mauricio reyes - Academia.edu (original) (raw)

Papers by mauricio reyes

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014

In many tertiary clinical care centers, decisionmaking and treatment selection for acute ischemic... more In many tertiary clinical care centers, decisionmaking and treatment selection for acute ischemic stroke is based on magnetic resonance imaging (MRI). The "mismatch" concept aims to segregate the infarct core from potentially salvageable hypo-perfused tissue, the so-called penumbra that is determined from a combination of different MRI modalities. Recent studies have challenged the current concept of tissue at risk stratification targeted to identify the best treatment options for every individual patient. Here, we propose a novel, more elaborate image analysis approach that is based on supervised classification methods to automatically segment and predict the extent of the tissue compartments of interest (healthy, infarct, penumbra regions). The output of the algorithm is a label image including quantitative volumetric information about each tissue compartment. The approach has been evaluated on an image dataset of 10 stroke patients and it compared favorably to currently available tools.

Tumors of the Central Nervous System, 2013

Lecture Notes in Computer Science, 2012

In this paper we present a new population-based implant design methodology, which advances the st... more In this paper we present a new population-based implant design methodology, which advances the state-of-the-art approaches by combining shape and bone quality information into the design strategy. The method enhances the mechanical stability of the fixation and reduces the intra-operative in-plane bending which might impede the functionality of the locking mechanism. The method is presented for the case of mandibular locking fixation plates, where the mandibular angle and the bone quality at screw locations are taken into account. Using computational anatomy techniques, the method automatically derives, from a set of computed tomography images, the mandibular angle and the bone thickness and intensity values at the path of every screw. An optimisation strategy is then used to optimise the two parameters of plate angle and screw position. Results for the new design are presented along with a comparison with a commercially available mandibular locking fixation plate. A statistically highly significant improvement was observed. Our experiments allowed us to conclude that an angle of 126 degrees and a screw separation of 8 mm is a more suitable design than the standard 120 degrees and 9 mm.

Lecture Notes in Computer Science, 2009

We propose to increment a statistical shape model with surrogate variables such as anatomical mea... more We propose to increment a statistical shape model with surrogate variables such as anatomical measurements and patient-related information, allowing conditioning the shape distribution to follow prescribed anatomical constraints. The method is applied to a shape model of the human femur, modeling the joint density of shape and anatomical parameters as a kernel density. Results show that it allows for a fast, intuitive and anatomically meaningful control on the shape deformations and an effective conditioning of the shape distribution, allowing the analysis of the remaining shape variability and relations between shape and anatomy. The approach can be further employed for initializing elastic registration methods such as Active Shape Models, improving their regularization term and reducing the search space for the optimization.

Lecture Notes in Computer Science, 2014

In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor se... more In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semisupervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre-and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.

Studies in Mechanobiology, Tissue Engineering and Biomaterials, 2011

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011

We present an automatic method to segment brain tissues from volumetric MRI brain tumor images. T... more We present an automatic method to segment brain tissues from volumetric MRI brain tumor images. The method is based on non-rigid registration of an average atlas in combination with a biomechanically justified tumor growth model to simulate soft-tissue deformations caused by the tumor mass-effect. The tumor growth model, which is formulated as a mesh-free Markov Random Field energy minimization problem, ensures correspondence between the atlas and the patient image, prior to the registration step. The method is non-parametric, simple and fast compared to other approaches while maintaining similar accuracy. It has been evaluated qualitatively and quantitatively with promising results on eight datasets comprising simulated images and real patient data.

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, 2010

In this paper we present a novel hybrid approach for multimodal medical image registration based ... more In this paper we present a novel hybrid approach for multimodal medical image registration based on diffeomorphic demons. Diffeomorphic demons have proven to be a robust and efficient way for intensity-based image registration. A very recent extension even allows to use mutual information (MI) as a similarity measure to registration multimodal images. However, due to the intensity correspondence uncertainty existing in some anatomical parts, it is difficult for a purely intensity-based algorithm to solve the registration problem. Therefore, we propose to combine the resulting transformations from both intensity-based and landmark-based methods for multimodal non-rigid registration based on diffeomorphic demons. Several experiments on different types of MR images were conducted, for which we show that a better anatomical correspondence between the images can be obtained using the hybrid approach than using either intensity information or landmarks alone.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2010

In this paper we present a novel hybrid approach for multimodal medical image registration based ... more In this paper we present a novel hybrid approach for multimodal medical image registration based on diffeomorphic demons. Diffeomorphic demons have proven to be a robust and efficient way for intensity-based image registration. A very recent extension even allows to use mutual information (MI) as a similarity measure to registration multimodal images. However, due to the intensity correspondence uncertainty existing in some anatomical parts, it is difficult for a purely intensity-based algorithm to solve the registration problem. Therefore, we propose to combine the resulting transformations from both intensity-based and landmark-based methods for multimodal non-rigid registration based on diffeomorphic demons. Several experiments on different types of MR images were conducted, for which we show that a better anatomical correspondence between the images can be obtained using the hybrid approach than using either intensity information or landmarks alone.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2010

We propose a new and clinically oriented approach to perform atlas-based segmentation of brain tu... more We propose a new and clinically oriented approach to perform atlas-based segmentation of brain tumor images. A mesh-free method is used to model tumor-induced soft tissue deformations in a healthy brain atlas image with subsequent registration of the modified atlas to a pathologic patient image. The atlas is seeded with a tumor position prior and tumor growth simulating the tumor mass effect is performed with the aim of improving the registration accuracy in case of patients with space-occupying lesions. We perform tests on 2D axial slices of five different patient data sets and show that the approach gives good results for the segmentation of white matter, grey matter, cerebrospinal fluid and the tumor.

Many methodologies dealing with prediction or simulation of soft tissue deformations on medical i... more Many methodologies dealing with prediction or simulation of soft tissue deformations on medical image data require preprocessing of the data in order to produce a different shape representation that complies with standard methodologies, such as mass–spring networks, finite element method s (FEM). On the other hand, methodologies working directly on the image space normally do not take into account mechanical behavior of tissues and tend to lack physics foundations driving soft tissue deformations. This chapter presents a method to simulate soft tissue deformations based on coupled concepts from image analysis and mechanics theory. The proposed methodology is based on a robust stochastic approach that takes into account material properties retrieved directly from the image, concepts from continuum mechanics and FEM. The optimization framework is solved within a hierarchical Markov random field (HMRF) which is implemented on the graphics processor unit (GPU See Graphics processing unit ).

IEEE International Symposium on Biomedical Imaging, 2009

Extensive recent work has taken place on the construction of probabilistic atlases of anatomical ... more Extensive recent work has taken place on the construction of probabilistic atlases of anatomical organ. We propose a probabilistic atlas of ten major abdominal organs which retains structural variability by using a size-preserving affine registration, and normalizes the physical organ locations to an anatomical landmark. Restricting the degrees of freedom in the transformation, the bias from the reference data is minimized, in terms of organ shape, size and position. Additionally, we present a scheme for the study of anatomical variability within the abdomen, including the clusterization of the modes of variation. The analysis of deformation fields showed a strong correlation with anatomical landmarks and known mechanical deformations in the abdomen. The atlas and its dependencies represent a potentially important research tool for abdominal diagnosis, modeling and soft tissue interventions.

During an emission tomography exam of lungs, respiratory motion blurs the reconstructed image, wh... more During an emission tomography exam of lungs, respiratory motion blurs the reconstructed image, which may lead to misinterpretations and imprecise diagnosis. Solutions like respiratory gating, correlated dynamic PET techniques, listmode data based techniques and others have been tested with improvements over the spatial activity distribution in lungs lesions, but with the disadvantages of either requiring extra hardware or more expensive scanner systems, or discarding part of the acquired data. The objective of this study is to include a respiratory motion model in the image tomographic reconstruction process, which will allow to consider all the acquired data, without any additional requirement. To this end, we propose an extension of the MLEM reconstruction algorithm, in which we extend the probability matrix to take into account both the motion and the deformation of the voxels to be reconstructed. We present results from synthetic simulations incorporating real respiratory motion data, demonstrating the potential benefits of such an approach.

IEEE International Symposium on Biomedical Imaging, 2007

Statistical shape analysis techniques commonly employed in the medical imaging community, such as... more Statistical shape analysis techniques commonly employed in the medical imaging community, such as active shape models or active appearance models, rely on principal component analysis (PCA) to decompose shape variability into a reduced set of interpretable components. In this paper we propose principal factor analysis (PFA) as an alternative and complementary tool to PCA providing a decomposition into modes of variation that can be more easily interpretable, while still being a linear efficient technique that performs dimensionality reduction (as opposed to independent component analysis, ICA). The key difference between PFA and PCA is that PFA models covariance between variables, rather than the total variance in the data. The added value of PFA is illustrated on 2D landmark data of corpora callosa outlines. Then, a study of the 3D shape variability of the human left femur is performed. Finally, we report results on vector-valued 3D deformation fields resulting from non-rigid registration of ventricles in MRI of the brain.

Recent Advances in the 3D Physiological Human, 2009

Abstract Many methodologies dealing with prediction or simulation of soft tis-sue deformations on... more Abstract Many methodologies dealing with prediction or simulation of soft tis-sue deformations on medical image data require preprocessing of the data in order to produce a different shape representation that complies with standard methodol-ogies, such as mass–spring ...

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011

ABSTRACT In this paper, we introduce a hybrid image registration approach for diffusion weighted ... more ABSTRACT In this paper, we introduce a hybrid image registration approach for diffusion weighted image (DWI) distortion correction. General intensity-based multimodal registration uses mutual information (MI) as the similarity metric, which can cause matching ambiguities due to the intensity correspondence uncertainty in some anatomical regions. We propose to overcome such limitations by enhancing the registration framework with automatically detected landmarks. These landmarks are then integrated naturally into multimodal diffeomorphic demons algorithm using Gaussian radial basis functions. The proposed algorithm was tested with clinical DWI data, with results demonstrating that better distortion correction can be achieved using the hybrid algorithm as compared to using a pure intensity-based approach.

Lecture Notes in Computer Science, 2012

Locally affine (polyaffine) image registration methods capture intersubject non-linear deformatio... more Locally affine (polyaffine) image registration methods capture intersubject non-linear deformations with a low number of parameters, while providing an intuitive interpretation for clinicians. Considering the mandible bone, anatomical shape differences can be found at different scales, e.g. left or right side, teeth, etc. Classically, sequential coarse to fine registration are used to handle multiscale deformations, instead we propose a simultaneous optimization of all scales. To avoid local minima we incorporate a prior on the polyaffine transformations. This kind of groupwise registration approach is natural in a polyaffine context, if we assume one configuration of regions that describes an entire group of images, with varying transformations for each region. In this paper, we reformulate polyaffine deformations in a generative statistical model, which enables us to incorporate deformation statistics as a prior in a Bayesian setting. We find optimal transformations by optimizing the maximum a posteriori probability. We assume that the polyaffine transformations follow a normal distribution with mean and concentration matrix. Parameters of the prior are estimated from an initial coarse to fine registration. Knowing the region structure, we develop a blockwise pseudoinverse to obtain the concentration matrix. To our knowledge, we are the first to introduce simultaneous multiscale optimization through groupwise polyaffine registration. We show results on 42 mandible CT images.

Lecture Notes in Computer Science, 2011

Non-linear image registration is an important tool in many areas of image analysis. For instance,... more Non-linear image registration is an important tool in many areas of image analysis. For instance, in morphometric studies of a population of brains, free-form deformations between images are analyzed to describe the structural anatomical variability. Such a simple deformation model is justified by the absence of an easy expressible prior about the shape changes. Applying the same algorithms used in brain imaging to orthopedic images might not be optimal due to the difference in the underlying prior on the inter-subject deformations. In particular, using an un-informed deformation prior often leads to local minima far from the expected solution. To improve robustness and promote anatomically meaningful deformations, we propose a locally affine and geometry-aware registration algorithm that automatically adapts to the data. We build upon the log-domain demons algorithm and introduce a new type of OBBTree-based regularization in the registration with a natural multiscale structure. The regularization model is composed of a hierarchy of locally affine transformations via their logarithms. Experiments on mandibles show improved accuracy and robustness when used to initialize the demons, and even similar performance by direct comparison to the demons, with a significantly lower degree of freedom. This closes the gap between polyaffine and non-rigid registration and opens new ways to statistically analyze the registration results.

2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2010

Currently there is an increase usage of CT-based bone diagnosis because low-radiation and cost-ef... more Currently there is an increase usage of CT-based bone diagnosis because low-radiation and cost-effective 2D imaging modalities do not provide the necessary 3D information for bone diagnosis. The fundamental objective of our work is to build a model connecting 2D X-ray information to 3D CT information through regression. As a first step we propose an univariate non-parametric regression on individual predictor variables to explore the non-linearity of the data. To later combine these univariate models we then replace them with parametric models. We examine two predictors, shaft length and caput collum diaphysis angle on a database of 182 CT images of femurs. We show that for each predictor it is possible to describe 99% of the variance through a simple up to second order parametric model. These findings will allow us to extend to the multivariate case in the future.

Medical Imaging 2011: Image Processing, 2011

Osteoarticular allograft transplantation is a popular treatment method in wide surgical resection... more Osteoarticular allograft transplantation is a popular treatment method in wide surgical resections with large defects. For this reason hospitals are building bone data banks. Performing the optimal allograft selection on bone banks is crucial to the surgical outcome and patient recovery. However, current approaches are very time consuming hindering an efficient selection. We present an automatic method based on registration of femur bones to overcome this limitation. We introduce a new regularization term for the log-domain demons algorithm. This term replaces the standard Gaussian smoothing with a femur specific polyaffine model. The polyaffine femur model is constructed with two affine (femoral head and condyles) and one rigid (shaft) transformation. Our main contribution in this paper is to show that the demons algorithm can be improved in specific cases with an appropriate model. We are not trying to find the most optimal polyaffine model of the femur, but the simplest model with a minimal number of parameters. There is no need to optimize for different number of regions, boundaries and choice of weights, since this fine tuning will be done automatically by a final demons relaxation step with Gaussian smoothing. The newly developed synthesis approach provides a clear anatomically motivated modeling contribution through the specific three component transformation model, and clearly shows a performance improvement (in terms of anatomical meaningful correspondences) on 146 CT images of femurs compared to a standard multiresolution demons. In addition, this simple model improves the robustness of the demons while preserving its accuracy. The ground truth are manual measurements performed by medical experts.

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014

In many tertiary clinical care centers, decisionmaking and treatment selection for acute ischemic... more In many tertiary clinical care centers, decisionmaking and treatment selection for acute ischemic stroke is based on magnetic resonance imaging (MRI). The "mismatch" concept aims to segregate the infarct core from potentially salvageable hypo-perfused tissue, the so-called penumbra that is determined from a combination of different MRI modalities. Recent studies have challenged the current concept of tissue at risk stratification targeted to identify the best treatment options for every individual patient. Here, we propose a novel, more elaborate image analysis approach that is based on supervised classification methods to automatically segment and predict the extent of the tissue compartments of interest (healthy, infarct, penumbra regions). The output of the algorithm is a label image including quantitative volumetric information about each tissue compartment. The approach has been evaluated on an image dataset of 10 stroke patients and it compared favorably to currently available tools.

Tumors of the Central Nervous System, 2013

Lecture Notes in Computer Science, 2012

In this paper we present a new population-based implant design methodology, which advances the st... more In this paper we present a new population-based implant design methodology, which advances the state-of-the-art approaches by combining shape and bone quality information into the design strategy. The method enhances the mechanical stability of the fixation and reduces the intra-operative in-plane bending which might impede the functionality of the locking mechanism. The method is presented for the case of mandibular locking fixation plates, where the mandibular angle and the bone quality at screw locations are taken into account. Using computational anatomy techniques, the method automatically derives, from a set of computed tomography images, the mandibular angle and the bone thickness and intensity values at the path of every screw. An optimisation strategy is then used to optimise the two parameters of plate angle and screw position. Results for the new design are presented along with a comparison with a commercially available mandibular locking fixation plate. A statistically highly significant improvement was observed. Our experiments allowed us to conclude that an angle of 126 degrees and a screw separation of 8 mm is a more suitable design than the standard 120 degrees and 9 mm.

Lecture Notes in Computer Science, 2009

We propose to increment a statistical shape model with surrogate variables such as anatomical mea... more We propose to increment a statistical shape model with surrogate variables such as anatomical measurements and patient-related information, allowing conditioning the shape distribution to follow prescribed anatomical constraints. The method is applied to a shape model of the human femur, modeling the joint density of shape and anatomical parameters as a kernel density. Results show that it allows for a fast, intuitive and anatomically meaningful control on the shape deformations and an effective conditioning of the shape distribution, allowing the analysis of the remaining shape variability and relations between shape and anatomy. The approach can be further employed for initializing elastic registration methods such as Active Shape Models, improving their regularization term and reducing the search space for the optimization.

Lecture Notes in Computer Science, 2014

In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor se... more In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semisupervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre-and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.

Studies in Mechanobiology, Tissue Engineering and Biomaterials, 2011

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011

We present an automatic method to segment brain tissues from volumetric MRI brain tumor images. T... more We present an automatic method to segment brain tissues from volumetric MRI brain tumor images. The method is based on non-rigid registration of an average atlas in combination with a biomechanically justified tumor growth model to simulate soft-tissue deformations caused by the tumor mass-effect. The tumor growth model, which is formulated as a mesh-free Markov Random Field energy minimization problem, ensures correspondence between the atlas and the patient image, prior to the registration step. The method is non-parametric, simple and fast compared to other approaches while maintaining similar accuracy. It has been evaluated qualitatively and quantitatively with promising results on eight datasets comprising simulated images and real patient data.

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, 2010

In this paper we present a novel hybrid approach for multimodal medical image registration based ... more In this paper we present a novel hybrid approach for multimodal medical image registration based on diffeomorphic demons. Diffeomorphic demons have proven to be a robust and efficient way for intensity-based image registration. A very recent extension even allows to use mutual information (MI) as a similarity measure to registration multimodal images. However, due to the intensity correspondence uncertainty existing in some anatomical parts, it is difficult for a purely intensity-based algorithm to solve the registration problem. Therefore, we propose to combine the resulting transformations from both intensity-based and landmark-based methods for multimodal non-rigid registration based on diffeomorphic demons. Several experiments on different types of MR images were conducted, for which we show that a better anatomical correspondence between the images can be obtained using the hybrid approach than using either intensity information or landmarks alone.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2010

In this paper we present a novel hybrid approach for multimodal medical image registration based ... more In this paper we present a novel hybrid approach for multimodal medical image registration based on diffeomorphic demons. Diffeomorphic demons have proven to be a robust and efficient way for intensity-based image registration. A very recent extension even allows to use mutual information (MI) as a similarity measure to registration multimodal images. However, due to the intensity correspondence uncertainty existing in some anatomical parts, it is difficult for a purely intensity-based algorithm to solve the registration problem. Therefore, we propose to combine the resulting transformations from both intensity-based and landmark-based methods for multimodal non-rigid registration based on diffeomorphic demons. Several experiments on different types of MR images were conducted, for which we show that a better anatomical correspondence between the images can be obtained using the hybrid approach than using either intensity information or landmarks alone.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2010

We propose a new and clinically oriented approach to perform atlas-based segmentation of brain tu... more We propose a new and clinically oriented approach to perform atlas-based segmentation of brain tumor images. A mesh-free method is used to model tumor-induced soft tissue deformations in a healthy brain atlas image with subsequent registration of the modified atlas to a pathologic patient image. The atlas is seeded with a tumor position prior and tumor growth simulating the tumor mass effect is performed with the aim of improving the registration accuracy in case of patients with space-occupying lesions. We perform tests on 2D axial slices of five different patient data sets and show that the approach gives good results for the segmentation of white matter, grey matter, cerebrospinal fluid and the tumor.

Many methodologies dealing with prediction or simulation of soft tissue deformations on medical i... more Many methodologies dealing with prediction or simulation of soft tissue deformations on medical image data require preprocessing of the data in order to produce a different shape representation that complies with standard methodologies, such as mass–spring networks, finite element method s (FEM). On the other hand, methodologies working directly on the image space normally do not take into account mechanical behavior of tissues and tend to lack physics foundations driving soft tissue deformations. This chapter presents a method to simulate soft tissue deformations based on coupled concepts from image analysis and mechanics theory. The proposed methodology is based on a robust stochastic approach that takes into account material properties retrieved directly from the image, concepts from continuum mechanics and FEM. The optimization framework is solved within a hierarchical Markov random field (HMRF) which is implemented on the graphics processor unit (GPU See Graphics processing unit ).

IEEE International Symposium on Biomedical Imaging, 2009

Extensive recent work has taken place on the construction of probabilistic atlases of anatomical ... more Extensive recent work has taken place on the construction of probabilistic atlases of anatomical organ. We propose a probabilistic atlas of ten major abdominal organs which retains structural variability by using a size-preserving affine registration, and normalizes the physical organ locations to an anatomical landmark. Restricting the degrees of freedom in the transformation, the bias from the reference data is minimized, in terms of organ shape, size and position. Additionally, we present a scheme for the study of anatomical variability within the abdomen, including the clusterization of the modes of variation. The analysis of deformation fields showed a strong correlation with anatomical landmarks and known mechanical deformations in the abdomen. The atlas and its dependencies represent a potentially important research tool for abdominal diagnosis, modeling and soft tissue interventions.

During an emission tomography exam of lungs, respiratory motion blurs the reconstructed image, wh... more During an emission tomography exam of lungs, respiratory motion blurs the reconstructed image, which may lead to misinterpretations and imprecise diagnosis. Solutions like respiratory gating, correlated dynamic PET techniques, listmode data based techniques and others have been tested with improvements over the spatial activity distribution in lungs lesions, but with the disadvantages of either requiring extra hardware or more expensive scanner systems, or discarding part of the acquired data. The objective of this study is to include a respiratory motion model in the image tomographic reconstruction process, which will allow to consider all the acquired data, without any additional requirement. To this end, we propose an extension of the MLEM reconstruction algorithm, in which we extend the probability matrix to take into account both the motion and the deformation of the voxels to be reconstructed. We present results from synthetic simulations incorporating real respiratory motion data, demonstrating the potential benefits of such an approach.

IEEE International Symposium on Biomedical Imaging, 2007

Statistical shape analysis techniques commonly employed in the medical imaging community, such as... more Statistical shape analysis techniques commonly employed in the medical imaging community, such as active shape models or active appearance models, rely on principal component analysis (PCA) to decompose shape variability into a reduced set of interpretable components. In this paper we propose principal factor analysis (PFA) as an alternative and complementary tool to PCA providing a decomposition into modes of variation that can be more easily interpretable, while still being a linear efficient technique that performs dimensionality reduction (as opposed to independent component analysis, ICA). The key difference between PFA and PCA is that PFA models covariance between variables, rather than the total variance in the data. The added value of PFA is illustrated on 2D landmark data of corpora callosa outlines. Then, a study of the 3D shape variability of the human left femur is performed. Finally, we report results on vector-valued 3D deformation fields resulting from non-rigid registration of ventricles in MRI of the brain.

Recent Advances in the 3D Physiological Human, 2009

Abstract Many methodologies dealing with prediction or simulation of soft tis-sue deformations on... more Abstract Many methodologies dealing with prediction or simulation of soft tis-sue deformations on medical image data require preprocessing of the data in order to produce a different shape representation that complies with standard methodol-ogies, such as mass–spring ...

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011

ABSTRACT In this paper, we introduce a hybrid image registration approach for diffusion weighted ... more ABSTRACT In this paper, we introduce a hybrid image registration approach for diffusion weighted image (DWI) distortion correction. General intensity-based multimodal registration uses mutual information (MI) as the similarity metric, which can cause matching ambiguities due to the intensity correspondence uncertainty in some anatomical regions. We propose to overcome such limitations by enhancing the registration framework with automatically detected landmarks. These landmarks are then integrated naturally into multimodal diffeomorphic demons algorithm using Gaussian radial basis functions. The proposed algorithm was tested with clinical DWI data, with results demonstrating that better distortion correction can be achieved using the hybrid algorithm as compared to using a pure intensity-based approach.

Lecture Notes in Computer Science, 2012

Locally affine (polyaffine) image registration methods capture intersubject non-linear deformatio... more Locally affine (polyaffine) image registration methods capture intersubject non-linear deformations with a low number of parameters, while providing an intuitive interpretation for clinicians. Considering the mandible bone, anatomical shape differences can be found at different scales, e.g. left or right side, teeth, etc. Classically, sequential coarse to fine registration are used to handle multiscale deformations, instead we propose a simultaneous optimization of all scales. To avoid local minima we incorporate a prior on the polyaffine transformations. This kind of groupwise registration approach is natural in a polyaffine context, if we assume one configuration of regions that describes an entire group of images, with varying transformations for each region. In this paper, we reformulate polyaffine deformations in a generative statistical model, which enables us to incorporate deformation statistics as a prior in a Bayesian setting. We find optimal transformations by optimizing the maximum a posteriori probability. We assume that the polyaffine transformations follow a normal distribution with mean and concentration matrix. Parameters of the prior are estimated from an initial coarse to fine registration. Knowing the region structure, we develop a blockwise pseudoinverse to obtain the concentration matrix. To our knowledge, we are the first to introduce simultaneous multiscale optimization through groupwise polyaffine registration. We show results on 42 mandible CT images.

Lecture Notes in Computer Science, 2011

Non-linear image registration is an important tool in many areas of image analysis. For instance,... more Non-linear image registration is an important tool in many areas of image analysis. For instance, in morphometric studies of a population of brains, free-form deformations between images are analyzed to describe the structural anatomical variability. Such a simple deformation model is justified by the absence of an easy expressible prior about the shape changes. Applying the same algorithms used in brain imaging to orthopedic images might not be optimal due to the difference in the underlying prior on the inter-subject deformations. In particular, using an un-informed deformation prior often leads to local minima far from the expected solution. To improve robustness and promote anatomically meaningful deformations, we propose a locally affine and geometry-aware registration algorithm that automatically adapts to the data. We build upon the log-domain demons algorithm and introduce a new type of OBBTree-based regularization in the registration with a natural multiscale structure. The regularization model is composed of a hierarchy of locally affine transformations via their logarithms. Experiments on mandibles show improved accuracy and robustness when used to initialize the demons, and even similar performance by direct comparison to the demons, with a significantly lower degree of freedom. This closes the gap between polyaffine and non-rigid registration and opens new ways to statistically analyze the registration results.

2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2010

Currently there is an increase usage of CT-based bone diagnosis because low-radiation and cost-ef... more Currently there is an increase usage of CT-based bone diagnosis because low-radiation and cost-effective 2D imaging modalities do not provide the necessary 3D information for bone diagnosis. The fundamental objective of our work is to build a model connecting 2D X-ray information to 3D CT information through regression. As a first step we propose an univariate non-parametric regression on individual predictor variables to explore the non-linearity of the data. To later combine these univariate models we then replace them with parametric models. We examine two predictors, shaft length and caput collum diaphysis angle on a database of 182 CT images of femurs. We show that for each predictor it is possible to describe 99% of the variance through a simple up to second order parametric model. These findings will allow us to extend to the multivariate case in the future.

Medical Imaging 2011: Image Processing, 2011

Osteoarticular allograft transplantation is a popular treatment method in wide surgical resection... more Osteoarticular allograft transplantation is a popular treatment method in wide surgical resections with large defects. For this reason hospitals are building bone data banks. Performing the optimal allograft selection on bone banks is crucial to the surgical outcome and patient recovery. However, current approaches are very time consuming hindering an efficient selection. We present an automatic method based on registration of femur bones to overcome this limitation. We introduce a new regularization term for the log-domain demons algorithm. This term replaces the standard Gaussian smoothing with a femur specific polyaffine model. The polyaffine femur model is constructed with two affine (femoral head and condyles) and one rigid (shaft) transformation. Our main contribution in this paper is to show that the demons algorithm can be improved in specific cases with an appropriate model. We are not trying to find the most optimal polyaffine model of the femur, but the simplest model with a minimal number of parameters. There is no need to optimize for different number of regions, boundaries and choice of weights, since this fine tuning will be done automatically by a final demons relaxation step with Gaussian smoothing. The newly developed synthesis approach provides a clear anatomically motivated modeling contribution through the specific three component transformation model, and clearly shows a performance improvement (in terms of anatomical meaningful correspondences) on 146 CT images of femurs compared to a standard multiresolution demons. In addition, this simple model improves the robustness of the demons while preserving its accuracy. The ground truth are manual measurements performed by medical experts.