Performance gain in computer‐assisted detection schemes by averaging scores generated from artificial neural networks with adaptive filtering

Abstract

The authors investigated a new method to optimize artificial neural networks (ANNs) with adaptive filtering used in computer-assisted detection schemes in digitized mammograms and to assess performance changes when averaging classification scores from three sets of optimized schemes. Two independent training and testing image databases involving 978 and 830 digitized mammograms, respectively, were used in this study. In the training data set, initial filtering and subtraction resulted in the identification of 592 mass regions and 3790 suspicious, but actually negative regions. These regions (including both true-positive and negative regions) were segmented into three subsets three times based on the calculation of the values of three features as segmentation indices. The indices were "mass" size multiplied by their digital value contrast, conspicuity, and circularity. Nine ANN-based classifiers were separately optimized using a genetic algorithm for each subset of regions. Each region was assigned three classification scores after applying the three adaptive ANNs. The performance gain of the CAD scheme after averaging the three scores for each suspicious region was tested using an independent data set and a ROC methodology. The experimental results showed that the areas under ROC curves (Az) for the testing database using three sets of optimized ANNs individually were 0.84+/-0.01, 0.83+/-0.01, and 0.84+/-0.01, respectively. The between-index correlations of three A values were 0.013, -0.007, and 0.086. Similar to averaging diagnostic ratings from independent observers, by averaging three ANN-generated scores for each testing region, the performance of the CAD scheme was significantly improved (p<0.001) with Az value of 0.95+/-0.01.

A completely automated CAD system for mass detection in a large mammographic database

“…A number of classifiers based on linear discriminant analysis, 26,27 artificial neural networks, [28][29][30] and rule-based methods 31,32 have shown effectiveness in detection and diagnostic systems. We used a supervised two-layered feedforward neural network, trained with the gradient descent learning rule 33 for the ROI pattern classification:…”

Computer-aided Detection Performance in Mammographic Examination of Masses: Assessment

“…Another system (Second Look, version 6.0 Beta; CADx Systems, Beavercreek, Ohio) was used to process all images as well. A third system was an in-house-developed scheme, and its use has been reported in the past (23)(24)(25).…”

Effect of correlation on combining diagnostic information from two images of the same patient

“…1,2 In computer-aided detection and computeraided diagnosis ͑CAD͒, combining computer ratings produced by multiple classifiers from the same images, or by a single classifier from multiple images, can achieve a similar effect. [3][4][5][6][7] It is standard practice in mammography to acquire two views: the mediolateral oblique ͑MLO͒ view and the craniocaudal ͑CC͒ view. Whereas the precise way in which radiologists combine the diagnostic information contained in these images is unknown, an approach often taken in CAD is to analyze each image of the same patient independently and then to combine the results calculated from each image into a single diagnostic variable.…”