-
[show abstract]
[hide abstract]
ABSTRACT: Validation of image registration algorithms is a difficult task and open-ended problem, usually application-dependent. In this paper, we focus on deep brain stimulation (DBS) targeting for the treatment of movement disorders like Parkinson's disease and essential tremor. DBS involves implantation of an electrode deep inside the brain to electrically stimulate specific areas shutting down the disease's symptoms. The subthalamic nucleus (STN) has turned out to be the optimal target for this kind of surgery. Unfortunately, the STN is in general not clearly distinguishable in common medical imaging modalities. Usual techniques to infer its location are the use of anatomical atlases and visible surrounding landmarks. Surgeons have to adjust the electrode intraoperatively using electrophysiological recordings and macrostimulation tests. We constructed a ground truth derived from specific patients whose STNs are clearly visible on magnetic resonance (MR) T2-weighted images. A patient is chosen as atlas both for the right and left sides. Then, by registering each patient with the atlas using different methods, several estimations of the STN location are obtained. Two studies are driven using our proposed validation scheme. First, a comparison between different atlas-based and nonrigid registration algorithms with a evaluation of their performance and usability to locate the STN automatically. Second, a study of which visible surrounding structures influence the STN location. The two studies are cross validated between them and against expert's variability. Using this scheme, we evaluated the expert's ability against the estimation error provided by the tested algorithms and we demonstrated that automatic STN targeting is possible and as accurate as the expert-driven techniques currently used. We also show which structures have to be taken into account to accurately estimate the STN location
IEEE Transactions on Medical Imaging 12/2006; · 3.64 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a validation study on statistical nonsupervised brain tissue classification techniques in magnetic resonance (MR) images. Several image models assuming different hypotheses regarding the intensity distribution model, the spatial model and the number of classes are assessed. The methods are tested on simulated data for which the classification ground truth is known. Different noise and intensity nonuniformities are added to simulate real imaging conditions. No enhancement of the image quality is considered either before or during the classification process. This way, the accuracy of the methods and their robustness against image artifacts are tested. Classification is also performed on real data where a quantitative validation compares the methods' results with an estimated ground truth from manual segmentations by experts. Validity of the various classification methods in the labeling of the image as well as in the tissue volume is estimated with different local and global measures. Results demonstrate that methods relying on both intensity and spatial information are more robust to noise and field inhomogeneities. We also demonstrate that partial volume is not perfectly modeled, even though methods that account for mixture classes outperform methods that only consider pure Gaussian classes. Finally, we show that simulated data results can also be extended to real data.
IEEE Transactions on Medical Imaging 01/2006; · 3.64 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a method for brain atlas deformation in the presence of large space-occupying tumors, based on an a priori model of lesion growth that assumes radial expansion of the lesion from its starting point. Our approach involves three steps. First, an affine registration brings the atlas and the patient into global correspondence. Then, the seeding of a synthetic tumor into the brain atlas provides a template for the lesion. The last step is the deformation of the seeded atlas, combining a method derived from optical flow principles and a model of lesion growth. Results show that a good registration is performed and that the method can be applied to automatic segmentation of structures and substructures in brains with gross deformation, with important medical applications in neurosurgery, radiosurgery, and radiotherapy.
IEEE Transactions on Medical Imaging 11/2004; · 3.64 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: A method for brain atlas deformation in presence of large space-occupying tumors, based on an a priori model of lesion growth that assumes radial expansion of the lesion from its starting point is proposed. First, an affine registration brings the atlas and the patient into global correspondence. Then, the seeding of a synthetic tumor into the brain atlas provides a template for the lesion. Finally, the seeded atlas is deformed, combining a method derived from optical flow principles and a model of lesion growth (MLG). Results show that the method can be applied to the automatic segmentation of structures and substructures in brains with gross deformation, with important medical applications in neurosurgery, radiosurgery and radiotherapy.
Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on; 10/2003
-
[show abstract]
[hide abstract]
ABSTRACT: Besides classic criteria, cerebral perfusion imaging could improve patient selection for thrombolytic therapy. The purpose of this study was to compare quantitative perfusion CT imaging and qualitative diffusion- and perfusion-weighted MRI (DWI and PWI) in acute stroke patients at the time of their emergency evaluation.
Thirteen acute stroke patients underwent perfusion CT and DWI or PWI on admission. The size of infarct and ischemic lesion (infarct plus penumbra) on the admission perfusion CT was compared with that of the MR abnormalities as shown on the DWI trace and on the relative cerebral blood volume, cerebral blood flow, time to peak, and mean transit time maps calculated from PWI studies.
The most significant correlation was found between infarct size on the admission perfusion CT and abnormality size on the admission DWI map (r=0.968, P<0.001). A significant correlation was also observed between the size of the ischemic lesion (infarct plus penumbra) on the admission perfusion CT and the abnormality size on the mean transit time map calculated from admission PWI (r=0.946, P<0.001). Information about cerebral infarct and total ischemia (infarct plus penumbra) carried by both imaging techniques was similar, with slopes of 0.913 and 0.905, respectively.
An imaging technique may be helpful in the identification of cerebral penumbra in acute stroke patients and thus in the selection of patients for thrombolytic therapy. Perfusion CT and DWI/PWI are equivalent in this task.
Stroke 08/2002; 33(8):2025-31. · 5.73 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: A relatively large class of information theoretical measures, including e.g. mutual information or normalized entropy, has been used in multi-modal medical image registration. Even though the mathematical foundations of the different measures were very similar, the final expressions turned out to be surprisingly different. Therefore one of the main aims of this paper is to enlight the relationship of different objective functions by introducing a mathematical framework from which several known optimization objectives can be deduced. Furthermore we extend existing measures in order to be applicable on image features different than image intensities and introduce "feature efficiency" as a very general concept to qualify such features. The presented framework is very general and not at all restricted to medical images. Still we want to discuss the possible impact of our theoretical framework for the particular problem of medical image registration, where the feature space has traditionally been fixed to image intensities. Our theoretical approach is very general though and can be used for any kind of multi-modal signals, such as for the broad field of multi-media applications.
Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on; 02/2002
-
[show abstract]
[hide abstract]
ABSTRACT: We describe a method for the registration of functional brain data acquired with transcranial magnetic stimulation (TMS) on MRI brain images. TMS is a non-invasive method largely used in the study of brain functions. For the registration process we acquire 150 points on the patient's scalp with a magnetic-field digitizer. Then, we minimize the mean square distance between those points and the segmented scalp surface drawn from the MR image. The distance to the scalp surface is computed with the help of a 3D Euclidean distance transformation. For each stimulation, the position of the TMS device is acquired with the digitizer. The registration transformation is applied to the TMS coordinate in order to map TMS data and anatomical information. The results show that the method is precise (4 mm) and reproducible (1 mm).
Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on; 02/2002
-
[show abstract]
[hide abstract]
ABSTRACT: This paper present a reliable, fast and efficient method for measuring the volume density of pancreatic endocrine volume density. The algorithm segmentates digitized images in three different classes: the endocrine (En), exocrine (Ex) and artifact (At) components. A statistical classifier based on the k-Nearest Neighbour (k-NN) decision rule in the RGB color space was compared with a standard point counting technique. The k-NN rule classifies other pixels in the class that is mostly represented among the k nearest training samples in the RGB space, which is efficiently implemented with a fast k-distance transform algorithm. All extracted areas were quantified in absolute (μm<sup>2</sup>) and relative (%) values. The different tissues were point counting determined and their quantifications statistically compared with those obtained semi-automatically. All analyses were performed by an expert pathologist and showed no significant differences between the two approaches.
Molecular, Cellular and Tissue Engineering, 2002. Proceedings of the IEEE-EMBS Special Topic Conference on; 02/2002
-
[show abstract]
[hide abstract]
ABSTRACT: Presents an automatic algorithm to measure fibrosis in muscle sections of mdx mice, a mutant species used as a model of the Duchenne dystrophy. The algorithm described herein automatically segments three different tissues: muscle cell tissue (MT), pure collagen fiber deposit (CD) and cellular infiltrates surrounded by loose collagen deposit (CI), by using a statistical classifier based on the k-nearest neighbour (k-NN) decision rule in the RGB color space. The algorithm is trained by selecting a number of correctly classified pixels from each class. The k-NN rule classifies other pixels in the class that is most represented among the k nearest training samples in the RGB space, which is efficiently implemented with a fast k-distance transform algorithm. All extracted areas are quantified in absolute (μm<sup>2</sup>) and relative (%) values. For validation of this method, the different tissues were manually segmented and their quantifications statistically compared with those obtained automatically. Statistical analysis showed interoperator variability in manual segmentation. Automatic quantifications of the same areas did not differ significantly from their mean manual evaluations. In conclusion, this method produce fast, reliable and reproducible results.
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE; 02/2001
-
[show abstract]
[hide abstract]
ABSTRACT: In the study of many neurological pathologies, the accurate
quantization of the white matter (WM) and gray matter (GM) volumes of
the brain is essential Moreover, regional volume calculations may bring
even more useful diagnostic information. We present therefore the
segmentation of internal structures of the brain for further regional WM
and GM volume quantization. A priori information about the brain anatomy
is included in the segmentation process by the registration of the
patient MR images with a computerized brain atlas. We propose the
combination of a global affine transformation used to initialize key
boundary surfaces (lateral ventricles and cortical surfaces) of both
images with a local free-form transformation based on an optical flow
algorithm. We apply this technique to segment the cerebellum and the
cerebral trunk in order to exclude them from our WM and GM volume
quantization. Validation has been conducted on a large number of images,
showing excellent results
Image Processing, 2001. Proceedings. 2001 International Conference on; 02/2001
-
[show abstract]
[hide abstract]
ABSTRACT: A method for the automatic segmentation, recognition and measurement of neuronal myelinated fibers in nerve histological sections is presented. In this method, the fiber parameters i.e. perimeter, area, position of the fiber and myelin sheath thickness are automatically computed. Obliquity of the sections may be taken into account. First, the image is thresholded to provide a coarse classification between myelin and non-myelin pixels. Next, the resulting binary image is further simplified using connected morphological operators. By applying semantic rules to the zonal graph axon candidates are identified. Those are either isolated or still connected. Then, separation of connected fibers is performed by evaluating myelin sheath thickness around each candidate area with an Euclidean distance transformation. Finally, properties of each detected fiber are computed and false positives are removed. The accuracy of the method is assessed by evaluating missed detection, false positive ratio and comparing the results to the manual procedure with sampling. In the evaluated nerve surface, a 0.9% of false positives was found, along with 6.36% of missed detections. The resulting histograms show strong correlation with those obtained by manual measure. The noise introduced by this method is significantly lower than the intrinsic sampling variability. This automatic method constitutes an original tool for morphometrical analysis.
Journal of Neuroscience Methods 05/2000; 97(2):111-22. · 1.98 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a method for the automatic segmentation, recognition and measurement of neuronal fibers in microscopic images of nerves. This permits a quantitative analysis of the distribution of the areas of the fibers, while nowadays such morphometrical methods are limited by the practical impossibility to process large amounts of fibers in histological routine. First, the image is thresholded to provide a coarse classification between myelin (black) and non-myelin (white) pixels. The resulting binary image is simplified using connected morphological operators. These operators simplify the zonal graph, whose vertices are the connected areas of the binary image. An appropriate set of semantic rules allow us to identify a number of white areas as axon candidates, some of which are isolated, some of which are connected. To separate connected fibers -- candidates sharing the same neighboring black area - we evaluate the thickness of the myelin ring around each candidate area through Euclidean distance transformation by propagation with a stopping criterion on the pixels in the propagation front. Finally, properties of each detected fibers are computed and false alarms are suppressed. The computational cost of the method is evaluated and the robustness of the method is assessed by comparison to the manual procedure. We conclude that the method is fast and accurate for our purpose.
10/1999;
-
[show abstract]
[hide abstract]
ABSTRACT: INTRODUCTION Dilation and erosion are the basic operators of mathematical morphology (see Serra (2)). The dilation of a set of points X by a structural element B is written X B and is defined as follows. { } ) ( ) ( B b X x b x B X + = (1) Erosion is the dual of dilation, i.e. the complement of a dilation performed on the complement set of X. Other morphological operators can be derived by combining dilation and erosion, and provide a full toolkit of operators to process objects in a binary image according to their shape. Symmetrical and circular structural elements (SE) play a central role in mathematical morphology in the continuous plane, since they provide an isotropic treatment of the image. On the other hand, for digital images, circular SE are rarely used because there is no simple and efficient implementation of the dilation by such a SE on a discrete lattice. Inde
10/1999;
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a new signed or unsigned Euclidean distance transformation algorithm, based on the local corrections of the well-known 4SED algorithm of Danielsson (1980). Those corrections are only applied to a small neighborhood of a small subset of pixels from the image, which keeps the cost of the operation low. In contrast with all fast algorithms previously published, our algorithm produces perfect Euclidean distance maps in a time linearly proportional to the number of pixels in the image. The computational cost is close to the cost of the 4SSED approximation
Acoustics, Speech, and Signal Processing, 1999. ICASSP '99. Proceedings., 1999 IEEE International Conference on; 04/1999
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a new method to compute the morphological dilation of a
binary image with a circular structuring element of any given size, on a
discrete lattice. The algorithm is equivalent to applying a threshold on
an exact Euclidean distance map, but computations are restricted to a
minimum number of pixels. The complexity of this dilation algorithm is
compared to the complexity of the commonly used approximation of
circular structuring elements and found to have a similar cost, while
providing better results
Image Processing and Its Applications, 1999. Seventh International Conference on (Conf. Publ. No. 465); 02/1999
-
[show abstract]
[hide abstract]
ABSTRACT: A new region growing algorithm has been proposed for computing
Euclidean distance maps in a time comparable to widely used chamfer
distance transform. We show how this algorithm can be extended to more
complex tasks such as the computation of distance maps on anisotropic
grids and the generation of a new type of Euclidean skeletons
Image Processing, 1997. Proceedings., International Conference on; 11/1997
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a method for the automatic segmentation, recognition and measurement of neuronal fibers in microscopic images of nerves. This permits a quantitative analysis of the distribution of the areas of the fibers, while nowadays such morphometrical methods are limited by the practical impossibility to process large amounts of fibers in histological routine. First, the image is thresholded to provide a coarse classification between myelin (black) and non-myelin (white) pixels. The resulting binary image is simplified using connected morphological operators. These operators simplify the zonal graph, whose vertices are the connected areas of the binary image. An appropriate set of semantic rules allow us to identify a number of white areas as axon candidates, some of which are isolated, some of which are connected. To separate connected fibers – candidates sharing the same neighboring black area -we evaluate the thickness of the myelin ring around each candidate area through Euclidean distance transformation by propagation with a stopping criterion on the pixels in the propagation front. Finally, properties of each detected fibers are computed and false alarms are suppressed. The computational cost of the method is evaluated and the robustness of the method is assessed by comparison to the manual procedure. We conclude that the method is fast and accurate for our purpose.
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a method for the registration of MRI brain images with the physical space. Points on the patients scalp are acquired using a magnetic-field digitizer. The registration transform is the rigid transform that minimizes the mean square distance between those points and the scalp surface segmented from the MRI. The distance to the scalp surface is effciently computed using a 3d Euclidean distance transformation. We apply this method to the visualization of transcranial magnetic stimulation and show that results are precise (4mm) and reproducible (1mm).
-
-
