The different enhancement behaviors of malignant and benign breast lesions cannot be explained by MVD alone; however, a low MVD in the center of carcinoma is reflected quantitatively by a high enhancement ratio and qualitatively by rim enhancement, with an implication of adverse prognosis.
Although MR imaging is most sensitive for the detection of small tumors, routine preoperative MR imaging appears to be unnecessary for most patients if a combination of mammography and whole-breast sonography is used. Additional MR imaging can be restricted to problematic cases in women with dense breast parenchyma.
The aim of this study was to evaluate the capability of improved artificial neural networks (ANN) and additional novel training methods in distinguishing between benign and malignant breast lesions in contrast-enhanced magnetic resonance-mammography (MRM). A total of 604 histologically proven cases of contrast-enhanced lesions of the female breast at MRI were analyzed. Morphological, dynamic and clinical parameters were collected and stored in a database. The data set was divided into several groups using random or experimental methods [Training & Testing (T&T) algorithm] to train and test different ANNs. An additional novel computer program for input variable selection was applied. Sensitivity and specificity were calculated and compared with a statistical method and an expert radiologist. After optimization of the distribution of cases among the training and testing sets by the T & T algorithm and the reduction of input variables by the Input Selection procedure a highly sophisticated ANN achieved a sensitivity of 93.6% and a specificity of 91.9% in predicting malignancy of lesions within an independent prediction sample set. The best statistical method reached a sensitivity of 90.5% and a specificity of 68.9%. An expert radiologist performed better than the statistical method but worse than the ANN (sensitivity 92.1%, specificity 85.6%). Features extracted out of dynamic contrast-enhanced MRM and additional clinical data can be successfully analyzed by advanced ANNs. The quality of the resulting network strongly depends on the training methods, which are improved by the use of novel training tools. The best results of an improved ANN outperform expert radiologists.
Detection of enhancing incidental lesions should lead to a thorough reevaluation of mammograms and sonograms. If not reidentified, suspicious enhancing incidental lesions should be biopsied, and enhancing incidental lesions that are probably benign should be carefully followed up. Indeterminate enhancing incidental lesions should be histologically examined by minimally invasive techniques or, if they are small, followed up by another MRI 6 months later.
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.