Advances in technology have always had the potential and opportunity to shape the practice of medicine, and in no medical specialty has technology been more rapidly embraced and adopted than radiology. Machine learning and deep neural networks promise to transform the practice of medicine, and, in particular, the practice of diagnostic radiology. These technologies are evolving at a rapid pace due to innovations in computational hardware and novel neural network architectures. Several cutting-edge postprocessing analysis applications are actively being developed in the fields of thoracic and cardiovascular imaging, including applications for lesion detection and characterization, lung parenchymal characterization, coronary artery assessment, cardiac volumetry and function, and anatomic localization. Cardiothoracic and cardiovascular imaging lies at the technological forefront of radiology due to a confluence of technical advances. Enhanced equipment has enabled computed tomography and magnetic resonance imaging scanners that can safely capture images that freeze the motion of the heart to exquisitely delineate fine anatomic structures. Computing hardware developments have enabled an explosion in computational capabilities and in data storage. Progress in software and fluid mechanical models is enabling complex 3D and 4D reconstructions to not only visualize and assess the dynamic motion of the heart, but also quantify its blood flow and hemodynamics. And now, innovations in machine learning, particularly in the form of deep neural networks, are enabling us to leverage the increasingly massive data repositories that are prevalent in the field. Here, we discuss developments in machine learning techniques and deep neural networks to highlight their likely role in future radiologic practice, both in and outside of image interpretation and analysis. We discuss the concepts of validation, generalizability, and clinical utility, as they pertain to this and other new technologies, and we reflect upon the opportunities and challenges of bringing these into daily use.

The diagnosis of a common cause of chronic pelvic pain can be made by visualizing reflux in the ovarian veins. Fluoroscopic venography is the gold standard for diagnosing ovarian vein reflux, but it is an invasive technique that exposes patients to ionizing radiation. MRI, with its lack of ionizing radiation and capability of high-temporal and spatial-resolution vascular imaging, has the potential to provide similar diagnostic information. This retrospective report describes and assesses the utility of a dynamic contrast-enhanced MRI technique based on Differential Subsampling with Cartesian Ordering (DISCO)-MRI in 30 patients with chronic pelvic pain. Among the 14 patients who underwent both DISCO-MRI and fluoroscopic venograms, 11 (78.6%) exhibited concordant results, while 3 patients (21.4%) had discordant findings. These results suggest the potential of multiphasic contrast-enhanced DISCO-MRI as a non-invasive diagnostic tool for evaluating chronic pelvic pain.

Diffusion-weighted MRI (DW-MRI) offers a potential adjunct to dynamic contrast-enhanced MRI to discriminate benign from malignant breast lesions by yielding quantitative information about tissue microstructure. Multi-component modeling of the DW-MRI signal over an extended b-value range (up to 3000 s/mm²) theoretically isolates the slowly diffusing (restricted) water component in tissues. Previously, a three-component restriction spectrum imaging (RSI) model demonstrated the ability to distinguish malignant lesions from healthy breast tissue. We further evaluated the utility of this three-component model to differentiate malignant from benign lesions and healthy tissue in 12 patients with known malignancy and synchronous pathology-proven benign lesions. The signal contributions from three distinct diffusion compartments were measured to generate parametric maps corresponding to diffusivity on a voxel-wise basis. The three-component model discriminated malignant from benign and healthy tissue, particularly using the restricted diffusion C₁ compartment and product of the restricted and intermediate diffusion compartments (C₁ and C₂). However, benign lesions and healthy tissue did not significantly differ in diffusion characteristics. Quantitative discrimination of these three tissue types (malignant, benign, and healthy) in non-pre-defined lesions may enhance the clinical utility of DW-MRI in reducing excessive biopsies and aiding in surveillance and surgical evaluation without repeated exposure to gadolinium contrast.