-
[show abstract]
[hide abstract]
ABSTRACT: A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D Magnetic Resonance (MR) images. It builds on a discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. The method uses multi-channel MR intensities (T1, T2, and FLAIR), knowledge on tissue classes and long-range spatial context to discriminate lesions from background. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the proposed methods is carried out on publicly available labeled cases from the MICCAI MS Lesion Segmentation Challenge 2008 dataset. When tested on the same data, the presented method compares favorably to all earlier methods. In an a posteriori analysis, we show how selected features during classification can be ranked according to their discriminative power and reveal the most important ones.
NeuroImage 07/2011; 57(2):378-90. · 5.89 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Recent advances in computer science and medical imaging allow the design of new computational models of the patient which are used to assist physicians. These models, whose parameters are optimized to fit in vivo acquired images, from cells to an entire body, are designed to better quantify the observations (computer aided diagnosis), to simulate the evolution of a pathology (computer aided prognosis), to plan and simulate an intervention to optimize its effects (computer aided therapy), therefore addressing some of the major challenges of medicine of 21(st) century.
Medecine sciences: M/S 02/2011; 27(2):208-13. · 0.64 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Estimation of glioblastoma (GBM) growth patterns is of tremendous value in determining tumour margins for radiotherapy. We have previously developed a numerical simulation model for the pattern of spread of glioblastoma tumours. This model involved the creation of a digital atlas of the brain with elasticity and resistance-to-invasion values for specific brain structures and also included probable direction of tumour spread as estimated by Diffusion Tensor Imaging (DTI). The current study is aimed at comparing the outcome of such simulation with conventional irradiation margins currently in use.
Actual patient data were used to simulate the direction of microscopic extension, using a variety of margin-, proliferation- and diffusion-rate scenarios to generate growth patterns, which were then compared with current standard radiotherapy margins.
Our patient growth pattern simulations showed microscopic invasion beyond irradiation margins for both combinations of high-diffusion/low-proliferation and low-diffusion/high-proliferation rate scenarios. The model also indicated that some healthy brain tissue that was projected to be safe from recurrence fell inside treatment margins.
These results may explain the current inadequacy of our treatment techniques in preventing locoregional recurrences of GBM.
Physica Medica 11/2010; 27(2):103-8. · 1.07 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D MR images. It builds
on the discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume.
Our method uses multi-channel MR intensities (T1, T2, Flair), spatial prior and long-range comparisons with 3D regions to
discriminate lesions. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an
asymmetric way. Quantitative evaluation of the data is carried out on publicly available labeled cases from the MS Lesion
Segmentation Challenge 2008 dataset and demonstrates improved results over the state of the art.
09/2010: pages 111-118;
-
[show abstract]
[hide abstract]
ABSTRACT: Radiotherapy for brain glioma treatment relies on magnetic resonance (MR) and computed tomography (CT) images. These images provide information on the spatial extent of the tumor, but can only visualize parts of the tumor where cancerous cells are dense enough, masking the low density infiltration. In radiotherapy, a 2 m constant margin around the tumor is taken to account for this uncertainty. This approach however, does not consider the growth dynamics of gliomas, particularly the differential motility of tumor cells in the white and in the gray matter. In this article, we propose a novel method for estimating the full extent of the tumor infiltration starting from its visible mass in the patients' MR images. This estimation problem is a time independent problem where we do not have information about the temporal evolution of the pathology nor its initial conditions. Based on the reaction-diffusion models widely used in the literature, we derive a method to solve this extrapolation problem. Later, we use this formulation to tailor new tumor specific variable irradiation margins. We perform geometrical comparisons between the conventional constant and the proposed variable margins through determining the amount of targeted tumor cells and healthy tissue in the case of synthetic tumors. Results of these experiments suggest that the variable margin could be more effective at targeting cancerous cells and preserving healthy tissue.
Medical image analysis 04/2010; 14(2):111-25. · 3.09 Impact Factor
-
Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010, 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I; 01/2010
-
IEEE Trans. Med. Imaging. 01/2010; 29:77-95.
-
[show abstract]
[hide abstract]
ABSTRACT: A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D MR images. It builds on the discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. Our method uses multi-channel MIR intensities (T1, T2, Flair), spatial prior and long-range comparisons with 3D regions to discriminate lesions. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the data is carried out on publicly available labeled cases from the MS Lesion Segmentation Challenge 2008 dataset and demonstrates improved results over the state of the art.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2010; 13(Pt 1):111-8.
-
IEEE Trans. Med. Imaging. 01/2009; 28:1914-1928.
-
[show abstract]
[hide abstract]
ABSTRACT: The advent of magnetic resonance imaging (MRI) has allowed the follow-up of tumor growth by precise volumetric measurements. Such information about tumor dynamics is, however, usually not fully integrated in the therapeutic management, and the assessment of tumor evolution is still limited to qualitative description. In parallel, computational models have been developed to simulate in silico tumor growth and treatment efficacy. Nevertheless, direct clinical interest of these models remains questionable, and there is a gap between scientific advances and clinical practice. In this paper, WHO grade II glioma will serve as a paradigmatic example to illustrate that computational models allow characterizing tumor dynamics from serial MRIs. The role of these dynamics for both therapeutic management and biological research will be discussed.
Neurosurgical Review 08/2008; 31(3):263-9. · 2.04 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Glioblastoma multiforma (GBM) is one of the most aggressive tumors of the central nervous system. It can be represented by two components: a proliferative component with a mass effect on brain structures and an invasive component. GBM has a distinct pattern of spread showing a preferential growth in the white fiber direction for the invasive component. By using the architecture of white matter fibers, we propose a new model to simulate the growth of GBM. This architecture is estimated by diffusion tensor imaging in order to determine the preferred direction for the diffusion component. It is then coupled with a mechanical component. To set up our growth model, we make a brain atlas including brain structures with a distinct response to tumor aggressiveness, white fiber diffusion tensor information and elasticity. In this atlas, we introduce a virtual GBM with a mechanical component coupled with a diffusion component. These two components are complementary, and can be tuned independently. Then, we tune the parameter set of our model with an MRI patient. We have compared simulated growth (initialized with the MRI patient) with observed growth six months later. The average and the odd ratio of image difference between observed and simulated images are computed. Displacements of reference points are compared to those simulated by the model. The results of our simulation have shown a good correlation with tumor growth, as observed on an MRI patient. Different tumor aggressiveness can also be simulated by tuning additional parameters. This work has demonstrated that modeling the complex behavior of brain tumors is feasible and will account for further validation of this new conceptual approach.
Physics in Medicine and Biology 03/2008; 53(4):879-93. · 2.83 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Preoperative magnetic resonance imaging (MRI), functional MRI, diffusion tensor MRI, magnetic resonance spectroscopy, and positron-emission tomographic scans may be aligned to intraoperative MRI to enhance visualization and navigation during image-guided neurosurgery. However, several effects (both machine- and patient-induced distortions) lead to significant geometric distortion of intraoperative MRI. Therefore, a precise alignment of these image modalities requires correction of the geometric distortion. We propose and evaluate a novel method to compensate for the geometric distortion of intraoperative 0.5-T MRI in image-guided neurosurgery.
In this initial pilot study, 11 neurosurgical procedures were prospectively enrolled. The scheme used to correct the geometric distortion is based on a nonrigid registration algorithm introduced by our group. This registration scheme uses image features to establish correspondence between images. It estimates a smooth geometric distortion compensation field by regularizing the displacements estimated at the correspondences. A patient-specific linear elastic material model is used to achieve the regularization. The geometry of intraoperative images (0.5 T) is changed so that the images match the preoperative MRI scans (3 T).
We compared the alignment between preoperative and intraoperative imaging using 1) only rigid registration without correction of the geometric distortion, and 2) rigid registration and compensation for the geometric distortion. We evaluated the success of the geometric distortion correction algorithm by measuring the Hausdorff distance between boundaries in the 3-T and 0.5-T MRIs after rigid registration alone and with the addition of geometric distortion correction of the 0.5-T MRI. Overall, the mean magnitude of the geometric distortion measured on the intraoperative images is 10.3 mm with a minimum of 2.91 mm and a maximum of 21.5 mm. The measured accuracy of the geometric distortion compensation algorithm is 1.93 mm. There is a statistically significant difference between the accuracy of the alignment of preoperative and intraoperative images, both with and without the correction of geometric distortion (P < 0.001).
The major contributions of this study are 1) identification of geometric distortion of intraoperative images relative to preoperative images, 2) measurement of the geometric distortion, 3) application of nonrigid registration to compensate for geometric distortion during neurosurgery, 4) measurement of residual distortion after geometric distortion correction, and 5) phantom study to quantify geometric distortion.
Neurosurgery 03/2008; 62(3 Suppl 1):209-15; discussion 215-6. · 2.79 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The emergence of new modalities such as Diffusion Tensor Imaging (DTI) is of great interest for the characterization and the temporal study of Multiple Sclerosis (MS). DTI indeed gives information on water diffusion within tissues and could therefore reveal alterations in white matter fibers before being visible in conventional MRI. However, recent studies generally rely on scalar measures derived from the tensors such as FA or MD instead of using the full tensor itself. Therefore, a certain amount of information is left unused. In this article, we present a framework to study the benefits of using the whole diffusion tensor information to detect statistically significant differences between each individual MS patient and a database of control subjects. This framework, based on the comparison of the MS patient DTI and a mean DTI atlas built from the control subjects, allows us to look for differences both in normally appearing white matter but also in and around the lesions of each patient. We present a study on a database of 11 MS patients, showing the ability of the DTI to detect not only significant differences on the lesions but also in regions around them, enabling an early detection of an extension of the MS disease.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 02/2008; 11(Pt 1):975-82.
-
Nikos Chrisochoides,
Andriy Fedorov,
Andriy Kot,
Neculai Archip,
Daniel Goldberg-Zimring,
Dan Kacher,
Stephen Whalen,
Ron Kikinis,
Ferenc Jolesz, Olivier Clatz,
Simon K. Warfield,
Peter M. Black,
Alexandra Golby
[show abstract]
[hide abstract]
ABSTRACT: In this paper we present our experience with an Image Guided Neurosurgery Grid-enabled Software Environment (IGNS-GSE) which
integrates real-time acquisition of intraoperative Magnetic Resonance Imaging (IMRI) with the preoperative MRI, fMRI, and
DT-MRI data. We describe our distributed implementation of a non-rigid image registration method which can be executed over
the Grid. Previously, non-rigid registration algorithms which use landmark tracking across the entire brain volume were considered
not practical because of the high computational demands. The IGNS-GSE, for the first time ever in clinical practice, alleviated
this restriction. We show that we can compute and present enhanced MR images to neurosurgeons during the tumor resection within
minutes after IMRI acquisition. For the last 12 months this software system is used routinely (on average once a month) for
clinical studies at Brigham and Women’s Hospital in Boston, MA. Based on the analysis of the registration results, we also
present future directions which will take advantage of the vast resources of the Grid to improve the accuracy of the method
in places of the brain where precision is critical for the neurosurgeons.
07/2007: pages 980-987;
-
Neculai Archip, Olivier Clatz,
Stephen Whalen,
Dan Kacher,
Andriy Fedorov,
Andriy Kot,
Nikos Chrisochoides,
Ferenc Jolesz,
Alexandra Golby,
Peter M Black,
Simon K Warfield
[show abstract]
[hide abstract]
ABSTRACT: The usefulness of neurosurgical navigation with current visualizations is seriously compromised by brain shift, which inevitably occurs during the course of the operation, significantly degrading the precise alignment between the pre-operative MR data and the intra-operative shape of the brain. Our objectives were (i) to evaluate the feasibility of non-rigid registration that compensates for the brain deformations within the time constraints imposed by neurosurgery, and (ii) to create augmented reality visualizations of critical structural and functional brain regions during neurosurgery using pre-operatively acquired fMRI and DT-MRI.
Eleven consecutive patients with supratentorial gliomas were included in our study. All underwent surgery at our intra-operative MR imaging-guided therapy facility and have tumors in eloquent brain areas (e.g. precentral gyrus and cortico-spinal tract). Functional MRI and DT-MRI, together with MPRAGE and T2w structural MRI were acquired at 3 T prior to surgery. SPGR and T2w images were acquired with a 0.5 T magnet during each procedure. Quantitative assessment of the alignment accuracy was carried out and compared with current state-of-the-art systems based only on rigid registration.
Alignment between pre-operative and intra-operative datasets was successfully carried out during surgery for all patients. Overall, the mean residual displacement remaining after non-rigid registration was 1.82 mm. There is a statistically significant improvement in alignment accuracy utilizing our non-rigid registration in comparison to the currently used technology (p<0.001).
We were able to achieve intra-operative rigid and non-rigid registration of (1) pre-operative structural MRI with intra-operative T1w MRI; (2) pre-operative fMRI with intra-operative T1w MRI, and (3) pre-operative DT-MRI with intra-operative T1w MRI. The registration algorithms as implemented were sufficiently robust and rapid to meet the hard real-time constraints of intra-operative surgical decision making. The validation experiments demonstrate that we can accurately compensate for the deformation of the brain and thus can construct an augmented reality visualization to aid the surgeon.
NeuroImage 05/2007; 35(2):609-24. · 5.89 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We propose a dynamic model of cerebrospinal fluid and intracranial pressure regulation. In this model, we investigate the coupling of biological parameters with a 3-D model, to improve the behavior of the brain in surgical simulators. The model was assessed by comparing the simulated ventricular enlargement with a patient case study of communicating hydrocephalus. In our model, cerebro-spinal fluid production-resorption system is coupled with a 3-D representation of the brain parenchyma. We introduce a new bi-phasic model of the brain (brain tissue and extracellular fluid) allowing for fluid exchange between the brain extracellular space and the venous system. The time evolution of ventricular pressure has been recorded on a symptomatic patient after closing the ventricular shunt. A finite element model has been built based on a computed tomography scan of this patient, and quantitative comparisons between experimental measures and simulated data are proposed.
IEEE Transactions on Biomedical Engineering 04/2007; 54(4):755-8. · 2.28 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Bridging the gap between clinical applications and mathematical models is one of the new challenges of medical image analysis. In this paper, we propose an efficient and accurate algorithm to solve anisotropic Eikonal equations, in order to link biological models using reaction-diffusion equations to clinical observations, such as medical images. The example application we use to demonstrate our methodology is tumor growth modeling. We simulate the motion of the tumor front visible in images and give preliminary results by solving the derived anisotropic Eikonal equation with the recursive fast marching algorithm.
Information processing in medical imaging: proceedings of the ... conference 02/2007; 20:687-99.
-
[show abstract]
[hide abstract]
ABSTRACT: In cancer treatment, understanding the aggressiveness of the tumor is essential in therapy planning and patient follow-up. In this article, we present a novel method for quantifying the speed of invasion of gliomas in white and grey matter from time series of magnetic resonance (MR) images. The proposed approach is based on mathematical tumor growth models using the reaction-diffusion formalism. The quantification process is formulated by an inverse problem and solved using anisotropic fast marching method yielding an efficient algorithm. It is tested on a few images to get a first proof of concept with promising new results.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 02/2007; 10(Pt 1):549-56.
-
ERCIM News. 01/2007; 2007.
-
Nikos Chrisochoides,
Andriy Fedorov,
Andriy Kot,
Neculai Archip,
Daniel Goldberg-Zimring,
Daniel F. Kacher,
Stephen Whalen,
Ron Kikinis,
Ferenc A. Jolesz, Olivier Clatz,
Simon K. Warfield,
Peter M. Black,
Alexandra Golby
Computational Science - ICCS 2007, 7th International Conference Beijing, China, May 27-30, 2007, Proceedings, Part I; 01/2007
