Objective measurement of erythema in psoriasis using digital color photography with color calibration.

BACKGROUND: Traditional metrics for evaluating the severity of psoriasis are subjective, which complicates efforts to measure effective treatments in clinical trials. METHODS: We collected images of psoriasis plaques and calibrated the coloration of the images according to an included color card. Features were extracted from the images and used to train a linear discriminant analysis classifier with cross-validation to automatically classify the degree of erythema. The results were tested against numerical scores obtained by a panel of dermatologists using a standard rating system. RESULTS: Quantitative measures of erythema based on the digital color images showed good agreement with subjective assessment of erythema severity (κ = 0.4203). The color calibration process improved the agreement from κ = 0.2364 to κ = 0.4203. CONCLUSION: We propose a method for the objective measurement of the psoriasis severity parameter of erythema and show that the calibration process improved the results.

The reliability of measuring physical characteristics of spiculated masses on mammography.

The goal of this study was to assess the reliability of measurements of the physical characteristics of spiculated masses on mammography. The images used in this study were obtained from the Digital Database for Screening Mammography. Two experienced radiologists measured the properties of 21 images of spiculated masses. The length and width of all spicules and the major axis of the mass were measured. In addition, the observers counted the total number of spicules. Interobserver and intraobserver variability were evaluated using a hypothesis test for equivalence, the intraclass correlation coefficient (ICC) and Bland-Altman statistics. For an equivalence level of 30% of the mean of the senior radiologist's measurement, equivalence was achieved for the measurements of average spicule length (p<0.01), average spicule width (p = 0.03), the length of the major axis (p<0.01) and for the count of the number of spicules (p<0.01). Similarly, with the ICC analysis technique "excellent" inter-rater agreement was observed for the measurements of average spicule length (ICC = 0.770), the length of the major axis (ICC = 0.801) and for the count of the number of spicules (ICC = 0.780). "Fair to good" agreement was observed for the average spicule width (ICC = 0.561). Equivalence was also demonstrated for intraobserver measurements. Physical properties of spiculated masses can be measured reliably on mammography. The interobserver and intraobserver variability for this task is comparable with that reported for other measurements made on medical images.

Bayesian networks of BI-RADStrade mark descriptors for breast lesion classification.

We investigated Bayesian network structure learning and probability estimation from mammographic feature data in order to classify breast lesions into different pathological categories. We compared the learned networks to naive Bayes classifiers, which are similar to the expert systems previously investigated for breast lesion classification. The learned network structures reflect the difference in the classification of biopsy outcome and the invasiveness of malignant lesions for breast masses and microcalcifications. The difference between masses and microcalcifications should be taken into consideration when interpreting systems for automatic pathological classification of breast lesions. The difference may also affect use of these systems for tasks such as estimating the sampling error of biopsy.

A neural network approach to breast cancer diagnosis as a constraint satisfaction problem.

A constraint satisfaction neural network (CSNN) approach is proposed for breast cancer diagnosis using mammographic and patient history findings. Initially, the diagnostic decision to biopsy was formulated as a constraint satisfaction problem. Then, an associative memory type neural network was applied to solve the problem. The proposed network has a flexible, nonhierarchical architecture that allows it to operate not only as a predictive tool but also as an analysis tool for knowledge discovery of association rules. The CSNN was developed and evaluated using a database of 500 nonpalpable breast lesions with definitive histopathological diagnosis. The CSNN diagnostic performance was evaluated using receiver operating characteristic analysis (ROC). The results of the study showed that the CSNN ROC area index was 0.84+/-0.02. The CSNN predictive performance is competitive with that achieved by experienced radiologists and backpropagation artificial neural networks (BP-ANNs) presented before. Furthermore, the study illustrates how CSNN can be used as a knowledge discovery tool overcoming some of the well-known limitations of BP-ANNs.

Application of the mutual information criterion for feature selection in computer-aided diagnosis.

The purpose of this study was to investigate an information theoretic approach to feature selection for computer-aided diagnosis (CAD). The approach is based on the mutual information (MI) concept. MI measures the general dependence of random variables without making any assumptions about the nature of their underlying relationships. Consequently, MI can potentially offer some advantages over feature selection techniques that focus only on the linear relationships of variables. This study was based on a database of statistical texture features extracted from perfusion lung scans. The ultimate goal was to select the optimal subset of features for the computer-aided diagnosis of acute pulmonary embolism (PE). Initially, the study addressed issues regarding the approximation of MI in a limited dataset as it is often the case in CAD applications. The MI selected features were compared to those features selected using stepwise linear discriminant analysis and genetic algorithms for the same PE database. Linear and nonlinear decision models were implemented to merge the selected features into a final diagnosis. Results showed that the MI is an effective feature selection criterion for nonlinear CAD models overcoming some of the well-known limitations and computational complexities of other popular feature selection techniques in the field.

Toward objective selection of representative microscope images.

Scientists wishing to communicate the essential characteristics of a pattern (such as an immunofluorescence distribution) currently must make a subjective choice of one or two images to publish. We therefore developed methods for objectively choosing a typical image from a set, with emphasis on images from cell biology. The methods involve calculation of numerical features to describe each image, calculation of similarity between images as a distance in feature space, and ranking of images by distance from the center of the feature distribution. Two types of features were explored, image texture measures and Zernike polynomial moments, and various distance measures were utilized. Criteria for evaluating methods for assigning typicality were proposed and applied to sets of images containing more than one pattern. The results indicate the importance of using distance measures that are insensitive to the presence of outliers. For collections of images of the distributions of a lysosomal protein, a Golgi protein, and nuclear DNA, the images chosen as most typical were in good agreement with the conventional understanding of organelle morphologies. The methods described here have been implemented in a web server (http://murphylab.web.cmu.edu/services/TyplC).

Automated recognition of patterns characteristic of subcellular structures in fluorescence microscopy images.

Methods for numerical description and subsequent classification of cellular protein localization patterns are described. Images representing the localization patterns of 4 proteins and DNA were obtained using fluorescence microscopy and divided into distinct training and test sets. The images were processed to remove out-of-focus and background fluorescence and 2 sets of numeric features were generated: Zernike moments and Haralick texture features. These feature sets were used as inputs to either a classification tree or a neural network. Classifier performance (the average percent of each type of image correctly classified) on previously unseen images ranged from 63% for a classification tree using Zernike moments to 88% for a backpropagation neural network using a combination of features from the 2 feature sets. These results demonstrate the feasibility of applying pattern recognition methods to subcellular localization patterns, enabling sets of previously unseen images from a single class to be classified with an expected accuracy greater than 99%. This will provide not only a new automated way to describe proteins, based on localization rather than sequence, but also has potential application in the automation of microscope functions and in the field of gene discovery.