Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed.

Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a generative adversarial network using two publicly available data sets of brain MRI. We demonstrate two unique benefits that the synthetic images provide. First, we illustrate improved performance on tumor segmentation by leveraging the synthetic images as a form of data augmentation. Second, we demonstrate the value of generative models as an anonymization tool, achieving comparable tumor segmentation results when trained on the synthetic data versus when trained on real subject data. Together, these results offer a potential solution to two of the largest challenges facing machine learning in medical imaging, namely the small incidence of pathological findings, and the restrictions around sharing of patient data.

A key challenge in developing nanoplatform-based molecular imaging is to achieve an optimal pharmacokinetic profile to allow sufficient targeting and to avoid rapid clearance by the reticuloendothelial system (RES). In the present study, iron oxide nanoparticles (IONPs) were coated with a PEGylated amphiphilic triblock copolymer, making them water soluble and function-extendable. These particles were then conjugated with a near-infrared fluorescent (NIRF) dye IRDye800 and cyclic Arginine-Glycine-Aspartic acid (RGD) containing peptide c(RGDyK) for integrin αvβ3 targeting. In vitro binding assays confirmed the integrin-specific association between the RGD-particle adducts and U87MG glioblastoma cells. Successful tumor homing in vivo was perceived in a subcutaneous U87MG glioblastoma xenograft model by both magnetic resonance imaging (MRI) and NIRF imaging. Ex vivo histopathological studies also revealed low particle accumulation in the liver, which was attributed to their compact hydrodynamic size and PEGylated coating. In conclusion, we have developed a novel RGD-IONP conjugate with excellent tumor integrin targeting efficiency and specificity as well as limited RES uptake for molecular MRI.

The success of cancer therapy can be difficult to predict, as its efficacy is often predicated upon characteristics of the cancer, treatment, and individual that are not fully understood or are difficult to ascertain. Monitoring the response of disease to treatment is therefore essential and has traditionally been characterized by changes in tumor volume. However, in many instances, this singular measure is insufficient for predicting treatment effects on patient survival. Molecular imaging allows repeated in vivo measurement of many critical molecular features of neoplasm, such as metabolism, proliferation, angiogenesis, hypoxia, and apoptosis, which can be employed for monitoring therapeutic response. In this review, we examine the current methods for evaluating response to treatment and provide an overview of emerging PET molecular imaging methods that will help guide future cancer therapies.