Jeffrey L. Solka

COMPARATIVE EVALUATION OF PATTERN RECOGNITION TECHNIQUES FOR DETECTION OF MICROCALCIFICATIONS IN MAMMOGRAPHY

Computer-assisted detection of microcalcifications in mammographic images will likely require a multistage algorithm that includes segmentation of possible microcalcifications, pattern recognition techniques to classify the segmented objects, a method to determine if a cluster of calcifications exists, and possibly a method to determine the probability of malignancy. This paper focuses on the first three of these stages, and especially on the classification of segmented local bright spots as either calcification or noncalcification. Seven classifiers (linear and quadratic classifiers, binary decision trees, a standard backpropagation network, 2 dynamic neural networks, and a K-nearest neighbor) are compared. In addition, a postprocessing step is performed on objects identified as calcifications by the classifiers to determine if any clusters of microcalcifications exist. A database of digitized film mammograms is used for training and testing. Detection accuracy of individual and clustered microcalcificat...

The application of fractal analysis to mammographic tissue classification

As a first step in determining the efficacy of using computers to assist in diagnosis of medical images, an investigation has been conducted which utilizes the patterns, or textures, in the images. To be of value, any computer scheme must be able to recognize and differentiate the various patterns. An obvious example of this in mammography is the recognition of tumorous tissue and non-malignant abnormal tissue from normal parenchymal tissue. We have developed a pattern recognition technique which uses features derived from the fractal nature of the image. Further, we are able to develop mathematical models which can be used to differentiate and classify the many tissue types. Based on a limited number of cases of digitized mammograms, our computer algorithms have been able to distinguish tumorous from healthy tissue and to distinguish among various parenchymal tissue patterns. These preliminary results indicate that discrimination based on the fractal nature of images may well represent a viable approach to utilizing computers to assist in diagnosis.

Identification of man-made regions in unmanned aerial vehicle imagery and videos

Details work in our group on the use of low-level features for the identification of man-made regions in unmanned aerial vehicle (UAV) imagery. The feature sets that we have examined include classical statistical features such as the coefficient of variation in a window about a pixel, locally computed fractal dimension, and fractal dimension computed in the presence of wavelet boundaries. We discuss these techniques of feature extraction along with our approach to the classification of the features. Our classification work has focused on the use of a semiparametric probability density estimation technique. In addition, we present classification results for region of interest identification based on a set of test images from an UAV test flight.

Class cover catch digraphs for latent class discovery in gene expression monitoring by DNA microarrays

The purpose of this article is to introduce a data visualization technique for class cover catch digraphs which allows for the discovery of latent subclasses. We illustrate the technique via a pedagogical example and an application to data sets from artificial nose chemical sensing and gene expression monitoring by DNA microarrays. Of particular interest is the discovery of latent subclasses representing chemical concentration in the artificial nose data and two subtypes of acute lymphoblastic leukemia in the gene expression data and the associated conjectures pertaining to the geometry of these subclasses in their respective high-dimensional observation spaces.

Fast computation of optimal paths using a parallel Dijkstra algorithm with embedded constraints

Abstract We have developed a new optimal path algorithm in which the paths are subjected to turning constraints. The restriction which we have incorporated is the next link in the path must not make an angle exceeding 45 ° in magnitude with the preceeding link. This algorithm has a natural implementation as an artificial neural system with either synchronous or asynchronous weight updating, and as an automata executing on a massively parallel array processor. At a given step in the path solution process our path planning artificial neural system keeps track of all constrained optimal paths flowing into the nodes of the network. This new algorithm has applications to any path planning problem where the vehicle traveling the path is subject to a limited turning capability. The ability of the network to solve for constrained paths is illustrated with both a graph theoretic example and a scenario involving an unmanned vehicle that must travel a constrained path through a real terrain area containing artificially generated keep out zones.

A Method for Detecting Microcalcifications in Digital Mammograms

Microcalcification clusters are often an important indicator for the detection of malignancy in mammograms. In many cases, microcalcifications are the only indication of a malignancy. However, the detection of microcalcifications can be a difficult process. They are small and can be embedded in dense tissue. This paper presents a method for automatically detecting microcalcifications. We utilize a high-boost filter to suppress background clutter enabling segmentation even in very dense breast tissue. We then use a threshholding and region growing technique to extract candidate microcalcifications. Likely microcalcifications are then identified by a linear classifier. We apply this method to images selected from the LLNL/UCSF Digital Mammogram Library, and produce a receiver operating characteristic (ROC) curves to detail the trade-off between probability of detection and false alarms. Finally, we exam the ability to properly select a threshold to achieve a desired probability of detection based upon a training set.

Mixture structure analysis using the Akaike Information Criterion and the bootstrap

Given i.i.d. observations x1,x2,x3,...,xn drawn from a mixture of normal terms, one is often interested in determining the number of terms in the mixture and their defining parameters. Although the problem of determining the number of terms is intractable under the most general assumptions, there is hope of elucidating the mixture structure given appropriate caveats on the underlying mixture. This paper examines a new approach to this problem based on the use of Akaike Information Criterion (AIC) based pruning of data driven mixture models which are obtained from resampled data sets. Results of the application of this procedure to artificially generated data sets and a real world data set are provided.

Iterative Denoising for Cross-Corpus Discovery

We consider the problem of statistical pattern recognition in a heterogeneous, high-dimensional setting. In particular, we consider the search for meaningful cross-category associations in a heterogeneous text document corpus. Our approach involves “iterative denoising ” — that is, iteratively extracting (corpus-dependent) features and partitioning the document collection into sub-corpora. We present an anecdote wherein this methodology discovers a meaningful cross-category association in a heterogeneous collection of scientific documents.

A Deterministic Method for Robust Estimation of Multivariate Location and Shape

Abstract The existence of outliers in a data set and how to deal with them is an important problem in statistics. The minimum volume ellipsoid (MVE) estimator is a robust estimator of location and covariate structure; however its use has been limited because there are few computationally attractive methods. Determining the MVE consists of two parts—finding the subset of points to be used in the estimate and finding the ellipsoid that covers this set. This article addresses the first problem. Our method will also allow us to compute the minimum covariance determinant (MCD) estimator. The proposed method of subset selection is called the effective independence distribution (EID) method, which chooses the subset by minimizing determinants of matrices containing the data. This method is deterministic, yielding reproducible estimates of location and scatter for a given data set. The EID method of finding the MVE is applied to several regression data sets where the true estimate is known. Results show that the ...

A Visualization Technique for Studying the Iterative Estimation of Mixture Densities

Abstract This article focuses on recent work that analyzes the expectation maximization (EM) evolution of mixtures-based estimators. The goal of this research is the development of effective visualization techniques to portray the mixture model parameters as they change in time. This is an inherently high-dimensional process. Techniques are presented that portray the time evolution of univariate, bivariate, and trivariate finite and adaptive mixtures estimators. Adaptive mixtures is a recently developed variable bandwidth kernel estimator where each of the kernels is not constrained to reside at a sample location. The future role of these techniques in developing new versions of the adaptive mixtures procedure is also discussed.