Method for automatically segmenting an organ on a three-dimensional medical image

Abstract

The invention relates to a method for segmenting a three-dimensional image of at least one organ of a patient, comprising at least the steps of: extracting from the three-dimensional image of the organ a probability map which assigns to each voxel of the image a probability of belonging to a contour of the organ on the image; extracting from the probability map at least one target point based on the probability of belonging to the contour of the organ on the image, each target point being extracted from the probability map by applying to the probability map at least one threshold for the probability of belonging to the contour of the organ on the image; and based on each target point extracted in the preceding step, deforming a deformable model of this organ in order to obtain the three-dimensional segmentation of the organ on the image.

Description

[0001]Method for automatic segmentation of an organ on a three-dimensional medical image The present invention relates to the field of medical imaging for purposes, for example, of diagnosis, such as disease screening, for purposes, for example, of treatment, such as guiding surgical instruments, etc. The invention relates more particularly to organ segmentation on three-dimensional medical images, i.e. determining the outline of the organ in such an image. BACKGROUND OF THE INVENTION Several technologies exist for obtaining three-dimensional images of a patient's organ. One of the most widely used is ultrasound, which allows images to be obtained quickly, possibly intraoperatively, using relatively inexpensive equipment compared to other technologies such as magnetic resonance imaging or MRI.Once the image is obtained, it may be useful for the practitioner to identify the outline of the organ to be analyzed. This is particularly the case if the outline of the organ is subsequently required to plan an operation, or to merge different images together. This outline identification operation can be performed manually, with tools allowing the outline of the organ to be drawn directly on the image. However, this is time-consuming, tedious, and fails to meet two essential needs: high accuracy and reproducibility. Image segmentation algorithms are known that exploit image properties such as intensity discontinuities in the image (Edge-Based Segmentation method based on gradients) or similarities between image elements (pixels for two-dimensional images, voxels for three-dimensional images; Region-Based Segmentation method).However, these algorithms are rarely effective on the entire contour of the organ present in the image. Thus, in the case of prostate ultrasound, it is difficult to distinguish the contour of the organ from the surrounding tissues, in particular for the lower part of the prostate, mainly due to the low contrast between the prostatic and non-prostatic areas, the granularity of the ultrasound images which may present speckles and / or shimmers and the short range of gray levels available. OBJECT OF THE INVENTION The invention aims in particular to improve the segmentation of medical images.SUMMARY OF THE INVENTION To this end, the invention provides a method for segmenting a three-dimensional image of at least one organ of a patient comprising at least the steps of: - extracting from the three-dimensional image of said organ, a probability map which assigns to each voxel of the image a probability of belonging to a contour of the organ on the image; - extracting from said probability map, at least one target point based on said probability of belonging to the contour of the organ on the image, each target point being extracted from the probability map by applying to the probability map at least one probability threshold of belonging to the contour of the organ on the image; - from each target point extracted in the previous step, deforming a deformable model of this organ to obtain the three-dimensional segmentation of said organ on the image.The model is said to be deformable in that it can be applied to an image and deformed from at least one target point to correspond at every point to the contour of the organ sought in the image. We thus begin by first searching for at least one target point whose membership in the contour of the organ present in the image has a probability considered sufficient and the deformable model is applied to the image from this target point. Thus, the target points whose membership in the contour is most probable are considered exact and the definition of the contour is completed from the anatomical data of the deformable model.The least probable points are therefore not taken into account when applying the deformable model because this could introduce an error into the segmentation, by deforming the deformable model from target points whose probability of belonging to the contour of the organ would be too low, and therefore for which the risk that these points would not truly belong to the contour of the organ would be too high. This combination significantly improves the segmentation carried out, and this is all the more so when the number of target points retained by the method is high. In particular, with the invention, only the highest probability values ​​are retained to determine the target points. Thus, with the invention, the most doubtful areas of belonging to the organ are removed from the probability map instead of trying to adjust them. The probability map is in three dimensions.The probability map is not only defined by two unique values, one of which would represent the belonging to the organ contour and the other would represent the absence of belonging to the organ contour. Usually, more than a single target point is extracted from the probability map. Usually, a cloud of target points is thus extracted from the probability map. We therefore understand that the threshold makes it possible to discard all the voxels of the image for which the probability of belonging to the organ contour is too low. Optionally, the probability map is extracted via a model distinct from the deformable model. Optionally, the distinct model is defined by a segmentation method that is at least partly automatic. Optionally, this distinct model is defined by at least one artificial intelligence (or a neural network) trained from segmented images of the organ of at least other people.Optionally, the at least one threshold is global. Optionally, the at least one threshold is local. Optionally, the at least one threshold has a value independent of the organ and / or the patient and / or the three-dimensional image and / or the probability map. Optionally, the at least one threshold has a value dependent on the organ and / or the patient and / or the three-dimensional image and / or the probability map. Optionally, the at least one threshold is dynamic. Optionally, the at least one dynamic threshold is a local threshold allowing only local probability maxima of the probability map to be selected. Optionally, the value of the at least one threshold can be modulated manually.Optionally, the probability map is extracted using a model distinct from the deformable model, and in which the value of said at least one threshold can be automatically modulated if at least one characteristic of the three-dimensional image considered differs from those of the images from which the distinct model was designed. Optionally, the deformable model is a statistical shape model of the organ to be segmented. A statistical shape model is a model which, as its name indicates, is defined from different shapes of the organ considered according to the frequency of these shapes in the population. Optionally, the deformable model has an initial shape defined from the average of the shapes of the same organ considered but of other patients than the targeted patient. Optionally, the initial shape of the deformable model is determined by an imaging technology other than ultrasound.Optionally, the deformable model has an initial shape combined with a segmentation of the same organ considered in the same patient, segmentation obtained from an image acquired prior to an acquisition of the image currently being segmented. Optionally, the segmentation obtained during a previous examination is determined by an imaging technology other than ultrasound. Optionally, at least one target point can be manually added to said at least one target point extracted from the probability map. Optionally, if the number of target points is lower than a predetermined threshold, the process is interrupted. Optionally, in the event of interruption, the probability map is abandoned and the deformable model is deformed from manually added target points. Optionally, the deformable model is first pre-deformed.Optionally, the deformable model is pre-deformed by being globally pre-aligned to the target points. Optionally, the deformable model is deformed based on only a portion of the target points used in the pre-deformation step. Optionally: - from each target point extracted from the probability map, the deformable model is pre-deformed, - then only a portion of the target points extracted from the probability map is selected to form a subgroup of target points having a higher probability of belonging to the contour of the organ on the image than the target points not being part of the subgroup, - from each target point of the subgroup, the deformable model is deformed. Optionally, the deformation of the deformable model is performed by an iterative approach. Optionally, at each iteration, each target point is paired with the closest point of the deformable model.Optionally, at each iteration, the deformed model is first deformed globally via an affine transformation (and / or scaled) and then deformed locally. Optionally, the deformation of the deformable model is performed iteratively by alternating at least one scaling phase with an elastic deformation phase. Optionally, during the scaling phase, a global deformation is also performed, and in which at each iteration, an elastic deformation field resulting from the elastic deformation is decomposed into an affine component and a non-linear residual deformation, the affine component being used for the global deformation during the following iteration. Optionally, the iterations are stopped when the distances between the target points and corresponding points of the deformable model are less than a predetermined threshold. Optionally, the quality of the segmentation obtained is estimated.Optionally, the quality of the segmentation obtained is estimated by evaluating a spatial correlation between the probability map and said segmentation. The invention also relates to an installation comprising at least one image-taking apparatus and means for segmenting at least one image acquired by said apparatus according to the method as mentioned above. The invention also relates to a computer program comprising instructions which cause an installation as mentioned above to execute the method as mentioned above. The invention also relates to a computer-readable recording medium, on which the computer program as mentioned above is recorded. Other characteristics and advantages of the invention will become apparent upon reading the following description of particular and non-limiting implementations of the invention. BRIEF DESCRIPTION OF THE DRAWINGS Reference will be made to the appended drawings, among which: [Fig.1] Figure 1 is a flowchart of a first embodiment of the method of the invention; [Fig. 2] Figure 2 is a flowchart of a second embodiment of the method of the invention; [Fig. 3] Figure 3 is a view of an ultrasound image of a prostate, on which target points are searched; [Fig. 4] Figure 4 is a view of the same ultrasound image on which target points have been selected; [Fig. 5] Figure 5 is a view of the same ultrasound image on which a contour has been traced; [Fig. 6] Figure 6 is a schematic view of an ultrasound apparatus for implementing the method of the invention. DETAILED DESCRIPTION OF THE INVENTION The invention is described here in application to the segmentation of an ultrasound image of a patient's prostate.The invention is however applicable to the image of any organ and / or any patient (animal or human) and / or to any technology for acquiring an image of such an organ. The invention is a method for segmenting a three-dimensional image. In the figures, for reasons of simplicity, the images represented are two-dimensional images. With reference to figures 1 and 2, in the two implementations described here, the segmentation method is based on an Anatomical Model ^^ and an Artificial Intelligence Model ^^^. The Anatomical Model ^^ is developed from at least one image bank ^^. ^including ^ images of the prostate. The ^ images are optionally images acquired with a different technology than that used for the acquisition of the images which will have to be segmented subsequently and for example by MRI technology. Each image ^ is then segmented. The segmentation is for example carried out manually during human segmentation ^^ ^. Optionally, this segmentation is carried out by a practitioner or another qualified person. Then these segmentations are then processed by computer (C) to calculate an average of said segmentations (denoted average shape ^^ hereinafter) and to deduce the Anatomical Model ^^. The Anatomical Model ^^ is a statistical model of deformable shape which is thus obtained by a statistical study of an average shape of the prostate and its variations. It should be noted that the design of an anatomical model is known in itself and will not be further described here. The Artificial Intelligence Model ^^^ is developed from at least one image bank ^^ ^ including K images of the prostate. The image bank ^^ ^ is optionally different from the image bank ^^ ^ used to create the Anatomical Model ^^. Each image ^ is then segmented. Segmentation is for example carried out manually during human segmentation ^^^ . Optionally, this segmentation is carried out by a practitioner or another qualified person. Preferably, the development of the Artificial Intelligence Model ^^^ is carried out from segmented images whose imaging modality corresponds to that of the images that we wish to segment subsequently. Thus, the ^ images here are images captured with the same technology as that used for the acquisition of the images that will have to be segmented subsequently, here ultrasound. These segmentations resulting from ^^ ^train an artificial intelligence ^^ to train it to estimate for each voxel of a given image the probability that this voxel belongs to the contour of the prostate present on said image. We thus obtain the artificial intelligence model ^^^. It will be noted that the design and training of an artificial intelligence to obtain an artificial intelligence model are known in themselves and will not be described further here. For this purpose, the artificial intelligence model can be obtained by means of automatic learning (or "machine learning" in English) and for example can be obtained by means of a neural network and for example by means of deep learning (or "deep learning" in English). First implementation To segment an image of the prostate of a patient by means of the method according to the first mode of implementation represented in figure 1,it is necessary to acquire an image ^^ of the patient's prostate, transmit the image ^^ to a computer system applying the Artificial Intelligence Model ^^^ on the image ^^ received as input. It will be understood that the neural network can be implemented on the same computer system or on a different system. We thus obtain at output a prediction, in the form of a probability map ^^ in three dimensions in which to each voxel of position ^, ^, ^ in the image, is assigned a probability ^(^, ^, ^) of belonging to the contour of the prostate present in the image ^^. The probability map ^^ is thus a three-dimensional image. Advantageously,the membership probability has a value V which is between two limits of a closed interval (for example between 0 and 1 or between 0 and 100). The probability map ^^ is thus precise because it is not only defined by binary values ​​0 or 1 but by a range of values ​​V all between two limits of a closed interval. This probability map ^^ can optionally be presented to an operator. Optionally, the membership probability can be symbolized by a color code to simplify the operator's understanding. For example,the higher the probability of belonging to the prostate, the warmer and closer its color is, and the lower the probability of belonging to the prostate, the colder the color. A zero probability of belonging to the prostate is thus symbolized by giving the associated voxel the color black, and a certain probability of belonging to the prostate is thus symbolized by giving the associated voxel the color red. Given that some voxels in the probability map ^^ may have a zero probability of belonging to the prostate (in particular voxels internal to the prostate, it being recalled here that all voxels in the image ^^ are concerned by the first segmentation step), this may lead to the fact that the probability map ^^ may not have entirely closed contours. After having defined a global threshold ^ of probability of belonging (this global threshold ^ being predefined),corresponding to an acceptable membership probability, the computer system executes a voxel filtering algorithm of the probability map to select, during a selection operation ^, ^ target points each corresponding to a voxel of position ^, ^, ^ having a probability ^(^, ^, ^) greater than the global threshold ^. The threshold ^ is said to be global because it applies in the same way and with the same value for all voxels. Optionally, the threshold ^ is fixed, unlike a dynamic threshold whose value would be adapted to the probability map CP and / or to the image considered IP. This threshold ^ thus makes it possible to discard all voxels for which the probability of belonging to the contour is too low. Consequently, the value of the threshold ^ is fixed for the intended application and the Artificial Intelligence Model ^^^ used at an optimized value. Preferably,the value of the threshold ^ will be modified according to the intended application and the Artificial Intelligence Model ^^^ used in order to set it to a new optimized value. The value of the threshold ^ may in particular be determined by a compromise between the desired precision and sensitivity of the model, established via the analysis of sensitivity-precision curves or ROC curves. The selection operation ^ is thus a filtering operation on the probability map ^^. In this way, only target points with a very high probability of belonging to the contour of the prostate in the image ^^ are retained. We therefore understand that the target points are in three dimensions. We also understand that at the end of the selection operation ^, we obtain a cloud of target points. Depending on the image ^^, the number of target points thus extracted can be high. Therefore, at the end of the selection operation ^,some target point groups can already locally draw contours of a prostate (in the form of at least one continuous surface and / or at least one discontinuous surface formed by points). However, given that other voxels of the probability map ^^ have been discarded (because their probability ^(^, ^, ^) of belonging to the prostate in the image ^^ was too low and therefore lower than the threshold ^), these contours are necessarily partial. In no case, at the end of the selection operation ^, do we obtain a representation of a prostate whose contours would be entirely closed. During a deformation operation ^, we apply the Anatomical Model ^^ to the image ^^ by deforming the Anatomical Model ^^ from the ^ target points retained at the end of the operation ^. We understand that the anatomical model ^^ thus makes it possible to determine the contour of the prostate on the image to be segmented based on the ^ target points. For example,the Anatomical Model ^^ draws one or more continuous surfaces between neighboring target points (by interpolating and / or connecting them) and completes said surfaces to draw a closed contour of the prostate using the anatomical information it contains. The Anatomical Model ^^ only deforms from the target points. The Anatomical Model ^^ thus makes it possible to close the partial contour(s) that were defined by the target point cloud. The deformation operation ^ can therefore be seen as a transformation step of the Anatomical Model ^^ on the target point cloud previously established. The deformation of the Anatomical Model ^^ can be carried out in a single phase or several phases. For example, the deformation of the Anatomical Model ^^ can be carried out by iteration. For example, at each iteration i: - each target point is paired with the closest point of the Anatomical Model ^^,- then the Anatomical Model ^^ is scaled (by scaling we mean that the Anatomical Model ^^ is enlarged or shrunk in its entirety to better correspond to the target points - this scaling being particularly interesting for a patient whose organ considered is of dimensions much larger or smaller than the average and therefore for whom the organ considered is of dimensions much larger or smaller than the Anatomical Model ^^) and deformed globally via an affine transformation based on the distance between each target point considered and the point of the Anatomical Model ^^ which is paired with it (for example the transformation is determined so as to minimize the sum of said distances and / or for example the transformation is calculated with the Arun algorithm), - then the Anatomical Model ^^ is elastically deformed,under the action of external forces deforming the Anatomical Model ^^ towards the target points and internal forces ensuring the regularity of the surface of the Anatomical Model ^^ (elastic deformation being well known in the prior art, it will not be detailed further, it being understood that the external forces are obtained based on the distance between each target point considered and the point of the Anatomical Model ^^ which is paired with it and the internal forces are obtained based on the Anatomical Model ^^ before deformation and / or on a constraint of having a smooth deformed contour, the deformation being based on the sum of these external and internal forces to deduce a displacement of each of the vertices of the Anatomical Model ^^). The iterations i are stopped when the distances between the target points and the corresponding paired points of the Anatomical Model ^^ are, for all the target points,lower than a predetermined threshold. This successively affine then elastic iterative approach allows the elastic deformations to progressively correct the errors of the previous affine transformation, and vice versa. We thus carry out an extrapolation of the contour from the Anatomical Model ^^. This iterative approach is particularly interesting in places where the Anatomical Model ^^ is very far from a target point or a group of target points and / or in places where there are few target points. This iterative approach makes it possible to generate a very good quality extrapolation of the contour from the Anatomical Model ^^ even in places where the Anatomical Model ^^ is very far from a target point or a group of target points and / or in places where there are few target points. We then obtain the segmentation ^, ^^of the image ^^. Preferably, the deformation operation ^ takes into account at least one mesh consistency constraint during the deformation of the Anatomical Model ^^: prevent the creation of a fold in the mesh, apply an elastic deformation constraint or fluid mechanics optionally according to a biomechanical model of the organ during the propagation of the deformation, … Optionally, at each iteration i and via the Arun algorithm, an affine transformation is extracted during the elastic deformation of the Anatomical Model ^^. For example, the elastic deformation field used during the elastic deformation is decomposed using the Arun algorithm into an affine component and a non-linear residual deformation. It is then possible to use this affine component to scale said model during the following iteration i+1.This allows for a consistent global deformation during the i+1 iteration even in areas not covered by target points. Optionally, at least one of the internal forces is defined from at least one statistical study on the shape of the prostate (study identical or different from that which allowed the creation of the Anatomical Model ^^). An internal force thus makes it possible to further limit the risk of obtaining a segmentation ^. ^^anatomically improbable. It is understood that even if the Anatomical Model ^^ is deformed from ^ target points, the Anatomical Model ^^ may only pass through a portion of the n target points. It is possible to refine the selection of target points by using a double filtering algorithm. Such double filtering is explained in relation to the second mode of implementation below but can also be used with the first mode of implementation. Figure 6 shows an example of a device that can be used for examining a patient in the context of the method of the invention. It is an ultrasound device 10 comprising a housing 11 containing a computer system 12 connected to an ultrasound probe 13, a screen 14 and to a computer network R. The computer system 12 is a computer that comprises at least one processor and a memory.The memory here comprises the models ^^^ and ^^ and a computer program having instructions arranged to implement the method of the invention. Optionally, the computer program has instructions arranged to implement the neural network itself implementing the artificial intelligence model ^^^. The ultrasound probe 13 allows the acquisition of the images ^^ which will be processed by the computer system 12 and displayed on the screen 14. The network R is used for connection to a server containing, for example, reports, images of examinations of patients for which the practitioner or the organization in which he practices is responsible, etc. Second implementation In the second mode of implementation shown in Figure 2, we have the Artificial Intelligence Model ^^^ and the Anatomical Model ^^. We also have an old segmentation ^. ^^ ^^^of the patient's prostate that is being examined (by old, we mean that it was performed during a previous examination). In a combination operation ^^^^, the Anatomical Model ^^ is combined with the old segmentation ^ ^^ ^^^ , for example by replacing the average form ^^ contained in the ^^ by this segmentation ^ ^^ ^^^ . Of course, other combination possibilities are possible: for example, performing an average of MS and this segmentation ^ ^^ ^^^ or even a weighted average of the average form ^^ and of this segmentation ^ ^^^ ^ ^ . We thus obtain a combined Anatomical Model ^^′. We note that the old segmentation ^ ^^ ^^^perhaps from an ultrasound image or obtained via another technology such as an MRI image. As before, we start by acquiring an image ^^ of the patient's prostate. As before, the image ^^ is transmitted to a computer system in order to apply the artificial intelligence model to the image ^^ received as input. This makes it possible to obtain a prediction as output in the form of a three-dimensional probability map ^^ in which each voxel of position ^, ^, ^ in the image is assigned a probability ^(^, ^, ^) of belonging to the contour of the prostate. The probability map ^^ is thus a three-dimensional image. Advantageously, the probability of belonging has a value V which is between two limits of an interval,the two limits being included (for example between 0 and 1 or between 0 and 100). The probability map ^^ is thus precise because it is not only defined by binary values ​​0 or 1 but by a range of values ​​V all included between two limits of an interval, the two limits being included. This probability map ^^ can optionally be presented to an operator. Optionally, the membership probability can be symbolized by a color code to simplify the operator's understanding. For example,the higher the probability of belonging to the prostate, the warmer and closer its color is, and the lower the probability of belonging to the prostate, the colder the color. A zero probability of belonging to the prostate is thus symbolized by giving the associated voxel the color black, and a certain probability of belonging to the prostate is thus symbolized by giving the associated voxel the color red. Given that some voxels in the probability map ^^ may have a zero probability of belonging to the prostate (in particular voxels internal to the prostate, it being recalled here that all voxels in the image ^^ are concerned by the first segmentation step), this may result in the probability map ^^ not having entirely closed contours. The computer system then executes a filtering algorithm for the voxels in the probability map to select, during a selection operation ^′,^ target points for which a high degree of certainty of belonging to the contour has been assigned (i.e. the probability ^(^, ^, ^) is high). For example, as for the first implementation, after having defined a fixed global threshold ^ of probability of belonging (this global threshold ^ being predefined), corresponding to an acceptable probability of belonging, the computer system executes an algorithm for filtering the voxels of the probability map to select, during a selection operation ^, ^ target points each corresponding to a voxel of position ^, ^, ^ having a probability ^(^, ^, ^) greater than the fixed global threshold ^. The inventors were able to observe that the difficulty of the segmentation task varies greatly from one image to another. This is why the use of a single fixed global threshold generally has the effect of over-segmenting or under-segmenting the contour of the organs. For this reason,the filtering algorithm preferably performs a second filtering of the filtered voxels, with a second threshold different from the first. As already indicated, the second filtering is also applicable to the first implementation, so that the following is indeed applicable to the first implementation. The second threshold is a dynamic threshold i.e. a threshold specific to the image considered. The second threshold is optionally local, i.e. it is applied to only a part of the CP probability map considered or its value depends on the area of ​​the CP probability map on which it is applied, unlike a global threshold which has the same value on the entire CP probability map. For example, as the anterior part of the prostate is more difficult to segment than the posterior part of the prostate,the second threshold may have a lower value when applied in the area of ​​the anterior part of the prostate than in the area of ​​the posterior part of the prostate. The value of the second threshold is therefore adapted automatically (to each new probability map processed) and locally according to the considered area(s) of a given probability map ^^. Depending on the application considered, this thresholding can exploit the gradient of the prediction to reject areas where the estimated contour is too diffuse or wide for the segmented area to be considered anatomically correct. During this second filtering step (part of the selection operation ^′), we will search for a reduced number of contour points, for example associated with local maxima of probability of presence of the contour of the organ in these positions (figure 3 illustrates these local maxima). In practice,The program executed by the computer system proceeds as follows. A decomposition # of the image ^^ associated with the probability map ^^ is carried out into boxes (also called boxes) and for example into boxes of identical dimensions and for example into rectangular parallelepipeds or cubes. Optionally, each box has dimensions $^, $^, $^ with a resolution of $^ = $^ = $^ and for example $^ = $^ = $^ = & with α between 3 and 6 millimeters and for example between 5 and 5.5 millimeters. We say that the probability map considered has a local maximum in a given voxel '^(^ when there exists a neighborhood of '^(^ such that for any voxel in this neighborhood, the associated probability is less than or equal to that of '^(^. For a box, we thus select the voxel of maximum probability '^(^ within said box,to finally extract it as a target point. This process is repeated for a new box to extract a new target point, etc. This process is stopped as soon as we obtain ^ target points. The number ^ (for example 100) is the number of target points that will be used to deform the model, this number being predefined. The number ^ is predefined by the manufacturer and / or by the practitioner. Preferably, it is possible to consider that we have an insufficient number of target points, for example if the number of target points retained at the end of this second filtering is lower than a minimum threshold predefined (for example by the manufacturer and / or the practitioner). The segmentation process is then interrupted to propose to the operator to segment the organ without benefiting from the method of the invention. The selection operation ^′ is thus a filtering operation on the probability map ^^. In this way,we retain only target points presenting a very high probability of belonging to the contour of the prostate in the image ^^. We therefore understand that the target points are in three dimensions. We also understand that at the end of the selection operation ^′, we obtain a cloud of target points. Depending on the image ^^, the number of target points thus extracted can be high. Therefore, at the end of the selection operation ^′, certain groupings of target points can already locally draw contours of a prostate (in the form of at least one continuous surface and / or at least one discontinuous surface formed by points). However, given that other voxels of the probability map ^^ were discarded (because their probability ^(^, ^, ^) of belonging to the prostate in the image ^^ was too low and therefore lower than the threshold ^), these contours are necessarily partial. In no case, at the end of the selection operation T′,we obtain a representation of a prostate whose contours would be entirely closed. Considering that we have obtained a sufficient number of target points (for example that ^ points have been obtained), the program begins the deformation operation ^' during which we apply the Combined Anatomical Model ^^^^ to the image ^^ by deforming Combined Anatomical Model ^^^^ from the ^ target points retained at the end of the operation ^′. We understand that the combined anatomical model thus makes it possible to determine the contour of the prostate from the ^ target points. For example,The Combined Anatomical Model ^^^^ draws one or more continuous surfaces between neighboring target points (by interpolating and / or connecting them) and completes said surfaces to draw a closed contour of the prostate using the anatomical information it contains. The Combined Anatomical Model ^^^^ only deforms from the target points. The Combined Anatomical Model ^^^^ thus allows the partial contour(s) that were defined by the target point cloud to be closed. The deformation operation ^′ can therefore be seen as a transformation step of the Combined Anatomical Model ^^^^ on the target point cloud. The deformation of the Combined Anatomical Model ^^^^ can be performed in a single phase or several phases. For example, the deformation of the Combined Anatomical Model ^^^^ can be performed by iteration. For example,at each iteration i: - each target point is paired with the closest combined Anatomical Model point ^^^^ e,- then the Combined Anatomical Model ^^^^ is scaled (by scaling we mean that the Combined Anatomical Model ^^^^ is enlarged or shrunk in its entirety to better correspond to the target points – this scaling being particularly interesting for a patient whose organ considered is of dimensions much larger or smaller than the average and therefore for whom the organ considered is of dimensions much larger or smaller than the Combined Anatomical Model ^^^^) and deformed globally via an affine transformation based on the distance between each target point considered and the point of the Combined Anatomical Model ^^^^ which is paired with it (for example the transformation is determined so as to minimize the sum of said distances and / or for example the transformation is calculated with the Arun algorithm), - then the Combined Anatomical Model ^^^^ is elastically deformed,under the action of external forces deforming the Combined Anatomical Model ^^^^ towards the target points and internal forces ensuring the regularity of the surface of the Combined Anatomical Model ^^^^ (elastic deformation being well known in the prior art, it will not be detailed further, it being understood that the external forces are obtained based on the distance between each target point considered and the point of the Combined Anatomical Model ^^^^ which is paired with it and the internal forces are obtained based on the Combined Anatomical Model ^^^^ before deformation and / or on a constraint of having a smooth deformed contour,the deformation based on the sum of these external and internal forces to deduce a displacement of each of the vertices of the Combined Anatomical Model ^^^^). The iterations i are stopped when the distances between the target points and the corresponding paired points of the Combined Anatomical Model ^^^^ are (for at least some of the target points and preferably for all the target points) less than a predetermined threshold. This successively affine then elastic iterative approach allows the elastic deformations to progressively correct the errors of the previous affine transformation,and vice versa. This way, we extrapolate the contour from the Combined Anatomical Model ^^^^. This iterative approach is particularly useful in places where the Combined Anatomical Model ^^^^ is very far from a target point or a group of target points and / or in places where there are few target points. This iterative approach allows us to generate a very high-quality contour extrapolation from the Combined Anatomical Model ^^^^ even in places where the Combined Anatomical Model ^^^^ is very far from a target point or a group of target points and / or in places where there are few target points. This iterative approach is particularly useful in places where the Combined Anatomical Model ^^^^ is very far from a target point or a group of target points. Indeed,the combined Anatomical Model ^^^^ ^^ is thus deformed by iteration and in a localized manner to reach this or these target points and / or the area comprising this or these target points. This localized deformation is preferably of the same order of magnitude as the localized deformation carried out at the locations where the combined Anatomical Model ^^^^ is close to a target point or a group of target points and is deformed in view of this target point or these target points. We then obtain the segmentation ^, ^^' of the image ^^. Preferably, the deformation operation ^ takes into account at least one mesh consistency constraint when deforming the combined Anatomical Model ^^^^: prevent the creation of a fold in the mesh, apply an elastic deformation or liquid mechanics constraint during the propagation of the deformation, … Optionally, at each iteration i and via the Arun algorithm, an affine scaling transformation is extracted during the elastic deformation of the Anatomical Model ^^ . For example, the elastic deformation field used during the elastic deformation is decomposed using the Arun algorithm into an affine component and a non-linear residual deformation. It is then possible to use this affine component to scale said model during the following iteration i+1.This allows for a consistent global deformation during the i+1 iteration even in areas not covered by target points. Optionally, at least one of the internal forces is defined from at least one statistical study on the shape of the prostate (study identical or different from that which allowed the creation of the Anatomical Model ^^). An internal force thus makes it possible to further limit the risk of obtaining a segmentation ^. ^^ ' anatomically improbable. In Figure 5, the segmentation is shown ^ ^^ ' obtained using the combined Anatomical Model ^^^^ and segmentation ^ ^^ which would have been obtained using only the Anatomical Model ^^. Optionally, the computer program preferably performs an automatic comparison of the segmentation ^ ^^ (in the case of the first implementation), or segmentation ^ ^^' (in the case of the second implementation), with the old segmentation ^ ^^ ^^^. Such a comparison (for example using the Dice coefficient or the volumetric difference) makes it possible to warn the practitioner when the two segmentations of the same organ are not consistent with each other. For both implementations, it can be provided that the program allows modulation of the influence of the prediction from the artificial intelligence model in the deformation of the anatomical model by varying the selectivity of the filtering process described above. Using a cursor, a box with a value to be completed (for example by a percentage) or a check box displayed on the screen 14, the practitioner can adjust, in the segmentation obtained, the share of information predicted by the neural network and that completed by the anatomical model. If desired, the practitioner can therefore use only the deformable anatomical model.In a clinical routine, the practitioner can accept or reject the segmentation automatically proposed by the method of the invention regardless of the implementation considered. The computer program thus gives the practitioner the possibility of modifying the segmentation proposed by the method by: - ​​adding target points manually regardless of the number of target points selected by the method of the invention; - deleting target points selected by the method of the invention. Then, the anatomical model is then deformed towards these target points. A method has thus been described for segmenting a three-dimensional image. The segmentation of the image makes it possible to obtain an outline which can be used to carry out, for example, image fusion or to plan an operating procedure.Of course, the invention is not limited to the embodiments described but encompasses any variant falling within the scope of the invention as defined by the claims. In particular, it is possible to combine the two implementation modes in whole or in part. For example, it is possible to introduce into the first implementation mode double threshold filtering and / or the use of an old segmentation and / or the algorithm described comprising the steps of decomposing the probability map into boxes and searching for a '^(^ for at least one of the boxes. Whatever the implementation considered, the filtering may be global or local. Whatever the implementation considered, the filtering may be fixed or dynamic.If the filtering is dynamic, the filtering can be adapted so that for at least a first zone of the probability map, the threshold value depends on the value of at least one threshold of at least a second zone of the probability map neighboring or adjacent to the first. We can have dynamic and global filtering and / or fixed and local filtering and / or fixed and global filtering and / or a dynamic and local threshold. The examination device can be different from that described by the technology used (MRI instead of ultrasound for example) or by the arrangement and / or the choice of its components. The value of at least one threshold could be manually adjustable for example by the practitioner. The segmentation process can be based on a model other than the ^^^ to establish the probability map.For example, instead of ^^^, the method may rely on a segmentation method that is at least partly automatic other than that based on the ^^^ model and for example any segmentation method that is at least partly automatic capable of generating localized information on the reliability of its result. In general, each of the steps of the method of the invention may be automatic or only partly automatic. Although here the statistical shape model has an average shape that is the average of the shapes of the same organ in a set of patients not including the patient in question, the statistical shape model may have an average shape that is the average of the shapes of the same organ in a set of patients including the patient in question. Similarly, the artificial intelligence may be trained from images of the same organ in a set of patients including or not including the patient in question.The model ^^ and / or the model ^^^ and / or the three-dimensional image to be segmented can be designed using statistical processing of segmented images whose imaging modality differs from that of ultrasound and for example by MRI technology (T1 sequence and / or T2 sequence and / or DC sequence and / or ADC sequence etc.), by scanner technology (such as PET Scan) …, Although here each image ^ and / or each image ^ is segmented manually during the pre-intervention phase, this segmentation can be carried out differently. For example for at least one image ^ and / or at least one image ^, the segmentation can be automatic or partly automatic (for example the segmentation is carried out automatically and controlled and retouched by a human afterwards).Although here the image bank used to create the Artificial Intelligence Model is different from the Anatomical Model, the Artificial Intelligence Model may be established from at least one image bank used to create the Anatomical Model. The ^ images may be images captured with a different technology than that used for acquiring the images that will subsequently be segmented, such as MRI technology. The ^ images may be images captured with the same technology as that used for acquiring the images that will subsequently be segmented. In a preliminary step, the practitioner may manually place target points on the outline of the organ present in the image displayed on the screen 14 to initialize the placement of the anatomical model and the evolution of its nearest neighbors toward these indicated points. This initialization may be automated.Preferably, the target points used to initialize the placement of the deformable model will be different from those used by the present invention to deform the deformable model. The deformable model may have an initial shape defined by the shape of several organs (for example the average of said shapes) and / or by the shape of a single organ (and for example that of the patient obtained during a previous examination) and / or by an analytical shape (for example drawn by a practitioner or any other expert) and / or a combination of said aforementioned shapes. In the case where the deformable model is linked to shapes of several organs, we will therefore speak of a “statistical deformable shape model”. The shape of the patient’s organ may be included or excluded to define the deformable model. We may also include only the patient’s organ (whose shape varies from one image to another for example) to create the “statistical deformable shape model”.For the two implementation modes described above, the method may include one or more additional steps. For example, the method may include an additional step of pre-deformation of the anatomical model followed by the actual deformation step described above. For example, during the pre-deformation step, the anatomical model may be roughly deformed to quickly obtain a first deformation. The pre-deformation step is thus robust. Then, during the actual deformation, the anatomical model will continue to be deformed more precisely as proposed above. Optionally, a first group of target points is thus extracted from the probability map by applying to the probability map at least a first probability threshold of belonging to the outline of the organ on the image.This first threshold is then relatively non-selective in order to create a first group containing a large number of target points. The anatomical model is then pre-deformed using these target points. For example, the anatomical model is deformed so as to align with the different target points of the first group, each target point being paired with the closest point of the anatomical model. This alignment is for example carried out using the Arun algorithm. Then, a second group of target points is extracted from the first group of target points by applying at least a second threshold of probability of belonging to the contour of the organ on the image to the first group. This first threshold is more selective than the first threshold. This second threshold is thus defined so as to retain the points having a high probability of belonging to the contour.We then find ourselves in the configuration described with regard to the two embodiments and we can then proceed to the deformation step itself which was described previously (with regard to the two embodiments) based on this second group of target points. This deformation is thus more local and precise. For example, the method includes an additional step of automatic estimation of the quality of the segmentation obtained. For example, such a step could make it possible to provide an indicator of reliability of the result obtained to the operator and for example a quality score Q. For example, when Q is below a first predetermined threshold, the segmentation obtained ^. ^^ or ^ ^^′ is automatically discarded and / or when Q is between this first predetermined threshold and a second predetermined threshold, the operator is automatically warned that the quality of the segmentation obtained is doubtful. For example Q is calculated by evaluating the spatial correlation between the probability map CP and the segmentation obtained ^ ^^ or ^ ^^ ′. For example, an automatic estimation of the quality of the segmentation ^ ^^ or ^ ^^ ′ is performed by calculating a quality score Q such that: Q=Q0+α×r with - r the Pearson correlation coefficient, and - Q0 and α estimated by a linear regression model, where the explained variable is the Dice coefficient between the segmentation ^ ^^ or ^ ^^′ and a manually obtained segmentation, and the explanatory variable is this correlation r. The Pearson correlation coefficient r is optionally calculated between the probability map ^^ and an ideal probability map ^ + ^ obtained from the final segmentation ^ ^^ or ^ ^^ ′. This ideal probability map ^ + ^, very strongly correlated with the final segmentation ^ ^^ or ^ ^^ ′ from which it comes, is of the same size as the probability map ^^. It allows the calculation of the Pearson correlation coefficient r (representative of the spatial correlation between the probability map ^^ and the ideal probability map ^ + ^) without having to binarize the probability map ^^ with an arbitrary threshold that would lose information. The ideal probability map ^ + ^ is calculated from the following formula: where p(i) is a probability value of a voxel i of the ideal probability map ^ + ^ and δ(i,j) the Euclidean distance between the point associated with voxel i (usually the center of said voxel) and the point associated with voxel j (usually the center of said voxel) which is the contour point of ^ ^^ or ^ ^^ ′ closest to the point associated with voxel i. We normalize the distance δ(i,j) by the maximum Euclidean distance δmax of the voxels of this probability map ^ + ^.

Claims

CLAIMS 1. Method for segmenting a three-dimensional image of at least one organ of a patient comprising at least the steps of: - extracting from the three-dimensional image of said organ, a probability map which assigns to each voxel of the image a probability of belonging to a contour of the organ on the image; - extracting from said probability map, at least one target point based on said probability of belonging to the contour of the organ on the image, each target point being extracted from the probability map by applying to the probability map at least one probability threshold of belonging to the contour of the organ on the image; - from each target point extracted in the previous step, deforming a deformable model of this organ to obtain the three-dimensional segmentation of said organ on the image. 2.Method according to claim 1, wherein the probability map is extracted via a model distinct from the deformable model.

3. Method according to claim 2, wherein the distinct model is defined by an at least partly automatic segmentation method.

4. Method according to claim 3, wherein the distinct model is defined by at least one artificial intelligence trained from segmented images of the organ of at least other people.

5. Method according to one of the preceding claims, wherein the at least one threshold is global or local.

6. Method according to one of claims 1 to 5, in which the at least one threshold has a value independent of, or dependent on, the organ and / or the patient and / or the three-dimensional image and / or the probability map.

7. Method according to one of claims 1 to 6, in which the at least one threshold is dynamic.

8. Method according to claim 7, in which the at least one dynamic threshold is a local threshold making it possible to select only local probability maxima of the probability map.

9. Method according to one of the preceding claims, in which the deformable model is a statistical model of the shape of the organ to be segmented.

10. Method according to one of the preceding claims, in which the deformable model has an initial shape defined from the average of the shapes of the same organ considered but of patients other than the targeted patient. 11.Method according to one of the preceding claims, in which the initial shape of the deformable model is determined by an imaging technology other than ultrasound.

12. Method according to one of the preceding claims, in which the deformable model has an initial shape combined with a segmentation of the same organ considered in this same patient, segmentation obtained from an image acquired prior to an acquisition of the image currently being segmented.

13. Method according to one of the preceding claims, in which: - from each target point extracted from the probability map, the deformable model is pre-deformed. - then only a portion of the target points extracted from the probability map is selected to form a subgroup of target points having a higher probability of belonging to the contour of the organ on the image than the target points not forming part of the subgroup, - from each target point of the subgroup, the deformable model is deformed.

14. Method according to one of the preceding claims, in which the deformation of the deformable model is carried out iteratively by alternating at least one scaling phase with an elastic deformation phase. 15.Method according to claim 14, in which during the scaling phase a global deformable is also carried out, and in which at each iteration, an elastic deformation field resulting from the elastic deformation is decomposed into an affine component and a non-linear residual deformation, the affine component being used for the global deformation during the following iteration.

16. Method according to one of the preceding claims, in which the quality of the segmentation obtained is estimated by evaluating a spatial correlation between the probability map and said segmentation.

17. Method according to one of the preceding claims, in which if the number of target points is less than a predetermined threshold, the method is interrupted.

18. Installation comprising at least one image-taking apparatus and means for segmenting at least one image acquired by said apparatus according to the method according to one of the preceding claims.

19. A computer program comprising instructions that. cause a processor of an installation according to claim 18 to execute the method according to one of claims 1 to 17.

20. Computer-readable recording medium, on which the computer program according to claim 19 is recorded.

Images