Darrin C. Edwards

MUC1-associated proliferation signature predicts outcomes in lung adenocarcinoma patients

BackgroundMUC1 protein is highly expressed in lung cancer. The cytoplasmic domain of MUC1 (MUC1-CD) induces tumorigenesis and resistance to DNA-damaging agents. We characterized MUC1-CD-induced transcriptional changes and examined their significance in lung cancer patients.MethodsUsing DNA microarrays, we identified 254 genes that were differentially expressed in cell lines transformed by MUC1-CD compared to control cell lines. We then examined expression of these genes in 441 lung adenocarcinomas from a publicly available database. We employed statistical analyses independent of clinical outcomes, including hierarchical clustering, Students t-tests and receiver operating characteristic (ROC) analysis, to select a seven-gene MUC1-associated proliferation signature (MAPS). We demonstrated the prognostic value of MAPS in this database using Kaplan-Meier survival analysis, log-rank tests and Cox models. The MAPS was further validated for prognostic significance in 84 lung adenocarcinoma patients from an independent database.ResultsMAPS genes were found to be associated with proliferation and cell cycle regulation and included CCNB1, CDC2, CDC20, CDKN3, MAD2L1, PRC1 and RRM2. MAPS expressors (MAPS+) had inferior survival compared to non-expressors (MAPS-). In the initial data set, 5-year survival was 65% (MAPS-) vs. 45% (MAPS+, p < 0.0001). Similarly, in the validation data set, 5-year survival was 57% (MAPS-) vs. 28% (MAPS+, p = 0.005).ConclusionsThe MAPS signature, comprised of MUC1-CD-dependent genes involved in the control of cell cycle and proliferation, is associated with poor outcomes in patients with adenocarcinoma of the lung. These data provide potential new prognostic biomarkers and treatment targets for lung adenocarcinoma.

Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions.

We are using Bayesian artificial neural networks (BANNs) to classify mammographic masses in schemes for computer-aided diagnosis, and we are extending this methodology to a three-class classification task. We investigated whether a BANN can estimate ideal observer decision variables to distinguish malignant, benign, and false-positive computer detections. Five features were calculated for 63 malignant and 29 benign computer-detected mass lesions, and for 1049 false-positive computer detections, in 440 mammograms randomly divided into a training and testing set. A BANN was trained on the training set features and applied to the testing set features. We then used a known relation between three-class ideal observer decision variables and that used by a two-class ideal observer when two of three classes are grouped into one class, giving one decision variable for distinguishing malignant from nonmalignant detections, and a second for distinguishing true-positive from false-positive computer detections. For comparison, we grouped the training data into two classes in the same two ways and trained two-class BANNs for these two tasks. The three-class BANN decision variables were essentially identical in performance to the specifically trained two-class BANNs, with the average difference in area under the ROC curves being less than 0.0035 and no differences in area being statistically significant. Thus, the BANN outputs obey the same theoretical relationship as do the three-class and two-class ideal observer decision variables, which is consistent with the claim that the three-class BANN output can provide good estimates of the decision variables used by a three-class ideal observer.

Computerized three-class classification of MRI-based prognostic markers for breast cancer

The purpose of this study is to investigate whether computerized analysis using three-class Bayesian artificial neural network (BANN) feature selection and classification can characterize tumor grades (grade 1, grade 2 and grade 3) of breast lesions for prognostic classification on DCE-MRI. A database of 26 IDC grade 1 lesions, 86 IDC grade 2 lesions and 58 IDC grade 3 lesions was collected. The computer automatically segmented the lesions, and kinetic and morphological lesion features were automatically extracted. The discrimination tasks-grade 1 versus grade 3, grade 2 versus grade 3, and grade 1 versus grade 2 lesions-were investigated. Step-wise feature selection was conducted by three-class BANNs. Classification was performed with three-class BANNs using leave-one-lesion-out cross-validation to yield computer-estimated probabilities of being grade 3 lesion, grade 2 lesion and grade 1 lesion. Two-class ROC analysis was used to evaluate the performances. We achieved AUC values of 0.80 ± 0.05, 0.78 ± 0.05 and 0.62 ± 0.05 for grade 1 versus grade 3, grade 1 versus grade 2, and grade 2 versus grade 3, respectively. This study shows the potential for (1) applying three-class BANN feature selection and classification to CADx and (2) expanding the role of DCE-MRI CADx from diagnostic to prognostic classification in distinguishing tumor grades.

Restrictions on the three-class ideal observer's decision boundary lines

We are attempting to develop expressions for the coordinates of points on the three-class ideal observers receiver operating characteristic (ROC) hypersurface as functions of the set of decision criteria used by the ideal observer. This is considerably more difficult than in the two-class classification task, because the conditional probabilities in question are not simply related to the cumulative distribution functions of the decision variables, and because the slopes and intercepts of the decision boundary lines are not independent; given the locations of two of the lines, the location of the third will be constrained depending on the other two. In this paper, we attempt to characterize those constraining relationships among the three-class ideal observers decision boundary lines. As a result, we show that the relationship between the decision criteria and the misclassification probabilities is not one-to-one, as it is for the two-class ideal observer.

Evaluation of the channelized Hotelling observer for signal detection in 2D tomographic imaging

Signal detection by the channelized Hotelling (ch-Hotelling) observer is studied for tomographic application by employing a small, tractable 2D model of a computed tomography (CT) system. The primary goal of this manuscript is to develop a practical method for evaluating the ch-Hotelling observer that can generalize to larger 3D cone-beam CT systems. The use of the ch-Hotelling observer for evaluating tomographic image reconstruction algorithms is also demonstrated. For a realistic model for CT, the ch-Hotelling observer can be a good approximation to the ideal observer. The ch-Hotelling observer is applied to both the projection data and the reconstructed images. The difference in signal-to-noise ratio for signal detection in both of these domains provides a metric for evaluating the image reconstruction algorithm.

Optimization of Restricted ROC Surfaces in Three-Class Classification Tasks

We have shown previously that an N-class ideal observer achieves the optimal receiver operating characteristic (ROC) hypersurface in a Neyman-Pearson sense. Due to the inherent complexity of evaluating observer performance even in a three-class classification task, some researchers have suggested a generally incomplete but more tractable evaluation in terms of a surface, plotting only the three ldquosensitivities.rdquo More generally, one can evaluate observer performance with a single sensitivity or misclassification probability as a function of two linear combinations of sensitivities or misclassification probabilities. We analyzed four such formulations including the ldquosensitivityrdquo surface. In each case, we applied the Neyman-Pearson criterion to find the observer which achieves optimal performance with respect to each given set of ldquoperformance description variablesrdquo under consideration. In the unrestricted case, optimization with respect to the Neyman-Pearson criterion yields the ideal observer, as does maximization of the observers expected utility. Moreover, during our consideration of the restricted cases, we found that the two optimization methods do not merely yield the same observer, but are in fact completely equivalent in a mathematical sense. Thus, for a wide variety of observers which maximize performance with respect to a restricted ROC surface in the Neyman-Pearson sense, that ROC surface can also be shown to provide a complete description of the observers performance in an expected utility sense.

Estimation of three-class ideal observer decision functions with a Bayesian artificial neural network

We are using Bayesian artificial neural networks (BANNs) to eliminate false-positive detections in our computer-aided diagnosis schemes. In the present work, we investigated whether BANNs can be used to estimate likelihood ratio, or ideal observer, decision functions for distinguishing observations which are drawn from three classes. Three univariate normal distributions were chosen representing three classes. We sampled 3,000 values of x for each of 10 training datasets, and 3,000 values of x for a single testing dataset. A BANN was trained on each training dataset, and the two outputs from each trained BANN, which estimate p(class 1x) and p(class 2x), were recorded for each value of x in the testing dataset. The mean BANN output and its standard error were calculated using the ten sets of BANN output. We repeated the above procedure to estimate the means and standard errors of the two likelihood ratio decision functions p(xclass 1)/p(xclass 3)/p(xclass 2)/p(xclass 3). We found that the BANN can estimate the a posteriori class probabilities quite accurately, except in regions of data space where outcomes are unlikely. Estimation of the likelihood ratios is more problematic, which we attribute to error amplification caused by taking the ratio of two imprecise estimates. We hope to improve these estimates by constraining the BANN training procedure.

Ideal observer estimation and generalized ROC analysis for computer-aided diagnosis

The research presented in this dissertation represents an innovative application of computer-aided diagnosis and signal detection theory to the specific task of early detection of breast cancer in the context of screening mammography. A number of automated schemes have been developed in our laboratory to detect masses and clustered microcalcifications in digitized mammograms, on the one hand, and to classify known lesions as malignant or benign, on the other. The development of fully automated classification schemes is difficult, because the output of a detection scheme will contain false-positive detections in addition to detected malignant and benign lesions, resulting in a three-class classification task. Researchers have so far been unable to extend successful tools for analyzing two-class classification tasks, such as receiver operating characteristic (ROC) analysis, to three-class classification tasks. The goals of our research were to use Bayesian artificial neural networks to estimate ideal observer decision variables to both detect and classify clustered microcalcifications and mass lesions in mammograms, and to derive substantial theoretical results indicating potential avenues of approach toward the three-class classification task. Specifically, we have shown that an ideal observer in an N-class classification task achieves an optimal ROC hypersurface, just as the two-class ideal observer achieves an optimal ROC curve; and that an obvious generalization of a well-known two-class performance metric, the area under the ROC curve, is not useful as a performance metric in classification tasks with more than two classes. This work is significant for three reasons. First, it involves the explicit estimation of feature-based (as opposed to image-based) ideal observer decision variables in the tasks of detecting and classifying mammographic lesions. Second, it directly addresses the three-class classification task of distinguishing malignant lesions, benign lesions, and false-positive computer detections. Finally, it develops important theoretical results for N-class classification tasks that should prove of value in the development of a three-class extension to ROC analysis methods.

Eliminating false-positive microcalcification clusters in a mammography CAD scheme using a Bayesian neural network

We have applied a Bayesian Neural network (BNN) to the task of distinguishing between true-positive (TP) and false- positive (FP) detected clusters in a computer-aided diagnosis (CAD) scheme for detecting clustered microcalcifications in mammograms. Because BNNs can approximate ideal observer decision functions given sufficient training data, this approach should have better performance than our previous FP cluster elimination methods. Eight cluster-based features were extracted from the TP and FP clusters detected by the scheme in a training dataset of 39 mammograms. This set of features was used to train a BNN with eight input nodes, five hidden nodes, and one output node. The trained BNN was tested on the TP and FP clusters and detected by our scheme in an independent testing set of 50 mammograms. The BNN output was analyzed using ROC and FROC analysis. The detection scheme with BNN for FP cluster elimination had substantially better cluster sensitivity at low FP rates (below 0.8 FP clusters per image) than the original detection scheme without the BNN. Our preliminary research shows that a BNN can improve the performance of our scheme for detecting clusters of microcalcifications.

Review of several proposed three-class classification decision rules and their relation to the ideal observer decision rule

We analyzed a variety of recently proposed decision rules for three-class classification from the point of view of ideal observer decision theory. We considered three-class decision rules which have been proposed recently: one by Scurfield, one by Chan et al., and one by Mossman. Scurfields decision rule can be shown to be a special case of the three-class ideal observer decision rule in two different situations: when the pair of decision variables is the pair of likelihood ratios used by the ideal observer, and when the pair of decision variables is the pair of logarithms of the likelihood ratios. Chan et al. start with an ideal observer model, where two of the decision lines used by the ideal observer overlap, and the third line becomes undefined. Finally, we showed that the Mossman decision rule (in which a single decision line separates one class from the other two, while a second line separates those two classes) cannot be a special case of the ideal observer decision rule. Despite the considerable difficulties presented by the three-class classification task compared with two-class classification, we found that the three-class ideal observer provides a useful framework for analyzing a wide variety of three-class decision strategies.