The present invention relates to a method and system for segmenting anatomy structures in an image, a method and system for constructing a 3D surface model of a segmented structure. The particular application example is the segmentation and modeling of brain ventricular system in medical images, such as MR images and CT images.
As shown in
MR imaging has made it possible to obtain in vivo 3D images of the human brain noninvasively. Since changes in the CSF volume and ventricle shapes are commonly associated with several intrinsic and extrinsic pathologies, segmentation and quantification of the ventricular system from MR images are therefore of primary importance.
Since manual segmentation of ventricles is time consuming, subjective and non-reproductive (or non-repeatable), a number of automated methods have also been proposed for the segmentation of ventricles. In general, methods for segmentation of ventricles can be classified into either model-based methods or non model-based methods depending on whether 3D ventricular models are used.
Non model-based methods, such as intensity thresholding [17] and region growing [12, 13, 19] are adaptive to the shape and size variations of the ventricular system. However, since these methods do not utilize the shape prior-knowledge of the ventricles, “leakage” from the ventricular regions to the non-ventricular regions may arise. Furthermore, some ventricular regions may be left out by these methods due to the non-homogeneity of the images or the presence of noise and partial volume artifacts in the images. The accurate segmentation of the third ventricle is especially challenging when using these non model-based methods since the precise boundaries of the third ventricle depend on the shape and topological constraints of themselves and their relationship with surrounding objects.
On the contrary, model-based methods, such as atlas warping [4] or geometrical and parametric model deformation [3, 6, 18], adopt an explicit or implicit model to act as the shape prior knowledge of the ventricles. These methods are robust to noise and are able to achieve precise segmentation when the variation between the shapes of the model and the studied object is small. However, due to the large variation in the shapes and sizes of the ventricles, it is difficult to design a reasonable energy or similarity function to achieve a model deformation adaptable to every variation. Furthermore, the local minimization problem which causes the false segmentation inevitably exists in these methods.
In general, there are two main difficulties in the segmentation of anatomic structures from images. First, transition regions between a studied structure (for example, the ventricular system) and its surrounding tissues (for example, gray matters) may be present due to the partial volume effect. If these transition regions are completely excluded, the structure may be under-segmented or broken into several disconnected components. Second, some boundaries between the studied structure and its surrounding tissue are too thin to be detected in the image. As a result, some object regions may “leak” (i.e. connect) to other non-object regions. Currently, no existing method can detect the transition regions and at the same time, prevent the “leaking” of object regions to non-object regions.
The present invention aims to provide a method and system for the segmentation and constructing 3D surface models of structures in an image.
Specifically, the present invention proposes a method for segmenting one or more ventricles in a three-dimensional brain scan image composed of brain scan data. The method comprises of the steps:
The invention may further include a step of constructing a surface model of the segmented anatomy structure and editing the surface model to accurately describe the features and details lost in segmentation.
Step (c) may include generating the volumes in the form of connected regions, and prior to step (d) there may be steps of trimming the volumes based on anatomical knowledge specific to the ventricle concerned.
The invention may alternatively be expressed as a computer system for performing such methods. This computer system may be integrated with devices for acquiring the image. The invention may also be expressed as a computer program product, such as one recorded on a tangible computer medium, containing program instructions operable by a computer system to perform the steps of the methods.
This patent or patent application publication contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee. This patent or patent application publication contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.
An embodiment of the invention will now be illustrated for the sake of example only with reference to the following drawings, in which:
a)-(c) illustrate one example of the human cerebral ventricular system.
Referring to
The input to method 200 is a volume image. In step 202, the ventricles in the volume image are segmented. In step 204, a 3D surface model is built for each ventricle and the 3D surface model is edited to improve its accuracy. Note that in other embodiments step 202 may not be followed by step 204. Furthermore, the methods of steps 204 have other possible applications than in the method 200, and may be performed separately, or in combination, in a wide range of 3-D modelling situations.
Referring to
The input to method 202 is a volume image. In step 302, the image is reformatted to the standard Talairach space and the standard ventricular model is then warped onto the image according to a plurality (e.g. 10) of automatically identified ventricular landmarks. In step 304, the region of interest for each ventricle is specified using the deformed ventricular model. In steps 308, 310 and 312, the lateral, third and fourth ventricles are segmented. Hysteric thresholding (that is, thresholding with a hysteresis) is performed in steps 306a, 306b and 306c to generate a connected CSF region containing a ventricular component, with the CSF region containing minimal non-ventricular regions.
Given a volume image I, Talairach transformation [9] is commonly used to reformat the image I into the standard Talairach space [14] so that it can be processed or understood with anatomical knowledge. However, occasionally when the Talairach landmarks cannot be located automatically, the Talairach transformation cannot be automated.
Therefore, in example embodiments, a cortical outline-based registration approach is used to reformat the image. A cortical outline of a brain is an approximation convex hull of its cortical surface. The cortical outline S1 in the image is automatically extracted using morphologic analysis [11] and the cortical outline S2 in the 3D Talairach space is generated by interpolating [8] the 2D digital electronic version of the 3D Talairach-Tournoux (TT) brain atlas and the ventricular system in the 3D TT brain atlas [8] is taken as the standard volumetric ventricular model.
The outlines S1 and S2 are represented by triangular meshes, with vertices denoted as Q1 and Q2 respectively. Applying the Iterated Closest Points (ICP) method [2] to register the point set Q1 to Q2, a linear transformation is obtained and is used to reformat the image I into the Talairach space. The standard radiological convention (http://www.grahamwideman.com/gw/brain/orientation/orientterms.htm) is adopted to define a coordinate system (xyz) in the Talairach space with its origin located at the anterior commissure of the 3D TT atlas, with x running from the subject's right to left, y running from the subject's posterior to anterior and z running from the subject's inferior to superior.
In example embodiments, to specify the region of interest for each ventricular component, ten ventricular landmarks [7] are first identified in the image and in the 3D TT atlas. A model-based semi-global approach is used to automatically identify the ten ventricular landmarks in the image whereas the tool Medical Image Understanding Environment (MIUE) [7, 8] is used to interactively specify these landmarks in the 3D TT atlas as domain knowledge.
In one example, four of these landmarks are on each lateral ventricle and they are the most posterior point, the most superior point, the anterior lateral frontal pole and the posterior center-line intersection of each lateral ventricle. The landmarks also include the anterior pole on the third ventricle and the posterior-superior point on the fourth ventricle.
Based on the ten ventricular landmarks in the image and the TT brain atlas, the standard ventricular model is then registered onto the image. Since the localization of the automatically detected landmarks may not be accurate [7, 10], a thin plate spline approximation approach [10] is used to obtain the registration (or warping) function.
The warped (or deformed) volumetric ventricular model is then divided into four sub-volumes: V, (left lateral ventricle), V2 (right lateral ventricle), V3 (third ventricle) and V4 (fourth ventricle and adequate). The corresponding regions of interest Ωi for each ventricular component are then defined by expanding the corresponding warped sub-volume Vi according to Equation (1).
In Equation (1), the regions of interest Ω1 to Ω4 are used for the segmentation of the left lateral, right lateral, third and fourth ventricles respectively. s(Vi,p) indicates the signed minimal Euclidean distance of the voxel p (p=(px, py, pz)εR3) to the boundary of the volume V1, with a positive value of s(Vi, p) indicating that the voxel p is outside the volume Vi and a negative value of s(Vi,p) indicating that the voxel p is inside the volume Vi. In one example, d0 is set to 6 mm so that each region is just large enough to contain three type of brain tissue: gray matter, white matter and CSF including the related ventricular component. This allows the threshold for the related ventricular component to be subsequently estimated in the region. In addition, V0 represents the middle sagittal slab. In one example, the thickness of V0 is set to 8 mm according to Equation (2) and V0 is excluded from Ω1 and Ω2 to prevent the “leakage” of the two lateral ventricles into the inter-hemisphere CSF or the “leakage” of the two lateral ventricles into each other.
V
0
={p|−4≦
x≦4} (2)
Steps 306a, 306b and 306c: Perform Hysteretic Thresholding
Although several methods [5, 15, 16, 21] are available to segment CSF regions from brain volumes, the extracted CSF regions usually contain not only the ventricular regions but also a large part of the non-ventricular regions. It is difficult to segment the ventricular regions from the numerous inter-connected non-ventricle regions. As a result, these methods may fail to locate the transition regions between the ventricular CSF and the non-ventricular tissues, resulting in under-segmentation. Although existing methods [20] are available for extracting transition regions, these methods are either gradient-based or local entropy-based. Therefore, they are likely to extract a large part of non-ventricular CSF regions as transition regions.
In example embodiments, the regions of interest Ω1 (Ω1 to Ω4) specified in step 304 are used as a guide in steps 306a, 306b and 306c to collect a connected CSF region X that contains its corresponding ventricle component. In steps 306a, 306b and 306c, hysteretic thresholding is used to collect the region X corresponding to region Ωi according to the following sub-steps:
Step 1: Two pairs of intensity thresholds for the ventricular component in each region Ωi is calculated respectively.
In one example, step 1 is performed according to the following steps.
Firstly, the fuzzy c-mean method [1] is used to classify all voxels of the image in the region Ωi into five clusters according to their intensities. These five clusters represent three types of tissue (GM, WM and CSF) and two transition regions CSF_GM (between CSF and GM) and GM_VM (between GM and WM)).
Next, denoting the membership of intensity g to cluster k as uk(g) and the intensity of each cluster center as ck (k=1, 2, . . . , 5) and without loss of generality, supposing that c1<c2< . . . c5, the intersection point gk of two membership functions uk and uk+, is then calculated such that uk(gk)=uk+1(gk) where k=1, 2, . . . , 4. The low and high thresholds tkL and tkH of cluster k are then set to gk−1 and gk respectively, with go and g5 being set to the possible minimum and maximum intensities respectively.
According to domain knowledge, two clusters corresponding to the CSF and CSF_GM are then picked out. In one example, in the T1-MR images, the first cluster with intensity thresholds [t1L, t1H] is selected as CSF_GM. The threshold containing the CSF cluster is taken to be the narrow threshold [TL1, TH1] whereas the threshold containing both the CSF and the CSF_GM clusters is taken to be the wide threshold [TL2, TH2]. In other words, TL1=t1L, TH1=t1H, TL2=min{t1L, t2L}, TH2=max{t1H, t2H}.
Step 2: For each Ωi a corresponding kernel region K of the ventricular component is collected according to the narrow thresholds [TL1, TH1];
In one example, step 2 is performed according to the following steps.
Firstly, the image I is binarized with the low and high thresholds TL1 and TH1 to obtain the CSF cluster {p|TL1≦I(p)≦TH1}. Next, the maximum connected region K is extracted from the CSF cluster according to the 6-neighbor connectivity. Since the region Ωi is generated by expanding the deformed ventricular component, which is a rough fit of the corresponding ventricular component in the image, naturally, the region K is or at least includes the main part of the related lateral ventricle in the region Ω. In other words, the region K obtained from the region Ω3 includes the main part of the third ventricle, while the region K obtained from each of the other regions, is the main part of the left lateral ventricle, right lateral ventricle, or the fourth ventricle. The region K is denoted as a kernel region of the related ventricle component.
Step 3: The region K is adaptively expanded to include transition regions according to the wide thresholds [TL2, TH2].
In one example, step 3 is performed using a boundary patch-based region growing procedure to adaptively expand the region K to include the transition regions of the ventricular component and at the same time to avoid “leaking” of the region K to non-ventricular regions.
A boundary voxel p of the volume is taken to be an active voxel if at least one of its 26 nearest-neighbors q is such that qεΩ-K and TL2≦I(q)≦TH2. Active boundary voxels of K are then grouped into a set of boundary patches {∂1, ∂2, . . . , ∂n} according to the 26-neighbor connectivity, where n represents the number of patches. All voxels within a patch ∂i are 26-neighbor connected, while two different patches ∂i and ∂j (i≠j) are disconnected.
Region growing is applied on each patch ∂i separately. Initially, ∂i,0 is set as ∂i and ∂i,k+1 is repeatedly generated from ∂i,k according to Equation (3). In Equation (3), N26(p) represents the 26-neighbor of the voxel p.
The procedure of generating from ∂i,k+1 continues until at k=ki is empty or until the number of voxels in ∂i,k
At the end of the procedure, a new volume Vi=Un=0k
X=∪
i=0
n(∪n=0k
In steps 306a, 306b and 306c of steps 308, 310 and 312 respectively, the connected CSF region is further trimmed according to the domain knowledge about the shape, intensity and anatomy of the ventricular system as follows.
To segment the two lateral ventricles, hysteretic thresholding is applied on the regions Ω1 and Ω2 separately to obtain two volumes X1 and X2 which are the main parts of left and right ventricles. To detect the possible remaining parts of the lateral ventricles in the middle sagittal slab V0, the boundary patches ∂1 and ∂2 of X1 and X2 that are inside the region V0, respectively, are first located and the boundary patch-based region growing procedure is then used to adaptively expand ∂1 and ∂2 in the region V0. Two new volumes X1 and X2, which contain the remaining parts of the left and right lateral ventricles, are hence obtained.
Step 308a: Lateral Ventricle Separation
When the septum pellucidum between the two lateral ventricles is large enough (in one example, at least one voxel thickness in the sagittal direction. This occurs in about 30% of subjects in the test data sets), X1 and X2 are separate (i.e., the overlap X12=X1∩X2 of the volumes X1 and X2 is empty), and X1∪X1 and X2∪X2 are taken to be the left and right ventricles respectively. In the case when the septum pellucidum is very thin, the two regions X1 and X2 may be joined together by the non-empty overlap region X12, it is then necessary to separate the left and right lateral ventricles according to the following steps: first, X12 is removed from X1 and XZ to obtain two regions X′1=X1−X12 and X′2=X2−X12. Then, for each voxel p in X12, if its distance to the boundary of region X′1 is less than that to region X′2, i.e., s(X′1, p)<s(X2, p), the voxel p is distributed into X′1, otherwise if s(X′1, p)>s(X2, p), the voxel p is distributed into X′2. If s(X′2, p)=s(X′2, p), p is regarded as a voxel from the septum lucidum. Finally, the unions) X1∪X, and X2∪X′2 are taken as the segmentation of the left and right ventricles, i.e., X1 and X2 are updated to) X1∪X′1 and X2∪X′2, respectively.
Hysteretic thresholding is first applied to region Ω3 to obtain a connected CSF volume X3.
Next, voxels identified to be a part of either the left or right lateral ventricle are removed from X3. In other words, X3 is updated to be X3−(X1+X2). Finally, other extra-ventricular voxels are removed from X3.
Step 310a: Projection-Based Non-Ventricular Region Trimming
In one example, a projection-based trimming method is used to remove non-ventricular voxels from X3. Since the third ventricle is a narrow opening in the middle of the brain and the non-ventricular part contained in the volume X3 is much wider than the third ventricle along the sagittal (left-to-right) direction. The steps of the project-based trimming method are as follows.
Step 1: A two-dimensional image f(y,z) is generated by projecting the volume X3 onto the middle sagittal plane x=0 according to Equation (6).
f(y,z)=#{p|py=y,pz=z,pεX3} (6)
In Equation (6), # represents the cardinal of a set i.e. at a point (y, z) in the plane x=0, f(y,z) represents the number of voxels of volume X3 on the project line at the point (y, z).
Step 2: A fuzzy c-mean method is then used to classify all non-zero values {f(y,z)≠0} into two clusters and an adaptive threshold h is obtained whereby f(y,z) is less than h in one cluster and is more than h in the other cluster.
Step 3: For each voxel pεX3, if f(py, pz)>h, the voxel is removed from X3.
Step 310b: Landmark Guided Non-Ventricular Region Trimming
After applying the projection-based extra-ventricle trimming method, X3 may still contain a small narrow non-ventricular region at the anterior-inferior part of the third ventricle. In one example, a landmark guided non-ventricular region trimming method is used to remove this non-ventricular region. In the landmark guided non-ventricular region trimming method, all voxels anterior to the anterior pole of the third ventricle are removed. The landmark (anterior pole of the third ventricle) is identified in the image using the model-based approach [7].
Step 310c: Shape-Based Non-Ventricular Region Trimming
At the superior of the third ventricle, X3 may contain a thin C-shaped region composed of the Transverse Fissure and the ICV. Furthermore, from the PC (or PG) towards the inferior-posterior, X3 may contain one or more small narrow paths “leaking” to the basal cistern. In one example, these “leakages” are removed using a shape-based non-ventricular region trimming method based on the strip-like shape features of the “leakages”. Firstly, all candidate components for removal are located by grouping connected regions on coronal slices from posterior to anterior. Next, from these candidate components, strip-like “leakages” are identified and removed. In one example, the following sub-steps are performed in the shape-based non-ventricular region trimming method.
Step 1: A candidate leakage component set and a temporary component set
0 are initialized.
In step 1, the most posterior coronal slice y0=min{y|p(x,y,z) E X3} of the volume X3 is located, and is set to empty whereas
is set to {{C0}|C0εS0}, where C0 denotes one of all the 8-neighbor connected regions S0 of X3 on the coronal slice indexed by y0, {C0} is a candidate leakage component composed of region C0.
Step 2: All candidate leakage components are located by tracing each component in to generate
k+1(k=0, 1, 2 . . . ).
For each component Lk={C0, C1, . . . , Ck}ε, if there is a 8-neighbor connected region Ck+1 on the coronal slice indexed by y0+k+1, and Ck+1 is connected to Ck in the sense that there is at least one voxel pk+1εCk+1 that is a 26-neighbor of another voxel pkεCk, the region Ck+1 is appended to the component Lk to form a new component Lk+1={Co, C1, . . . , Ck, Ck+1}.
If the area ratio of the voxels in Ck+1 to the voxels in Ck is greater than a given threshold r (in one example, r is set as 3), Lk+1 is appended into . Otherwise Lk+1 is appended into
for further growing. If
k+1 is not empty, step 2 is repeated by generating
from
.
Step 3: In step 3, the C-shape leakage component on the superior of X3 is removed.
A candidate component Lk+1={C0, C1, Ck, Ck+1}ε is identified as the C-shape leakage component composed of transverse fissure and the ICV if it satisfies the following three conditions.
(1) Ck+1 is a branch region, i.e., there is another connected region C′kεS(k) and C′k≠Ck.
(2) The angle ∠PkPk+1P′k is less than 30°, where Pk, Pk+1, are the mass centers of region Ck, Ck+1 and C′k, respectively, and,
(3) each region C1εLk+1 (i=0, 1, . . . k+1) is on the superior of all voxels of X3 in the coronal slice indexed by y0+i, i.e., max{z|p(x,y0+i,z)εCi}>max{z|p(x,y0+i,z)εX3−Ci}
If Lk+1={C0, C1, Ck, Ck+1} is identified as the C-shape leakage component, C0, C1, Ck are removed from X3, and Lk+1 is removed from .
Step 4: In step 4, strip-like leakage components on the posterior of X3 are removed.
For each candidate component Lk+1={C0, C1, Ck, Ck+1}ε, if it is located at the posterior of mass center G(x, y, z) of the region Ω3, i.e., y0+k+1<Gy, then it is identified as a leakage component. C0, C1, Ck are then removed from X3 whereas Lk+1 is removed from
.
The final X3 region is the segmentation result of the third ventricle.
Since there is no well-defined boundary between the fourth ventricle and the adequate, they are segmented simultaneously. Applying hysterical thresholding on the region Ω4, a volume X4 is obtained. At the joint of the aqueduct and the fourth ventricle, since the posterior wall (i.e. corpora quadrigemina) of the aqueduct becomes very thin and may not be identified from the image, X4 may “leak” from the fourth ventricle to the basal cistern surrounding the cerebellum. At the same time, since the aqueduct is only a narrow path connecting the third and fourth ventricles, a part of the aqueduct or the entire aqueduct may not be included in X4.
Step 312a: Shape-Based Trimming of the Fourth Ventricle
To remove the “leakage”, the number of voxels f(z) in each axial slice of volume X4 indexed as coordinate z is calculated. The slice zmax where f(z) reaches its maximum is located. For slices with f(z)>0, the relative increase ratio from the slice zmax to subsequent slices in the superior (or dorsal) direction is calculated according to Equation (7).
q(z)=[f(z+1)−f(z)]/f(z) (7)
The first leakage slice from zmax towards the ventral direction (denoted as the axial slice Zleak) is located at where q(z) reaches its positive maximum since f(z) increases greatly at where the “leakage” begins. If the maximum value of q(z) is not positive, this implies that X4 did not “leak” to the basal cistern. In this case, Zleak is set as the maximum z coordinate of the voxels in V4.
Since the adequate slants anterior to join with the third ventricle, denoting yleak as the most posterior of the volume X4 on the leakage slice zleak, all voxels from Zleak onwards in the dorsal direction with y coordinates less than yleak are taken to be “leakage” and are removed from the volume X4.
From the slice zmax down towards the inferior (or dorsal) direction, it is required that f(z) does not increase. Therefore, if there is a slice zmin such that f(zmin+1)>f(zmin), all voxels with z coordinates less than zmin would be trimmed from X4.
The final X4 region is the segmentation result of the fourth ventricle.
To find the adequate, denoting [TL2, TH2] as the wide threshold obtained in region Ω4, Nz+(p)={(Px+i, Py+k, pz+k)|i,j=−1,0,1, k=0,1} as the directional neighbors of a voxel p(x,y,z) and So as all voxels of volume X4 in the slice Zleak, Sn+1 is generated from Sn by directional region growing according to Equation (8).
Sn+1 is repeatedly generated from Sn until Sn+1 is empty or until the number of voxels in Sn+1 is greater than the number of voxels in S0 (i.e. #(Sn+1)>#(S0)). The adequate volume is then taken as S1∪S2 . . . ∪Sn. If the procedure of repeatedly generating Sn+1 from Sn stops when #(Sn+1)>#(S0), this may be because the detected adequate reached the third ventricle. On the other hand, if the procedure of repeatedly generating Sn+1 from Sn stops when Sn+1 is empty, this may be because that the detected adequate failed to reach the third ventricle due to partial volume effects. In most situations, the procedure stops when #(Sn+1)>#(S0).
Step 202 produces segmentation results of ventricles. However, some details may still be missing or inaccurate in the case where distances between slices are big and/or the studying image is of a poor quality. In such circumstances, a geometric surface model is more flexible and smoother for describing anatomical structures with subtle features lost in between image slices or disrupted by image quality. To build accurate surface models of ventricles, the well known Marching-cube method [22] can be used to generate initial surface models from the ventricle volumes output from step 202. Then the initial surface models presented as triangulated meshs are simplified [23] to reduce computing time and increase efficiency for the subsequent processing.
To enhance the accuracy, the system in the example embodiments supports user modification of the surface model using the local sine warping method. Based on domain knowledge, users can indicate the missing subtle features by placing amendment points on the 3D model space. The local sine deformation (LSD) function warps a confined region to smoothly approach the amendment points to recover the lost subtle features without losing the continuity of anatomy structures (as shown in
Suppose a user placed an amendment point A near the model M, indicating that a detail feature is missing in the model. The model is presented as a polygonal mesh, for each vertex V on the mesh, the distance from A to V is denoted as d(A,V). The distance between A and the model is d(A, M)=min(d(A,V)|VεM). Given a radius R>d(A,M), (R is adjustable in the system), a limited set of vertices points P={p1, p2, pk|d(A,pi)<R} is constructed. For each point pi in the set P, a corresponding point qi is calculated as follows: qi is positioned on the line along A to pi {i=1, 2, . . . k} and the distance from A to qi is computed by the LSD function according to Equation (9):
By replacing each pi with qi {i=1, 2, . . . k} computed as above, the local region of the surface model is warped towards the amendment point A so that the missing subtle anatomy features can be recovered.
The surface model enhancement procedure in step 204 is an interactive procedure and can be carried out iteratively until the output is satisfactory.
A volumetric deformable model is used in step 202 as domain knowledge to automatically define a region of interest for the segmentation of the structure to be studied, for example the ventricular structure in the example embodiments. A proper ROI is critical for an accurate segmentation. If the ROI is too small, it may not contain the structure to be studied. On the other hand, if the ROI is too large, it may contain too much unrelated information leading to wrong segmentation. In step 202, the model is first deformed to roughly fit its corresponding structure in the image by a 3D point landmark-based warping approach and the ROI is then defined by expanding (or dilating) the deformed model. The resulting ROI takes the prior shape of the structure to be studied and hence, the amount of unrelated information in the ROI is minimized. Therefore, step 202 is robust to noise and to large shape and size variations.
Furthermore, a hysteretic thresholding approach is employed for the region growing procedure in a given region of interest in step 202. In the hysteretic thresholding approach, two pairs of intensity thresholds, namely a narrow one and a wide one, are used. The range of the narrow thresholds is contained in the range of the wide thresholds. The pair of narrow thresholds is used to collect a kernel part excluding the transition regions whereas the pair of wide thresholds is used to collect the transition regions of the structure. The region growing procedure stops when “leakage” is detected. The region growing procedure in step 202 is capable of detecting transition regions while minimizing “leakage”. This is advantageous since the capability of transition region detection is critical for correct segmentation whereas “leakage” minimization greatly alleviates the burden for the region trimming procedure.
In addition, the multiple knowledge-based strategies, such as project-based, landmark guided, and shape-based trimming proposed for the region trimming procedure in step 202 are critical for the correct segmentation of the third ventricle.
Also, step 202 is advantageous over the prior art methods, for example [19]. The method proposed in [19] relies on the accurate identification of AC, PC and MSP and hence may fail to work if the supplied positions of AC, PC and MSP are not highly accurate (errors in the positions of AC and PC need to be less than 3 mm). In addition, in the method proposed in [19], only one pair of thresholds is used within a region of interest, therefore the method fails to cope with the partial volume problem which may cause disconnection of some parts of components. Particularly, the shape of the ROI used in the method in [19] is rectangular which is very different from the shape of the ventricles. Therefore, a large amount of non-ventricle tissues are included in the ROI, leading to potential segmentation errors and “leakages” in [19]. In contrast, in step 202, ten ventricular landmarks are used to warp the ventricular model to fit its corresponding ventricle structure in the image. Since the thin plate spline approximation approach [10] is used to obtain the warping function and the deformed model is further expanded to a thickness of 6 mm, step 202 is more tolerable to large landmark identification errors (up to 3.4 mm in the IBSR-18 (as shown in Table 2 in [7]). Although an erroneous identification of the anterior pole of the third ventricle can affect the accuracy of third ventricle segmentation by step 202, the effect of this is local and small since the anterior pole of the third ventricle is only used to trim the posterior of the third ventricle which is a relatively small portion of the entire third ventricle. Furthermore, the use of hysteretic thresholding in step 202, which employs two pairs of wide and narrow thresholds to develop the region of interest adaptively, ensures that transition regions are included in the ROIs while at the same time minimizing non-ventricle regions. Also, since the ROIs used in step 202 are derived from the ventricular shapes in the brain atlas, the shapes of the ROIs are very close to the shapes of the target structures, hence significantly reducing potential segmentation errors and “leakages”.
[16] W. Wells, W. Grimson, R. Kikinis, and F. Jolesz (1996) “Adaptive segmentation of MRI data”. IEEE Transactions on Medical Imaging 15, 429-442.
[22] Lorensen W E and Cline H E, “Marching Cubes: A High Resolution 3D Surface Construction Algorithm,” Computer Graphics, 1987, 21(4), 163-169
This application is a 371 National Stage application based on PCT/SG2009/000075, filed Feb. 27, 2009, which is based on U.S. provisional application 61/032,518, filed Feb. 29, 2008.
Filing Document | Filing Date | Country | Kind | 371c Date |
---|---|---|---|---|
PCT/SG2009/000075 | 2/27/2009 | WO | 00 | 8/27/2010 |
Number | Date | Country | |
---|---|---|---|
61032518 | Feb 2008 | US |