The authors investigated the potential utility of artificial neural networks as a decision-making aid to radiologists in the analysis of mammographic data. Three-layer, feed-forward neural networks with a back-propagation algorithm were trained for the interpretation of mammograms on the basis of features extracted from mammograms by experienced radiologists. A network that used 43 image features performed well in distinguishing between benign and malignant lesions, yielding a value of 0.95 for the area under the receiver operating characteristic curve for textbook cases in a test with the round-robin method. With clinical cases, the performance of a neural network in merging 14 radiologist-extracted features of lesions to distinguish between benign and malignant lesions was found to be higher than the average performance of attending and resident radiologists alone (without the aid of a neural network). The authors conclude that such networks may provide a potentially useful tool in the mammographic decision-making task of distinguishing between benign and malignant lesions.
A computer-aided diagnosis (CAD) scheme has been developed in our laboratory for the detection of clustered microcalcifications in digital mammograms. In this study, we apply a shift-invariant neural network to eliminate false-positive detections reported by the CAD scheme. The shift-invariant neural network is a multilayer back-propagation neural network with local, shift-invariant interconnections. The advantage of the shift-invariant neural network is that the result of the network is not dependent on the locations of the clustered microcalcifications in the input layer. The neural network is trained to detect each individual microcalcification in a given region of interest (ROI) reported by the CAD scheme. A ROI is classified as a positive ROI if the total number of microcalcifications detected in the ROI is greater than a certain number. The performance of the shift-invariant neural network was evaluated by means of a jackknife (or holdout) method and ROC analysis using a database of 168 ROIs, as reported by the CAD scheme when applied to 34 mammograms. The analysis yielded an average area under the ROC curve (Az) of 0.91. Approximately 55% of false-positive ROIs were eliminated without any loss of the true-positive ROIs. The result is considerably better than that obtained in our previous study using a conventional three-layer, feed-forward neural network. The effect of the network structure on the performance of the shift-invariant neural network is also studied.
Artificial neural networks have been applied to the differentiation of actual "true" clusters from normal parenchymal patterns and also to the differentiation of actual clusters from false-positive clusters as reported by a computerized scheme for the detection of microcalcifications in digital mammograms. The differentiation was carried out in both the spatial and frequency domains. The performance of the neural networks was evaluated quantitatively by means of receiver operating characteristic (ROC) analysis. It was found that the networks could distinguish clustered microcalcifications from normal nonclustered areas in the frequency domain, and that they could eliminate approximately 50% of false-positive clusters of microcalcifications while preserving 95% of the positive clusters, when applied to the results of the automated detection scheme. A large, comprehensive training database is needed for neural networks to perform reliably in clinical situations.
We developed a theoretical model which describes the improvement of signal-to-noise ratio (SNR) by a grid in digital radiography. The model takes into account the effects of spatial variations in the scatter-to-primary ratio and in the large-area contrast over an image with structured background on quantum noise, and the effects of noise in the imaging system such as electronic noise and digitization noise. Based on the theoretical model, we analyzed the effects of these factors on the SNR when a grid is employed. We performed experimental measurements to evaluate the improvement in the SNR by a grid when quantum noise is the dominant noise source. It was found that the measured SNR improvement factor due to quantum noise agreed closely with that determined from the measured transmission values of a grid, as predicted from our theoretical model. In order to evaluate the relative performance of grids with various geometric design parameters for digital radiographic systems, we employed Monte Carlo calculations and determined the transmission values of a number of grids under various scatter conditions. The calculated SNR improvement factor, due to quantum noise, correlated well with the measured improvement of the SNR by the grids. Our model predicts that the SNR improvement factor depends strongly on the local contrast ratio and also on the scatter-to-primary ratio. The SNR improvement factor is higher in the underpenetrated regions than in the well-penetrated regions of an image.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.