Learn More
For many supervised learning tasks it may be infeasible (or very expensive) to obtain objective and reliable labels. Instead, we can collect subjective (possibly noisy) labels from multiple experts or annotators. In practice, there is a substantial amount of disagreement among the annotators, and hence it is of great practical interest to address(More)
We describe a probabilistic approach for supervised learning when we have multiple experts/annotators providing (possibly noisy) labels but no absolute gold standard. The proposed algorithm evaluates the different experts and also gives an estimate of the actual hidden labels. Experimental results indicate that the proposed method is superior to the(More)
Supervised learning from multiple labeling sources is an increasingly important problem in machine learning and data mining. This paper develops a probabilistic approach to this problem when annotators may be unreliable (labels are noisy), but also their expertise varies depending on the data they observe (annotators may have knowledge about different parts(More)
OBJECTIVE The objective of our study was to determine the relative accuracy of mammography, sonography, and MRI in predicting residual tumor after neoadjuvant chemotherapy for breast cancer as compared with the gold standards of physical examination and pathology. SUBJECTS AND METHODS Forty-one women with stage IIB-III palpable breast cancer were(More)
OBJECTIVE The purpose of this study was to evaluate the usefulness of MRI of the breast in cases in which mammographic or sonographic findings are inconclusive. MATERIALS AND METHODS We retrospectively reviewed images from 115 MRI examinations of the breast performed from 1999 to 2005 for the indication of problem-solving for inconclusive findings on a(More)
The purpose of this study is to report further about the statistically significant results from a prospective study, which suggests that fusion of prone F-18 Fluoro-deoxy-glucose (FDG) positron emission tomography (PET) and magnetic resonance (MR) breast scans increases the positive predictive value (PPV) and specificity for patients in whom the MR outcome(More)
PURPOSE To evaluate feasibility of using magnetization transfer ratio (MTR) in conjunction with dynamic contrast-enhanced MRI (DCE-MRI) for differentiation of benign and malignant breast lesions at 3 Tesla. MATERIALS AND METHODS This prospective study was IRB and HIPAA compliant. DCE-MRI scans followed by MT imaging were performed on 41 patients. Regions(More)
Recent advances in deep learning for object recognition in natural images has prompted a surge of interest in applying a similar set of techniques to medical images. Most of the initial attempts largely focused on replacing the input to such a deep convolutional neural network from a natural image to a medical image. This, however, does not take into(More)
PURPOSE To determine the number of patients who received a diagnosis of breast cancer after having an area of clinical concern at presentation and combined negative mammographic and ultrasonographic (US) findings. MATERIALS AND METHODS During a 4-year period, 829 patients with a palpable abnormality at presentation and combined negative mammographic and(More)