Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T7/00—Image analysis
  • G06T7/70—Determining position or orientation of objects or cameras
  • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/10—Image acquisition modality
  • G06T2207/10072—Tomographic images
  • G06T2207/10088—Magnetic resonance imaging [MRI]
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/10—Image acquisition modality
  • G06T2207/10116—X-ray image
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/10—Image acquisition modality
  • G06T2207/10132—Ultrasound image
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/30—Subject of image; Context of image processing
  • G06T2207/30004—Biomedical image processing
  • G06T2207/30101—Blood vessel; Artery; Vein; Vascular

Definitions

• TITLE Method for determining the position of a target element on an image of interest of a body area
• the present invention relates to a method for determining the position of at least one target element on at least one image of interest of a body area.
• the present invention also relates to an associated determination system.
• lymphadenectomy resection of the lymph node chain
• the concept of the sentinel lymph node was developed to make it possible to isolate the first lymph node(s) draining a solid tumor.
• Detection of the sentinel lymph node is currently based on a combined technique combining an injection of radioisotope before the intervention and either an injection of blue dye just after anesthetic induction, or colorimetric detection alone with indocyanine green. intraoperatively.
• laparoscopy also called laparoscopy
• laparoscopy it is difficult to locate the sentinel lymph node on laparoscopic images.
• the present description relates to a method for determining the position of at least one target element on at least one image of interest of a body zone, the body zone comprising at least one intermediate element imaged on the 'image of interest, the image of interest having been acquired by an imaging device, each image acquired by the imaging device having its own marker, called image marker, in which the elements of the image are identified , the position of the imaging device at each image acquisition being located in a fixed reference, called tracking reference, the body area being immobile in the tracking reference during the implementation of the method, the method being implemented computer work and including: has. a preparatory phase comprising the following steps: i.
• obtaining a geometric representation, called local geometric representation, of the intermediate element the local geometric representation being located in a fixed geometric reference, called local reference, the target element having a relative position with respect to the element intermediate which is known in the local reference, it.
• obtaining preparatory images of the body area the preparatory images having been acquired by the imaging device for different positions of the imaging device, each position of the imaging device corresponding to a different angle of view of the area bodily, ill.
• an exploitation phase comprising the following steps: i.
• the method comprises one or more of the following characteristics, taken in isolation or in all technically possible combinations:
• the steps of the exploitation phase are repeated over time for images of interest corresponding to different positions of the imaging device;
• the exploitation phase includes a step of displaying the image of interest on a screen with superimposed a representation of the target element at the position determined on the image of interest;
• the local geometric representation is obtained as functions of cross-sectional images of the body area comprising the intermediate element and the target element, the cross-sectional images having been acquired by a medical imaging device;
• the step of determining the local transformation includes: a. the determination, for each preparatory image, of a geometric representation, called annotated representation, of the intermediate element, the annotated representations being identified in the tracking marker as a function of the position of the imaging device during the acquisition of said images, b. placing the local geometric representation at an initial position in the tracking frame, c. determining, in the tracking reference, based on the annotated representations, a representation, called a preparatory geometric representation, and d. determining the local transformation by registration of the local geometric representation and the preparatory geometric representation in the tracking frame (R s );
• the intermediate element has an invariant form in projective geometry
• the intermediate element is an arterial network, such as the iliac arterial network
• the target element is a lymph node, preferably a sentinel lymph node.
• the present invention also relates to a system for determining the position of at least one target element on at least one image of interest of a body zone, the body zone comprising an intermediate element imaged on the image of interest , the image of interest having been acquired by an imaging device, each image acquired by the imaging device having its own marker, called image marker, in which the elements of the image are identified, the position of the device imaging at each image acquisition being located in a fixed reference, called tracking reference, the system comprising a calculator configured to implement the steps of a method according to the invention; And
• the system also includes: a. the imaging device for acquiring preparatory images and images of interest, b. a support on which the imaging device is mounted, and c. a tracking device connected to the support for moving the imaging device and tracking the movements of the imaging device.
• the present description also relates to a computer program product on which a computer program comprising program instructions is stored, the computer program being loaded onto a data processing unit and causing the implementation of a method as described above when the computer program is implemented on the data processing unit.
• the present description also relates to a readable information medium on which a computer program product is stored comprising instructions for program, the computer program being loaded on a data processing unit and causing the implementation of a method as described above when the computer program is implemented on the data processing unit.
• the present description also relates to a surgical method comprising: placing an imaging device in the body of the (anesthetized) patient, acquiring, by the imaging device, preparatory images of a body area, the body zone comprising an intermediate element (visible on the images) and a target element (visible or not on the images), the implementation of the preparatory phase of the determination method as described previously according to the preparatory images acquired, the acquisition, by the imaging device, of an image of interest of the body zone, and implementation of the operating phase of the determination method as described previously for the acquired image of interest.
• FIG 1 Figure 1
• Figure 2 Figure 2
• Figure 2 a flowchart of an example of implementation of a method for determining the position of a target element on images of interest of a body area
• FIG 3 Figure 3 a schematic view illustrating an example of obtaining a local geometric representation based on cross-sectional images (coming from a medical imaging device),
• FIG 4 Figure 4 a schematic representation of an example of an annotated representation of an intermediate element, the annotated representation having been obtained from a preparatory image, and
• FIG 5 Figure 5 a schematic representation of an example of registration of a local geometric representation and a preparatory geometric representation in the tracking frame.
• FIG. 1 An example of a system 10 for determining the position of a target element Ec on images of interest of a body area Z is illustrated in Figure 1.
• the target element Ec is illustrated in Figure 3.
• the system 10 includes an imaging device 12, a support 14, a tracking device 16, and a calculator 18.
• the system 10 only includes the computer 18.
• the imaging device 12 is capable of acquiring images of a body zone Z.
• the imaging device 12 is, for example, a camera.
• the images acquired are two-dimensional (2D) images.
• the images acquired are three-dimensional (3D) images, for example obtained directly from a 3D video stream or resulting from two 2D video streams combined to obtain 3D images.
• the support 14 supports the imaging device 12.
• the support 14 is able to be moved, thus allowing the movement of the imaging device 12.
• the support 14 is, for example, a tube into which the imaging device 12 is inserted.
• the tracking device 16 is connected to the support 14.
• the tracking device 16 is able to move the imaging device 12 and to follow the movements of the support 14, and therefore of the imaging device 12.
• the tracking device 16 is an instrumented arm.
• the calculator 18 is, for example, connected by wire or wireless (Wifi, Bluetooth), on the one hand, to the imaging device 12 so as to receive the images acquired by the imaging device 12, and on the other hand, to the tracking device 16 to obtain the position of the imaging device 12.
• the calculator 18 is, for example, a computer interacting with a computer program product.
• the calculator 18 typically comprises a processor comprising a data processing unit, memories and an information support reader.
• the computer 18 also conventionally includes a man-machine interface (keyboard), a screen (touch or not) and a mouse.
• the computer program product includes an information carrier.
• the information medium is a medium readable by the computer 18, usually by the data processing unit.
• the readable information medium is a medium suitable for storing electronic instructions and capable of being coupled to a bus of a computer system.
• the information carrier is a USB key, a floppy disk or floppy disk, an optical disk, a CD-ROM, a magneto-optical disk, a ROM memory , a RAM memory, an EPROM memory, an EEPROM memory, a magnetic card, an optical card or even a punched card.
• the computer program comprising program instructions is stored on the information carrier.
• the computer program can be loaded onto the data processing unit of the calculator 18 and is adapted to cause the implementation of a method for determining the position of a target element Ec on images of interest of a body zone Z.
• Figure 2 illustrates a flowchart of a method for determining the position of a target element Ec on images of interest of a body area Z and Figures 1 and 3 to 5, which illustrate examples of implementation of steps of the method.
• the determination method described in the following aims to determine the position of a target element Ec on images of interest of a body zone Z.
• the body zone Z comprises at least one intermediate element Ei and at least one target element Ec.
• the intermediate element Ei is visible on the images of interest, the target element Ec is generally not visible on the images of interest (hidden by organs or tissues of body area Z). It is understood that the intermediate element Ei and the target element Ec are nearby.
• the intermediate element Ei has an invariant shape in projective geometry, that is to say that the shape of the intermediate element does not vary when the element is projected (in a plane for example).
• the intermediate element Ei has, for example, a tubular shape.
• the intermediate element Ei is an arterial network, such as the iliac arterial network
• the target element Ec is a lymph node, preferably a sentinel lymph node.
• Figure 1 generally illustrates the geometric benchmarks and transformations considered during the implementation of this method.
• an image marker Ri (variable) specific to each image acquired by the imaging device 12 and in which the elements of the image are identified.
• the images considered in the remainder of the description are the preparatory images IM P and the images of interest IMi.
• the tracking mark Rs is for example a mark relating to the tracking device ( base of the articulated arm for example).
• a local reference frame RL fixed in which a local geometric representation GL of the intermediate element Ei is located (obtained from cross-sectional images also identified in the local reference frame).
• Figure 1 also illustrates the transformations allowing you to move from one benchmark to another, namely:
• the local transformation L T S is a constant transformation whatever the position of the imaging device 12.
• the preparatory transformation s Ti' is a variable transformation depending on the position of the imaging device 12 during acquisition of the image considered (the index "i" indicates that the transformation is variable, i being incremented during time).
• the image transformation L Ti' is a variable transformation depending on the position of the imaging device 12 during acquisition of the image considered (the index "i" indicates that the transformation is variable, i being incremented during time).
• the aim of the present method is to determine the image transformation L Ti' making it possible to realign position information (position of the target element) identified in the image reference Ri of the image considered towards the local reference RL. For this, it is necessary to know the preparatory transformation s Ti' for the image considered and the local transformation L T S. The preparatory transformation s Ti' is capable of being obtained via the monitoring device 16. Thus, it remains to determine the local transformation L Ts.
• the determination method comprises a preparatory phase 100 and an operating phase 200.
• the preparatory phase 100 aims to determine the local transformation L T S making it possible to move from the tracking reference R s to the local reference RL.
• the determined local transformation L T S is used to determine the image transformation L Ti' making it possible to determine the position of the target element on the image of interest IMi considered.
• the determination method is implemented for a body zone Z immobile in the tracking reference R s .
• the determination method is implemented by the calculator 18 of the determination device 10, that is to say it is implemented by computer.
• the phases and steps described for the determination method relate to image processing on previously acquired images of a body area Z.
• the present method does not relate to the acquisition of images, these images being only obtained, in the sense of loading data, by the computer 18.
• the steps of the process are therefore entirely implemented outside the human body, without contact with the human body. None of these steps is therefore surgical or therapeutic in nature.
• the determination method therefore concerns a non-surgical method of determining the position of a target element Ec on images of interest of a body area Z.
• the preparatory phase 100 will now be described in more detail.
• the preparatory phase 100 aims to identify the local transformation L T S (constant) making it possible to move from the tracking reference R s to the local reference RL.
• the preparatory phase 100 includes a step 110 of obtaining a geometric representation, called local geometric representation GL, of the intermediate element Ei.
• obtaining is meant loading of the images by the computer 18, these images having for example been previously stored in a memory of the computer 18, or coming from a digital data stream to which is connected the calculator 18.
• the local geometric representation GL is a three-dimensional representation.
• the local geometric representation GL is located in the local coordinate system RL.
• the target element Ec has a relative position with respect to the intermediate element Ei which is known in the local reference frame RL (for example obtained via the sectional images identified in the local reference frame RL and having made it possible to obtain the local geometric representation GL).
• the local geometric representation GL is obtained as functions of cross-sectional images of the body zone Z comprising the intermediate element Ei and the target element Ec.
• the cross-sectional images were obtained by a medical imaging device.
• the medical imaging device is, for example, an MRI device, a CBCT device, an optical imaging device, a scanner, or even an ultrasound ultrasound device.
• the cross-sectional images are for example IM S scanner images.
• a scanner image is a slice image of a body area Z obtained by positron emission tomography coupled (SPECT) with computed tomography (CT) thus making it possible to image both the intermediate element Ei and the element target Ec.
• 2D IM S scanner images are used to reconstruct a 3D representation of the intermediate element Ei (iliac arterial network).
• the image processing software used (3D slicer® for example, see for example the following article: Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin JC, Pujol S, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging. Nov 2012;30(9):1323-41) makes it possible to generate a skeletonization of the arterial network. This skeleton forms the local geometric representation GL.
• this skeleton is, for example, formed of 2D curves immersed in 3D (represented by points or mathematical functions (splines, Bézier curves, etc.)) .
• the skeleton materializes the points of the intermediate element Ei respecting a property of projective invariance (axis of revolution of the tubes for example).
• the preparatory phase 100 comprises a step 120 of obtaining preparatory images IM P of the body zone Z.
• the preparatory images IM P were acquired by the imaging device 12 for different positions of the imaging device 12. Each position of the imaging device 12 corresponds to a different viewing angle of the body zone Z.
• the preparatory images IM P each have a known position in the tracking frame R s .
• This known position was for example obtained as a function of the position of the imaging device 12 obtained via the tracking device 16, to which the preparatory transformation s Ti' is applied making it possible to move from the image reference frame Ri to the tracking reference point R s .
• the preparatory transformation s Ti' is considered known when the position of the imaging device 12 is known.
• the preparatory transformation s Ti' as a function of the position of the imaging device 12 is obtained upstream, for example from supplier data or via prior calibration.
• the preparatory transformation s Ti' is composed of two elements.
• This second transformation is obtained via the tracking device 16.
• the preparatory phase 100 includes a step 130 of determining the local transformation L T S making it possible to move from the tracking reference R s to the local reference RL.
• There local transformation L T S is determined as a function of the local geometric representation GL, the preparatory images IMP, and the positions of the imaging device 12 during the acquisition of the preparatory images IM P.
• the determination step 130 comprises a sub-step 130A according to which, for each preparatory image IM P , a geometric representation of the intermediate element Ei, called annotated representation GA, is determined. In this example, at least three preparatory images IM P are considered.
• each representation annotated GA is a two-dimensional representation.
• the annotated representations GA are identified in the tracking marker Rs as a function of the position of the imaging device 12 during the acquisition of said images.
• the annotated representation GA of each preparatory image IM P is obtained by the action of an operator annotating / highlighting / pointing out a portion of the intermediate element Ei on the image (for example via a touch screen).
• the annotated representation GA of each preparatory image IM P is obtained semi-automatically, that is to say by an annotation carried out by the computer followed by validation/rectification by an operator.
• the annotation carried out by the computer is for example carried out by a detection algorithm.
• Figure 4 illustrates an example of a preparatory image IM P on which part of the intermediate element Ei has been identified by annotation, highlighting or pointing (automatically, manually or semi-automatically), the annotations / highlighting / pointing thus forming the annotated representation GA.
• the determination step 130 includes a sub-step 130B of placing the local geometric representation GL at a starting position in the tracking frame R s .
• the initial position is known (but can be chosen in any way).
• the determination step 130 comprises a sub-step 130C of determination, in the tracking reference R s , as a function of the annotated representations GA, of a representation, called the preparatory geometric representation G P .
• the preparatory geometric representation G P is obtained by projection of the annotated representations GA and cross-checking of said projections. Indeed, the intersection of the projective surfaces corresponds to the annotated/highlighted/pointed invariant portion of the intermediate element Ei (typically the center C of the artery).
• the preparatory geometric representation G P is then a “skeleton” of the network at the intersection of the projected surfaces as illustrated in Figure 5.
• the determination step 130 comprises a sub-step 130D of determining the local transformation L T S as a function of the local geometric representation GL and the preparatory geometric representation Gp.
• the local transformation L T S is obtained by realigning (preferably by superimposing) the local geometric representation GL and the preparatory geometric representation Gp in the tracking frame R s (and knowing the initial position of the local geometric representation GL in the tracking mark R s ).
• the local transformation L T s is, for example, obtained by minimizing the distances between the local geometric representation GL and the preparatory geometric representation Gp.
• minimization consists of minimizing the root mean square (RMS) of the distances between the curves forming the local geometric representation GL and the preparatory geometric representation Gp.
• the minimization is carried out by a method called gradient descent or by any other corresponding method of minimizing distances.
• Figure 5 illustrates an example of iterations to minimize the distances between the local geometric representation GL and the preparatory geometric representation Gp.
• the degree of similarity is lower than a predetermined threshold (threshold set by default in the software but adaptable by the operator)
• a predetermined threshold threshold set by default in the software but adaptable by the operator
• conditions have been set so that the algorithm stops the calculation iterations.
• These conditions include at least one of the following conditions:
• the operating phase 200 comprises a step 210 of obtaining an image of interest IMi of the body zone Z.
• the image of interest IMi was acquired by the imaging device 12 for a position of the device d imagery 12 known via the tracking device 16.
• the operating phase 200 comprises a step 220 of determining an image transformation L Ti' for the image of interest IMi as a function of the local transformation L Ts determined previously and the position of the imaging device 12 during the acquisition of the image of interest IMi.
• the position of the imaging device 12 makes it possible to obtain the preparatory transformation s Ti' for the image of interest IMi considered (for example in the same way as in the examples described previously for the preparatory phase).
• the operating phase 200 comprises a step 230 of determining the position Pi of the target element Ec on the image of interest IMi as a function of the determined image transformation L Ti' and the known relative position of the element target Ec relative to the intermediate element Ei.
• the exploitation phase 200 comprises a step 240 of displaying the image of interest IMi on a screen (of the calculator 18) with superposition (i.e. augmented reality) a representation of the target element Ec at the position Pi determined on the image of interest IMi.
• superposition i.e. augmented reality
• the steps of the operating phase 200 are repeated over time for images of interest I Mi corresponding to different positions of the imaging device 12.
• the repetition is preferably carried out in real time and continuously , that is to say as the images of interest IMi are received by the computer 18.
• the present method and the present system 10 make it possible to determine the position of a target element Ec on images of a body area Z acquired from different points of view.
• an intermediate element Ei is used to register a representation of the target element Ec on the image of interest I Mi considered.
• One of the advantages of the present method is that once the local transformation L Ts has been obtained, and provided that the body zone Z remains immobile, the registration can be carried out on images of interest IMi of the body zone Z acquired whatever the position of the imaging device 12. In other words, the imaging device 12 can be freely moved to acquire different images of interest I Mi of the body zone Z without having to re-perform a preparatory calibration phase.
• the method can therefore be used to locate sentinel lymph nodes (ie target element E c ) invisible by the imaging device 12 (eg endoscopic camera, laparoscope).
• the imaging device 12 eg endoscopic camera, laparoscope.
• the intermediate element Ei iliac arterial network
• the imaging device 12 eg endoscopic camera, laparoscope
• the intermediate element Ei iliac arterial network
• preoperative CT computed tomography

Landscapes

• Engineering & Computer Science (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Theoretical Computer Science (AREA)
• Apparatus For Radiation Diagnosis (AREA)
• Studio Devices (AREA)
• Image Analysis (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=84053265

Family Applications (1)

Country Status (3)

Families Citing this family (1)

• 2022
  • 2022-09-28 FR FR2209860A patent/FR3140193B1/fr active Active
• 2023
  • 2023-09-27 WO PCT/EP2023/076646 patent/WO2024068698A1/fr not_active Ceased
  • 2023-09-27 EP EP23777277.7A patent/EP4595005A1/de active Pending

Also Published As

Similar Documents

Legal Events