IMU Sensor Fusion Algorithm for Monitoring Knee Kinematics in ACL Reconstructed Patients.

In this paper we propose a sensor embedded knee brace to monitor knee flexion and extension and other lower limb joint kinematics after anterior cruciate ligament (ACL) injury. The system can be easily attached to a standard post-surgical brace and uses a novel sensor fusion algorithm that does not require calibration. The wearable system and the sensor fusion algorithm were validated for various physical therapy exercises against a validated motion capture system. The proposed sensor fusion algorithm demonstrated significantly lower root-mean-square error (RMSE) than the benchmark Kalman filtering algorithm and excellent correlation coefficients (CCC and ICC). The demonstrated error for most exercises was lower than other devices in the literature. The quantitative measures obtained by this system can be used to obtain longitudinal range-of-motion and functional biomarkers. These biomarkers can be used to improve patient outcomes through the early detection of at-risk patients, tracking patient function outside of the clinic, and the identification of relationships between patient presentation, intervention, and outcomes.

Teleimmersion for the doctor's office.

The purpose of our research is the development of a new technology, teleimmersion, which will make possible 3D visual communication between people distributed over the globe. We are putting together a low-end, PC-based, affordable hardware system, and are developing the software for a teleimmersion node (T-node). The software is based on accurate polynocular stereo. We will describe a testbed for the system, show results, and discuss challenges for future research and implementation.

Elastically deforming 3D atlas to match anatomical brain images.

To evaluate our system for elastically deforming a three-dimensional atlas to match anatomical brain images, six deformed versions of an atlas were generated. The deformed atlases were created by elastically mapping an anatomical brain atlas onto different MR brain image volumes. The mapping matches the edges of the ventricles and the surface of the brain; the resultant deformations are propagated through the atlas volume, deforming the remainder of the structures in the process. The atlas was then elastically matched to its deformed versions. The accuracy of the resultant matches was evaluated by determining the correspondence of 32 cortical and subcortical structures. The system on average matched the centroid of a structure to within 1 mm of its true position and fit a structure to within 11% of its true volume. The overlap between the matched and true structures, defined by the ratio between the volume of their intersection and the volume of their union, averaged 66%. When the gray-white interface was included for matching, the mean overlap improved to 78%; each structure was matched to within 0.6 mm of its true position and fit to within 6% of its true volume. Preliminary studies were also made to determine the effect of the compliance of the atlas on the resultant match.

Underestimation of visual texture slant by human observers: a model.

The perspective image of an obliquely inclined textured surface exhibits shape and density distortions of texture elements which allow a human observer to estimate the inclination angle of the surface. However, it has been known since the work of Gibson (1950) that, in the absence of other cues, humans tend to underestimate the slant angle of the surface, particularly when the texture is perceived as being "irregular." The perspective distortions which affect texture elements also shift the projected spatial frequencies of the texture in systematic ways. Using a suitable local spectral filter to measure these frequency gradients, the inclination angle of the surface may be estimated. A computational model has been developed which performs this task using distributions of outputs from filters found to be a good description of simple-cell receptive fields. However, for "irregular" textures the filter output distributions are more like those of "regular" textures at shallower angles of slant, leading the computational algorithm to underestimate the slant angle. This behavioral similarity between human and algorithm suggests the possibility that a similar visual computation is performed in cortex.

Evaluation of elastic matching system for anatomic (CT, MR) and functional (PET) cerebral images.

To evaluate the performance of our elastic matching system, we have created a digitized atlas from the brain of a normal young man, using 135 myelin-stained sections at 700 microns spacing. Software was written to enter and edit regional anatomic contours, which were stacked and aligned to create a three-dimensional atlas. We then evaluated the matching system by comparing computer generated contours with expert defined contours for several subcortical structures, based on CT scans from six neurologically normal patients. The error in positioning, as defined by the distance between the centers of gravity, averaged 4.2 mm for the computer and 1.7 mm for the worst expert's reading, with the computer drawn region frequently inscribed within that of the expert. Comparison was also made for each structure by determining the volume of overlap and the volumes not overlapping. On average, the computer's agreement with the experts was approximately 20% less than the agreement among the experts. This was a preliminary test of the system using only subcortical structures. The results are promising, and techniques are being implemented to overcome the current deficiencies.

The Diagnostic Imaging Information Center.

The authors have developed a Diagnostic Radiology Imaging Information Center, in which the physician can see at a glance, with minimum expenditure of time and maximum emphasis on relevance, a summary of the patient's studies and procedures done in the x-ray department.

Visual and conceptual hierarchy: a paradigm for studies of automated generation of recognition strategies.

The purpose of this correspondence is to show the design considerations in the choice of mechanisms when a flexible querysystem of visual scenes is being constructed. More concretely, the issues are: ¿ flexibility in adding new information to the knowledge base; ¿ power of inferencing; ¿ avoiding unnecessary generation of hypotheses where a great deal of image processing has to be perfected in order to test it; ¿ having the power of automatic generation of recognition strategies.

A computerized system for the elastic matching of deformed radiographic images to idealized atlas images.

A system of computer programs is described which, for the first time, is able to use computerized tomographic data to automatically locate, measure, and describe anatomical structures of interest with accuracy and consistency. Input to the system consists of any digitized radiographic data. Computer assisted tomographic (CAT) scans of the head were used in this first implementation. Using these data and a predefined atlas picture representing an idealized view of the average normal image, an individualized atlas was created. From the individualized atlas, structure size, density, location displacement, and distortion may be calculated. The individualized atlas created using high resolution data, such as the CAT scan, may then be directly superimposed on pictures obtained using lower resolution modalities, such as positron emission tomographic scan images. This allows the precise location of structures poorly visualized by the secondary imaging modality. This system is capable of using either two- or three-dimensional data.

Model-driven visualization of coronary arteries.

In a joint project between the Department of Computer and Information Sciences and the Department of Radiology, we are applying techniques of artificial intelligence to improve clinical performance in coronary arteries. Specifically, we are investigating how images from intravenous digital subtraction angiography (DSA) can be enhanced so that their efficacy for lesion detection and quantitation becomes comparable with that of the more dangerous procedure of selective coronary arteriography. The enhancement techniques (which include algorithms for 3-dimensional vessel detection, reconstruction and display, as well as for accurate lumen-size estimation) are based on models of (i) the 3-dimensional topological structure of the coronary arterial tree, (ii) myocardial dynamics, and (iii) the X-ray imaging process involved in producing digital subtraction angiograms. The evaluation of these model-driven visualization techniques is done by the standard psychophysical method of Receiver Operating Characteristic (ROC) analysis applied to observer performance tests on images from an animal coronary atherosclerosis model.

Packing volumes by spheres.

In this note we present an algorithm for packing spheres in an arbitrary shaped volume. This algorithm is similar to Blum's transform in that it fits spheres into a volume, but it is different in that it fits only tangential spheres, and thereby the data reduction is larger than by Blum's transform. The spheres are of variable radii, which enables us to achieve a hierarchy of intrinsic volume properties, i.e., from gross to more detailed. The result of this algorithm is a graph where the nodes are the centers of spheres and the arcs are the connections between two tangent spheres. Analysis of computational complexity and the time and error considerations are provided.

Technical note. Computer assisted analysis of tomographic images of the brain.

A computer system for the analysis of computed tomography and positron emission tomography scans of the brain is described. The system, called TOAP (Tomographic Overlay and Analysis Program), permits the registration of user specified slices from a digital brain atlas with the tomographic images. Regions of interest can then be defined with respect to the atlas. The system thus affords an objective and reproducible means for the analysis of tomographic images.