WO2014180972A2 - Système et procédé d'analyse tridimensionnelle de structures anatomiques pour une population de patients - Google Patents

Système et procédé d'analyse tridimensionnelle de structures anatomiques pour une population de patients Download PDF

Info

Publication number
WO2014180972A2
WO2014180972A2 PCT/EP2014/059504 EP2014059504W WO2014180972A2 WO 2014180972 A2 WO2014180972 A2 WO 2014180972A2 EP 2014059504 W EP2014059504 W EP 2014059504W WO 2014180972 A2 WO2014180972 A2 WO 2014180972A2
Authority
WO
WIPO (PCT)
Prior art keywords
patient
variation
anatomy
area
modes
Prior art date
Application number
PCT/EP2014/059504
Other languages
English (en)
Other versions
WO2014180972A3 (fr
Inventor
Bart BOSMANS
Original Assignee
Materialise 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 Materialise N.V. filed Critical Materialise N.V.
Publication of WO2014180972A2 publication Critical patent/WO2014180972A2/fr
Publication of WO2014180972A3 publication Critical patent/WO2014180972A3/fr

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/108—Computer aided selection or customisation of medical implants or cutting guides
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/25—User interfaces for surgical systems
    • A61B2034/256—User interfaces for surgical systems having a database of accessory information, e.g. including context sensitive help or scientific articles

Definitions

  • This application relates to the performance of clinical studies in a patient population. More particularly, this application relates to a system and method for analyzing anatomic structures using three-dimensional (“3D”) surface models.
  • 3D three-dimensional
  • a system for creating a patient-specific medical device based on three dimensional image data analysis of a patient population may include a database configured to store image data corresponding to an area of anatomy for the patient population and an imaging device configured to capture an image of the area of anatomy for a patient.
  • a three dimensional image processing module may be configured to perform data segmentation by extracting geometries from the stored image data corresponding to the area of anatomy for the patient population.
  • the system may further include a computer aided design/meshing module which is configured to convert the extracted geometries to tubular, triangulated surfaces and parameterize the converted extracted geometries.
  • a dataset may be created by remeshing the tubular, triangulated surfaces.
  • a numerical analysis module may then be provided which is configured to generate a statistical shape model comprising an average shape of the area of anatomy based on the dataset and further comprising modes of variation for a plurality of components and determine a shape of the captured image in relation to the statistical shape model.
  • the numerical analysis module may be further configured to identify the closest mode of variation to the determined shape and create a patient-specific design for the medical device based on the identified closest mode of variation.
  • the system may further include an additive manufacturing device configured to receive the patient-specific design and generate a patient-specific medical device based on the patient-specific design.
  • the accuracy of measurements often depends greatly on the skill and experience of the investigator tasked with taking the measurements.
  • a statistical shape model comprising the average shape of the area of anatomy and modes of variation for a plurality of components; and then determining a shape of the captured image in relation to the statistical shape model and identifying the closest mode of variation to the determined shape
  • the system is able to generate a patient-specific design for the medical device which is impacted less by any inaccuracies in measurement.
  • the effects of any inaccuracy in an individual measurement can be reduced, at least in part, by corresponding measurements made for the patient population. Consequently, it is possible to generate an improved patient-specific medical device which is affected less by inaccurate measurements.
  • a system for analyzing three dimensional image data for a population of patients may include a database configured to store raw image data of images of an area of anatomy for the population of patents.
  • the system may further include a three dimensional image processing module configured to perform data segmentation by extracting geometries from the stored raw image data.
  • a computer aided design/meshing module may also be provided.
  • the computer aided design/meshing module may be configured to convert the extracted geometries to tubular, triangulated surfaces and parameterize the converted extracted geometries. A dataset may then be created by remeshing the tubular, triangulated surfaces.
  • the system may further include a numerical analysis module configured to calculate an average shape of the area of anatomy based on the dataset and calculate modes of variation for a plurality of components. Each individual member of the dataset may then be expressed using the calculated average shape and a linear combination of the modes of variation. Correlations may then be analyzed between the modes of variation and at least one of a clinic outcome or a disease symptom.
  • a numerical analysis module configured to calculate an average shape of the area of anatomy based on the dataset and calculate modes of variation for a plurality of components. Each individual member of the dataset may then be expressed using the calculated average shape and a linear combination of the modes of variation. Correlations may then be analyzed between the modes of variation and at least one of a clinic outcome or a disease symptom.
  • a method of creating a patient-specific medical device based on three dimensional image data analysis of a patient population may include storing image data corresponding to an area of anatomy for the patient population and capturing an image of the area of anatomy for a patient.
  • Data segmentation may be performed by extracting geometries from the stored image data corresponding to the area of anatomy for the patient population, and the extracted geometries are converted to tubular, triangulated surfaces.
  • the method may further include parameterizing the converted extracted geometries and creating a data set by remeshing the tubular, triangulated surfaces.
  • a statistical shape model may be generate, the statistical shape model comprising an average shape of the area of anatomy based on the data set, and further comprising modes of variation for a plurality of components.
  • the method further may include determining a shape of the captured image in relation to the statistical shape model and identifying the closest mode of variation to the determined shape.
  • a patient specific design is then created for the medical device based on the identified closest mode of variation, and a patient-specific medical device is generated based on the patient-specific design.
  • a method of analyzing three dimensional image data for a population of patients includes storing raw image data of images of an area of anatomy for the population of patents and performing data segmentation by extracting geometries from the stored raw image data.
  • the method further may include converting the extracted geometries to tubular, triangulated surfaces and parameterizing the converted extracted geometries.
  • a dataset may then be created by remeshing the tubular, triangulated surfaces, and an average shape of the area of anatomy may be calculated based on the dataset.
  • the method may further include calculating modes of variation for a plurality of components and expressing each individual member of the dataset using the calculated average shape and a linear combination of the modes of variation. Correlations between the modes of variation and at least one of a clinical outcome or a disease symptom may then be displayed.
  • Figure 1 is a high level system diagram of a computing environment suitable for practicing various embodiments disclosed herein.
  • Figure 2 is a more detailed view of the database shown in Figure 1.
  • Figure 3 is a flowchart illustrating a method of providing a full 3D characterization and analysis of anatomy by generating a statistical shape model according to one or more embodiments.
  • Figure 4 is a graphical illustration of measurements of a different aortic arches among a patient population, along with an average shape of those measured aortic arches.
  • Figure 5 is a graphical illustration of the average shape and two first modes of variation in a statistical shape model of an aortic arch which may be generated in accordance with one or more embodiments disclosed herein.
  • Figure 6 is a flowchart of a method for using statistical shape modeling to study the impact of anatomical variations in a patient population on disease symptoms and/or outcomes in accordance with one or more embodiments disclosed herein.
  • Figure 7 is a flow chart of a method of designing a patient specific aortic valve based on clinical studies using statistical shape modeling and population analysis of the aortic anatomy.
  • Systems and methods disclosed herein provide improved techniques for utilizing 3D data in connection with clinical studies.
  • the complete anatomical geometry is reconstructed in three dimensions using segmentation to isolate the anatomy of interest.
  • a reconstruction algorithm e.g., marching cubes
  • Each of the different shapes of the measured population are parameterized on a tubular surface, and then they are converted to corresponding point clouds.
  • the point clouds may be combined into a statistical shape model, which allows each patient's anatomy to be described as a combination of the average anatomy and a linear combination of the modes of variation.
  • the parameters associated with the modes of variation are used as variables in the statistical analysis to describe anatomical variation. Utilizing these techniques, a full 3-D characterization and analysis of anatomy may be performed without the need for a human analyst to perform accurate measurements.
  • FIG. 1 provides one example of a computer-based system 100 which may be used to implement the systems and methods disclosed herein.
  • the system 100 may include an imaging device 102.
  • the imaging device 102 may take the form of a CT scanner or some other known imaging device, such as MRI, microCT, CBCT, Ultrasound, and/or Confocal Microscopy, which is capable of generating tomographic images of specific areas of the human body.
  • the system 100 may further include a 3-D image processing module 104 which is configured to provide for the segmentation of 3D medical images.
  • the 3-D image processing module 104 may take the form of a computing device having 3-D image processing software installed in its operating system.
  • the 3-D image processing module 104 may be primarily software in nature, or alternatively it may be a combination of hardware and software.
  • the image processing module 104 may include the MIMICS software by Materialise NV of Leuven, Belgium.
  • the system 100 may also include a computer aided design ("CAD") and/or meshing module 106.
  • the CAD/meshing module 106 generally is configured to provide computer aided design tools with preprocessing/meshing capabilities.
  • the computer aided design functionality may be provided by one software application, with the image preprocessing/meshing capabilities being provided by a second, separate computer application.
  • all of these functionalities may be provided in a single computer program such as, for example, the 3-matic Suite from Materialise NV.
  • the CAD/meshing module 106 may be configured to receive triangulated and/or otherwise processed image files from the 3-D image processing module 104.
  • the system 100 may further include numerical analysis module 108.
  • the numerical analysis module 108 may be a numerical computing environment such as MATLAB from MathWorks. Other numerical analysis software packages may be utilized, including but not limited to FreeMat, IGOR Pro, jBEAM, SCaViS, Origin, VisSim, and the like. In addition, the functionality of the numerical analysis module 108 may be incorporated into one or more of the other modules described above. As will be discussed in additional detail below, the numerical analysis module 108 maybe configured to receive datasets generated by the CAD/meshing module and produce statistical shape models based on those datasets.
  • the system 100 also may include a database 1 10.
  • the database 1 10 may take various forms and may perform various functions within the system 100.
  • the database 1 10 may include an image database for storing raw image data captured by the imaging device 102.
  • the image database may be a relational database, or alternatively it may be an object oriented database, and object relational database, or some other type of suitable for the capture's, storage, and providing access for software applications and other devices to raw image data stored in the database.
  • the database 1 10 may also include patient specific data (either anonymous or protected) which is related to image data stored within the image database.
  • the database 110 may also be part of a picture archiving and communication system ("PACS") or a radiology information system (“RIS”), or some combination of both.
  • the database may be a research database which provides anonymous medical image data for research purposes.
  • system 100 described in Figure 1 is merely one of many suitable environments in which the systems and methods disclosed herein may be practiced.
  • system 100 may be connected to a computer network, or it may be standalone an isolated from computer networks in order to ensure medical privacy.
  • system 100 may be connected to a computer network, or it may be standalone an isolated from computer networks in order to ensure medical privacy.
  • various components described in Figure 1 are described separately, they may be functionally combined into fewer modules, or alternatively divided into additional modules.
  • the database 1 10 may store raw image data 202.
  • the raw image data 202 may be captured from the imaging device 102, which in some embodiments is a CT scanner.
  • the database 110 may also include 3-D segmentation data 204.
  • the 3-D segmentation data 204 may be created from the raw image data. More specifically, the 3-D image processing module 104 may access raw image data in the database 1 10 and generate the 3-D segmentation data 204 to be stored separately in the database 110.
  • the database 1 10 also may include surface model data 206.
  • the surface model data 206 may be generated by the CAD/meshing module 106 based on 3D segmentation data 204.
  • the CAD/meshing module 106 may be configured to convert 3D segmentation data 204 into tubular, triangulated surface model data 206 which can be used to create a statistical shape model.
  • the database 1 10 may further include shape data 208.
  • the shape data 208 may take the form of parameterized surface data which is converted into a statistical shape model using the numerical analysis module 108.
  • the database 1 10 may also include patient data 210.
  • the patient data 210 may include data regarding a patient awaiting treatment for a condition related to an anatomical area stored among one or more of the other types of data in the database 110.
  • the patient data 210 may be compared to the shape data 208 (or some other data stored in the database 210) in order to determine a optimal course of treatment. Additionally, a comparison may also be used to design patient specific medical devices, such as, for example heart valves used in transcatheter aortic valve implantation ("TAVI”) procedures.
  • TAVI transcatheter aortic valve implantation
  • Figure 3 is a flowchart illustrating a process by which anatomic structures can be analyzed in accordance with one or more embodiments of the invention.
  • the process begins at block 302, where images of the anatomical area of interest are stored. Typically, these images will be stored as raw image data 202 in the database 1 10. In some embodiments, these images will be taken from many different patients among a sample patient population. Moreover, in many embodiments, the images will be captured using an imaging device 102 such as a CT scanner, for example.
  • the process moves to block 304. There, data segmentation is performed by extracting geometries from the raw image data 202. This data segmentation may be performed in some embodiments by the 3-D image processing module 104.
  • the 3-D image processing module 104 may generate 3-D segmentation data 204 for storage in the database 110.
  • the process moves to block 306, where the extracted geometries are converted to tubular, triangulated surfaces. In some embodiments, this conversion is performed by the CAD/meshing module 106.
  • the CAD/meshing module 106 may be configured to generate surface model data 206 from the 3-D segmentation data 204 and stored in the database 1 10.
  • the extracted geometries are parameterized, minimizing the parameter space needed to fit all shapes accurately.
  • each shape is represented by a point cloud Vi... n .
  • each of the extracting geometries will have the same number of points, and each of those points will correspond to each other on the different surfaces.
  • the techniques such as those described in Huysmans, Toon, Jan Sijbers, and Verdonk Brigitte, "Automatic Construction of Correspondences for Tubular Surfaces," Pattern Analysis and Machine Intelligence, IEEE Transactions on 32.4 (2010):636-651, the entire contents of which are hereby incorporated by reference.
  • the process moves to block 312 where the average shape of the extracted geometries is calculated.
  • this calculation will be performed by the numerical analysis module 108.
  • the average shape may be determined using the following equation:
  • the process moves to block 314, where modes of variation are determined.
  • the modes of variation may be determined using principal component analysis ("PCA") to generate a series of components, and/or by applying the following calculations on the dataset:
  • PCA principal component analysis
  • each individual member of the population can be described as a sum of the average and a linear combination of principal components:
  • Figure 3 is a graphical illustration of measurements of a different aortic arches among a patient population, along with an average shape of those measured aortic arches which may be determined using the process outlined in Figure 3.
  • a first measured aortic arch 402(a) is shown alongside a second measured aortic arch 402(b).
  • many more measurements may be utilized (as indicated by the ellipses) to determine the average shape 402(n) in the statistical shape model of the aortic arch.
  • Figure 5 is a graphical illustration of the average shape, the first two components along with their respective two first modes of variation in the statistical shape model generated from the dataset shown in Figure 4.
  • the statistical shape model includes an average shape 502.
  • Providing a frame of reference with the average shape 502 are three axes labeled "X" (not shown) "Y" (which appears as a "-") and "Z” (which appears on its side as a "N") to show relative distances in the images.
  • Also shown in Figure 5 are the modes of variation for two different components— Component 1 (images 504 and 506) and Component 2 (images 508 and 510).
  • each of these components and their respective modes of variation contain variations in different portions/locations of the aortic arch.
  • Figure 6 is a flowchart of a method for using statistical shape modeling to study the impact of anatomical variations in a patient population on disease symptoms and/or outcomes in accordance with one or more embodiments.
  • the process begins at block 602 where an object of study is identified.
  • the object of study may be a disease symptom, or a clinical outcome from a medical procedure, or some other medically significant event.
  • the clinical outcome could be patients suffering from a mild degree of leakage alongside a TAVI implant.
  • the statistical shape model of the aorta, including the aortic arch may be used in these embodiments to describe the average shape and modes of variation in the patient population.
  • the process moves to decision block 604, where it is determined whether there are additional components in the statistical shape model generated from the patient population which is the subject of study. If there are components in the SSM not yet analyzed, the process moves to block 606, where correlations between modes of variation and the disease symptoms/clinical outcome are investigated, determined, and/or recorded. Each time a component is analyzed, the process returns to block 604 to determine whether additional components in the statistical shape model remain to be investigated. If so, each additional component is investigated at block 606, and the process repeats again. When no more additional components remain in the statistical shape model, the process moves from decision block 604 to block 608. There, the most significant correlations are identified, among the correlations investigated in connection with the statistical shape model. Then the process moves to block 610, where these additional correlations may then be stored in the database 110 for further analysis and study.
  • FIG. 7 is a flow chart of a one example of a method of designing a patient specific aortic implant based on clinical studies using statistical shape modeling and population analysis of the aortic anatomy.
  • the process begins at block 702 where the system 100 receives a CT image of a patient's aortic valve anatomy.
  • This image may be stored as patient data 210 in the database 1 10. Alternatively, the image may be stored as raw image data 202.
  • the process moves to block 704 where the image of the patient's aortic valve anatomy is used to determine its shape in relation to the statistical shape model stored in the database 1 10.
  • the patient's aortic valve shape is compared to the modes of variation which have been deemed significant in the statistical shape model. The closest mode of variation is identified at block 808. Based on the identified mode of variation, a patient specific aortic implant may be designed to account for the specific anatomical characteristics of the patient.
  • the patient specific aortic implant may be produced using three-dimensional printing techniques, such as, for example, those described in U.S. Patent Pub. No. 2010-0228369 Al , the disclosure of which is hereby incorporated by reference in its entirety.
  • the patient specific aortic implant may be produced using techniques described in PCT/EP2012/069715 (WO 2013/050525), the entire disclosure of which is also incorporated by reference herein in its entirety.
  • aspects ofthe system 100 and its various functions described herein may be embodied in one or more executable software modules that may be stored on any type of non-transitory computer storage medium or system, and that some or all of the functions may alternatively be embodied in application-specific circuitry.
  • the various illustrative logical blocks, modules, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.

Landscapes

  • Health & Medical Sciences (AREA)
  • Surgery (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Robotics (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Processing (AREA)

Abstract

L'invention concerne des systèmes et des procédés d'analyse tridimensionnelle de structures anatomiques pour une population de patients. Divers modes de réalisation permettent l'examen de la géométrie tridimensionnelle complète de structures anatomiques. Des données d'imagerie sont converties en un modèle de surface tridimensionnel par segmentation de données et reconstruction 3D. Un modèle de forme statistique est généré à partir du modèle de surface, et l'anatomie de chaque patient peut être décrite comme une combinaison de l'anatomie moyenne décrite dans le modèle de forme statistique et comme une combinaison linéaire des modes de variation. Les paramètres associés aux modes de variation peuvent être utilisés pour étudier des variations anatomiques et leur impact sur des symptômes de maladie et/ou des résultats cliniques. De plus, des dispositifs médicaux spécifiques à un patient peuvent être conçus sur la base de corrélations découvertes par l'analyse du modèle de forme statistique.
PCT/EP2014/059504 2013-05-08 2014-05-08 Système et procédé d'analyse tridimensionnelle de structures anatomiques pour une population de patients WO2014180972A2 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201361820802P 2013-05-08 2013-05-08
US61/820,802 2013-05-08
US201361860196P 2013-07-30 2013-07-30
US61/860,196 2013-07-30

Publications (2)

Publication Number Publication Date
WO2014180972A2 true WO2014180972A2 (fr) 2014-11-13
WO2014180972A3 WO2014180972A3 (fr) 2015-02-05

Family

ID=50877237

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2014/059504 WO2014180972A2 (fr) 2013-05-08 2014-05-08 Système et procédé d'analyse tridimensionnelle de structures anatomiques pour une population de patients

Country Status (1)

Country Link
WO (1) WO2014180972A2 (fr)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10405993B2 (en) 2013-11-13 2019-09-10 Tornier Sas Shoulder patient specific instrument
US10716676B2 (en) 2008-06-20 2020-07-21 Tornier Sas Method for modeling a glenoid surface of a scapula, apparatus for implanting a glenoid component of a shoulder prosthesis, and method for producing such a component
US10959742B2 (en) 2017-07-11 2021-03-30 Tornier, Inc. Patient specific humeral cutting guides
US11065016B2 (en) 2015-12-16 2021-07-20 Howmedica Osteonics Corp. Patient specific instruments and methods for joint prosthesis
US11166764B2 (en) 2017-07-27 2021-11-09 Carlsmed, Inc. Systems and methods for assisting and augmenting surgical procedures
US11166733B2 (en) 2017-07-11 2021-11-09 Howmedica Osteonics Corp. Guides and instruments for improving accuracy of glenoid implant placement
US11376076B2 (en) 2020-01-06 2022-07-05 Carlsmed, Inc. Patient-specific medical systems, devices, and methods
USD958151S1 (en) 2018-07-30 2022-07-19 Carlsmed, Inc. Display screen with a graphical user interface for surgical planning
US11432943B2 (en) 2018-03-14 2022-09-06 Carlsmed, Inc. Systems and methods for orthopedic implant fixation
US11439514B2 (en) 2018-04-16 2022-09-13 Carlsmed, Inc. Systems and methods for orthopedic implant fixation
US11443838B1 (en) 2022-02-23 2022-09-13 Carlsmed, Inc. Non-fungible token systems and methods for storing and accessing healthcare data
EP4170667A1 (fr) 2021-10-25 2023-04-26 Anamos GmbH Configurateur basé sur base de données pour la création de modèles anatomiques
US11696833B2 (en) 2018-09-12 2023-07-11 Carlsmed, Inc. Systems and methods for orthopedic implants
US11793577B1 (en) 2023-01-27 2023-10-24 Carlsmed, Inc. Techniques to map three-dimensional human anatomy data to two-dimensional human anatomy data
US11806241B1 (en) 2022-09-22 2023-11-07 Carlsmed, Inc. System for manufacturing and pre-operative inspecting of patient-specific implants
US11854683B2 (en) 2020-01-06 2023-12-26 Carlsmed, Inc. Patient-specific medical procedures and devices, and associated systems and methods
US12127769B2 (en) 2021-11-19 2024-10-29 Carlsmed, Inc. Patient-specific jig for personalized surgery

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100228369A1 (en) 2007-10-10 2010-09-09 Materialise Nv Method and apparatus for automatic support generation for an object made by means of a rapid prototype production method
WO2013050525A1 (fr) 2011-10-07 2013-04-11 Materialise N.V. Procédés pour la fabrication d'une endoprothèse intraluminale

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8246673B2 (en) * 2002-09-19 2012-08-21 Exstent Limited External support for a blood vessel
DE102004020020B4 (de) * 2004-04-23 2009-04-23 Charité - Universitätsmedizin Berlin Dreidimensionales Modell eines menschlichen Kinderschädels in Lebensgröße

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100228369A1 (en) 2007-10-10 2010-09-09 Materialise Nv Method and apparatus for automatic support generation for an object made by means of a rapid prototype production method
WO2013050525A1 (fr) 2011-10-07 2013-04-11 Materialise N.V. Procédés pour la fabrication d'une endoprothèse intraluminale

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HUYSMANS; TOON; JAN SIJBERS; VERDONK BRIGITTE: "Automatic Construction of Correspondences for Tubular Surfaces", PATTERN ANALYSIS AND MACHINE INTELLIGENCE, IEEE TRANSACTIONS ON 32.4, 2010, pages 636 - 651

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10716676B2 (en) 2008-06-20 2020-07-21 Tornier Sas Method for modeling a glenoid surface of a scapula, apparatus for implanting a glenoid component of a shoulder prosthesis, and method for producing such a component
US11432930B2 (en) 2008-06-20 2022-09-06 Tornier Sas Method for modeling a glenoid surface of a scapula, apparatus for implanting a glenoid component of a shoulder prosthesis, and method for producing such a component
US11179249B2 (en) 2013-11-13 2021-11-23 Tornier Sas Shoulder patient specific instrument
US10405993B2 (en) 2013-11-13 2019-09-10 Tornier Sas Shoulder patient specific instrument
US12097129B2 (en) 2013-11-13 2024-09-24 Tornier Sas Shoulder patient specific instrument
US11065016B2 (en) 2015-12-16 2021-07-20 Howmedica Osteonics Corp. Patient specific instruments and methods for joint prosthesis
US11980377B2 (en) 2015-12-16 2024-05-14 Howmedica Osteonics Corp. Patient specific instruments and methods for joint prosthesis
US11234721B2 (en) 2017-07-11 2022-02-01 Howmedica Osteonics Corp. Guides and instruments for improving accuracy of glenoid implant placement
US11166733B2 (en) 2017-07-11 2021-11-09 Howmedica Osteonics Corp. Guides and instruments for improving accuracy of glenoid implant placement
US11278299B2 (en) 2017-07-11 2022-03-22 Howmedica Osteonics Corp Guides and instruments for improving accuracy of glenoid implant placement
US11918239B2 (en) 2017-07-11 2024-03-05 Howmedica Osteonics Corp. Guides and instruments for improving accuracy of glenoid implant placement
US11399851B2 (en) 2017-07-11 2022-08-02 Howmedica Osteonics Corp. Guides and instruments for improving accuracy of glenoid implant placement
US11076873B2 (en) 2017-07-11 2021-08-03 Howmedica Osteonics Corp. Patient specific humeral cutting guides
US12035929B2 (en) 2017-07-11 2024-07-16 Howmedica Osteonics Corp. Patient specific humeral cutting guides
US10959742B2 (en) 2017-07-11 2021-03-30 Tornier, Inc. Patient specific humeral cutting guides
US11166764B2 (en) 2017-07-27 2021-11-09 Carlsmed, Inc. Systems and methods for assisting and augmenting surgical procedures
US11857264B2 (en) 2017-07-27 2024-01-02 Carlsmed, Inc. Systems and methods for physician designed surgical procedures
US11497559B1 (en) 2017-07-27 2022-11-15 Carlsmed, Inc. Systems and methods for physician designed surgical procedures
US11432943B2 (en) 2018-03-14 2022-09-06 Carlsmed, Inc. Systems and methods for orthopedic implant fixation
US11439514B2 (en) 2018-04-16 2022-09-13 Carlsmed, Inc. Systems and methods for orthopedic implant fixation
USD958151S1 (en) 2018-07-30 2022-07-19 Carlsmed, Inc. Display screen with a graphical user interface for surgical planning
US11696833B2 (en) 2018-09-12 2023-07-11 Carlsmed, Inc. Systems and methods for orthopedic implants
US11717412B2 (en) 2018-09-12 2023-08-08 Carlsmed, Inc. Systems and methods for orthopedic implants
US11678938B2 (en) 2020-01-06 2023-06-20 Carlsmed, Inc. Patient-specific medical systems, devices, and methods
US11854683B2 (en) 2020-01-06 2023-12-26 Carlsmed, Inc. Patient-specific medical procedures and devices, and associated systems and methods
US11376076B2 (en) 2020-01-06 2022-07-05 Carlsmed, Inc. Patient-specific medical systems, devices, and methods
WO2023072838A1 (fr) 2021-10-25 2023-05-04 Anamos Gmbh Configurateur à base de base de données pour la création de modèles anatomiques
EP4170667A1 (fr) 2021-10-25 2023-04-26 Anamos GmbH Configurateur basé sur base de données pour la création de modèles anatomiques
US12127769B2 (en) 2021-11-19 2024-10-29 Carlsmed, Inc. Patient-specific jig for personalized surgery
US11443838B1 (en) 2022-02-23 2022-09-13 Carlsmed, Inc. Non-fungible token systems and methods for storing and accessing healthcare data
US11984205B2 (en) 2022-02-23 2024-05-14 Carlsmed, Inc. Non-fungible token systems and methods for storing and accessing healthcare data
US11806241B1 (en) 2022-09-22 2023-11-07 Carlsmed, Inc. System for manufacturing and pre-operative inspecting of patient-specific implants
US11793577B1 (en) 2023-01-27 2023-10-24 Carlsmed, Inc. Techniques to map three-dimensional human anatomy data to two-dimensional human anatomy data

Also Published As

Publication number Publication date
WO2014180972A3 (fr) 2015-02-05

Similar Documents

Publication Publication Date Title
WO2014180972A2 (fr) Système et procédé d'analyse tridimensionnelle de structures anatomiques pour une population de patients
Sermesant et al. Applications of artificial intelligence in cardiovascular imaging
US20210158531A1 (en) Patient Management Based On Anatomic Measurements
US10622102B2 (en) Personalized assessment of bone health
Cruz et al. Deepcsr: A 3d deep learning approach for cortical surface reconstruction
Wang et al. STL rapid prototyping bio-CAD model for CT medical image segmentation
CN112640000A (zh) 根据医学数据对预测性数字孪生体模型的数据驱动的估计
US11941812B2 (en) Diagnosis support apparatus and X-ray CT apparatus
JP6695954B2 (ja) 形状の予測
JP2015080720A (ja) コンピュータ補助診断方法及び装置
US20180108131A1 (en) Generation of a Patient-Specific Anatomical Atlas
CN118298269B (zh) 一种基于共享表征的膝关节ct和磁共振多模态影像融合方法
Ciuşdel et al. Towards deep learning based estimation of fracture risk in osteoporosis patients
US20230126877A1 (en) Synthetic data generation and annotation for tumor diagnostics and treatment
CN116309346A (zh) 医学图像的检测方法、装置、设备、存储介质及程序产品
US20140032180A1 (en) Method and apparatus for computing deformation of an object
Pascual et al. Computerized three-dimmensional craniofacial reconstruction from skulls based on landmarks
CN109637633A (zh) 一种基于大数据与机器学习的诊断乳腺癌病情的方法
Zhang et al. Xsede-enabled high-throughput lesion activity assessment
Ciuşdel et al. Towards real time machine learning based estimation of fracture risk in osteoporosis patients
EP4198997A1 (fr) Procédé mis en uvre par ordinateur, procédé et système
Swanson The Development of a Patient-Specific, Open Source Computational Fluid Dynamics Tool to Comprehensively and Innovatively Study Coarctation of the Aorta in a Limited Resource Clinical Context
Gothard et al. A method for reconstructing 3D patient-specific total knee arthroplasty tibia models from 2D bi-planar radiographs
CN108885905A (zh) 人或动物躯干的生物力学模型生成
Lugadilu Development of a statistical shape and appearance model of the skull from a South African population

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: 14727421

Country of ref document: EP

Kind code of ref document: A2

122 Ep: pct application non-entry in european phase

Ref document number: 14727421

Country of ref document: EP

Kind code of ref document: A2