Nelson G. Durdle

A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography

A support vector machines (SVM) classifier was used to assess the severity of idiopathic scoliosis (IS) based on surface topographic images of human backs. Scoliosis is a condition that involves abnormal lateral curvature and rotation of the spine that usually causes noticeable trunk deformities. Based on the hypothesis that combining surface topography and clinical data using a SVM would produce better assessment results, we conducted a study using a dataset of 111 IS patients. Twelve surface and clinical indicators were obtained for each patient. The result of testing on the dataset showed that the system achieved 69-85% accuracy in testing. It outperformed a linear discriminant function classifier and a decision tree classifier on the dataset

Sobel edge detection processor for a real-time volume rendering system

This paper describes a novel fast and low-power Sobel edge detection processor targeted for image processing and volume rendering applications. The Sobel processor was built as a part of the real-time shear-warp factorization volume rendering system to compute a gradient. Sobel operator processor was designed and implemented in 0.18 /spl mu/m CMOS technology. Optimizations made at the mathematical model led to a simple regular architecture. High speed and low power consumption were achieved due to implementation of pipelining and parallelism at the components level. Employing the non-full swing CPL to design the Sobel processor sub-components reduced the power-delay product up to 40%. Simulation results showed that processor achieved the worst-case delay time of 4.61 ns and dissipates an average of 8.24 mW at 1.8 V and 200 MHz.

Low-power low-voltage 4-2 compressors for VLSI applications

This paper presents new 4-2 compressor architectures, a full-swing bipolar double pass-transistor 4-2 compressor, a new full-swing BiNMOS 4-2 compressor, a reduced-swing bipolar double pass-transistor 4-2 compressor and a reduced-swing double pass-transistor BiNMOS 4-2 compressor, that outperform a standard CMOS 4-2 compressor up to 3 times in power-efficiency at supply voltages 1.5 V-3 V. The bipolar double pass-transistor 4-2 compressor is more power-efficient than a standard CMOS 4-2 compressor even at a fanout of 1. All remaining proposed 4-2 compressors have a lower crossover capacitance with a standard CMOS 4-2 compressor than previously reported low-power 4-2 compressors. Circuits were designed and fabricated in 0.8 /spl mu/m BiCMOS technology.

The effect of pulsed electromagnetic fields on chondrocyte morphology

Osteoarthritis is a debilitating joint disease where the articular cartilage surface degrades and is unable to repair itself through natural processes. Chondrocytes reside within the cartilage matrix and maintain its structure. We conducted in vitro experiments to investigate the morphological response of cultured human chondrocytes under different pulsed electromagnetic field (PEMF) conditions. In the control experiments, cultured chondrocytes attached to the bottom of a culture dish typically displayed either a stellate or spindle morphology with extended processes. Experimental chondrocyte cultures were placed in a Helmholtz coil to which a ramp waveform was applied. Exposure to PEMFs caused the chondrocytes to retract their processes, becoming spherical in shape. This change in morphology followed a progression from stellate to spindle to spherical. These morphological changes were reflected in an average reduction of 30% in the surface contact area of the chondrocytes to the culture dish. Understanding the mechanisms by which PEMFs affect the morphology of chondrocytes will help lead to new treatments for osteoarthritis.

Classifying torso deformity in scoliosis using orthogonal maps of the torso

Analysis of three-dimensional (3D) images of human torsos for torso deformities such as scoliosis requires classifying torso distortion. Assessing torso distortion from 3D images is not trivial as actual torsos are non-symmetric and show an outstanding range of variations leading to high classification errors. As the degree of spinal deformity (and classification of torso shape) influences scoliosis treatment options, the development of more accurate classification procedures is desirable. This paper presents a technique for assessing torso shape and classifying scoliosis into mild, moderate and severe categories using two indices, ‘twist’ and ‘bend’, obtained from orthogonally transformed images of the complete torso surface called orthogonal maps. Four transforms (axial line, unfolded cylinder, enclosing cylinder and subtracting cylinder) were used. Blind tests on 361 computer models with known deformation parameter values show 100% classification accuracy. Tests on eight volunteers without scoliosis validated the system and tests on 22 torso images of volunteers with scoliosis showed up to 95.5% classification accuracy. In addition to classifying scoliosis, orthogonal maps present the entire torso in one view and are viable for use in scoliosis clinics for monitoring the progression of scoliosis.

A low power accelerometer used to improve posture

A monitoring system for training people to improve posture has been developed. The prototype system consists of one accelerometer, a low-powered 16-bit microcontroller, RAM, real time clock and battery. This prototype device was used to investigate its feasibility of using accelerometers to monitor human posture. A subject who had kyphosis (round back) for many years wore the system for two days. The system provided feedback to the subject only on the second day. By comparing the data collected on both days, we found that the system was able to detect postural changes and alert the subject to improve his posture.

Characterizing Torso Shape Deformity in Scoliosis Using Structured Splines Models

This paper describes a method of characterizing the torso shape deformity associated with scoliosis by both its type and severity. This problem is challenging because regular human torsos show an astounding range of variations that is only compounded by scoliosis, and it is difficult to isolate natural shape variations from those caused by scoliosis. Torso shape characterization is important in the clinical management of scoliosis because torso aesthetics is a key concern that influences a patients quality of life. Our method involves modeling 3-D torso range images into structured sequences of 3-D spline curves stacked along the spine. We obtain local shape measures from points of maximal curvature (dominant points) along each torso cross section by evaluating the relative symmetry of the spline curve at that cross section. This results in a scalable characterization scheme for torso deformity type and a measure of torso deformity severity. We assess the accuracy and precision of this shape characterization scheme, and its relationship to the actual deformities present in the underlying spine.

A wearable computer for physiotherapeutic scoliosis treatment

A posture monitoring system for the treatment of idiopathic scoliosis using electromagnetic and accelerometer technology is discussed. Distributed processors are used to allow parallel execution of data collection. The system is carried by the patient and provides feedback to allow correction of posture during daily activities.

Medical image registration in computational intelligence framework: a review

The purpose of this paper is to provide a review of computational intelligence techniques and their application to medical image registration. Each computational intelligence technique is summarised and its utility to medical image registration is analysed. Genetic computation provides an efficient search methodology. Neural networks can learn complex nonlinear input-output relationships. Fuzzy sets use symbols to summarise the domain knowledge allowing them to handle inconsistent or noisy data and to produce understandable results. Rough sets offer tools to handle different types of uncertainty in data. Some challenges to medical image registration and the application of computational intelligence technologies are indicated.

A low-power posture measurement system for the treatment of scoliosis

A battery-powered electromagnetic (EM) system has been developed to measure topographical features of the trunks of patients with scoliosis. The system includes an EM measurement system and a data acquisition system. The system resolution and accuracy are 0.25 cm in the range of 15-30 cm. The entire system can be carried by scoliotic patients during daily activities. The dimensions of the system are 10 cm/spl times/14 cm/spl times/4 cm and its weight is 100 g. A patients posture can be evaluated in real time so that appropriate feedback can be provided to correct his/her posture.