3D statistical shape models of patella for sex classification.

This paper proposes a new sex classification method from patellae using a novel automated feature extraction technique. A dataset of 228 patellae (95 females and 133 males) was collected and CT scanned. After the CT data was segmented, a set of features was automatically extracted, normalized, and ranked.

ASIC Design for Wireless Surgical MEMS Device and Instrumentation.

There is an increasing demand on computerized surgical instrumentation and implants that can acquire intra-operative or in-vivo data for surgeons and engineers. The sensory system is gaining complexity in order to obtain more accurate measurements. Although many off-the-shelf components and chips exist, multiple components are often required to achieve the desired function.

Biocompatible MEMS electrode array for determination of three-dimensional strain.

Sensor arrays for the measurement of the load condition of polyethylene spacers in the total knee arthroplasty (TKA) prosthesis have been developed. Arrays of capacitive sensors are used to determine the three-dimensional strain within the polyethylene prosthesis component. Data from these sensors can be used to give researchers better understanding of component motion, loading, and wear phenomena for a large range of activities.

Constrained RLS algorithm for narrow band interference rejection from EEG signal during CES.

The filtering of signals in the presence of a narrow-band interference noise is a common problem in biomedical signal processing. A double adaptive band-rejection filter is applied to an electroencephalographic (EEG) signal corrupted by a double narrow-band white Gaussian noise during cranial electrical stimulation (CES). The multiple adaptive IIR digital band-rejection filters are designed by the pole-zero placement on the unit circle method using a unique second-order filter structure.

Genetic evolution of radial basis function coverage using orthogonal niches.

A well-performing set of radial basis functions (RBFs) can emerge from genetic competition among individual RBFs. Genetic selection of the individual RBFs is based on credit sharing which localizes competition within orthogonal niches. These orthogonal niches are derived using singular value decomposition and are used to apportion credit for the overall performance of the RBF network among individual nonorthogonal RBFs.

Circular-Mellin features for texture segmentation.

Texture is an important cue in region-based segmentation of images. We provide an insight into the development of a new set of distortion-invariant texture operators. These "circular-Mellin" operators are invariant to both scale and orientation of the target and represent the spectral decomposition of the image scene in the polar-log coordinate system.

A neural network filter to detect small targets in high clutter backgrounds.

The detection of objects in high-resolution aerial imagery has proven to be a difficult task. In the authors' application, the amount of image clutter is extremely high. Under these conditions, detection based on low-level image cues tends to perform poorly.

An approach to automated detection of tumors in mammograms.

An automated system for detecting and classifying particular types of tumors in digitized mammograms is described. The analysis of mammograms is performed in two stages. First, the system identifies pixel groupings that may correspond to tumors.