invention allows to use only two-dimensional image data with a dynamically defined orientation with the organ to be segmented.
  • the desired image plane may be defined using a graphical user interface (GUI) where the user can interactively rotate and shift a virtual plane in relation to a phantom drawing of the three-dimensional organ surface representing the shape of the segmentation model.
  • GUI graphical user interface
  • a two-dimensional segmentation model can be derived from the three-dimensional segmentation model by means of the plane defined by the user via the GUI.
  • the desired viewing direction within the desired plane orientation may be defined by an advanced GUI (e.g., where the user can position the ultrasound transducer or draw a scan acquisition direction).
  • Fig. 1 shows a schematic representation of a medical imaging system in use to scan a volume of a patient's body
  • Fig. 2 shows a schematic block diagram of an embodiment of the ultrasound imaging apparatus
  • Fig. 3 shows a two-dimensional ultrasound image captured by an ultrasound probe
  • Fig. 4 shows a schematic diagram of a segmentation of an anatomical object
  • Fig. 5 shows an alignment of the segmentation model and the ultrasound image in order to segment an anatomical object in the field of view;
  • Fig. 6 shows a detailed diagram of segmentation model forming a three- dimensional representation of an anatomical object together with additional information about anatomical features and/or pattern recognition;
  • Fig. 7 shows an alignment of two-dimensional segmentation model and medical image data to segment an anatomical object in the field of view
  • Fig. 8 shows a schematic flow diagram of a method for segmenting an object in the field of view of an ultrasound acquisition unit.
  • Fig. 1 shows a schematic illustration of an ultrasound imaging apparatus 10 according to an embodiment, in particular a medical ultrasound two-dimensional imaging system.
  • the ultrasound imaging apparatus 10 is applied to inspect a volume of an anatomical site, in particular an anatomical site of a patient 12.
  • the ultrasound imaging apparatus 10 comprises an ultrasound probe (or ultrasound acquisition unit) 14 having at least one transducer array having a multitude of transducer elements for transmitting and/or receiving ultrasound waves.
  • the transducer elements are arranged in an array so that the ultrasound probe 14 can determine two-dimensional ultrasound data in a field of view in an image plane of the anatomical site of the patient 12.
  • the ultrasound imaging apparatus 10 comprises a control unit 16 that controls the ultrasound probe 14 and the acquisition of the ultrasound data.
  • control unit 16 controls not only the acquisition of ultrasound data via the ultrasound probe but also signal and image processing that form the ultrasound images out of the echoes of the ultrasound beam received by the transducer array of the ultrasound probe 14.
  • the control unit 16 further segments anatomical objects in the field of view of the ultrasound probe 14 by aligning the image plane of the ultrasound probe 14 and a segmentation plane of a segmentation of the respective anatomical object and aligns the segmentation and the ultrasound image data as described in detail below.
  • the ultrasound imaging apparatus 10 further comprises a position determining unit 18, which determines a position and a viewing direction of the ultrasound probe 14 in order to determine the spatial orientation of an image plane of the ultrasound data acquired by the ultrasound probe 14.
  • the position determining unit 18 may be incorporated in the ultrasound probe 14 as shown in Fig. 1 or, alternatively may be provided as a separate positioning determining unit such as an electromagnetic tracking unit.
  • the ultrasound imaging apparatus 10 further comprises a display 20 for displaying an image including the ultrasound data and the respectively aligned segmentation model for defining a volume or a surface of the anatomical object in the field of view of the ultrasound probe 14.
  • a display 20 for displaying an image including the ultrasound data and the respectively aligned segmentation model for defining a volume or a surface of the anatomical object in the field of view of the ultrasound probe 14.
  • an input device 22 may be provided that may comprise keys or a keyboard 24 for providing a user input.
  • the input device 22 may be connected to the display 20 or directly to the control unit 16.
  • Fig. 2 shows a detailed schematic diagram of the ultrasound imaging apparatus 10 shown in Fig. 1. Identical elements are denoted by identical reference numerals, wherein here merely the differences are described in detail.
  • the ultrasound probe 14 comprises the transducer array 26 for transmitting and receiving ultrasound waves 28 in a field of view 29.
  • the ultrasound probe 14 comprises the position determining unit 18 for determining a position and a viewing direction of the ultrasound probe 14 or the transducer array 26.
  • the position determining unit 18 determines on the basis of the position and the viewing direction of the ultrasound probe 14 or the transducer array 26 an image plane of ultrasound data 30 captured by the transducer array 26 and provided to the control unit 16.
  • the ultrasound data is two-dimensional ultrasound data, wherein two-dimensional image data can be derived from the two-dimensional ultrasound data.
  • the ultrasound data is preferably a continuous data stream and provided as live image data.
  • the ultrasound probe 14 is connected to an input interface 32 of the control unit 16 to provide the ultrasound data 30 and the position and the viewing direction of the ultrasound probe 14 or the image plane of the ultrasound data 30 to the control unit 16.
  • the control unit 16 comprises in general an image processor 34, which is connected to the data interface 32 for receiving the ultrasound data 30 and the position and the viewing direction or the image plane from the position determining unit 18.
  • the control unit 16 further comprises a segmentation unit 36 which is connected to a data interface 38 for receiving medical image data from a database 40 or an additional medical imaging apparatus 40.
  • the image processor 34 in general determines an ultrasound image on the basis of the ultrasound data 30 and provides the image data 42 to the display 20 in order to display the image data to the user.
  • the segmentation unit 36 receives three-dimensional medical image data from the database or the external medical imaging apparatus 40 as image data of the patient 12 and provides a patient specific segmentation model of certain anatomical objects of the patient 12 on the basis of predefined segmentation models corresponding to the respective anatomical objects.
  • the external medical imaging apparatus 40 may be an MRT, a CT or a 3D ultrasound apparatus.
  • the patient specific segmentation model provided by the segmentation unit comprises an adapted mesh of the predefined model adapted to the patient's anatomy and in the patient's coordinate system.
  • the so determined three-dimensional segmentation model is provided by the segmentation unit 36 to the image processor 34.
  • the image processor 34 receives the two-dimensional ultrasound data 30 and the respective image plane having the same coordinate system as the three-dimensional segmentation model received from the input interface 32. On the basis of the image plane in which the two-dimensional ultrasound data is captured, a segmentation plane is determined and the three-dimensional segmentation model is cut or intersected along the segmentation plane so that the three-dimensional segmentation model is reduced to a two-dimensional segmentation model representing a contour or a shape of the respective anatomical object in the segmentation plane.
  • each of the model elements like segmentation lines are associated with additional information about the anatomical features and/or pattern information of the corresponding ultrasound image.
  • the three-dimensional segmentation model is based on a predefined segmentation model which is adapted to the respective anatomical object of the patient 12 on the basis of the three-dimensional medical image data. It is formed by a mesh of triangles, wherein each triangle includes boundary information, anatomical information or pattern information corresponding to the anatomical object and the respective image data associated with the anatomical object.
  • the triangles of the mesh are transformed to corresponding lines of the contour in the two-dimensional segmentation model, wherein the anatomical information, the boundary information and/or the pattern information associated with the triangles is also transformed to the two-dimensional segmentation model, so that the respective information is also associated with the lines of the two-dimensional segmentation model.
  • the image processor 34 is configured to combine the two-dimensional segmentation model and the ultrasound image data 30 in order to provide annotated image data 42 which is provided to the display unit 20.
  • the annotated image data 42 comprises ultrasound image data of the anatomical object and the contour data or the shape of the anatomical object superposed on the ultrasound image data in order to identify the anatomical object in the combined image data 42.
  • the different image portions or pixels are annotated or labeled as a certain anatomical feature, in order to identify or label the anatomical object.
  • the contour or shape of the two-dimensional segmentation model is adapted to the ultrasound image data by deforming the model contour on the basis of pattern detection.
  • an anatomic object such as an organ
  • the respective anatomical object can be identified or labeled precisely with low technical effort.
  • the anatomical information, the boundary information and/or the pattern information of the line segments of the two-dimensional segmentation model is utilized to align the two-dimensional
  • segmentation model to the ultrasound image data and, further, the information is used to adapt the shape of the two-dimensional segmentation model to the anatomical object in the ultrasound data on the basis of pattern detection, contrast information and/or contrast gradients in the ultrasound image data.
  • other mapped model parameters like energy weights balancing mesh stiffness versus image forces can be utilized to adapt the contour or the shape of the two-dimensional segmentation model to the image data. Since the segmentation plane and the respective two-dimensional
  • segmentation model can be determined with low technical effort and low computational effort and since the adaptation or deformation of the two-dimensional segmentation model to the ultrasound image data 30 can be performed with low computational effort and in a short time frame, the adaptation of the two-dimensional segmentation model can also be applied to live image data which is provided as a continuous data stream to the image processor 34. Hence, the segmentation of the anatomical object can also be applied to ultrasound live image applications.
  • Fig. 3 shows a schematic illustration of the ultrasound data 30 in the form of an ultrasound image captured along the image plane, which is in this particular case the yx- plane in the cartesian coordinate system indicated in Fig. 3.
  • the so determined image plane determined by the position determining unit 18 is provided to the image processor 34 so that the image processor 34 can determine the segmentation plane for segmentation of the anatomical object in the field of view 29 as described in the following.
  • the three- dimensional segmentation obtained by adapting a corresponding segmentation model is schematically shown as a mesh 46 of triangles 47.
  • the three-dimensional segmentation model 46 is determined on the basis of a corresponding, predefined three-dimensional segmentation model adapted to the anatomical object of the patient 12 on the basis of the three-dimensional medical image data received from the database 40 or the medical image apparatus 40 as described above and provided by the segmentation unit 36 to the image processor 34.
  • the image processor 34 determines a segmentation plane 48 corresponding to the coordinates of the image plane provided by the position determining unit 18 as shown in Fig. 4, wherein the segmentation plane corresponds to the yx-plane in the cartesian coordinate system as indicated in Fig. 4.
  • the segmentation plane 48 defines a cutting plane or an intersection plane of the three-dimensional segmentation model 46, wherein the image processor 34 is configured to determine two-dimensional segmentation model 50 on the basis of the three-dimensional segmentation model 46, the corresponding three-dimensional segmentation model, and the segmentation plane 48 as shown in Fig. 4.
  • the two-dimensional segmentation model 50 also defines a two-dimensional segmentation in the form of a two- dimensional contour or a shape of the anatomical object to be segmented.
  • the two-dimensional segmentation model 50 comprises different line segments 52 corresponding to the triangles 47 of the three-dimensional segmentation model 46 cut by the segmentation plane 48.
  • the triangles 47 of the adapted three-dimensional segmentation model 46 each comprises additional anatomical information, boundary information or pattern information, wherein the pattern information may include image contrast information, image intensity information, intensity gradients which are expected in the ultrasound image data 30.
  • the pattern information may be for example intensities on both sides of the triangle expected in the respective ultrasound image.
  • the information associated with each of the triangles of the three-dimensional segmentation model 46 is transformed to the two-dimensional segmentation model 50, so that each of the line segments 52 comprises the additional information and can be aligned accordingly to the ultrasound image.
  • the line segments 52 are e.g. not only adapted to the image data on the basis of edge detection but also correspondingly aligned to image intensity on both sides of the line segments 52.
  • the alignment of the two-dimensional segmentation model 50 is schematically shown in Fig. 5, wherein the segmentation model is superimposed and aligned to the anatomical object in the ultrasound image data 30.
  • an annotated image 42 is provided wherein each pixel is annotated or labeled as a certain anatomical object or feature and wherein the annotated image 42 shall be displayed on the display unit 20.
  • the contour of the two-dimensional segmentation model 50 is adapted to the ultrasound data 30 by deformation of the contour as schematically shown by an arrow 54 in Fig. 5.
  • the segmentation model can be adapted to the ultrasound image data 30 with low computation effort and within a short time frame so that also live ultrasound image data can be utilized for the respective definition or annotation of features of anatomical objects in the field of view.
  • the three-dimensional segmentation model 46 is shown as a three- dimensional mesh of triangles 47, wherein each triangle 47 comprises different anatomical information, pattern information and/or boundary information for the respective alignment to the image data.
  • the two- dimensional segmentation model 50 is derived and its contour can be aligned to the respective pattern in the ultrasound data 30 and superimposed in order to provide the annotated image 42 as shown in Fig. 7.
  • a schematic flow diagram illustrates a method for segmenting an anatomical object in the field of view 29 of the ultrasound acquisition unit 14.
  • the method is generally denoted by 60.
  • the method 60 starts at step 62.
  • the predefined three- dimensional model is provided to the segmentation unit 36 and at step 66 the segmentation unit 36 adapts the predefined three-dimensional segmentation model on the basis of the three- dimensional medical image data received from the database 40 or the imaging apparatus 40.
  • the three-dimensional segmentation model 46 is determined as a result of the adaption of the predefined segmentation model to the respective anatomical features of the patient 12 derived from the three-dimensional medical image data.
  • the image processor 34 receives the adapted three-dimensional segmentation model 46 from the segmentation unit 36 and the segmentation plane 48 from the position determining unit 18 and determines the two-dimensional segmentation model 50 by cutting or intersecting the adapted three-dimensional segmentation model 46.
  • the transducer array 26 captures the ultrasound data 30 and provides the ultrasound data 30 to the image processor 34, wherein the image processor 34 combines the adapted two- dimensional segmentation model 50 and the ultrasound image data 30 at step 72.
  • the image processor 34 adapts the two-dimensional segmentation model50 to the anatomical object in the ultrasound data 30 on the basis of pattern detection in the ultrasound data 30 and combines the so adapted segmentation model and the image data to the annotated or labeled image 42, wherein in step 76, the annotated image data 42 is displayed by the display unit 20.
  • the method 60 ends.
  • the anatomical object in the field of view 29 of the ultrasound probe 14 can be identified with low computational effort and reduced time consumption so that anatomical objects can be segmented in live ultrasound images.
  • the computer program may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Public Health (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • Physiology (AREA)
  • Quality & Reliability (AREA)
  • Epidemiology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Primary Health Care (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
  • Image Processing (AREA)

Abstract

An ultrasound imaging apparatus (10) for segmenting an anatomical object in a field of view (29) of an ultrasound acquisition unit (14) is disclosed. The ultrasound imaging apparatus comprises a data interface (32) configured to receive a two-dimensional ultrasound data (30) of the object in the field of view in an image plane from the ultrasound acquisition unit and to receive a three-dimensional segmentation model (46) as a three-dimensional representation of the object from a segmentation unit (36). An image processor (34) is configured to determine a two-dimensional segmentation model (50) on the basis of the three-dimensional segmentation model and a segmentation plane (48), wherein the segmentation plane and an image plane of the two-dimensional ultrasound data correspond to each other. The image processor is configured to adapt a contour of the two-dimensional segmentation model to the two-dimensional ultrasound data on the basis of pattern detection and where the image processor is configured to provide annotated two-dimensional image data (42) on the basis of the two-dimensional ultrasound data and the adapted segmentation model aligned to the two-dimensional ultrasound data.

Description

Ultrasound imaging apparatus and method for segmenting anatomical objects
FIELD OF THE INVENTION
The present invention relates to an ultrasound imaging apparatus for segmenting anatomical objects in a field of view of an ultrasound acquisition unit. The present invention further relates to a method for segmenting an anatomical object in a field of view of an ultrasound acquisition unit. In particular, the present invention relates to image processing and segmentation of anatomical objects in a scanned volume of a patient. The present invention further relates to a computer program comprising program code means for causing a computer to carry out the steps of the method according to the invention when said computer program is carried out on a computer.
BACKGROUND OF THE INVENTION
In the field of medical imaging systems it is generally known to combine different images of a patient acquired by identical or different medical analysis systems in order to improve the diagnostic possibilities. In particular, ultrasound systems are known which combine ultrasound images with pre-operative image data of a patient derived from different imaging systems.
Ultrasound imaging systems can further combine predefined models of the anatomical structure scanned by the ultrasound probe or segmentation data with the images derived from the acquired ultrasound data in order to provide segmented images on the basis of the anatomical model and the ultrasound image data. A corresponding system is e.g.
known from US 2012/0065510 Al .
During an ultrasound image assisted medical procedure such as a biopsy and/or branchytherapy, a real-time image and a corresponding real-time segmentation of anatomical objects i.e. a definition of a volume or a surface of an anatomical object in the field of view of the ultrasound probe can provide several advantages.
Conventional anatomical segmentation techniques require a clear contrast between different tissues visible in the provided image data such as magnet resonance tomography (MRT) or computer tomography (CT). However a majority of the known segmentation techniques have a reduced performance for ultrasound imaging systems, since the segmentation model cannot properly be aligned to the ultrasound images which have a poor signal-to-noise ratio. Usually a prior information about the shape of the anatomical structure to be segmented can improve the segmentation of the anatomical structures in the ultrasound images and these techniques are typically applied to three-dimensional data which require a large computation effort so that these techniques are typically expensive and cannot be applied to real-time applications.
In some further known biopsy and/or branchytherapy applications two- dimensional image data is acquired and on the basis of a position sensor reconstructed into a regular three-dimensional voxel array which is used for segmentation of anatomical objects.
The disadvantage of the known techniques for segmenting anatomical objects in ultrasound image data is that the previously determined three-dimensional segmentation models do not consider deformation of the anatomical objects during the analysis. The computational effort for aligning the segmentation model to real-time three-dimensional ultrasound image data makes three-dimensional segmentation in real-time during the intervention difficult. Furthermore, acquiring three-dimensional data during the intervention is complex so that typically only two-dimensional data is acquired during the intervention.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide an improved ultrasound imaging apparatus which can segment anatomical objects in ultrasound data with high precision and low technical effort. It is further an object of the present invention to provide a corresponding method for segmenting anatomical objects in ultrasound data. It is finally an object of the present invention to provide a computer program for implementing such method and a non-transitory memory for storing such computer program.
In a first aspect of the present invention an ultrasound imaging apparatus is provided for segmenting an anatomical object in a field of view of an ultrasound acquisition unit, comprising:
a data interface configured to receive two-dimensional ultrasound data of the object in the field of view in an image plane from the ultrasound acquisition unit and to receive a three-dimensional segmentation model as a three-dimensional representation of the object from a segmentation unit,
an image processor configured to determine a two-dimensional segmentation model on the basis of the three-dimensional segmentation model and a segmentation plane, wherein the segmentation plane and an image plane of the two-dimensional ultrasound data correspond to each other, and
wherein the image processor is configured to deformably adapt a contour of the two-dimensional segmentation model to the two-dimensional ultrasound data on the basis of pattern detection and wherein the image processor is configured to provide annotated two- dimensional image data on the basis of the two-dimensional ultrasound data and the segmentation model adapted to the two-dimensional ultrasound data.
According to another aspect of the present invention a method for segmenting an anatomical object in a field of view of an ultrasound acquisition unit is provided comprising the steps of:
receiving two-dimensional ultrasound data in an image plane of the object in the field of view from the ultrasound acquisition unit;
receiving a three-dimensional segmentation model as a three-dimensional representation of the object from a segmentation unit,
- determining a two-dimensional segmentation model on the basis of the three- dimensional segmentation model and a segmentation plane intersecting the three-dimensional segmentation model, wherein the segmentation plane and the image plane correspond to each other,
deforming a contour of the two-dimensional segmentation model to the two- dimensional ultrasound data on the basis of pattern detection in the two-dimensional ultrasound data, and
providing annotated two-dimensional image data on the basis of the two- dimensional ultrasound data and the two-dimensional segmentation model adapted to the two-dimensional ultrasound data.
According to another aspect a computer program is provided comprising program code means for causing a computer to carry out the steps of the method according to the invention when said computer program is carried out on a computer.
According to another aspect a storing medium is provided for storing the computer program according to the present invention.
Preferred embodiments of the invention are defined in the dependent claims. It shall be understood that the claimed method has similar and/or identical preferred
embodiments as the claimed device and as defined in the dependent claims.
The present invention is based on the idea to derive a two-dimensional segmentation model of an anatomical object from a three-dimensional segmentation model and a segmentation plane which corresponds to a cutting plane or an intersecting plane of the three-dimensional representation of the segmentation model, wherein an image plane of the acquired ultrasound data corresponds to the segmentation plane so that the corresponding two-dimensional segmentation model can be adapted to the two-dimensional ultrasound data with low computational effort and within a reduced time frame. In order to achieve a precise adaptation or correlation of the two-dimensional segmentation model and the two- dimensional ultrasound data, the two-dimensional segmentation model is further adapted to the two-dimensional ultrasound data by deforming a contour on the basis of pattern detected in the ultrasound data. After the adaptation of the model to the ultrasound data, a
correspondingly annotated two-dimensional image can be provided. In the annotated two dimensional image data, different image portions like different pixels are annotated or labeled as different anatomical features on the basis of the two dimensional segmentation model. In addition or alternatively, the surface pixels of the anatomical object can be annotated to provide a contour for visual display. Hence, the anatomical object can be segmented in the ultrasound data received from the ultrasound acquisition unit with low computational effort within a short time frame and with high precision.
On the basis of the so reduced computational effort the adaptation of a segmentation model and ultrasound data segmentation of the anatomical object can in particular be provided for a live image stream of the ultrasound data so that the imaging apparatus and the imaging method can, e.g., be used for biopsy or branchytherapy operations or other image-guided interventions.
In a preferred embodiment, the segmentation unit comprises a data interface configured to receive three-dimensional medical image data of the object, and wherein the segmentation unit is configured to adapt a predefined three-dimensional segmentation model of the anatomical object on the basis of the three-dimensional medical image data prior to the two-dimensional imaging procedure. This is a possibility to obtain a precise and a detailed segmentation that can be provided as the three-dimensional representation of the object. The adapted predefined three-dimensional segmentation model is a patient specifically adapted three-dimensional representation of the anatomical object and forms the three-dimensional segmentation. The predefined three-dimensional segmentation model and a patient specific three-dimensional segmentation is used in the following during processing of the two- dimensional segmentation.
This enables to utilize knowledge of general anatomical features and the image appearance of the object in the field of view derived from the predefined three-dimensional segmentation model. As a result, we obtain a two-dimensional segmentation model encoding the knowledge about anatomical features and the image appearance. This two-dimensional model only needs to be adapted to the individual anatomical features and image appearance of the patient.
In a further preferred embodiment, the segmentation unit is configured to provide the adapted three-dimensional segmentation model to the data interface.
In a preferred embodiment, the three-dimensional segmentation model and/or the two-dimensional segmentation model include a plurality of model elements forming a representation of the anatomical object and wherein anatomical information and/or pattern information are assigned to the model elements. The model elements preferably form line elements or surface elements of the two-dimensional segmentation model or the three- dimensional segmentation model. This is a possibility to improve the adaptation of the contour of the two-dimensional segmentation model and to improve the information provided in the annotated image data, since the segmentation model includes more information than the mere outer shape so that the probability of a misalignment or a wrong segmentation can be reduced.
In a preferred embodiment, the image processor is configured to deformably adapt a contour of the two-dimensional segmentation model to the ultrasound data on the basis of the anatomical information and/or the pattern information. This is a further possibility to improve the precision of the identification and the alignment, since the additional information like the anatomical information and/or the pattern information can be utilized in addition to the shape of the three-dimensional representation of the anatomical object. The model elements may comprise a pattern information so that the respective elements can be aligned to correspondingly formed pattern in the ultrasound image data, wherein not only edges are detected in the ultrasound image data but also local image intensities or other image patterns are taken into account.
In a preferred embodiment, the pattern information comprise ultrasound data intensity information of the object, wherein the image processor is configured to adapt a contour of the two-dimensional segmentation model to corresponding patterns in the two- dimensional ultrasound data. This is a possibility to improve the alignment of the
segmentation model to the ultrasound image data, since the alignment is not (only) based on simple edge detection but based on more general pattern information in the ultrasound image data. This is a possibility to improve the reliability of the alignment in general. In a preferred embodiment, the pattern information comprises intensity values and/or intensity gradients to which the model elements are aligned. This is a possibility to further improve the adaptation or the deformation of the shape of the two-dimensional segmentation model since further intensity or contrast information in the ultrasound data can be utilized to segment the anatomical object in the field of view. In this respect the intensity information may be an intensity on one or the two opposite sides of the model elements to which the model elements should be aligned so that not only the edge detection is utilized but also the intensity information of the adjacent tissue.
In a preferred embodiment, the image processor is configured to display the anatomical information in the annotated image data. This is a possibility to further improve the reliability of the object segmentation, since the user can check whether the respective anatomical feature of the segmentation is properly aligned to the anatomical features in the ultrasound image.
In a preferred embodiment, the ultrasound imaging apparatus further comprises a position determining unit for determining a position and a viewing direction of the ultrasound acquisition unit and for determining the image plane of the two-dimensional ultrasound data, wherein the image processor is configured to determine the segmentation plane corresponding to the determined image plane. This is a possibility to determine the two relevant planes i.e. the image plane of the two-dimensional ultrasound data and the segmentation plane corresponding to each other, so that an alignment of the two-dimensional segmentation model and the two-dimensional ultrasound data can be achieved with low computational effort, high precision, and within a short time frame. The image plane is determined by the position determining unit and on the basis of the so determined image plane, the segmentation plane is determined so that the three-dimensional segmentation model can be reduced to the corresponding two-dimensional segmentation model in the segmentation plane and the two-dimensional segmentation model can be applied to the ultrasound image in the image plane.
In an alternative embodiment, the segmentation plane is predefined in relation to the three-dimensional segmentation and the image plane is adapted to the predefined segmentation plane. This is a possibility to determine the plane in which the ultrasound image should be acquired and to adapt the respective image plane to the so-defined segmentation plane so that a user can define the image to be captured prior to the imaging procedure. In a further embodiment, the ultrasound imaging apparatus comprises a user interface, wherein the segmentation plane is predefined by the user via the user interface in relation to the three-dimensional segmentation model. This is a possibility to select the segmentation plane prior to the imaging and to adapt the image plane to the preselected segmentation plane. This allows to select the segmentation plane without the need of acquiring and segmenting a three-dimensional image before the start of two-dimensional imaging.
In a further preferred embodiment, the data interface is configured to receive the two-dimensional ultrasound data of the anatomical object in the field of view from the ultrasound acquisition unit as a continuous data stream. This is a possibility to utilize live images of the anatomical object which are received in a continuous data stream so that a biopsy or a branchytherapy or some other intervention can be performed on the basis of the respective segmentation of the anatomical object.
As mentioned above, the present invention provides a possibility to reduce the computational effort and the necessary time frame for segmenting an anatomical object. This is enabled by using two-dimensional instead of three-dimensional ultrasound data, since the two-dimensional segmentation model is determined on the basis of a three-dimensional segmentation model that is cut or intersected along the segmentation plane which
corresponds to the image plane of the two-dimensional ultrasound data to which the two- dimensional segmentation model shall be adapted. Further, the precision of the alignment can be improved since the shape of the so determined two-dimensional segmentation model can be deformably adapted to the ultrasound data on the basis of pattern detection in the ultrasound data. In other words a coarse alignment is achieved by the correlation of the respective segmentation plane and the image plane and a fine correlation or adaptation is achieved by the adaptation of the shape of the segmentation model so that also a deformation of the anatomical object during the analysis can be considered.
In addition, the present invention allows to use only two-dimensional image data with a dynamically defined orientation with the organ to be segmented. If three- dimensional data and a resulting segmentation is not available, the desired image plane may be defined using a graphical user interface (GUI) where the user can interactively rotate and shift a virtual plane in relation to a phantom drawing of the three-dimensional organ surface representing the shape of the segmentation model. In this way, a two-dimensional segmentation model can be derived from the three-dimensional segmentation model by means of the plane defined by the user via the GUI. The desired viewing direction within the desired plane orientation may be defined by an advanced GUI (e.g., where the user can position the ultrasound transducer or draw a scan acquisition direction).
BRIEF DESCRIPTION OF THE DRAWINGS
These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. In the following drawings
Fig. 1 shows a schematic representation of a medical imaging system in use to scan a volume of a patient's body;
Fig. 2 shows a schematic block diagram of an embodiment of the ultrasound imaging apparatus;
Fig. 3 shows a two-dimensional ultrasound image captured by an ultrasound probe;
Fig. 4 shows a schematic diagram of a segmentation of an anatomical object; Fig. 5 shows an alignment of the segmentation model and the ultrasound image in order to segment an anatomical object in the field of view;
Fig. 6 shows a detailed diagram of segmentation model forming a three- dimensional representation of an anatomical object together with additional information about anatomical features and/or pattern recognition;
Fig. 7 shows an alignment of two-dimensional segmentation model and medical image data to segment an anatomical object in the field of view; and
Fig. 8 shows a schematic flow diagram of a method for segmenting an object in the field of view of an ultrasound acquisition unit.
DETAILED DESCRIPTION OF THE INVENTION
Fig. 1 shows a schematic illustration of an ultrasound imaging apparatus 10 according to an embodiment, in particular a medical ultrasound two-dimensional imaging system. The ultrasound imaging apparatus 10 is applied to inspect a volume of an anatomical site, in particular an anatomical site of a patient 12. The ultrasound imaging apparatus 10 comprises an ultrasound probe (or ultrasound acquisition unit) 14 having at least one transducer array having a multitude of transducer elements for transmitting and/or receiving ultrasound waves. The transducer elements are arranged in an array so that the ultrasound probe 14 can determine two-dimensional ultrasound data in a field of view in an image plane of the anatomical site of the patient 12. The ultrasound imaging apparatus 10 comprises a control unit 16 that controls the ultrasound probe 14 and the acquisition of the ultrasound data. As will be explained in further detail below, the control unit 16 controls not only the acquisition of ultrasound data via the ultrasound probe but also signal and image processing that form the ultrasound images out of the echoes of the ultrasound beam received by the transducer array of the ultrasound probe 14. The control unit 16 further segments anatomical objects in the field of view of the ultrasound probe 14 by aligning the image plane of the ultrasound probe 14 and a segmentation plane of a segmentation of the respective anatomical object and aligns the segmentation and the ultrasound image data as described in detail below.
The ultrasound imaging apparatus 10 further comprises a position determining unit 18, which determines a position and a viewing direction of the ultrasound probe 14 in order to determine the spatial orientation of an image plane of the ultrasound data acquired by the ultrasound probe 14. The position determining unit 18 may be incorporated in the ultrasound probe 14 as shown in Fig. 1 or, alternatively may be provided as a separate positioning determining unit such as an electromagnetic tracking unit.
The ultrasound imaging apparatus 10 further comprises a display 20 for displaying an image including the ultrasound data and the respectively aligned segmentation model for defining a volume or a surface of the anatomical object in the field of view of the ultrasound probe 14. Further, an input device 22 may be provided that may comprise keys or a keyboard 24 for providing a user input. The input device 22 may be connected to the display 20 or directly to the control unit 16.
Fig. 2 shows a detailed schematic diagram of the ultrasound imaging apparatus 10 shown in Fig. 1. Identical elements are denoted by identical reference numerals, wherein here merely the differences are described in detail.
The ultrasound probe 14 comprises the transducer array 26 for transmitting and receiving ultrasound waves 28 in a field of view 29. The ultrasound probe 14 comprises the position determining unit 18 for determining a position and a viewing direction of the ultrasound probe 14 or the transducer array 26. The position determining unit 18 determines on the basis of the position and the viewing direction of the ultrasound probe 14 or the transducer array 26 an image plane of ultrasound data 30 captured by the transducer array 26 and provided to the control unit 16. The ultrasound data is two-dimensional ultrasound data, wherein two-dimensional image data can be derived from the two-dimensional ultrasound data. The ultrasound data is preferably a continuous data stream and provided as live image data. The ultrasound probe 14 is connected to an input interface 32 of the control unit 16 to provide the ultrasound data 30 and the position and the viewing direction of the ultrasound probe 14 or the image plane of the ultrasound data 30 to the control unit 16.
The control unit 16 comprises in general an image processor 34, which is connected to the data interface 32 for receiving the ultrasound data 30 and the position and the viewing direction or the image plane from the position determining unit 18. The control unit 16 further comprises a segmentation unit 36 which is connected to a data interface 38 for receiving medical image data from a database 40 or an additional medical imaging apparatus 40.
The image processor 34 in general determines an ultrasound image on the basis of the ultrasound data 30 and provides the image data 42 to the display 20 in order to display the image data to the user.
The segmentation unit 36 receives three-dimensional medical image data from the database or the external medical imaging apparatus 40 as image data of the patient 12 and provides a patient specific segmentation model of certain anatomical objects of the patient 12 on the basis of predefined segmentation models corresponding to the respective anatomical objects. The external medical imaging apparatus 40 may be an MRT, a CT or a 3D ultrasound apparatus. The patient specific segmentation model provided by the segmentation unit comprises an adapted mesh of the predefined model adapted to the patient's anatomy and in the patient's coordinate system. The so determined three-dimensional segmentation model is provided by the segmentation unit 36 to the image processor 34.
The image processor 34 receives the two-dimensional ultrasound data 30 and the respective image plane having the same coordinate system as the three-dimensional segmentation model received from the input interface 32. On the basis of the image plane in which the two-dimensional ultrasound data is captured, a segmentation plane is determined and the three-dimensional segmentation model is cut or intersected along the segmentation plane so that the three-dimensional segmentation model is reduced to a two-dimensional segmentation model representing a contour or a shape of the respective anatomical object in the segmentation plane.
During the transformation of the three-dimensional segmentation model to the two-dimensional segmentation model intersected along the segmentation plane, additional anatomical information and/or pattern information of the corresponding three-dimensional segmentation model is also transformed and the corresponding two-dimensional
segmentation model is created. In this two-dimensional segmentation model, each of the model elements like segmentation lines are associated with additional information about the anatomical features and/or pattern information of the corresponding ultrasound image.
The three-dimensional segmentation model is based on a predefined segmentation model which is adapted to the respective anatomical object of the patient 12 on the basis of the three-dimensional medical image data. It is formed by a mesh of triangles, wherein each triangle includes boundary information, anatomical information or pattern information corresponding to the anatomical object and the respective image data associated with the anatomical object. During the transformation of the three-dimensional segmentation model to the two-dimensional segmentation model, the triangles of the mesh are transformed to corresponding lines of the contour in the two-dimensional segmentation model, wherein the anatomical information, the boundary information and/or the pattern information associated with the triangles is also transformed to the two-dimensional segmentation model, so that the respective information is also associated with the lines of the two-dimensional segmentation model.
The image processor 34 is configured to combine the two-dimensional segmentation model and the ultrasound image data 30 in order to provide annotated image data 42 which is provided to the display unit 20. The annotated image data 42 comprises ultrasound image data of the anatomical object and the contour data or the shape of the anatomical object superposed on the ultrasound image data in order to identify the anatomical object in the combined image data 42. In the annotated image data 42 the different image portions or pixels are annotated or labeled as a certain anatomical feature, in order to identify or label the anatomical object. The contour or shape of the two-dimensional segmentation model is adapted to the ultrasound image data by deforming the model contour on the basis of pattern detection. Hence, a movement or a deformation of an anatomic object such as an organ can be considered and the respective anatomical object can be identified or labeled precisely with low technical effort. During the adaptation or deformation step the anatomical information, the boundary information and/or the pattern information of the line segments of the two-dimensional segmentation model is utilized to align the two-dimensional
segmentation model to the ultrasound image data and, further, the information is used to adapt the shape of the two-dimensional segmentation model to the anatomical object in the ultrasound data on the basis of pattern detection, contrast information and/or contrast gradients in the ultrasound image data. Further, other mapped model parameters like energy weights balancing mesh stiffness versus image forces can be utilized to adapt the contour or the shape of the two-dimensional segmentation model to the image data. Since the segmentation plane and the respective two-dimensional
segmentation model can be determined with low technical effort and low computational effort and since the adaptation or deformation of the two-dimensional segmentation model to the ultrasound image data 30 can be performed with low computational effort and in a short time frame, the adaptation of the two-dimensional segmentation model can also be applied to live image data which is provided as a continuous data stream to the image processor 34. Hence, the segmentation of the anatomical object can also be applied to ultrasound live image applications.
Fig. 3 shows a schematic illustration of the ultrasound data 30 in the form of an ultrasound image captured along the image plane, which is in this particular case the yx- plane in the cartesian coordinate system indicated in Fig. 3. The so determined image plane determined by the position determining unit 18 is provided to the image processor 34 so that the image processor 34 can determine the segmentation plane for segmentation of the anatomical object in the field of view 29 as described in the following. In Fig. 4, the three- dimensional segmentation obtained by adapting a corresponding segmentation model is schematically shown as a mesh 46 of triangles 47. The three-dimensional segmentation model 46 is determined on the basis of a corresponding, predefined three-dimensional segmentation model adapted to the anatomical object of the patient 12 on the basis of the three-dimensional medical image data received from the database 40 or the medical image apparatus 40 as described above and provided by the segmentation unit 36 to the image processor 34. The image processor 34 determines a segmentation plane 48 corresponding to the coordinates of the image plane provided by the position determining unit 18 as shown in Fig. 4, wherein the segmentation plane corresponds to the yx-plane in the cartesian coordinate system as indicated in Fig. 4. The segmentation plane 48 defines a cutting plane or an intersection plane of the three-dimensional segmentation model 46, wherein the image processor 34 is configured to determine two-dimensional segmentation model 50 on the basis of the three-dimensional segmentation model 46, the corresponding three-dimensional segmentation model, and the segmentation plane 48 as shown in Fig. 4. The two-dimensional segmentation model 50 also defines a two-dimensional segmentation in the form of a two- dimensional contour or a shape of the anatomical object to be segmented.
The two-dimensional segmentation model 50 comprises different line segments 52 corresponding to the triangles 47 of the three-dimensional segmentation model 46 cut by the segmentation plane 48. The triangles 47 of the adapted three-dimensional segmentation model 46 each comprises additional anatomical information, boundary information or pattern information, wherein the pattern information may include image contrast information, image intensity information, intensity gradients which are expected in the ultrasound image data 30. The pattern information may be for example intensities on both sides of the triangle expected in the respective ultrasound image. The information associated with each of the triangles of the three-dimensional segmentation model 46 is transformed to the two-dimensional segmentation model 50, so that each of the line segments 52 comprises the additional information and can be aligned accordingly to the ultrasound image. Hence, the line segments 52 are e.g. not only adapted to the image data on the basis of edge detection but also correspondingly aligned to image intensity on both sides of the line segments 52.
The alignment of the two-dimensional segmentation model 50 is schematically shown in Fig. 5, wherein the segmentation model is superimposed and aligned to the anatomical object in the ultrasound image data 30. In a further step, an annotated image 42 is provided wherein each pixel is annotated or labeled as a certain anatomical object or feature and wherein the annotated image 42 shall be displayed on the display unit 20. In order to improve the precision of the alignment, the contour of the two-dimensional segmentation model 50 is adapted to the ultrasound data 30 by deformation of the contour as schematically shown by an arrow 54 in Fig. 5.
Hence, the segmentation model can be adapted to the ultrasound image data 30 with low computation effort and within a short time frame so that also live ultrasound image data can be utilized for the respective definition or annotation of features of anatomical objects in the field of view.
In Fig. 6, the three-dimensional segmentation model 46 is shown as a three- dimensional mesh of triangles 47, wherein each triangle 47 comprises different anatomical information, pattern information and/or boundary information for the respective alignment to the image data. On basis of this detailed three-dimensional segmentation model 46, the two- dimensional segmentation model 50 is derived and its contour can be aligned to the respective pattern in the ultrasound data 30 and superimposed in order to provide the annotated image 42 as shown in Fig. 7.
In Fig. 8 a schematic flow diagram illustrates a method for segmenting an anatomical object in the field of view 29 of the ultrasound acquisition unit 14. The method is generally denoted by 60. The method 60 starts at step 62. At step 64, the predefined three- dimensional model is provided to the segmentation unit 36 and at step 66 the segmentation unit 36 adapts the predefined three-dimensional segmentation model on the basis of the three- dimensional medical image data received from the database 40 or the imaging apparatus 40. The three-dimensional segmentation model 46 is determined as a result of the adaption of the predefined segmentation model to the respective anatomical features of the patient 12 derived from the three-dimensional medical image data.
In step 68, the image processor 34 receives the adapted three-dimensional segmentation model 46 from the segmentation unit 36 and the segmentation plane 48 from the position determining unit 18 and determines the two-dimensional segmentation model 50 by cutting or intersecting the adapted three-dimensional segmentation model 46. At step 70, the transducer array 26 captures the ultrasound data 30 and provides the ultrasound data 30 to the image processor 34, wherein the image processor 34 combines the adapted two- dimensional segmentation model 50 and the ultrasound image data 30 at step 72. At step 74 the image processor 34 adapts the two-dimensional segmentation model50 to the anatomical object in the ultrasound data 30 on the basis of pattern detection in the ultrasound data 30 and combines the so adapted segmentation model and the image data to the annotated or labeled image 42, wherein in step 76, the annotated image data 42 is displayed by the display unit 20. At step 78, the method 60 ends.
Hence, the anatomical object in the field of view 29 of the ultrasound probe 14 can be identified with low computational effort and reduced time consumption so that anatomical objects can be segmented in live ultrasound images.
While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.
In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single element or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
The computer program may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope.

Claims

CLAIMS:
1. Ultrasound imaging apparatus (10) for segmenting an anatomical object in a field of view (29) of an ultrasound acquisition unit (14), comprising:
a data interface (32) configured to receive two-dimensional ultrasound data (30) of the object in the field of view in an image plane from the ultrasound acquisition unit (14) and to receive a three-dimensional segmentation model (46) as a three-dimensional representation of the object from a segmentation unit (36),
an image processor (34) configured to determine a two-dimensional segmentation model (50) on the basis of the three-dimensional segmentation model (46) and a segmentation plane (48), wherein the segmentation plane and an image plane of the two- dimensional ultrasound data correspond to each other, and
wherein the image processor is configured to adapt a contour of the two- dimensional segmentation model to the two-dimensional ultrasound data on the basis of pattern detection and wherein the image processor is configured to provide annotated two- dimensional image data (42) on the basis of the two-dimensional ultrasound data and the adapted segmentation model adapted to the two-dimensional ultrasound data.
2. Ultrasound imaging apparatus as claimed in claim 1, wherein the segmentation unit comprises a data interface (38) configured to receive three-dimensional medical image data of the object, and wherein the segmentation unit is configured to adapt a predefined three-dimensional segmentation model of the anatomical object on the basis of the three- dimensional medical image data.
3. Ultrasound imaging apparatus as claimed in claim 2, wherein the segmentation unit is configured to provide the adapted three-dimensional segmentation model to the data interface.
4. Ultrasound imaging apparatus as claimed in claim 1, wherein the three- dimensional segmentation model and/or the two-dimensional segmentation model include a plurality of surface elements (47) or line elements (52) forming the representation of the anatomical object surface or contour and wherein anatomical information and/or pattern information are assigned to the surface elements or line elements.
5. Ultrasound imaging apparatus as claimed in claim 4, wherein the image processor is configured to adapt a contour of the two-dimensional segmentation model to the ultrasound data on the basis of pattern information.
6. Ultrasound imaging apparatus as claimed in claim 4, wherein the pattern information comprise ultrasound data intensity information of the object and wherein the image processor is configured to adapt a contour of the two-dimensional segmentation model to corresponding intensities in the two-dimensional ultrasound data.
7. Ultrasound imaging apparatus as claimed in claim 4, wherein the image processor is configured to display the anatomical information in the annotated image data.
8. Ultrasound imaging apparatus as claimed in claim 1, further comprising a position determining unit (18) for determining a position and a viewing direction of the ultrasound acquisition unit and for determining the image plane of the two-dimensional ultrasound data, wherein the image processor is configured to determine the segmentation plane corresponding to the determined image plane.
9. Ultrasound imaging apparatus as claimed in claim 1, wherein the segmentation plane is predefined in relation to the three-dimensional segmentation model and wherein the image plane is adapted to the predefined segmentation plane.
10. Ultrasound imaging apparatus as claimed in claim 9, further comprising a user interface (22), wherein the segmentation plane is predefined by the user via the user interface.
11. Ultrasound imaging apparatus as claimed in claim 1 , wherein the data interface is configured to receive the two-dimensional ultrasound data of the anatomical object in the field of view from the ultrasound acquisition unit as a continuous data stream.
12. Method (60) for identifying an anatomical object in a field of view (29) of an ultrasound acquisition unit (14), comprising the steps of: receiving two-dimensional ultrasound data (30) in an image plane of the object in the field of view from the ultrasound acquisition unit;
receiving a three-dimensional segmentation model (46) as a three-dimensional representation of the object from a segmentation unit (36),
determining (68) a two-dimensional segmentation model (50) on the basis of the three-dimensional segmentation model and a segmentation plane (48) intersecting the three-dimensional segmentation model, wherein the segmentation plane and the image plane correspond to each other,
deforming a contour of the two-dimensional segmentation model to the two- dimensional ultrasound data on the basis of pattern detection in the two-dimensional ultrasound data, and
providing (76) annotated two-dimensional image data (42) on the basis of the two-dimensional ultrasound data and the adapted two-dimensional segmentation model aligned to the two-dimensional ultrasound data.
13. Computer program comprising program means for causing a computer to carry out the steps of the method (60) as claimed in claim 12 when said computer program is carried out on a computer.
PCT/EP2016/050021 2015-01-06 2016-01-04 Ultrasound imaging apparatus and method for segmenting anatomical objects WO2016110463A1 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2017535670A JP6644795B2 (en) 2015-01-06 2016-01-04 Ultrasound imaging apparatus and method for segmenting anatomical objects
CN201680005093.4A CN107106128B (en) 2015-01-06 2016-01-04 Ultrasound imaging apparatus and method for segmenting an anatomical target
US15/540,297 US10667786B2 (en) 2015-01-06 2016-01-04 Ultrasound imaging apparatus and method for segmenting anatomical objects
EP16700010.8A EP3242602B1 (en) 2015-01-06 2016-01-04 Ultrasound imaging apparatus and method for segmenting anatomical objects

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201562100136P 2015-01-06 2015-01-06
US62/100,136 2015-01-06
EP15152964 2015-01-29
EP15152964.1 2015-01-29

Publications (1)

Publication Number Publication Date
WO2016110463A1 true WO2016110463A1 (en) 2016-07-14

Family

ID=52396608

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2016/050021 WO2016110463A1 (en) 2015-01-06 2016-01-04 Ultrasound imaging apparatus and method for segmenting anatomical objects

Country Status (5)

Country Link
US (1) US10667786B2 (en)
EP (1) EP3242602B1 (en)
JP (1) JP6644795B2 (en)
CN (1) CN107106128B (en)
WO (1) WO2016110463A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018077747A1 (en) 2016-10-25 2018-05-03 Koninklijke Philips N.V. A method and apparatus for segmenting a two-dimensional image of an anatomical structure
KR20180070878A (en) * 2016-12-19 2018-06-27 지멘스 메디컬 솔루션즈 유에스에이, 인크. Method of providing annotation information of ultrasound probe and ultrasound system
CN110494188A (en) * 2017-03-30 2019-11-22 皇家飞利浦有限公司 Determine the final two dimensional image of an at least width for visualizing attention object in three-D ultrasonic volume
US11715196B2 (en) 2017-07-18 2023-08-01 Koninklijke Philips N.V. Method and system for dynamic multi-dimensional images of an object

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3711673A1 (en) * 2019-03-18 2020-09-23 Koninklijke Philips N.V. Methods and systems for adjusting the field of view of an ultrasound probe
US11478222B2 (en) * 2019-05-22 2022-10-25 GE Precision Healthcare LLC Method and system for ultrasound imaging multiple anatomical zones
CA3150534A1 (en) * 2019-09-12 2021-03-18 Allen Lu Systems and methods for automated ultrasound image labeling and quality grading

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004111937A1 (en) * 2003-06-13 2004-12-23 Philips Intellectual Property & Standards Gmbh 3d image segmentation
WO2013114257A2 (en) * 2012-02-03 2013-08-08 Koninklijke Philips N.V. Imaging apparatus for imaging an object
WO2014134188A1 (en) * 2013-02-28 2014-09-04 Rivanna Medical, LLC Systems and methods for ultrasound imaging

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4614548B2 (en) * 2001-01-31 2011-01-19 パナソニック株式会社 Ultrasonic diagnostic equipment
US6824517B2 (en) 2002-06-25 2004-11-30 Koninklijke Philips Electronics N.V. Ultrasound quantification in real-time using acoustic data in more than two dimensions
TR201815808T4 (en) 2005-06-21 2018-11-21 Anheuser Busch Inbev Sa Progressive model-based adaptation
WO2007034425A2 (en) 2005-09-23 2007-03-29 Philips Intellectual Property & Standards Gmbh A method of and a system for adapting a geometric model using multiple partial transformations
KR100870412B1 (en) * 2005-12-01 2008-11-26 주식회사 메디슨 Ultrasound system for forming 3d fetus ultrasound image based on fetus surface image extracted by svm-based texture classification and method for the same
ATE437421T1 (en) 2005-12-19 2009-08-15 Koninkl Philips Electronics Nv METHOD FOR FACILITATING POST-PROCESSING OF IMAGES VIA DEFORMABLE NETWORKS
US7889912B2 (en) * 2006-09-15 2011-02-15 The General Electric Company Method for real-time tracking of cardiac structures in 3D echocardiography
JP4935632B2 (en) 2007-11-07 2012-05-23 ソニー株式会社 Image processing apparatus, image processing method, and image processing program
DE102008030244A1 (en) * 2008-06-25 2009-12-31 Siemens Aktiengesellschaft Method for supporting percutaneous interventions
US10102347B2 (en) * 2008-09-26 2018-10-16 Koninklijke Philips N.V. Patient specific anatiomical sketches for medical reports
JP5491836B2 (en) * 2009-01-30 2014-05-14 株式会社東芝 Ultrasonic diagnostic apparatus, ultrasonic image processing apparatus, medical image diagnostic apparatus, and medical image processing apparatus
EP2545527B1 (en) * 2010-03-11 2014-07-02 Koninklijke Philips N.V. Probabilistic refinement of model-based segmentation
US20120065510A1 (en) 2010-09-09 2012-03-15 General Electric Company Ultrasound system and method for calculating quality-of-fit
CN103402453B (en) * 2011-03-03 2016-11-16 皇家飞利浦有限公司 Auto-initiation and the system and method for registration for navigation system
WO2013040693A1 (en) * 2011-09-23 2013-03-28 Hamid Reza Tizhoosh Computer system and method for atlas-based consensual and consistent contouring of medical images
US8724878B2 (en) * 2012-01-12 2014-05-13 General Electric Company Ultrasound image segmentation
US9375195B2 (en) * 2012-05-31 2016-06-28 Siemens Medical Solutions Usa, Inc. System and method for real-time ultrasound guided prostate needle biopsy based on biomechanical model of the prostate from magnetic resonance imaging data
US20140105473A1 (en) * 2012-10-12 2014-04-17 Samsung Electronics Co., Ltd. Method and apparatus for segmenting contour in image
US8831311B2 (en) * 2012-12-31 2014-09-09 General Electric Company Methods and systems for automated soft tissue segmentation, circumference estimation and plane guidance in fetal abdominal ultrasound images
US9147258B2 (en) * 2013-02-19 2015-09-29 General Electric Company Methods and systems for segmentation in echocardiography
WO2014181278A1 (en) * 2013-05-09 2014-11-13 Koninklijke Philips N.V. Method and system for mesh segmentation and mesh registration
CA2918295A1 (en) * 2013-07-15 2015-01-22 Tel Hashomer Medical Research, Infrastructure And Services Ltd. Mri image fusion methods and uses thereof
WO2015103388A1 (en) * 2014-01-02 2015-07-09 Metritrack, Inc. System and method for tracking completeness of co-registered medical image data
CN106659473B (en) * 2014-07-29 2020-04-21 皇家飞利浦有限公司 Ultrasonic imaging apparatus

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004111937A1 (en) * 2003-06-13 2004-12-23 Philips Intellectual Property & Standards Gmbh 3d image segmentation
WO2013114257A2 (en) * 2012-02-03 2013-08-08 Koninklijke Philips N.V. Imaging apparatus for imaging an object
WO2014134188A1 (en) * 2013-02-28 2014-09-04 Rivanna Medical, LLC Systems and methods for ultrasound imaging

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018077747A1 (en) 2016-10-25 2018-05-03 Koninklijke Philips N.V. A method and apparatus for segmenting a two-dimensional image of an anatomical structure
CN109863534A (en) * 2016-10-25 2019-06-07 皇家飞利浦有限公司 Method and apparatus for dividing the two dimensional image of anatomical structure
US10984533B2 (en) 2016-10-25 2021-04-20 Koninklijke Philips N.V. Method and apparatus for segmenting a two-dimensional image of an anatomical structure
CN109863534B (en) * 2016-10-25 2023-08-01 皇家飞利浦有限公司 Method and device for segmenting a two-dimensional image of an anatomical structure
KR20180070878A (en) * 2016-12-19 2018-06-27 지멘스 메디컬 솔루션즈 유에스에이, 인크. Method of providing annotation information of ultrasound probe and ultrasound system
KR102107581B1 (en) 2016-12-19 2020-05-07 지멘스 메디컬 솔루션즈 유에스에이, 인크. Method of providing annotation information of ultrasound probe and ultrasound system
CN110494188A (en) * 2017-03-30 2019-11-22 皇家飞利浦有限公司 Determine the final two dimensional image of an at least width for visualizing attention object in three-D ultrasonic volume
CN110494188B (en) * 2017-03-30 2021-09-10 皇家飞利浦有限公司 Device and method for determining at least one final two-dimensional image
US11715196B2 (en) 2017-07-18 2023-08-01 Koninklijke Philips N.V. Method and system for dynamic multi-dimensional images of an object

Also Published As

Publication number Publication date
CN107106128B (en) 2020-07-03
EP3242602B1 (en) 2019-08-07
EP3242602A1 (en) 2017-11-15
JP2018501005A (en) 2018-01-18
US20170360396A1 (en) 2017-12-21
JP6644795B2 (en) 2020-02-12
CN107106128A (en) 2017-08-29
US10667786B2 (en) 2020-06-02

Similar Documents

Publication Publication Date Title
US10667786B2 (en) Ultrasound imaging apparatus and method for segmenting anatomical objects
US10631829B2 (en) Segmentation of large objects from multiple three-dimensional views
US9129362B2 (en) Semantic navigation and lesion mapping from digital breast tomosynthesis
KR101059312B1 (en) Non-rigid Image Matching Device for Ultrasound and CT Images Using Brightness and Gradient Information
EP3174467B1 (en) Ultrasound imaging apparatus
US7889895B2 (en) Method and apparatus for identifying pathology in brain images
CN106456084B (en) Ultrasonic imaging apparatus
KR20210051141A (en) Method, apparatus and computer program for providing augmented reality based medical information of patient
EP3463097B1 (en) Correcting probe induced deformation in an ultrasound fusing imaging system
CN110956076B (en) Method and system for structure identification in three-dimensional ultrasound data based on volume rendering
KR20210052270A (en) Method, apparatus and computer program for providing augmented reality based medical information of patient
Alam et al. Evaluation of medical image registration techniques based on nature and domain of the transformation
JP2009301254A (en) Image processing device, method and program
KR20120000729A (en) Position tracking method for vascular treatment micro robot through registration between x ray image and ct 3d model
De Nigris et al. Fast and robust registration based on gradient orientations: case study matching intra-operative ultrasound to pre-operative mri in neurosurgery
JP6476125B2 (en) Image processing apparatus and surgical microscope system
KR20120000722A (en) Non rigid fusion method for multi medicla modality
Yang et al. A novel neurosurgery registration pipeline based on heat maps and anatomic facial feature points
KR20120000727A (en) Virtual x-ray image generation method with fiducial marker for multi medical modality
KR20130013504A (en) Ct 3d model registration method using x-ray raw data
García Corisco Registration of ultrasound medical images
KR20120000731A (en) Vascular path generation method using x-ray image
Foroughi Fast Elastic Registration of Ultrasound Images
KR20130013506A (en) Marker recognition method according to the direction of x-ray scan
KR20120000725A (en) Position tracking method for vascular treatment micro robot through non-rigid fusion

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: 16700010

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15540297

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2017535670

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2016700010

Country of ref document: EP