Artificial Neural Networks in Mammography Interpretation and Diagnostic Decision Making

Abstract

Screening mammography is the most effective means for early detection of breast cancer. Although general rules for discriminating malignant and benign lesions exist, radiologists are unable to perfectly detect and classify all lesions as malignant and benign, for many reasons which include, but are not limited to, overlap of features that distinguish malignancy, difficulty in estimating disease risk, and variability in recommended management. When predictive variables are numerous and interact, ad hoc decision making strategies based on experience and memory may lead to systematic errors and variability in practice. The integration of computer models to help radiologists increase the accuracy of mammography examinations in diagnostic decision making has gained increasing attention in the last two decades. In this study, we provide an overview of one of the most commonly used models, artificial neural networks (ANNs), in mammography interpretation and diagnostic decision making and discuss important features in mammography interpretation. We conclude by discussing several common limitations of existing research on ANN-based detection and diagnostic models and provide possible future research directions.

Automatic abstraction of imaging observations with their characteristics from mammography reports

“…7 8 For example, several works have demonstrated that statistical machine learning models such as neural networks and Bayesian networks can be built using BI-RADS descriptors and clinical data as inputs. [7][8][9] Although preliminary work to develop DSS for mammography using standardized vocabulary to describe the imaging features is promising, few DSS for mammography have been adopted in clinical practice, likely due to the challenge of interfacing DSS with the clinical workflow. DSS for mammography can disrupt the workflow, 7 10-12 since these systems require the radiologist to enter their observations in a separate interface, which duplicates the activity of generating the radiology report.…”

Optimization of multiplex quantitative polymerase chain reaction based on response surface methodology and an artificial neural network-genetic algorithm approach

“…As an alternative to RSM, artificial neural networks (ANNs)[ 15 ] are an integral component of artificial intelligence that can be applied for data analysis and prediction. As typical ANNs, back-propagation neural networks (BPNN) optimize and monitor the performance of neural networks under learning rules.…”

Methods Used in Computer-Aided Diagnosis for Breast Cancer Detection Using Mammograms: A Review

“…e strength of the connections is represented by weights such that the weight between two nodes represents the strength of the connection between them. Figure 4 shows the generic structure for ANN in mammography where the network receives the features at the input nodes and provides the predicted class at the output node [169].…”

“…e inhabitation occurs when the weight is -1 and the excitation occurs when the weight is 1. Within each node's design, a transfer function is introduced [169]. e most used transfer functions are a unit step function, sigmoid function, Gaussian function, linear function, and a piecewise linear function.…”

“…Because of this, scholars can improve their classification accuracy by combining outputs from different classifiers Output layer (malignancy probability) Figure 4: Structure of ANN for typical breast cancer detection using mammogram [169]. Table 1: e area under the ROC for some common classification techniques for mammograms.…”