WO2002027635A2 - Method and system for extracting spine frontal geometrical data including vertebra pedicle locations - Google Patents

Method and system for extracting spine frontal geometrical data including vertebra pedicle locations Download PDF

Info

Publication number
WO2002027635A2
WO2002027635A2 PCT/EP2001/010989 EP0110989W WO0227635A2 WO 2002027635 A2 WO2002027635 A2 WO 2002027635A2 EP 0110989 W EP0110989 W EP 0110989W WO 0227635 A2 WO0227635 A2 WO 0227635A2
Authority
WO
WIPO (PCT)
Prior art keywords
state
spine
candidates
pedicle
vertebra
Prior art date
Application number
PCT/EP2001/010989
Other languages
French (fr)
Other versions
WO2002027635A3 (en
Inventor
Olivier Gerard
Milena Planells-Rodriguez
Pierre Lelong
Sherif Makram-Ebeid
Original Assignee
Koninklijke Philips Electronics 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 Electronics N.V. filed Critical Koninklijke Philips Electronics N.V.
Priority to EP01982338A priority Critical patent/EP1386276A2/en
Priority to JP2002531340A priority patent/JP2004509722A/en
Publication of WO2002027635A2 publication Critical patent/WO2002027635A2/en
Publication of WO2002027635A3 publication Critical patent/WO2002027635A3/en

Links

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00ICT specially adapted for the handling or processing of medical images
    • G16H30/40ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S128/00Surgery
    • Y10S128/92Computer assisted medical diagnostics
    • Y10S128/922Computer assisted medical diagnostics including image analysis

Definitions

  • the invention relates to an image processing method for extracting frontal geometrical data of a spine image including vertebra pedicle locations.
  • the invention finds its application in medical imaging. Background of the Invention
  • a segmentation method applied to the spine is already known of the publication "Digital Radiography Segmentation of Scoliotic Vertebral Body using Deformable Models” by Claude Kauffinann and Jacques A. de Guise in SPIE Nol.3034, pp.243-251.
  • This publication describes a computer segmentation method based on the active contour model (g-snake) and using a prior knowledge. This method is adapted and used to detect automatically the contour lines of each vertebral body independently in digital radiographs of the scoliotic spine. These contour lines are used to identify correspondent anatomical landmarks for the 3D reconstruction of the scoliotic spine using a bi-planar technique.
  • the steps comprise: constructing a standard template for each kind of vertebrae (thoracic or lumbar), performing three best fits of the appropriate template on the spine radiograph, g-snake energy minimization, selection of a best contour for each vertebra individually, and anatomical landmark extraction (including corners and spine center-line points). Previous steps of digitization of the spine centerline and acquisition of a prior knowledge including the height and width of the standard template are first performed.
  • the method known of the cited document does not describe steps for specifically extracting the landmark corresponding to the location of the spine pedicles. It only provides the corner locations. Now, the pedicle locations are particularly useful to estimate the rotation angle of every vertebrae.
  • the present invention has for object to propose a image processing method to extract spine data called landmarks corresponding to the pedicle locations. This method has steps to perform the extraction of these pedicle landmarks using previously determined locations of other landmarks corresponding to the vertebra corner projections. For example, these steps are carried out by processing a frontal image of a number of adjacent vertebrae of the spine.
  • Such an image processing method is claimed in Claim 1.
  • An imaging system, an X-ray apparatus and a computer program product are also claimed to carry out the method.
  • FIG.1A, FIG. IB, FIG.1C are representations of a vertebra in various perspectives;
  • FIG.2A and FIG.2B show optimal landmarks of a vertebra, in frontal and lateral views;
  • FIG.3A and FIG.3B illustrate the step of positioning of the vertebra in a local referential
  • FIG.4A shows a spine frontal view and FIG.4B shows icons of successive vertebrae, each icon representing the features of the vertebra in its local referential;
  • FIG.5 A represents a particular vertebra and FIG.5B represents the corresponding icon
  • FIG.6 A shows, superimposed on an icon, a curve of feature accumulation and FIG.6B shows the corresponding curve of Costs ;
  • FIG.7A is the curve of Costs for the determination of a couple of pedicles and
  • FIG.7B is a 3-D Cost Matrix for determining the best paths where the left and right pedicles are to be found along the spine;
  • FIG.8 is a functional block diagram of medical diagnostic imaging system and apparatus for carrying out the method. Description of embodiments
  • the invention relates to an image processing method for extracting geometrical data of the spine, in order to localize specific elements of the spine in spine images, for studying spine deformities.
  • the specific elements are the pedicles of the vertebrae.
  • a vertebra shows a body 7, which defines the spine axis and the shape of the vertebral discs and which is substantially cylindrical with flattened elliptic bases 1, 2 called endplates (FIG1A, FIG.1C); a spineous process 4 located in the plane of symmetry of the vertebra (FIG.l A, FIG.
  • Fig.2A and FIG.2B Six optimal landmarks are selected, as represented respectively in the frontal and in the lateral images shown in Fig.2A and FIG.2B. These landmarks are the extremities of the projection of the vertebra body, which are the corners A, B, C, D, A', B', C, D* of the vertebra; and the position of the inner points E, F of the projection of the pedicles, further on called pedicle landmarks.
  • the present method supposes that the corners A, B, C, D of the interesting vertebrae have already been located in a frontal view. This method comprises steps of:
  • a frontal image of an examined patient is acquired.
  • This image may be formed by X-ray imaging, as shown in FIG.4A.
  • Each point has a luminance intensity and coordinates in a cartesian referential whose axes are parallel to the sides of said frontal view.
  • the frontal view may comprise a number of adjacent vertebrae, for example sixteen (16) vertebrae.
  • the processing method encounters problems due to the position of the pedicles with respect to the other landmarks in the different vertebrae along the spine.
  • the pedicles In the thoracic vertebrae, the pedicles are almost at the same height as the upper endplate or even higher and they are very difficult to detect.
  • the pedicles In the lumbar vertebrae the pedicles are in the upper half of the vertebrae and they are easier to detect.
  • the vertebrae have individual axes of rotation that are generally not vertical and that are different from each other.
  • each vertebra is processed separately in order to take advantage of the local intensity properties for pedicle detection.
  • the sides of the vertebra present a high contrast, which would interfere in the detection of the pedicles.
  • a restricted Region of Scanning is defined, which is a part of the image to be processed for pedicle detection.
  • each vertebra is attributed an independent cartesian referential in which the Region of Scanning is further defined.
  • the current frontal original vertebra image shows the corner landmarks A, B, C, D.
  • the middle points of the left and right lines joining the corners, respectively CA, DB, are denoted Oj . for AC and O 2 for BD.
  • the coordinates of these middle points Oi, O 2 are computed in the referential of the frontal view.
  • the line OjO 2 that goes through these points is an axis X' that is generally not horizontal as above-described.
  • the orthogonal axis Y' going through the center O of O ⁇ ;O 2 is generally not vertical.
  • a new referential X, Y is determined with a horizontal axis X and a vertical axis Y.
  • the Region of Scanning is obtained by rotating a part of the of the current frontal original vertebra image using a rotation angle ⁇ that is the angle between the X'-axis and the current horizontal axis defined in the frontal view.
  • the new X-axis is parallel to this current axis.
  • the center of the rotation is O and the part of the image to rotate is determined by the largest projections of the corners A, B, C and D onto the new X-axis.
  • the part of the image resulting from said rotation is rectangular with O as the center and constitutes the Region of Scanning. It is delimited by horizontal lines parallel to the X-axis at the ordinates Y_, YE, and by vertical lines parallel to the Y-axis at the abscissae X . , XE- So, the Region of Scanning in this new referential X, Y is defined by the rightmost projection of corners A and C onto the X-axis leading to X_, the leftmost projection of corners B and D onto the same X-axis leading to XE- The same procedure for the Y-axis leads to Y_ and Y E .
  • the Region of Scanning is defined by New Corners that are A 0 (X 0 , YE), B 0 (X E , YE), D 0 (X E , YE), and C 0 (X 0 , Yo).
  • Feature Estimation permits of constructing an Image of Features in the local referential X, Y of the Region of Scanning.
  • Different features can be considered for pedicle detection, such as gradient values, gray levels or intensity variance.
  • the features that are considered as most effective to discriminate the thin structures representing the pedicles are ridgeness values.
  • the image of the Region of Scanning can be a positive image, which is considered as a 3-D picture, having two dimensions for the co-ordinates of pixels and a third dimension for the intensity signals associated to said pixels.
  • a ridge is a crest-like structure formed by adjacent pixels having intensity signals that are maximum in a neighborhood, said pixels having specific dispositions the ones with respect to the others resulting in specific gradient values with respect to orientations.
  • a ridge pixel shows a low intensity gradient in a first determined direction in its neighborhood, and shows an intensity gradient that is maximum in a direction perpendicular to said first direction. The more a given structure is formed of pixels verifying this gradient property, the more the ridgeness measure of the structure is high.
  • troughs can be considered in a negative original image of the Region of Scanning for instance obtained by X-ray imaging.
  • a ridge structure is a dark structure on a lighter background.
  • the calculations for extracting the pedicles have for an object to extract trough pixels, which can be determined by measures similar to ridgeness calculations.
  • ridgeness calculations applied to troughs determination the estimation of specific intensity gradients that is required for characterizing ridges is still valuable for characterizing troughs. So, in the description of the present method, these calculations are called "ridgeness" calculations, whether they are applied to ridges or troughs in the Region of Scanning.
  • FIG.5 A shows an original frontal image of a vertebra.
  • the method comprises a step of "ridgeness” calculation applied to the image of the Region of Scanning corresponding to the vertebra of FIG.5A.
  • This "ridgeness” calculation is performed by applying, on the pixels, filters known as ridge-filters, which determine the pixels of the ridge or trough structures. Based on this ridgeness calculation, each pixel of the Region of Scanning is further associated to a ridgeness data. The resulting image is called Feature Image as shown on FIG.5B.
  • the features are computed on a Region of Interest ROI, which is constituted of a number of adjacent vertebrae and of a border region around these vertebrae represented in a frontal view such as the view shown on FIG.4A.
  • a Region of Interest ROI which is constituted of a number of adjacent vertebrae and of a border region around these vertebrae represented in a frontal view such as the view shown on FIG.4A.
  • an image called ROI Feature Image is formed.
  • the calculation of various new referentials by rotation and the calculation of various limited Regions of Scanning in said new referentials, as above- described, are then further performed based on said ROI Feature Image.
  • FIG.4B shows various icons of Feature Images corresponding to said various Regions of Scanning.
  • the icon 2 of FIG.4B is a Feature Image corresponding the circled vertebra of FIG.4A.
  • the icon 1 is a Feature Image of a vertebra above the circled one and the icons 3 to 10 are Feature Images of the successive
  • the contrast of the Feature Image, in each icon corresponding to the Region of Scanning is preferably further linearly enhanced.
  • This Feature Image is scanned parallel to the vertical Y-axis, and the Feature values are accumulated by summing, in the direction of the Y-axis for every X coordinates between Xo and X E , called X-Region.
  • this accumulation may be limited to be computed only on the upper-region of the vertebral body.
  • This upper-region may be defined as covering only 70% of the length of the Y-axes of the Region of Scanning, since the pedicles are usually located on this upper-region.
  • the summed Feature Nalues are projected onto the horizontal X-axis. This operation results in a curve of the Accumulated Feature Nalues, called AS, showing maximum values called Peaks corresponding to the occurrence of ridges substantially parallel to the vertical Y-axis.
  • the curve S is superimposed onto the Feature Image inverted in intensity.
  • LC is infinite when associated to every location on the X-axis where an Accumulated Value is found to be below the predetermined threshold level.
  • an associated cost LC is computed as the inverse of the corresponding Accumulated Value: a precise equation being for example:
  • FIG.6A shows the accumulation curve and FIG.6B shows the local cost curves for the vertebra presented in FIG. 5 A, 5B.
  • Fig. ⁇ B for visualization purpose, the image of the vertebra features are included, with reversed contrast, on the background of the graphs, as in FIG.6 A.
  • the cost graph has been limited to a 0-2000 range but actually goes to an INFINITE COST, which is defined at 10 9 , with 1000 limiting the useful region.
  • Projected pedicles mostly look like thin vertical lines.
  • the pedicle landmarks of FIG.2A situated on said thin lines are detected in the frontal view.
  • pedicle projections are elliptical-shaped.
  • the left and right external borders of the elliptical- shaped pedicles may be a source of errors.
  • the Y- accumulation procedure is used to perform a discrimination between the left and the right borders of each elliptical shaped pedicle.
  • the Feature Images may include some other sources of errors that are the borders of the vertebra, which also show high feature response and which are vertical, and the projection of the spurious process, which may appear as a vertical line roughly in the middle of the vertebral body but mostly in the lowest part of the body. According to the present method, the effects of these possible errors will be reduced by a further Dynamic Programming procedure.
  • the pedicle landmarks that are on the internal border locations of the left and right pedicles are respectively called Left and Right Pedicle Locations.
  • the present method has for an object to simultaneously detect the Left and Right Pedicle Locations for the specific spine vertebra of a specific patient.
  • the couples of Left and Right Pedicle Locations which are represented by couples of corresponding abscissae X , XR on the X-axis, are looked for, for all vertebrae.
  • the whole Region of Interest ROI of the spine is considered in order to take into account the locations of each couple candidate of a given vertebra with respect to the other couple candidate of the other vertebrae, which give more robustness in the location determinations;
  • the location of each vertebra in the spine, called state is defined by a vertebra index V, which is the name or the position of said vertebra in the spine, and a Database is accessible to provide average values of the distance, hereafter called Pedicle Distance, separating candidate couples of Left and Right Pedicle Locations, for each given vertebra; every possible Left Pedicle Location is determined in a range of coordinates between Xo and the middle of the X-Region (middle of X O XE), and a certain number of position candidates for the Right Pedicle Location is determined, typically in ten (10) bands called "bins", gathering 1 to 3 Right Pedicle Location candidates;
  • the procedure of finding Right Pedicle Locations PR, called PR candidate, from a given particular Left Pedicle Location P , called PL candidate comprises: searching for PR candidates at a distance DJ_,R estimated from the database, within a range proportional to the standard deviation to this distance, thus defining a search region; dividing this search region into a number of bins, favorably ten (10) bins, of equal size; selecting the same number (10) of P R candidates, one for each bin. If one bin is found empty, an infinite cost is applied. If several PR candidates are inside the same bin, the PR candidate having the minimum local cost is selected. Thus for every P candidate, a set of said number of for example ten (10) P R candidates is built.
  • the local cost associated with one state defined by the vertebra index V, with the PL candidate and with an associated P R candidate, as the sum of three terms that are: the Cost associated to the P L candidate; the minimum of the Costs associated to every PR candidate in the current bin, the deviation of the current distance DLR between said PL and PR candidates with respect to the "average" distances DL 5 R as estimated from the database.
  • the distance term is normalized by the cosine of the rotational angle of the current vertebra estimated by using information from only the left location.
  • SC(L, R) LC L + LC R + (D L R - D L?R ) which is the State Cost SC(L, R) for associating possible PL and PR candidates, expressed as the Sum of the Local Costs LC L and LCR at the indicated locations of said possible candidates, plus the difference between the actual distance DL, R between the locations of said candidates and the corresponding "average" normalized distance DJ_,,R for the given vertebra. It is to be noted that these Local Cost computations are performed for every vertebra and thus the previous equation depends upon V, the vertebra index.
  • These State Costs SC(V, L, R) are used for defining the Matrix-Costs of the 3D-state-Matrix illustrated on FIG7B.
  • a Dynamic Programming (DP) procedure is carried out in order to determine one Best Couple among the PL and P R candidates, for each vertebra of the spine, taking into account that for two successive vertebrae, the pedicles are substantially aligned (except in the case of a vertebral displacement) and that for the whole spine, the paths on which the pedicles are disposed are substantially smooth.
  • This Dynamic Programming (DP) is a non- iterative method, effective in contour detection, that uses Energy Functions and that is not described hereafter, because it is well known of those skilled in the art.
  • This procedure has for a purpose to determine the "most likely path" for the location of the PL and P R candidates.
  • the points that are to be linked are those that are most likely part of the pedicle internal sides.
  • the Dynamic Programming (DP) procedure calculates the Path of lowest Cost going from a node to another to yield this Path. The DP is performed in the frontal view in the vertical direction.
  • a 3-D Matrix of States is defined, as depicted in FIG.7B.
  • This Matrix has a P L -axis (vertical), for the number, for example 30, of P candidates; it has a P R -axis ( in the depth direction of FIG.7B) for the number of P R bins (10 bins) per each P L candidate; the PL- axis and the P R -axis define a plane, regarded as a band (vertical band on FIG.7B) of the 3-D Matrix.
  • the third dimension (horizontal) of this Matrix is the State given by the index V of the current vertebra under study among the number N of adjacent vertebrae that is user specified, typically 5 or 16 vertebrae.
  • a first pass is performed in a forward direction along the V-axis.
  • a first couple of P L and PR candidates for instance denoted by PLI , PRI, is defined as the one with the lowest State Cost in the corresponding first band of the Matrix of States.
  • the procedure has for an object to determine, in the following State (for the second vertebra), a couple of P and P R candidates, for example denoted by PL 2 , P R2 , which is one with the optimum State Cost in this second State and which is linked to the first couple of the first State with the lowest Transition Cost.
  • This Transition Cost is favorably the Sum of the distances between Pu, PL2 and between PR 1S P R 2.
  • This couple PL 2 , P R 2 that fulfils the Cost conditions in the second State is called Best Predecessor. So, for each State, the Best Predecessor is defined as the one with the lowest Path Cost. The search for this Best Predecessor is actually performed by first looking for the PL candidate that is the closest to the one of the current State (+10 locations).
  • a Path Cost is defined for linking the current State and its Predecessor State, composed of three Costs: the Local Costs of the previous State, the State Cost of the current State, the Transition Cost that is the Sum of the Distances between the couples of P L and P R candidates and is intended to penalize sudden local variation of the rotational angle.
  • the Backward Pass determines, for every State, the most probable predecessor, i.e. the Couple of the previous State that has the minimal Path Cost.
  • the Backward Pass begins in the State of the last vertebra having the lowest Path Cost. Going backwards, the Dynamic Programming Procedure retrieves the locations for both pedicles for every vertebra. Thus, it defines a line in the 3-D Cost Matrix. Two vertical lines are then drawn in the local referentials to display the determined pedicle landmark locations for every linked vertebra. The user can then select and move faulty lines towards correct locations.
  • the cost is modified such that a zero (0) Cost is associated to the selected location and an infinite Cost is set for all the other locations in the current half vertebra.
  • the building of a new Cost Matrix is then performed, followed by a new Dynamic Programming Procedure.
  • a medical examination apparatus 150 comprises means for acquiring digital frontal image data of the spine, and a digital processing system 120 for processing these data according to the processing method above-described.
  • the medical examination apparatus comprises means for providing image data to the processing system 120 which has at least one output 106 to provide image data to display and/or storage means 130, 140.
  • the display and storage means may respectively be the screen 140 and the memory of a workstation 110. Said storage means may be alternately external storage means.
  • This image processing system 120 may be a suitably programmed computer of the workstation 130, or a special purpose processor having circuit means such as LUTs, Memories, Filters, Logic Operators, that are arranged to perform the functions of the method steps according to the invention.
  • the workstation 130 may also comprise a keyboard 131 and a mouse 132.

Landscapes

  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Image Processing (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention relates to an image processing method of extracting geometrical data of the spine, for extracting the left and right pedicle landmarks of each spine vertebra, comprising steps of: acquiring image data of a 2-D frontal image of the spine; associating spine States to vertebra positions along the spine and estimating locations of left and right pedicle landmark Candidates in each State; defining a State Cost for forming Couples of left and right pedicle landmark Candidates (PL and PR); estimating sets of Best Couple Candidates, in each State, from the lowest State Costs; defining a Path Cost to go from one State to the next State; selecting a pedicle landmark Couple in each spine State (V) among the Best Couple Candidates from the minimum Path Costs, and localizing the left and right pedicle landmarks of each spine vertebra from said selected pedicle landmark Couple. The invention also relates to a system, a medical apparatus and a program product for carrying out the method.

Description

Method and system for extracting spine frontal geometrical data including vertebra pedicle locations
Field of the Invention
The invention relates to an image processing method for extracting frontal geometrical data of a spine image including vertebra pedicle locations. The invention finds its application in medical imaging. Background of the Invention
A segmentation method applied to the spine is already known of the publication "Digital Radiography Segmentation of Scoliotic Vertebral Body using Deformable Models" by Claude Kauffinann and Jacques A. de Guise in SPIE Nol.3034, pp.243-251.This publication describes a computer segmentation method based on the active contour model (g-snake) and using a prior knowledge. This method is adapted and used to detect automatically the contour lines of each vertebral body independently in digital radiographs of the scoliotic spine. These contour lines are used to identify correspondent anatomical landmarks for the 3D reconstruction of the scoliotic spine using a bi-planar technique. The steps comprise: constructing a standard template for each kind of vertebrae (thoracic or lumbar), performing three best fits of the appropriate template on the spine radiograph, g-snake energy minimization, selection of a best contour for each vertebra individually, and anatomical landmark extraction (including corners and spine center-line points). Previous steps of digitization of the spine centerline and acquisition of a prior knowledge including the height and width of the standard template are first performed. Summary of the Invention
The method known of the cited document does not describe steps for specifically extracting the landmark corresponding to the location of the spine pedicles. It only provides the corner locations. Now, the pedicle locations are particularly useful to estimate the rotation angle of every vertebrae. The present invention has for object to propose a image processing method to extract spine data called landmarks corresponding to the pedicle locations. This method has steps to perform the extraction of these pedicle landmarks using previously determined locations of other landmarks corresponding to the vertebra corner projections. For example, these steps are carried out by processing a frontal image of a number of adjacent vertebrae of the spine. Such an image processing method is claimed in Claim 1. An imaging system, an X-ray apparatus and a computer program product are also claimed to carry out the method.
These extracted geometrical data permit of providing information appropriate to help diagnosing scoliosis even on a single 2-D image. Said data also permit of three- dimensional image reconstruction of the spine from two bi-planar images using a technique of geometric modeling. Three-dimensional images of the spine particularly help diagnosing scoliosis because said disease is a 3-D deformity of the spine. The construction of the 3-D model of the spine is based on the location of the corner landmarks and the pedicle landmarks of the spine vertebrae. Brief Description of the Drawings
The invention is described hereafter in detail in reference to diagrεu imatic figures, wherein:
FIG.1A, FIG. IB, FIG.1C are representations of a vertebra in various perspectives; FIG.2A and FIG.2B show optimal landmarks of a vertebra, in frontal and lateral views;
FIG.3A and FIG.3B illustrate the step of positioning of the vertebra in a local referential;
FIG.4A shows a spine frontal view and FIG.4B shows icons of successive vertebrae, each icon representing the features of the vertebra in its local referential;
FIG.5 A represents a particular vertebra and FIG.5B represents the corresponding icon;
FIG.6 A shows, superimposed on an icon, a curve of feature accumulation and FIG.6B shows the corresponding curve of Costs ; FIG.7A is the curve of Costs for the determination of a couple of pedicles and
FIG.7B is a 3-D Cost Matrix for determining the best paths where the left and right pedicles are to be found along the spine;
FIG.8 is a functional block diagram of medical diagnostic imaging system and apparatus for carrying out the method. Description of embodiments
The invention relates to an image processing method for extracting geometrical data of the spine, in order to localize specific elements of the spine in spine images, for studying spine deformities. The specific elements are the pedicles of the vertebrae. Referring to FIG.l A to FIG.1C, in perspective views, a vertebra shows a body 7, which defines the spine axis and the shape of the vertebral discs and which is substantially cylindrical with flattened elliptic bases 1, 2 called endplates (FIG1A, FIG.1C); a spineous process 4 located in the plane of symmetry of the vertebra (FIG.l A, FIG. IB); two transverse processes 3 (FIG.l A, FIG.1C) and two pedicles 5 located at the bases of the vertebral arches (FIG.l A, FIG. IB); the pedicles define the intrinsic rotation of the vertebra around its axis.
Six optimal landmarks are selected, as represented respectively in the frontal and in the lateral images shown in Fig.2A and FIG.2B. These landmarks are the extremities of the projection of the vertebra body, which are the corners A, B, C, D, A', B', C, D* of the vertebra; and the position of the inner points E, F of the projection of the pedicles, further on called pedicle landmarks. The present method supposes that the corners A, B, C, D of the interesting vertebrae have already been located in a frontal view. This method comprises steps of:
A frontal image of an examined patient is acquired. This image may be formed by X-ray imaging, as shown in FIG.4A. Each point has a luminance intensity and coordinates in a cartesian referential whose axes are parallel to the sides of said frontal view. The frontal view may comprise a number of adjacent vertebrae, for example sixteen (16) vertebrae. The processing method encounters problems due to the position of the pedicles with respect to the other landmarks in the different vertebrae along the spine. In the thoracic vertebrae, the pedicles are almost at the same height as the upper endplate or even higher and they are very difficult to detect. In the lumbar vertebrae the pedicles are in the upper half of the vertebrae and they are easier to detect. The vertebrae have individual axes of rotation that are generally not vertical and that are different from each other.
Each vertebra is processed separately in order to take advantage of the local intensity properties for pedicle detection. In the region of the processed vertebra, the sides of the vertebra present a high contrast, which would interfere in the detection of the pedicles. In order to prevent this interfering, a restricted Region of Scanning is defined, which is a part of the image to be processed for pedicle detection. To this end, each vertebra is attributed an independent cartesian referential in which the Region of Scanning is further defined. Referring to FIG.3A, the current frontal original vertebra image shows the corner landmarks A, B, C, D. The middle points of the left and right lines joining the corners, respectively CA, DB, are denoted Oj. for AC and O2 for BD. The coordinates of these middle points Oi, O2 are computed in the referential of the frontal view. The line OjO2 that goes through these points is an axis X' that is generally not horizontal as above-described. The orthogonal axis Y' going through the center O of Oι;O2, is generally not vertical. A new referential X, Y is determined with a horizontal axis X and a vertical axis Y. The Region of Scanning is obtained by rotating a part of the of the current frontal original vertebra image using a rotation angle θ that is the angle between the X'-axis and the current horizontal axis defined in the frontal view. The new X-axis is parallel to this current axis. The center of the rotation is O and the part of the image to rotate is determined by the largest projections of the corners A, B, C and D onto the new X-axis.
Referring to FIG.3B, the part of the image resulting from said rotation is rectangular with O as the center and constitutes the Region of Scanning. It is delimited by horizontal lines parallel to the X-axis at the ordinates Y_, YE, and by vertical lines parallel to the Y-axis at the abscissae X., XE- So, the Region of Scanning in this new referential X, Y is defined by the rightmost projection of corners A and C onto the X-axis leading to X_, the leftmost projection of corners B and D onto the same X-axis leading to XE- The same procedure for the Y-axis leads to Y_ and YE. The Region of Scanning is defined by New Corners that are A0(X0, YE), B0(XE, YE), D0(XE, YE), and C0(X0, Yo).
Features that are characteristic of the points found in said Region of Scanning are estimated. The results of this operation of Feature Estimation permits of constructing an Image of Features in the local referential X, Y of the Region of Scanning. Different features can be considered for pedicle detection, such as gradient values, gray levels or intensity variance. The features that are considered as most effective to discriminate the thin structures representing the pedicles are ridgeness values.
The image of the Region of Scanning can be a positive image, which is considered as a 3-D picture, having two dimensions for the co-ordinates of pixels and a third dimension for the intensity signals associated to said pixels. A ridge is a crest-like structure formed by adjacent pixels having intensity signals that are maximum in a neighborhood, said pixels having specific dispositions the ones with respect to the others resulting in specific gradient values with respect to orientations. A ridge pixel shows a low intensity gradient in a first determined direction in its neighborhood, and shows an intensity gradient that is maximum in a direction perpendicular to said first direction. The more a given structure is formed of pixels verifying this gradient property, the more the ridgeness measure of the structure is high. Instead of ridges, troughs can be considered in a negative original image of the Region of Scanning for instance obtained by X-ray imaging. In an X-ray negative image, a ridge structure is a dark structure on a lighter background. In this case, the calculations for extracting the pedicles have for an object to extract trough pixels, which can be determined by measures similar to ridgeness calculations. In ridgeness calculations applied to troughs determination, the estimation of specific intensity gradients that is required for characterizing ridges is still valuable for characterizing troughs. So, in the description of the present method, these calculations are called "ridgeness" calculations, whether they are applied to ridges or troughs in the Region of Scanning.
FIG.5 A shows an original frontal image of a vertebra. The method comprises a step of "ridgeness" calculation applied to the image of the Region of Scanning corresponding to the vertebra of FIG.5A. This "ridgeness" calculation is performed by applying, on the pixels, filters known as ridge-filters, which determine the pixels of the ridge or trough structures. Based on this ridgeness calculation, each pixel of the Region of Scanning is further associated to a ridgeness data. The resulting image is called Feature Image as shown on FIG.5B.
Preferably, in a variant of this step of Feature Image formation, the features are computed on a Region of Interest ROI, which is constituted of a number of adjacent vertebrae and of a border region around these vertebrae represented in a frontal view such as the view shown on FIG.4A. From this Feature computation in the ROI, an image called ROI Feature Image is formed. The calculation of various new referentials by rotation and the calculation of various limited Regions of Scanning in said new referentials, as above- described, are then further performed based on said ROI Feature Image. FIG.4B shows various icons of Feature Images corresponding to said various Regions of Scanning. The icon 2 of FIG.4B is a Feature Image corresponding the circled vertebra of FIG.4A. The icon 1 is a Feature Image of a vertebra above the circled one and the icons 3 to 10 are Feature Images of the successive vertebrae below this circled one.
For every vertebra, the contrast of the Feature Image, in each icon corresponding to the Region of Scanning, is preferably further linearly enhanced. This Feature Image is scanned parallel to the vertical Y-axis, and the Feature values are accumulated by summing, in the direction of the Y-axis for every X coordinates between Xo and XE, called X-Region. Actually, this accumulation may be limited to be computed only on the upper-region of the vertebral body. This upper-region may be defined as covering only 70% of the length of the Y-axes of the Region of Scanning, since the pedicles are usually located on this upper-region. Avoiding to scan the lowest part of the Region of Scanning enables to avoid taking into account the lower endplates, thus avoiding interfering disturbances, and enables to reduce calculation amount. Referring to FIG.6A, the summed Feature Nalues are projected onto the horizontal X-axis. This operation results in a curve of the Accumulated Feature Nalues, called AS, showing maximum values called Peaks corresponding to the occurrence of ridges substantially parallel to the vertical Y-axis. The curve S is superimposed onto the Feature Image inverted in intensity.
These Accumulated Values are further transformed into Local Costs. In this step of Local Cost calculation, an inversion operation is required for providing a correspondence between the highest Accumulated Nalues or Peaks of the curve AS and lowest Local Costs. The X-region is split into two parts: a left part and a right part. For both parts independently, the Accumulated Nalues are submitted to a threshold operation. As an example, a threshold is set at 80% of the average level of the Accumulated Nalues. So, LC being the associated Local Cost:
LC = 0 when associated to the highest Accumulated values;
LC = 1000 when associated to an Accumulated Value equal to the predetermined threshold level;
LC is infinite when associated to every location on the X-axis where an Accumulated Value is found to be below the predetermined threshold level.
For the other locations, an associated cost LC is computed as the inverse of the corresponding Accumulated Value: a precise equation being for example:
Figure imgf000007_0001
where f the threshold level, S is the Accumulated Value, AS is its average and Ms its maximum value. FIG.6A shows the accumulation curve and FIG.6B shows the local cost curves for the vertebra presented in FIG. 5 A, 5B. In Fig.όB, for visualization purpose, the image of the vertebra features are included, with reversed contrast, on the background of the graphs, as in FIG.6 A. It is to be noted that the cost graph has been limited to a 0-2000 range but actually goes to an INFINITE COST, which is defined at 109, with 1000 limiting the useful region.
Projected pedicles mostly look like thin vertical lines. The pedicle landmarks of FIG.2A situated on said thin lines are detected in the frontal view. As shown on FIG.2A, pedicle projections are elliptical-shaped. The left and right external borders of the elliptical- shaped pedicles may be a source of errors. According to the present method, the Y- accumulation procedure is used to perform a discrimination between the left and the right borders of each elliptical shaped pedicle. The Feature Images may include some other sources of errors that are the borders of the vertebra, which also show high feature response and which are vertical, and the projection of the spurious process, which may appear as a vertical line roughly in the middle of the vertebral body but mostly in the lowest part of the body. According to the present method, the effects of these possible errors will be reduced by a further Dynamic Programming procedure.
It is important to note that only the internal border locations of the pedicles are looked for, because only these locations are used to estimate the rotation of the vertebra for diagnosing the severity of spine scoliosis. The pedicle landmarks that are on the internal border locations of the left and right pedicles are respectively called Left and Right Pedicle Locations. As explained previously, the present method has for an object to simultaneously detect the Left and Right Pedicle Locations for the specific spine vertebra of a specific patient. For performing this operation, the couples of Left and Right Pedicle Locations, which are represented by couples of corresponding abscissae X , XR on the X-axis, are looked for, for all vertebrae. Since a Local Cost is associated to each abscissa on the X-axis, couples XL, XR showing the lowest Costs are looked for, for each vertebra. For each given Left Pedicle Location X , several Right Pedicle Locations XR are possible, thus forming several couple candidates of Left and Right Pedicle Locations. For estimating the best couple candidates: the whole Region of Interest ROI of the spine is considered in order to take into account the locations of each couple candidate of a given vertebra with respect to the other couple candidate of the other vertebrae, which give more robustness in the location determinations; the location of each vertebra in the spine, called state, is defined by a vertebra index V, which is the name or the position of said vertebra in the spine, and a Database is accessible to provide average values of the distance, hereafter called Pedicle Distance, separating candidate couples of Left and Right Pedicle Locations, for each given vertebra; every possible Left Pedicle Location is determined in a range of coordinates between Xo and the middle of the X-Region (middle of XOXE), and a certain number of position candidates for the Right Pedicle Location is determined, typically in ten (10) bands called "bins", gathering 1 to 3 Right Pedicle Location candidates;
The procedure of finding Right Pedicle Locations PR, called PR candidate, from a given particular Left Pedicle Location P , called PL candidate, comprises: searching for PR candidates at a distance DJ_,R estimated from the database, within a range proportional to the standard deviation to this distance, thus defining a search region; dividing this search region into a number of bins, favorably ten (10) bins, of equal size; selecting the same number (10) of PR candidates, one for each bin. If one bin is found empty, an infinite cost is applied. If several PR candidates are inside the same bin, the PR candidate having the minimum local cost is selected. Thus for every P candidate, a set of said number of for example ten (10) PR candidates is built. computing the local cost associated with one state, defined by the vertebra index V, with the PL candidate and with an associated PR candidate, as the sum of three terms that are: the Cost associated to the PL candidate; the minimum of the Costs associated to every PR candidate in the current bin, the deviation of the current distance DLR between said PL and PR candidates with respect to the "average" distances DL5R as estimated from the database. Actually the distance term is normalized by the cosine of the rotational angle of the current vertebra estimated by using information from only the left location.
Referring to FIG.7A, the actual computation is performed according to:
SC(L, R) = LCL + LCR + (DL R - DL?R ) which is the State Cost SC(L, R) for associating possible PL and PR candidates, expressed as the Sum of the Local Costs LCL and LCR at the indicated locations of said possible candidates, plus the difference between the actual distance DL,R between the locations of said candidates and the corresponding "average" normalized distance DJ_,,R for the given vertebra. It is to be noted that these Local Cost computations are performed for every vertebra and thus the previous equation depends upon V, the vertebra index. These State Costs SC(V, L, R) are used for defining the Matrix-Costs of the 3D-state-Matrix illustrated on FIG7B.
A Dynamic Programming (DP) procedure is carried out in order to determine one Best Couple among the PL and PR candidates, for each vertebra of the spine, taking into account that for two successive vertebrae, the pedicles are substantially aligned (except in the case of a vertebral displacement) and that for the whole spine, the paths on which the pedicles are disposed are substantially smooth. This Dynamic Programming (DP) is a non- iterative method, effective in contour detection, that uses Energy Functions and that is not described hereafter, because it is well known of those skilled in the art. This procedure has for a purpose to determine the "most likely path" for the location of the PL and PR candidates. The points that are to be linked are those that are most likely part of the pedicle internal sides. The Dynamic Programming (DP) procedure calculates the Path of lowest Cost going from a node to another to yield this Path. The DP is performed in the frontal view in the vertical direction.
A 3-D Matrix of States is defined, as depicted in FIG.7B. This Matrix has a PL-axis (vertical), for the number, for example 30, of P candidates; it has a PR-axis ( in the depth direction of FIG.7B) for the number of PR bins (10 bins) per each PL candidate; the PL- axis and the PR-axis define a plane, regarded as a band (vertical band on FIG.7B) of the 3-D Matrix. The third dimension (horizontal) of this Matrix is the State given by the index V of the current vertebra under study among the number N of adjacent vertebrae that is user specified, typically 5 or 16 vertebrae.
For carrying out the Dynamic Programming Procedure, a first pass, called Forward Pass, is performed in a forward direction along the V-axis. In a first State (for a first vertebra), a first couple of PL and PR candidates, for instance denoted by PLI , PRI, is defined as the one with the lowest State Cost in the corresponding first band of the Matrix of States. The procedure has for an object to determine, in the following State (for the second vertebra), a couple of P and PR candidates, for example denoted by PL2 , PR2, which is one with the optimum State Cost in this second State and which is linked to the first couple of the first State with the lowest Transition Cost. This Transition Cost is favorably the Sum of the distances between Pu, PL2 and between PR1S PR2. This couple PL2, PR2 that fulfils the Cost conditions in the second State is called Best Predecessor. So, for each State, the Best Predecessor is defined as the one with the lowest Path Cost. The search for this Best Predecessor is actually performed by first looking for the PL candidate that is the closest to the one of the current State (+10 locations). Then, for determining the best PR candidate in said current State, a Path Cost is defined for linking the current State and its Predecessor State, composed of three Costs: the Local Costs of the previous State, the State Cost of the current State, the Transition Cost that is the Sum of the Distances between the couples of PL and PR candidates and is intended to penalize sudden local variation of the rotational angle.
A second pass, called Backward Pass, is performed in the backward direction. The Backward Pass determines, for every State, the most probable predecessor, i.e. the Couple of the previous State that has the minimal Path Cost. The Backward Pass begins in the State of the last vertebra having the lowest Path Cost. Going backwards, the Dynamic Programming Procedure retrieves the locations for both pedicles for every vertebra. Thus, it defines a line in the 3-D Cost Matrix. Two vertical lines are then drawn in the local referentials to display the determined pedicle landmark locations for every linked vertebra. The user can then select and move faulty lines towards correct locations. As soon as he releases a line, the cost is modified such that a zero (0) Cost is associated to the selected location and an infinite Cost is set for all the other locations in the current half vertebra. The building of a new Cost Matrix is then performed, followed by a new Dynamic Programming Procedure.
Referring to FIG.8, a medical examination apparatus 150 comprises means for acquiring digital frontal image data of the spine, and a digital processing system 120 for processing these data according to the processing method above-described. The medical examination apparatus comprises means for providing image data to the processing system 120 which has at least one output 106 to provide image data to display and/or storage means 130, 140. The display and storage means may respectively be the screen 140 and the memory of a workstation 110. Said storage means may be alternately external storage means. This image processing system 120 may be a suitably programmed computer of the workstation 130, or a special purpose processor having circuit means such as LUTs, Memories, Filters, Logic Operators, that are arranged to perform the functions of the method steps according to the invention. The workstation 130 may also comprise a keyboard 131 and a mouse 132.

Claims

CLAIMS:
1. An image processing method of extracting geometrical data of the spine, for extracting the left and right pedicle landmarks of each spine vertebra, comprising steps of: acquiring image data of a 2-D frontal image of the spine; associating spine States to vertebra positions along the spine and estimating locations of left and right pedicle landmark Candidates (PL and PR) in each State (V); defining a State Cost for forming Couples of left and right pedicle landmark Candidates; estimating sets of Best Couple Candidates, in each State, from the lowest State Costs; defining a Path Cost to go from one State to the next State; selecting a pedicle landmark Couple in each spine State among the Best Couple
Candidates from the minimum Path Costs, and localizing the left and right pedicle landmarks of each spine vertebra from said selected pedicle landmark Couple.
2. The image processing method of Claim 1 , wherein the step of selecting said pedicle landmark Couple comprises: defining a 3-D Cost Matrix having planes, defining Bands corresponding to the States, in which the Best Couple Candidates are located, said Cost Matrix having a directional axis, orthogonal to said planes, for indices corresponding to spine States; performing a first pass in a first direction along said directional axis, for computing the Path Costs between the Best Couple Candidates of each State and the Best Couple Candidates of the corresponding Predecessor State, and performing a second pass in the reverse direction for selecting a Couple in each State that show the lowest Path Cost to go to the next State.
3. The image processing method of Claim 2, wherein the Path Cost definition comprises compounding Local Costs related to the landmark location Candidates in the predecessor State, the State Cost for forming Couple Candidates in the current State and a Transition Cost that is function of the Distance between the Couple Candidates in each State, which penalizes sudden local variation of the rotational angle of the vertebrae of the predecessor and current State.
4. The image processing method of Claim 3, wherein the State Cost definition comprises summing respective Local Costs for left and right pedicle landmark location
Candidates, and a normalized Distance between said left and right pedicle landmark candidate locations in each State, which takes the index of the State into account.
5. The image processing method of one of Claims 1 to 4, wherein the estimation of left and right pedicle landmark location Candidates in each State comprises: computing, from the spine image data, Features Values that are characteristic of thin structures; scanning a region, called Region of Scanning, containing the pedicles, for each vertebra, along scan lines substantially parallel to the pedicle internal border lines, where the pedicle landmarks are to be localized; andaccumulating Feature Values of each scan line on an axis, called X-axis that is orthogonal to the scan lines, and transforming the accumulated Feature Values into Costs, called Local Costs, measured along said X- axis, said Local Cost Values being the smallest for the highest Accumulated Values; performing a search for the left and right pedicle landmark location Candidates among the points of said X-axis associated to the smallest Local Costs.
6. The image processing method of Claim 5, wherein the determination of the Best Couple Candidates, at a given State, comprises: determining a range for the left pedicle landmark location Candidates on the X-axis; determining a number of location Candidates for the right pedicle landmarks, in a
Search Region determined on said X-axis at a predetermined Distance of the current left pedicle location Candidate; dividing said Search Region into a number of bins, each containing a number of right pedicle landmark location Candidates; computing the State Cost and selecting sets of Best Couple Candidates linked by the smallest State Costs.
7. The image processing method of one of Claims 5 or 6, wherein the determination of the Region of Scanning comprises: selecting an image of a current vertebra delimited by lines joining its comer landmarks; estimating the median axis of the vertebra sides and the angle between said axis and a reference horizontal axis of the 2-D spine frontal image; rotating the image of said current vertebra by said angle and defining an horizontal axis, which is the X-axis corresponding to said current vertebra; and limiting the rotated image by the leftmost and the rightmost projections of the vertebra comer landmarks on said X-axis, thus defining a rectangular image region used as Region of Scanning.
8. The image processing method of one of Claims 5 to 7, wherein the Feature
Values are the ridgeness values estimated in the Region of Scanning.
9. A system comprising a suitably programmed computer or a special purpose processor having circuit means, which are arranged to process image data according to the method as claimed in any one of the preceding Claims.
10. A medical examination imaging apparatus having means for acquiring medical digital image data and having a system having access to said medical digital image data according to Claim 9, and having display means for displaying the medical digital images and the processed medical digital images.
11. A computer program product comprising a set of instructions for carrying out a method as claimed in one of Claims 1 to 8.
PCT/EP2001/010989 2000-09-29 2001-09-21 Method and system for extracting spine frontal geometrical data including vertebra pedicle locations WO2002027635A2 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP01982338A EP1386276A2 (en) 2000-09-29 2001-09-21 Method and system for extracting spine frontal geometrical data including vertebra pedicle locations
JP2002531340A JP2004509722A (en) 2000-09-29 2001-09-21 Method and system for extracting vertebral frontal geometry data including vertebral pedicle location

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP00402698 2000-09-29
EP00402698.5 2000-09-29

Publications (2)

Publication Number Publication Date
WO2002027635A2 true WO2002027635A2 (en) 2002-04-04
WO2002027635A3 WO2002027635A3 (en) 2002-12-27

Family

ID=8173888

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2001/010989 WO2002027635A2 (en) 2000-09-29 2001-09-21 Method and system for extracting spine frontal geometrical data including vertebra pedicle locations

Country Status (4)

Country Link
US (1) US6850635B2 (en)
EP (1) EP1386276A2 (en)
JP (1) JP2004509722A (en)
WO (1) WO2002027635A2 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9922418B2 (en) 2013-08-21 2018-03-20 Shimadzu Corporation Image processing device
US10062165B2 (en) 2014-10-29 2018-08-28 Shimadzu Corporation Image processing device
CN114224322A (en) * 2021-10-25 2022-03-25 上海工程技术大学 Scoliosis assessment method based on human skeleton key points

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2836818B1 (en) * 2002-03-05 2004-07-02 Eurosurgical PROCESS FOR VISUALIZING AND CHECKING THE BALANCE OF A SPINE COLUMN
US6980922B2 (en) * 2003-10-09 2005-12-27 Computational Biodynamics, Llc Computer simulation model for determining damage to the human central nervous system
US7561728B2 (en) * 2005-03-23 2009-07-14 Siemens Medical Solutions Usa, Inc. Detection of intervertebral disk orientation in spine images using curve evolution
TWI282268B (en) * 2005-09-15 2007-06-11 Univ Chung Shan Medical Medical image system and method for measuring vertebral axial rotation
US7949171B2 (en) * 2005-10-19 2011-05-24 Siemens Corporation System and method for tracing rib posterior in chest CT volumes
US20070242869A1 (en) * 2006-04-12 2007-10-18 Eastman Kodak Company Processing and measuring the spine in radiographs
US8165375B2 (en) * 2006-12-11 2012-04-24 Siemens Medical Solutions Usa, Inc. Method and system for registering CT data sets
US8423124B2 (en) * 2007-05-18 2013-04-16 Siemens Aktiengesellschaft Method and system for spine visualization in 3D medical images
US8685093B2 (en) * 2009-01-23 2014-04-01 Warsaw Orthopedic, Inc. Methods and systems for diagnosing, treating, or tracking spinal disorders
US8126736B2 (en) * 2009-01-23 2012-02-28 Warsaw Orthopedic, Inc. Methods and systems for diagnosing, treating, or tracking spinal disorders
CN101972165B (en) * 2010-11-18 2012-07-04 王铁铸 X-ray-film-based method for locating coordinates of pedicle screws
US8942917B2 (en) 2011-02-14 2015-01-27 Microsoft Corporation Change invariant scene recognition by an agent
US8571263B2 (en) * 2011-03-17 2013-10-29 Microsoft Corporation Predicting joint positions
US8891848B2 (en) * 2011-06-14 2014-11-18 Radnostics, LLC Automated vertebral body image segmentation for medical screening
CN103300856B (en) * 2012-03-13 2015-11-25 深圳迈瑞生物医疗电子股份有限公司 The cervical vertebral body axis of MRI image and the localization method of linked groups and device
US9235931B2 (en) * 2012-05-18 2016-01-12 Eiffel Medtech Inc. Method and system for the three-dimensional reconstruction of structures
US9857470B2 (en) 2012-12-28 2018-01-02 Microsoft Technology Licensing, Llc Using photometric stereo for 3D environment modeling
US9940553B2 (en) 2013-02-22 2018-04-10 Microsoft Technology Licensing, Llc Camera/object pose from predicted coordinates
WO2015063632A2 (en) 2013-10-30 2015-05-07 Koninklijke Philips N.V. Volumetric image data visualization
EP3151750B1 (en) 2014-06-06 2017-11-08 Koninklijke Philips N.V. Imaging system for a vertebral level
US9265463B1 (en) * 2014-12-22 2016-02-23 Medical Metrics, Inc. Methods for determining spine instability and for eliminating the impact of patient effort on stability determinations
EP3714792A1 (en) * 2019-03-26 2020-09-30 Koninklijke Philips N.V. Positioning of an x-ray imaging system
KR102078876B1 (en) 2019-09-03 2020-02-20 주식회사 루닛 Method and system for detecting pneumothorax
CN118557284B (en) * 2024-07-31 2024-10-11 北京大学第三医院(北京大学第三临床医学院) Guide plate generation method and device and guide plate

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5291537A (en) * 1992-09-14 1994-03-01 Lunar Corporation Device and method for automated determination and analysis of bone density and vertebral morphology

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5841833A (en) 1991-02-13 1998-11-24 Lunar Corporation Dual-energy x-ray detector providing spatial and temporal interpolation
WO1999052068A1 (en) 1998-04-03 1999-10-14 Koninklijke Philips Electronics N.V. Image processing method and system involving contour detection steps
US7046830B2 (en) * 2000-01-27 2006-05-16 Koninklijke Philips Electronics, N.V. Method and system for extracting spine geometrical data
US6608916B1 (en) * 2000-08-14 2003-08-19 Siemens Corporate Research, Inc. Automatic detection of spine axis and spine boundary in digital radiography
US6724924B1 (en) * 2000-08-14 2004-04-20 Siemens Corporate Research, Inc. Brightness and contrast invariant detection of vertebra pedicles
US6608917B1 (en) * 2000-08-14 2003-08-19 Siemens Corporate Research, Inc. Detection of vertebra endplates in digital radiography

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5291537A (en) * 1992-09-14 1994-03-01 Lunar Corporation Device and method for automated determination and analysis of bone density and vertebral morphology

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
KAUFFMANN C ET AL: "DIGITAL RADIOGRAPHY SEGMENTATION OF SCOLIOTIC VERTEBRAL BODY USING DEFORMABLE MODELS" PROCEEDINGS OF THE SPIE, SPIE, BELLINGHAM, VA, US, vol. 3034, no. PART 1/2, 1997, pages 243-251, XP000869811 cited in the application *
NELSON D ET AL: "MEASUREMENT OF VERTEBRAL AREA ON SPINE X-RAYS IN OSTEOPOROSIS: RELIABILITY OF DIGITIZING TECHNIQUES" JOURNAL OF BONE AND MINERAL RESEARCH, NEW YORK, NY, US, vol. 5, no. 7, 1 July 1990 (1990-07-01), pages 707-716, XP000575170 ISSN: 0884-0431 *
PETIT Y ET AL: "ESTIMATION OF 3D LOCATION AND ORIENTATION OF HUMAN VERTEBRAL FACET JOINTS FROM STANDING DIGITAL RADIOGRAPHS" MEDICAL AND BIOLOGICAL ENGINEERING AND COMPUTING, PETER PEREGRINUS LTD. STEVENAGE, GB, vol. 36, no. 4, 1 July 1998 (1998-07-01), pages 389-394, XP000755436 ISSN: 0140-0118 *
RAY L P: "MONOCULAR 3D VISION FOR A ROBOT ASSEMBLY ENVIRONMENT" INTERNATIONAL CONFERENCE ON SYSTEMS ENGINEERING. PITTSBURGH, AUG. 9 - 11, 1990, NEW YORK, IEEE, US, 9 August 1990 (1990-08-09), pages 430-433, XP000169433 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9922418B2 (en) 2013-08-21 2018-03-20 Shimadzu Corporation Image processing device
US10062165B2 (en) 2014-10-29 2018-08-28 Shimadzu Corporation Image processing device
CN114224322A (en) * 2021-10-25 2022-03-25 上海工程技术大学 Scoliosis assessment method based on human skeleton key points

Also Published As

Publication number Publication date
EP1386276A2 (en) 2004-02-04
JP2004509722A (en) 2004-04-02
WO2002027635A3 (en) 2002-12-27
US20020061126A1 (en) 2002-05-23
US6850635B2 (en) 2005-02-01

Similar Documents

Publication Publication Date Title
US6850635B2 (en) Method and system for extracting spine frontal geometrical data including vertebra pedicle locations
US7046830B2 (en) Method and system for extracting spine geometrical data
US6668083B1 (en) Deriving geometrical data of a structure from an image
US7492968B2 (en) System and method for segmenting a structure of interest using an interpolation of a separating surface in an area of attachment to a structure having similar properties
US20070116357A1 (en) Method for point-of-interest attraction in digital images
US8023732B2 (en) Accelerated image registration by means of parallel processors
US7106891B2 (en) System and method for determining convergence of image set registration
EP1975877B1 (en) Method for point-of-interest attraction in digital images
US20010036302A1 (en) Method and apparatus for cross modality image registration
EP1350222A2 (en) Image registration system and method using cross-entropy optimization
JP2004508856A (en) Image registration system and method using likelihood maximization
US6026142A (en) System and method for boundary detection in tomographic images by geometry-constrained edge detection of projected data
US20150154765A1 (en) Tomosynthesis reconstruction with rib suppression
WO2021081483A1 (en) System and method for analyzing three-dimensional image data
CN111429446A (en) Lung image processing method, device, equipment and storage medium
Nain et al. Intra-patient prone to supine colon registration for synchronized virtual colonoscopy
US8165375B2 (en) Method and system for registering CT data sets
CN1902640A (en) System and method for filtering and automatic detection of candidate anatomical structures in medical images
EP4113439B1 (en) Determining a location at which a given feature is represented in medical imaging data
US7590271B2 (en) System and method for automatic detection and localization of 3D bumps in medical images
US20240339198A1 (en) Technique for rendering a sheared-volume based medical image
US20240290471A1 (en) Method for automated processing of volumetric medical images
CN117132570A (en) Automatic tissue positioning calculation method and system based on CT image
Hauenstein et al. Exhibition and Evaluation of Two Schemes for Determining
Hong et al. Intensity-based registration and combined visualization of multimodal brain images for noninvasive epilepsy surgery planning

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): JP

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR

121 Ep: the epo has been informed by wipo that ep was designated in this application
ENP Entry into the national phase

Ref country code: JP

Ref document number: 2002 531340

Kind code of ref document: A

Format of ref document f/p: F

WWE Wipo information: entry into national phase

Ref document number: 2001982338

Country of ref document: EP

AK Designated states

Kind code of ref document: A3

Designated state(s): JP

AL Designated countries for regional patents

Kind code of ref document: A3

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR

WWP Wipo information: published in national office

Ref document number: 2001982338

Country of ref document: EP

WWW Wipo information: withdrawn in national office

Ref document number: 2001982338

Country of ref document: EP