Discriminating lung nodules as malignant or benign is still an underlying challenge. To address this challenge, radiologists need computer aided diagnosis (CAD) systems which can assist in learning discriminative imaging features corresponding to malignant and benign nodules. However, learning highly discriminative imaging features is an open problem. In this paper, our aim is to learn the most discriminative features pertaining to lung nodules by using an adversarial learning methodology. Specifically, we propose to use unsupervised learning with Deep Convolutional-Generative Adversarial Networks (DC-GANs) to generate lung nodule samples realistically. We hypothesize that imaging features of lung nodules will be discriminative if it is hard to differentiate them (fake) from real (true) nodules. To test this hypothesis, we present Visual Turing tests to two radiologists in order to evaluate the quality of the generated (fake) nodules. Extensive comparisons are performed in discerning real, generated, benign, and malignant nodules. This experimental set up allows us to validate the overall quality of the generated nodules, which can then be used to (1) improve diagnostic decisions by mining highly discriminative imaging features, (2) train radiologists for educational purposes, and (3) generate realistic samples to train deep networks with big data.

Deep learning has demonstrated tremendous revolutionary changes in the computing industry and its effects in radiology and imaging sciences have begun to dramatically change screening paradigms. Specifically, these advances have influenced the development of computer-aided detection and diagnosis (CAD) systems. These technologies have long been thought of as "second-opinion" tools for radiologists and clinicians. However, with significant improvements in deep neural networks, the diagnostic capabilities of learning algorithms are approaching levels of human expertise (radiologists, clinicians etc.), shifting the CAD paradigm from a "second opinion" tool to a more collaborative utility. This paper reviews recently developed CAD systems based on deep learning technologies for breast cancer diagnosis, explains their superiorities with respect to previously established systems, defines the methodologies behind the improved achievements including algorithmic developments, and describes remaining challenges in breast cancer screening and diagnosis. We also discuss possible future directions for new CAD models that continue to change as artificial intelligence algorithms evolve.

Myocardial fibrosis is a common endpoint in a variety of cardiac diseases and a major independent predictor of adverse cardiac outcomes. Short of histopathologic analysis, which is limited by sampling bias, most diagnostic modalities are limited in their depiction of myocardial fibrosis. Cardiac magnetic resonance (MR) imaging has the advantage of providing detailed soft-tissue characterization, and a variety of novel quantification methods have further improved its usefulness. Contrast material-enhanced cardiac MR imaging depends on differences in signal intensity between regions of scarring and adjacent normal myocardium. Diffuse myocardial fibrosis lacks these differences in signal intensity. Measurement of myocardial T1 times (T1 mapping) with gadolinium-enhanced inversion recovery-prepared sequences may depict diffuse myocardial fibrosis and has good correlation with ex vivo fibrosis content. T1 mapping calculates myocardial T1 relaxation times with image-based signal intensities and may be performed with standard cardiac MR imagers and radiologic workstations. Myocardium with diffuse fibrosis has greater retention of contrast material, resulting in T1 times that are shorter than those in normal myocardium. Early studies have suggested that diffuse myocardial fibrosis may be distinguished from normal myocardium with T1 mapping. Large multicenter studies are needed to define the role of T1 mapping in developing prognoses and therapeutic assessments. However, given its strengths as a noninvasive method for direct quantification of myocardial fibrosis, T1 mapping may eventually play an important role in the management of cardiac disease.

Anatomical and biophysical modeling of left atrium (LA) and proximal pulmonary veins (PPVs) is important for clinical management of several cardiac diseases. Magnetic resonance imaging (MRI) allows qualitative assessment of LA and PPVs through visualization. However, there is a strong need for an advanced image segmentation method to be applied to cardiac MRI for quantitative analysis of LA and PPVs. In this study, we address this unmet clinical need by exploring a new deep learning-based segmentation strategy for quantification of LA and PPVs with high accuracy and heightened efficiency. Our approach is based on a multi-view convolutional neural network (CNN) with an adaptive fusion strategy and a new loss function that allows fast and more accurate convergence of the backpropagation based optimization. After training our network from scratch by using more than 60K 2D MRI images (slices), we have evaluated our segmentation strategy to the STACOM 2013 cardiac segmentation challenge benchmark. Qualitative and quantitative evaluations, obtained from the segmentation challenge, indicate that the proposed method achieved the state-of-the-art sensitivity (90%), specificity (99%), precision (94%), and efficiency levels (10 seconds in GPU, and 7.5 minutes in CPU).