John S. DaPonte

Classification of ultrasonic image texture by statistical discriminant analysis and neural networks

In this paper the ability of two common statistical discriminant analysis procedures are compared with two commercial neural network software packages. The major objective of this study was to determine which of the procedures could best discriminate between normal and abnormal ultrasonic liver textures. The same set of features were input into both statistical discriminant analysis procedures and both neural network models. Preliminary results have found the restricted Coulomb Energy (RCE) neural network model to have a testing accuracy of 90.6% which is approximately 10% better than any of the other techniques investigated.

Enhancement of chest radiographs with gradient operators

Reference is made to the Sobel and Roberts gradient operators used to enhance image edges. Overall, the Sobel operator was found to be superior to the Roberts operator in edge enhancement. A theoretical explanation for the superior performance of the Sobel operator was developed based on the concept of analyzing the x and y Sobel masks as linear filters. By applying pill-box, Gaussian, or median filtering prior to applying a gradient operator, noise was reduced. The pill-box and Gaussian filters were more computationally efficient than the median filter with approximately equal effectiveness in noise reduction.

An evolutionary system for recognition and tracking of synoptic-scale storm systems

Abstract An evolutionary system was developed for generation of complete tracks of northern midlatitude synoptic-scale storm systems based on optical flow and cloud motion analyses of global satellite-based datasets produced by the International Satellite Cloud Climatology Project (ISCCP). The tracking results were compared with low sea level pressure anomaly (SLPA) tracks obtained from the NASA Goddard Institute for Space Studies (GISS). The SLPA tracks were produced at GISS by analysis of meteorological, ground-based National Center for Environmental Prediction (NCEP) datasets. Results from the evolutionary system were also compared with results from using (a) the k -nearest neighbor rule ( k -NN) and (b) self-organizing maps (SOM) to determine correspondences between consecutive locations within a track. The consistency of our evolutionary storm tracking results with the behavior of the low sea level pressure anomaly tracks, the ability of our evolutionary system to generate and evaluate complete tracks, and the close comparison between the results obtained by the evolutionary, k -NN, and SOM analyses of the ISCCP-derived datasets at tracking steps in which proximity or optical flow information sufficed to determine movement, demonstrate the applicability and the potential of evolutionary systems for tracking midlatitude storm systems through low-resolution ISCCP cloud product datasets.

Selective detection of linear features in geological remote sensing data

One of the major problems in the development of computer-assisted systems for geologic mapping is how to individualize the system to meet user needs. Ideally, the system should be responsive to specifications of desired types of output structures. Also, the system should be able to incorporate the users knowledge of regional characteristics into the feature extraction/selection and classification components. Automatic techniques for classification of remote sensing data typically require relatively large, labeled training sets which are well- organized with respect to the desired mapping between input and output patterns. The present paper focuses on the feature extraction/selection component of the system. Kohonen self- organizing feature maps in conjunction with image processing procedures for linear feature extraction are used for explorative data analysis, feature selection, and construction of exemplar patterns. The results of training Kohonen feature maps with different pattern sets and different feature combinations provide insight into the nature of pattern relationships which enables the user to develop sets of positive and negative training patterns for the classification component.

Comparison of thresholding techniques on nanoparticle images

Thresholding is an image processing procedure used to convert an image consisting of gray level pixels into a black and white binary image. One application of thresholding is particle analysis. Once foreground objects are separated from the background, a quantitative analysis that characterizes the number, size and shape of particles is obtained which can then be used to evaluate a series of nanoparticle samples. Numerous thresholding techniques exist differing primarily in how they deal with variations in noise, illumination and contrast. In this paper, several popular thresholding algorithms are qualitatively and quantitatively evaluated on transmission electron microscopy (TEM) and atomic force microscopy (AFM) images. Initially, six thresholding algorithms were investigated: Otsu, Riddler-Calvard, Kittler, Entropy, Tsai and Maximum Likelihood. The Riddler-Calvard algorithm was not included in the quantitative analysis because it did not produce acceptable qualitative results for the images in the series. Two quantitative measures were used to evaluate these algorithms. One is based on comparing object area the other on diameter before and after thresholding. For AFM images the Kittler algorithm yielded the best results followed by the Entropy and Maximum Likelihood techniques. The Tsai algorithm yielded the top results for TEM images followed by the Entropy and Kittler methods.

Unsupervised classification techniques for determination of storm region correspondences

The objective of this study is to compare statistical and unsupervised neural network techniques for determination of correspondences between storm system regions extracted from sequences of satellite images. Analysis was applied to the International Satellite Cloud Climatology Project (ISCCP) low resolution D1 database for selected storm systems during the period April 5 - 9, 1989. Cloud top pressure was used to delineate regions of interest and cloud optical thickness combined with spatial location was used to track regions throughout a given time sequence. The ability of the k-nearest neighbor classifier and of self-organizing maps to determine correspondences between storm regions was assessed. The two techniques generally yielded similar associations between regions of interest throughout the time sequence. Differences in final tracking results between the two techniques occurred primarily as a result of differences in the collections of points from a region in a time step t2 that corresponded to a region in an earlier time step t1. The tracking results were also compared to the results obtained at the NASA Goddard Institute for Space Studies using sea level pressure data from the National Meteorological Center (NMC). For the storm systems investigated in this study, the storm tracks exhibited the same general tracking behavior with expected variations between cloud system storm centers and low sea level pressure centers.

Application of evolutionary techniques to temporal classification of cloud systems using satellite imagery

The objective of this research is to automate the classification of the temporal behavior of storm cloud systems based on measurements derived from consecutive satellite images. The motivation behind this study is to develop improved descriptions of cloud dynamics which can be used in general circulation models for prediction of global climate change. Analysis was applied to the International Satellite Cloud Climatology Project (ISCCP) low resolution cloud top pressure database for the first six days in April 1989. A total of 296 midlatitude storm cloud components were tracked between consecutive 3-hour time frames. For each pair of components, temporal correspondence events were classified as either (1) direct, (2) merge, (3) split, or (4) reject. The reject class, which was used primarily to categorize pairs of unrelated systems, included storm cloud system dissipation and creation as well. Statistical, neural network, and evolutionary techniques were developed for finding solutions to the storm cloud correspondence problem. Evolutionary techniques applied to the problem consisted of (1) a constraint-handling hybrid evolutionary technique and (2) a genetic local search algorithm. The results demonstrate the potential of evolutionary techniques to yield meteorologically feasible solutions, given appropriate constraints, to the two- frame storm tracking problem.

Ultrasonic image texture classification using Markov random field models

Over the past several years we have been interested in the supervised classification of ultrasonic images of the liver based on quantitative texture features. Our most recent efforts are concerned with the inclusion of features computed from Markov random fields. After adding four such features to our existing model containing 17 features, we employed stepwise discriminant analysis to identify the features that could best discriminate among 184 previously classified normal and abnormal ultrasonic images. Three of the four features derived from Markov random field models were identified by stepwise discriminant analysis as being good discrimination along with 6 existing features. From these results we constructed a backpropagation neural network with an input layer consisting of 9 nodes. We found that this new model yielded slightly better results when compared to earlier models. Our most recent results yielded a sensitivity of 81%, a specificity of 77% and an overall accuracy of 79%.

Visualizing bone porosities using a tabletop scanning electron microscope

Pores are naturally occurring entities in bone. Changes in pore size and number are often associated with diseases such as Osteoporosis and even microgravity during spaceflight. Studying bone perforations may yield great insight into bones material properties, including bone density and may contribute to identifying therapies to halt or potentially reverse bone loss. Current technologies used in this field include nuclear magnetic resonance, micro-computed tomography and the field emission scanning electron microscope (FE-SEM) 2, 5. However, limitations in each method limit further advancement. The objective of this study was to assess the effectiveness of using a new generation of analytical instruments, the TM-1000 tabletop, SEM with back-scatter electron (BSE) detector, to analyze cortical bone porosities. Hind limb unloaded and age-based controlled mouse femurs were extracted and tested in vitro for changes in pores on the periosteal surface. An important advantage of using the tabletop is the simplified sample preparation that excludes extra coatings, dehydration and fixation steps that are otherwise required for conventional SEM. For quantitative data, pores were treated as particles in order to use an analyze particles feature in the NIH ImageJ software. Several image-processing techniques for background smoothing, thresholding and filtering were employed to produce a binary image suitable for particle analysis. It was hypothesized that the unloaded bones would show an increase in pore area, as the lack of mechanical loading would affect bone-remodeling processes taking place in and around pores. Preliminary results suggest only a slight different in frequency but not in size of pores between unloaded and control femurs.

Computer assisted analysis of microscopy images

The use of Transmission Electron Microscopy (TEM) to characterize the microstructure of a material continues to grow in importance as technological advancements become increasingly more dependent on nanotechnology1 . Since nanoparticle properties such as size (diameter) and size distribution are often important in determining potential applications, a particle analysis is often performed on TEM images. Traditionally done manually, this has the potential to be labor intensive, time consuming, and subjective2. To resolve these issues, automated particle analysis routines are becoming more widely accepted within the community3. When using such programs, it is important to compare their performance, in terms of functionality and cost. The primary goal of this study was to apply one such software package, ImageJ to grayscale TEM images of nanoparticles with known size. A secondary goal was to compare this popular open-source general purpose image processing program to two commercial software packages. After a brief investigation of performance and price, ImageJ was identified as the software best suited for the particle analysis conducted in the study. While many ImageJ functions were used, the ability to break agglomerations that occur in specimen preparation into separate particles using a watershed algorithm was particularly helpful4.