EP3371775A1 - Procede de suivi d'une cible clinique dans des images medicales - Google Patents
Procede de suivi d'une cible clinique dans des images medicalesInfo
- Publication number
- EP3371775A1 EP3371775A1 EP16806241.2A EP16806241A EP3371775A1 EP 3371775 A1 EP3371775 A1 EP 3371775A1 EP 16806241 A EP16806241 A EP 16806241A EP 3371775 A1 EP3371775 A1 EP 3371775A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- image
- target
- reference image
- contour
- cost function
- Prior art date
- Legal status (The legal status 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 status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20116—Active contour; Active surface; Snakes
Definitions
- the field of the invention is that of the treatment of medical images.
- the invention relates to a method for tracking a clinical target in a sequence of medical digital images.
- the invention finds particular application in the treatment of images obtained by an ultrasound imaging technique or endoscopy.
- Ultrasound or endoscopic imaging techniques are widely used in the medical field to help physicians visualize in real time a clinical target and / or surgical tool during a surgical procedure or invasive examination intended to diagnose a pathology.
- ultrasound techniques are frequently used during an intervention requiring the insertion of a needle, and especially in interventional radiology.
- dark or light aberrations such as shadows, halos, specularities or occlusions, may appear on the current image and disrupt monitoring. of a target.
- shadows are often observed in image sequences obtained by ultrasound imaging techniques or halos / specularities in endoscopic image sequences, which can strongly alter the contrast of the images. at target level and, in some cases, at least partially obscure the target.
- This confidence map is formed of estimated local confidence measures for the pixels or voxels of the current image.
- Each of these local confidence measurements corresponds to a value indicative of a probability or likelihood that the intensity of the pixel / voxel with which it is associated represents an object and is not affected by different disturbances such as, for example, shadows, reflections specular, or occultations generated by the presence of other objects.
- a disadvantage of this cost function is that it is not robust to changes in illumination, or gain, that may occur during acquisition.
- the invention aims in particular to overcome the disadvantages of the state of the art cited above.
- the invention aims to provide a clinical target tracking technique in a sequence of images that is robust regardless of the aberrations presented by the images of the sequence.
- An object of the invention is also to provide such a technique for monitoring a clinical target that has increased accuracy.
- deforming said obtained contour by minimizing a cost function based on a difference in intensity between the current image and the reference image in the determined zone, said cost function being weighted by the confidence measurements obtained for the elements image of said determined area.
- such a method of monitoring a clinical target further comprises a step of adapting the reference image at least from the intensities of the current image and the confidence measurements of the current image. in the target area and the cost function takes into account the intensities of the adapted reference image.
- the invention proposes to exploit the confidence measurements in the intensities of the current image to adapt the intensities of the reference image in the target area and thus to evaluate more precisely the relevant intensity difference to deform the contour of the target.
- said cost function takes into account a weighting of the combined probability density of the intensities of the current image and of the reference image by said confidence measurements.
- a target tracking method as described above further comprises a step of detecting at least one aberration portion in said reference image and in said current image and in that said detected aberration portion is taken into account in said step of obtaining a confidence measurement in said determined area for said reference image and for said current image.
- the deformation of the contour also takes into account a mechanical model of internal deformation of the target intended to correct said deformation resulting from the minimization of a cost function and in that the contour deformation resulting from the minimization of a cost function with respect to the deformation resulting from the mechanical model of internal deformation of the target in the area of the target.
- unit for obtaining a segmentation of a contour of said target from said reference image unit for determining a zone delimiting the inside of the segmented contour of the target in said reference image
- matching unit of the reference image at least from current image intensities and confidence measurements of the current image in the target area
- deformation unit of said contour via a minimization of a cost function based on a difference in intensity between the current image and the reference image in the determined zone, said cost function being weighted by the confidence measurements obtained for the image elements of the zone and taking into account the intensities of the adapted reference image.
- the invention also relates to a computer program comprising instructions for implementing the steps of a clinical target tracking method as described above, when this program is executed by a processor.
- This program can use any programming language.
- It can be downloaded from a communication network and / or recorded on a computer-readable medium.
- the invention finally relates to a recording medium, readable by a processor, integrated or not to the device for monitoring a clinical target according to the invention, optionally removable, storing a computer program implementing the method of followed by a clinical target as described above.
- FIG. 1 is a diagrammatic representation, in diagrammatic form, of the steps of an exemplary method for monitoring a clinical target according to the invention
- Fig. 2 is a segmented contour view of a target in a reference image
- Fig. 3 is a view of an image of a confidence measurement card
- FIG. 4 schematically shows an example of a hardware structure of a clinical target tracking device according to the invention.
- the principle of the invention is based in particular on a strategy for tracking a target in a sequence of medical images based on an approach based on the intensity of the deformations of the outer contour of the target, which takes into account the aberrations of the image by applying a weighting to the cost function used in the intensity-based approach based on a voxel confidence measure.
- this intensity-based approach can be combined with a mechanical model of the internal deformations of the target to allow a robust estimation of the position of the outer contour of the target.
- the image sequence is obtained by ultrasound imaging. It is a sequence of three-dimensional images, the elements of which are voxels.
- a first step 101 segmentation of the target is carried out in the initial image of the 3D medical image sequence, also called reference image in the following description, by a segmentation method known per se, which can be manual or automatic.
- a segmentation method known per se which can be manual or automatic.
- a zone (Z) delimiting the segmented contour of the target in the reference image is determined.
- a representation of the inside of the target's contour for example by generating a tetrahedral mesh.
- FIG. 2 An example of a mesh of zone Z is illustrated in FIG. 2. This figure corresponds to an ultrasound image comprising a target partially located in a shaded area, hatched in white.
- the mesh of the zone Z has N c vertices delimiting tetrahedral cells.
- Zone Z has a total of voxels.
- a confidence measurement by voxel in the Z zone of the reference image taken at time t o is then estimated, in a step 103, a confidence measurement by voxel in the Z zone of the reference image taken at time t o , for example according to the method described by Karamalis et al. ("Ultrasonic confidence map using random walks", Medical Image Analysis, 16 (2012) pp. 1101-1112, ed Elsevier). In this paper we measure the confidence of a pixel / voxel of the ultrasound image as the probability that a random walk in this pixel / voxel reaches the transducers of the ultrasound probe. The path is constrained by the model of propagation of an ultrasonic wave in the soft tissues.
- the value of the confidence measure that is assigned to each voxel during step 103 is between 0 and 255.
- low confidence measurement values ⁇ 20 are assigned to the intensity of each voxel located in a shaded part PO of zone Z, such as that shown hatched in FIG.
- FIG. 3 An example of an image of a confidence card U t obtained for zone Z is illustrated in FIG. 3. In this figure, the higher the confidence value of a voxel, the clearer this is.
- a confidence measurement by voxel is calculated in the zone Z of the current image of the sequence, taken at time t, according to the same method as that of step 103. This step is implemented for each new current image.
- step 103 need not be repeated when processing a new current image because the reference image remains unchanged.
- the shaded portions of zone Z are first detected at 103a.
- the step 103a for detecting the shaded portions of zone Z implements a technique known per se, for example described in the document by Pierre Hellier et al, entitled “An automatic geometric and statistical method to detect acoustic shadows in intraoperative ultrasound brain images "in the journal Medical Image Analysis, published by Elsevier, in 2010, vol. 14 (2), pp.195-204.
- This method involves analyzing ultrasound lines to determine positions corresponding to noise and intensity levels below predetermined thresholds.
- the confidence measure is calculated for the vertices of the tetrahedral cells rather than for the voxels. This value can be estimated by averaging the trust of voxels near the top position.
- An advantage of this variant is to be simpler and less computationally, given the fact that the area of the target has fewer vertices than voxels.
- an intensity-based approach is implemented to calculate the displacements of the contour of the target, of minimizing a cost function C expressed as:
- ⁇ q is the vector of the displacements of the vertices of the contour of the target
- H t is a diagonal matrix ( ⁇ , ⁇ ) calculated from the image of the confidence card U t ;
- p (t) is the vector of the positions of voxels at time t; It is a vector representing the intensity of the current image at time t;
- L represents the number of gray levels of the current image and the reference image; is the probability density of I t and is expressed under the
- ⁇ is a scalar parameter representing the minimum value of the confidence measurements
- ⁇ is a parameter that discriminates the values of the weakest confidence measures
- U t is the image of the confidence measurement map obtained in step 103.
- an estimate of the vector ⁇ is calculated iteratively from the formula:
- J is the Jacobian matrix associated with the cost function C, expressing itself in the form is the gradient of the intensity of the current image, which links the displacements of the external vertices ⁇ q to the variation of the intensity I.
- this estimate of the displacement of the vertices of the contour of the target ⁇ q is combined with internal displacements resulting from the simulation of the deformation of a mechanical mass-spring-damper system applied to the target.
- the displacement ⁇ d associated with the mass-spring-damper system is obtained by integrating the forces f exerted on each vertex q, via a semi-implicit Euler one, where f is expressed in the form with N i the number of neighboring vertices. connected to
- vertex q is the speed damping coefficient associated with the vertex q, and end is calculated using the following formulation:
- Ky is a scalar quantity representative of the stiffness of the spring which links the two vertices q
- qj and Dy is a coefficient of amortization.
- the values 3.0 and 0.1 are assigned to Ky and D ij respectively, irrespective of the spring that binds two vertices and the value 2.7 to G, for all the vertices. .
- the importance of the displacements ⁇ q with respect to the displacements ⁇ d in the PO part is minimized, during the estimation of the optimal displacement of the vertices of the contour of the target, by applying them a weighting.
- FIG. 4 an example of a simplified structure of a device 400 for monitoring a clinical target according to the invention is now presented.
- the device 400 implements the method for monitoring a clinical target according to the invention which has just been described with reference to FIG.
- the device 400 comprises a processing unit 410, equipped with a processor ⁇ ⁇ , and driven by a computer program Pg 1 420, stored in a memory 430 and implementing the coding method according to the invention .
- Pg 1 420 are for example loaded into a RAM memory before being executed by the processor of the processing unit 410.
- the processor of the processing unit 110 implements the steps of the method described above, according to the instructions of the computer program 420.
- the device In this exemplary embodiment of the invention, the device
- the 400 comprises at least one unit (U1) for obtaining a segmentation of a contour of the target from the reference image, a unit (U2) for determining an area delimiting the interior of the segmented contour. of the target in the reference image, a unit (U3) for obtaining a confidence measure per image element in said zone determined for the reference image and for the current image, a unit (U4 ) adaptation of the reference image at least from the intensities of the current image and confidence measurements of the current image in the target area and a unit (U5) of deformation of said contour via minimization a cost function based on a difference in intensity between the current image and the reference image in the determined zone, said cost function being weighted by the confidence measurements obtained for the image elements of the zone and taking into account the intensities of the reference image a daptée.
- Table 1 below presents the 4 sequences used for this evaluation.
- the targets of the PHA1 and PHA4 sequences undergo translational movements, that of the PHA2 sequence a rotational movement, while the target of the PHA3 sequence undergoes no movement.
- Table 2 compares the results obtained by implementing the target tracking method according to the invention, measured in the form of a difference, expressed in millimeters, between the estimated position of the 4 targets on the images of the targets. sequences and those established by a panel of expert practitioners with those of other methods, such as the SSD cost function and the SSD cost function weighted by confidence measures.
- the invention is not limited to target tracking in a three-dimensional image sequence, but also applies to a two-dimensional image sequence.
- the picture elements are pixels and the mesh elements of the triangles.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Image Processing (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1560541A FR3043234B1 (fr) | 2015-11-03 | 2015-11-03 | Procede de suivi d'une cible clinique dans des images medicales |
PCT/FR2016/052820 WO2017077224A1 (fr) | 2015-11-03 | 2016-10-28 | Procede de suivi d'une cible clinique dans des images medicales |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3371775A1 true EP3371775A1 (fr) | 2018-09-12 |
Family
ID=55451286
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP16806241.2A Withdrawn EP3371775A1 (fr) | 2015-11-03 | 2016-10-28 | Procede de suivi d'une cible clinique dans des images medicales |
Country Status (4)
Country | Link |
---|---|
US (1) | US20180322639A1 (fr) |
EP (1) | EP3371775A1 (fr) |
FR (1) | FR3043234B1 (fr) |
WO (1) | WO2017077224A1 (fr) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6611615B1 (en) * | 1999-06-25 | 2003-08-26 | University Of Iowa Research Foundation | Method and apparatus for generating consistent image registration |
US7689021B2 (en) * | 2005-08-30 | 2010-03-30 | University Of Maryland, Baltimore | Segmentation of regions in measurements of a body based on a deformable model |
WO2008073962A2 (fr) * | 2006-12-12 | 2008-06-19 | Rutgers, The State University Of New Jersey | Système et procédé de détection et de suivi de particularités dans les images |
DE102010022307A1 (de) * | 2010-06-01 | 2011-12-01 | Siemens Aktiengesellschaft | Verfahren zur Überprüfung der Segmentierung einer Struktur in Bilddaten |
US8619082B1 (en) * | 2012-08-21 | 2013-12-31 | Pelican Imaging Corporation | Systems and methods for parallax detection and correction in images captured using array cameras that contain occlusions using subsets of images to perform depth estimation |
-
2015
- 2015-11-03 FR FR1560541A patent/FR3043234B1/fr active Active
-
2016
- 2016-10-28 US US15/773,403 patent/US20180322639A1/en not_active Abandoned
- 2016-10-28 WO PCT/FR2016/052820 patent/WO2017077224A1/fr active Application Filing
- 2016-10-28 EP EP16806241.2A patent/EP3371775A1/fr not_active Withdrawn
Also Published As
Publication number | Publication date |
---|---|
US20180322639A1 (en) | 2018-11-08 |
FR3043234A1 (fr) | 2017-05-05 |
WO2017077224A1 (fr) | 2017-05-11 |
FR3043234B1 (fr) | 2017-11-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11551361B2 (en) | Method and system of computer-aided detection using multiple images from different views of a region of interest to improve detection accuracy | |
KR101121286B1 (ko) | 센서의 교정을 수행하는 초음파 시스템 및 방법 | |
KR101121353B1 (ko) | 2차원 초음파 영상에 대응하는 2차원 ct 영상을 제공하는 시스템 및 방법 | |
US10004448B2 (en) | Osteoporosis diagnostic support apparatus | |
CN107743638A (zh) | 用于对tof传感器图像进行实时运动伪影处理和去噪的方法和系统 | |
WO2011015952A1 (fr) | Procédé et système de stabilisation d'une série d'images intravasculaires ultrasonores, et extraction de lumière vasculaire dans les images | |
US20150371400A1 (en) | Segmentation and identification of closed-contour features in images using graph theory and quasi-polar transform | |
US9786056B2 (en) | Data display and processing algorithms for 3D imaging systems | |
JP2014516646A (ja) | 散乱媒質の深さ分解した物理的及び/又は光学的特性を決定する方法 | |
FR2936889A1 (fr) | Procede pour le recalage d'un ensemble de points dans des images | |
WO2010097534A1 (fr) | Méthodes de segmentation d'images et de détection de structures particulières | |
Kolluru et al. | Voxel-based plaque classification in coronary intravascular optical coherence tomography images using decision trees | |
EP2353144A2 (fr) | Procédé de traitement d'image pour estimer une déformation d'un cerveau d'un patient | |
Wen et al. | A novel Bayesian-based nonlocal reconstruction method for freehand 3D ultrasound imaging | |
Yan et al. | A novel segmentation approach for intravascular ultrasound images | |
FR3002732A1 (fr) | Procede automatique de determination predictive de la position de la peau | |
US10580138B2 (en) | Edge detection on images with correlated noise | |
EP3475916A1 (fr) | Segmentation d'os et de plaque dure en tomodensitométrie spectrale | |
CN102651130B (zh) | 水平集图像处理方法 | |
FR2965651A1 (fr) | Reconstruction tomographique d'un objet en mouvement | |
JP7497390B2 (ja) | 血管内機器の検出及び圧着測定のためのシステム及び方法 | |
EP3371775A1 (fr) | Procede de suivi d'une cible clinique dans des images medicales | |
WO2018104609A1 (fr) | Procede de suivi de cible dans une sequence d'images medicales, dispositif, equipement terminal et programmes d'ordinateurs associes | |
JP2020010734A (ja) | 検査支援装置、方法およびプログラム | |
CN112184576B (zh) | 一种光谱域光学相干层析成像中的高反射亮斑增强方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20180525 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: KRUPA, ALEXANDRE Inventor name: MARCHAL, MAUD Inventor name: ROYER, LUCAS |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: B COM |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
INTG | Intention to grant announced |
Effective date: 20190412 |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: MARCHAL, MAUD Inventor name: KRUPA, ALEXANDRE Inventor name: ROYER, LUCAS |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 20190823 |