Eric Grimson

Mutual information in coupled multi-shape model for medical image segmentation

This paper presents extensions which improve the performance of the shape-based deformable active contour model presented earlier in [IEEE Conf. Comput. Vision Pattern Recog. 1 (2001) 463] for medical image segmentation. In contrast to that previous work, the segmentation framework that we present in this paper allows multiple shapes to be segmented simultaneously in a seamless fashion. To achieve this, multiple signed distance functions are employed as the implicit representations of the multiple shape classes within the image. A parametric model for this new representation is derived by applying principal component analysis to the collection of these multiple signed distance functions. By deriving a parametric model in this manner, we obtain a coupling between the multiple shapes within the image and hence effectively capture the co-variations among the different shapes. The parameters of the multi-shape model are then calculated to minimize a single mutual information-based cost criterion for image segmentation. The use of a single cost criterion further enhances the coupling between the multiple shapes as the deformation of any given shape depends, at all times, upon every other shape, regardless of their proximity. We found that this resulting algorithm is able to effectively utilize the co-dependencies among the different shapes to aid in the segmentation process. It is able to capture a wide range of shape variability despite being a parametric shape-model. And finally, the algorithm is robust to large amounts of additive noise. We demonstrate the utility of this segmentation framework by applying it to a medical application: the segmentation of the prostate gland, the rectum, and the internal obturator muscles for MR-guided prostate brachytherapy.

Transcranial magnetic stimulation coregistered with MRI: a comparison of a guided versus blind stimulation technique and its effect on evoked compound muscle action potentials

INTRODUCTION AND METHODS Compound muscle action potentials (CMAPs) elicited by transcranial magnetic stimulation (TMS) are characterized by enormous variability, even when attempts are made to stimulate the same scalp location. This report describes the results of a comparison of the spatial errors in coil placement and resulting CMAP characteristics using a guided and blind TMS stimulation technique. The former uses a coregistration system, which displays the intersection of the peak TMS induced electric field with the cortical surface. The latter consists of the conventional placement of the TMS coil on the optimal scalp position for activation of the first dorsal interossei (FDI) muscle. RESULTS Guided stimulation resulted in significantly improved spatial precision for exciting the corticospinal projection to the FDI compared to blind stimulation. This improved precision of coil placement was associated with a significantly increased probability of eliciting FDI responses. Although these responses tended to have larger amplitudes and areas, the coefficient of variation between guided and blind stimulation induced CMAPs did not significantly differ. CONCLUSION The results of this study demonstrate that guided stimulation improves the ability to precisely revisit previously stimulated cortical loci as well as increasing the probability of eliciting TMS induced CMAPs. Response variability, however, is due to factors other than coil placement.

Volumetric Object Modeling for Surgical Simulation

Surgical simulation has many applications in medical education, surgical training, surgical planning and intra-operative assistance. However, extending current surface-based computer graphics methods to model phenomena such as the deformation, cutting, tearing or repairing of soft tissues poses significant challenges for real-time interactions. This paper discusses the use of volumetric methods for modeling complex anatomy and tissue interactions. New techniques are introduced that use volumetric methods for modeling soft-tissue deformation and tissue cutting at interactive rates. An initial prototype for simulating arthroscopic knee surgery is described which uses volumetric models of the knee derived from 3-D magnetic resonance imaging, visual feedback via real-time volume and polygon rendering, and haptic feedback provided by a force-feedback device.

Multi-class object tracking algorithm that handles fragmentation and grouping

We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several blobs) and grouping (multiple objects may appear as a single blob). We use foreground blobs obtained by background subtraction from a stationary camera as measurements. The main challenge is to associate blob measurements with objects, given the fragment-object-group ambiguity when the number of objects is variable and unknown, and object-class-specific models are not available. We first track foreground blobs till they merge or split. We then build an inference graph representing merge-split relations between the tracked blobs. Using this graph and a generic object model based on spatial connectedness and coherent motion, we label the tracked blobs as whole objects, fragments of objects or groups of interacting objects. The outputs of our algorithm are entire tracks of objects, which may include corresponding tracks from groups during interactions. Experimental results on multiple video sequences are shown.

Recovering Non-overlapping Network Topology Using Far-field Vehicle Tracking Data

This paper presents a weighted statistical method to learn the environments topology using a large amount of far field vehicle tracking data collected by multiple, stationary non-overlapping cameras. First, an appearance model is constructed by the combination of normalized color and overall model size to measure the moving objects appearance similarity across the non-overlapping views. Then based on the similarity in appearance, weighted votes are used to learn the temporally correlating information and hence to estimate the mutual information. By exploiting the statistical spatio-temporal information, our method can automatically learn the possible links between disjoint views and recover the topology of the network. The effectiveness of the proposed method is demonstrated by experimental results both on simulated and real video surveillance data

Three-Dimensional Reconstruction and Surgical Navigation in Pediatric Epilepsy Surgery

We have used MRI-based three-dimensional (3D) reconstruction and a real-time, frameless, stereotactic navigation device to facilitate the removal of seizure foci in children suffering from intractable epilepsy. Using this system, the location of subdural grid and strip electrodes is recorded on the 3D model to facilitate focus localization and resection. Ten operations were performed, including 2 girls and 8 boys ranging in age from 3 to 17, during which 3D reconstruction and surgical instrument tracking navigation was used. In all the cases, the patients tolerated the procedure well and showed no postoperative neurological deficits. We believe this to be a valuable tool for a complete and safe resection of seizure foci, thereby reducing the incidence of postoperative neurological deficits and significantly improving the overall quality of life of the patients.

Knowledge-Based Segmentation of Medical Images

Knowledge-based medical image segmentation provides applicationspecific context by constructing prior models and incorporating them into the segmentation process. In this chapter, we present recent work that integrates intensity, local curvature, and global shape information into level set based segmentation of medical images. The object intensity distribution is modeled as a function of signed distance from the object boundary, which fits naturally into the level set framework. Curvature profiles act as boundary regularization terms specific to the shape being extracted, as opposed to uniformly penalizing high curvature. We describe a representation for deformable shapes and define a probability distribution over the variances of a set of training shapes. The segmentation process embeds an initial curve as the zero level set of a higher dimensional surface, and evolves the surface such that the zero level set converges on the boundary of the object to be segmented. At each step of the surface evolution, we estimate the pose and shape of the object in the image, based on the prior shape information and the image information. We then evolve the surface globally, towards the estimate, and locally, based on image information and curvature. Results are demonstrated on magnetic resonance (MR) and computed tomography (CT) imagery.

Doctoral program rankings for U.S. computing programs: the national research council strikes out

A proposal for improving doctoral program ranking strategy.

Three-Dimensional Reconstruction for Cortical Surgery: The Brigham and Women's Hospital Experience

Abstract: This article describes the use of 3D reconstruction for preoperative surgical planning and intraoperative navigation for cortical surgery. Before each surgical procedure, a detailed structural and functional model is reconstructed from magnetic resonance imaging scans and functional mapping modalities. These models, when integrated with direct intraoperative cortical mapping, create an integral 3D map of the cortical surface surrounding the lesion and its relation to the whole brain anatomy. A navigation system is coupled to the surgical field using skin-to-skin registration involving infrared light-emitting diode instrument tracking. This allows accurate guidance in the mapped 3D space. These detailed, patient-specific 3D maps of the brain are used as a method of accurately assessing the surgical approach, determining the potential neurologic risks, and navigating within the brain. One hundred fifty-five patients have been treated with this system for either preoperative planning or surgical navigation.

Excision of Cortical Dysplasia in the Language Area with Use of a Surgical Navigator: A Case Report

Summary: Purpose: We have developed an intraoperative optical tracking‐based navigational system that allows localization in the operative space. Using three‐dimensional reconstruction, this system has provided precise spatial information for intraoperative cortical mapping in patients with intractable epilepsy in whom the lesion lies close to eloquent cortex.