Clinical Documentation and Patient Care Using Artificial Intelligence in Radiation Oncology

Detailed clinical documentation is required in the patient-facing specialty of radiation oncology. The burden of clinical documentation has increased significantly with the introduction of electronic health records and participation in payer-mandated quality initiatives. Artificial intelligence (AI) has the potential to reduce the burden of data entry associated with clinical documentation, provide clinical decision support, improve quality and value, and integrate patient data from multiple sources. The authors discuss key elements of an AI-enhanced clinic and review some emerging technologies in the industry. Challenges regarding data privacy, regulation, and medicolegal liabilities must be addressed for such AI technologies to be successful.     

Modern Perspectives on Radiation Oncology Residency Expansion,Fellowship Evolution,and Employment Satisfaction

PurposeIn an effort to better characterize the extent and impact of residency expansion and job placement, the authors conducted a multilevel survey of radiation oncologists exploring the current state of the radiation oncology employment market.MethodsA multilevel survey was conducted using the Qualtrics platform in the spring of 2017. Survey participants were categorized into five groups within radiation oncology: (1) chairpersons, (2) program directors, (3) new practitioners (at least 1 year out of residency), (4) new residency graduates (radiation oncology postgraduate year 5 graduates with new jobs), and (5) medical students. The Wilcoxon-Mann-Whitney test was used to compare Likert scale scores.ResultsA total of 752 participants were surveyed, with an overall response rate among all five groups of 31% and 92% of those completing the entire survey. Chairpersons were more likely to consider expanding their residency programs compared with program directors. Fellowship remained low on the job search, with less than 10% of new graduates and new practitioners interested in fellowship positions. Job satisfaction was high with 85% of new graduates, and 78% of new practitioners moderately to very satisfied with their future or current employment. The vast majority of both new practitioners (85%) and new graduates (81%) was moderately to very satisfied with their location of practice.ConclusionsResident job satisfaction remains high, whereas interest in radiation oncology fellowships remains low. Conflicting perception regarding the job market and residency expansion could have downstream impacts, such as deterring potential applicants.     

The Role of Generative Adversarial Networks in Radiation Reduction and Artifact Correction in Medical Imaging

Adversarial networks were developed to complete powerful image-processing tasks on the basis of example images provided to train the networks. These networks are relatively new in the field of deep learning and have proved to have unique strengths that can potentially benefit radiology. Specifically, adversarial networks have the potential to decrease radiation exposure to patients through minimizing repeat imaging due to artifact, decreasing acquisition time, and generating higher quality images from low-dose or no-dose studies. The authors provide an overview of a specific type of adversarial network called a “generalized adversarial network” and review its uses in current medical imaging research.     

Using Artificial Intelligence to Improve the Quality and Safety of Radiation Therapy

Within artificial intelligence, machine learning (ML) efforts in radiation oncology have augmented the transition from generalized to personalized treatment delivery. Although their impact on quality and safety of radiation therapy has been limited, they are increasingly being used throughout radiation therapy workflows. Various data-driven approaches have been used for outcome prediction, CT simulation, clinical decision support, knowledge-based planning, adaptive radiation therapy, plan validation, machine quality assurance, and process quality assurance; however, there are many challenges that need to be addressed with the creation and usage of ML algorithms as well as the interpretation and dissemination of findings. In this review, the authors present current applications of ML in radiation oncology quality and safety initiatives, discuss challenges faced by the radiation oncology community, and suggest future directions.     

From the Reading Room to the Courtroom—The Use of Molecular Radionuclide Imaging in Criminal Trials

Recent years have witnessed an expanded use of single-photon emission CT and PET for a wide range of clinical applications, including imaging of brain abnormalities. As a result, molecular brain imaging is now being more extensively utilized in criminal cases, in particular in the sentencing phase of a trial. This perspective aims to provide a brief overview for the practicing radiologist of this expanded use of single-photon emission CT and PET in criminal cases and will discuss the role of radiology in this field.