Deep Learning in Radiology.

As radiology is inherently a data-driven specialty, it is especially conducive to utilizing data processing techniques. One such technique, deep learning (DL), has become a remarkably powerful tool for image processing in recent years. In this work, the Association of University Radiologists Radiology Research Alliance Task Force on Deep Learning provides an overview of DL for the radiologist. This article aims to present an overview of DL in a manner that is understandable to radiologists; to examine past, present, and future applications; as well as to evaluate how radiologists may benefit from this remarkable new tool. We describe several areas within radiology in which DL techniques are having the most significant impact: lesion or disease detection, classification, quantification, and segmentation. The legal and ethical hurdles to implementation are also discussed. By taking advantage of this powerful tool, radiologists can become increasingly more accurate in their interpretations with fewer errors and spend more time to focus on patient care.

Building for tomorrow today: opportunities and directions in radiology resident research.

RATIONALE AND OBJECTIVES: With rapid scientific and technological advancements in radiological research, there is renewed emphasis on promoting early research training to develop researchers who are capable of tackling the hypothesis-driven research that is typically funded in contemporary academic research enterprises. This review article aims to introduce radiology residents to the abundant radiology research opportunities available to them and to encourage early research engagement among trainees. MATERIALS AND METHODS: To encourage early resident participation in radiology research, we review the various research opportunities available to trainees spanning basic, clinical, and translational science opportunities to ongoing research in information technology, informatics, and quality improvement research. CONCLUSIONS: There is an incredible breadth and depth of ongoing research at academic radiology departments across the country, and the material presented herein aspires to highlight both subject matter and opportunities available to radiology residents eager to engage in radiologic research. The opportunities for interested radiology residents are as numerous as they are broad, spanning the basic sciences to clinical research to informatics, with abundant opportunities to shape our future practice of radiology.

Online social networking for radiology.

Online social networking services have changed the way we interact as a society and offer many opportunities to improve the way we practice radiology and medicine in general. This article begins with an introduction to social networking. Next, the latest advances in online social networking are reviewed, and areas where radiologists and clinicians may benefit from these new tools are discussed. This article concludes with several steps that the interested reader can take to become more involved in online social networking.

Mobile computing for radiology.

The rapid advances in mobile computing technology have the potential to change the way radiology and medicine as a whole are practiced. Several mobile computing advances have not yet found application to the practice of radiology, while others have already been applied to radiology but are not in widespread clinical use. This review addresses several areas where radiology and medicine in general may benefit from adoption of the latest mobile computing technologies and speculates on potential future applications.

Radiology research and medical students.

Fostering radiology research among medical students can enhance a student's interest and understanding of radiology and research. It increases the academic productivity of the mentor and the department. Radiology faculty and departments should actively seek to recruit and engage students in research. Once involved, students benefit greatly from being given clear responsibility, close supervision, timely feedback, and a degree of autonomy. At the heart of the student research process is the crucial mentor-mentee relationship, and mentors should be cognizant of their vital role and methods of encouraging and enhancing this relationship. Ultimately, the advancement of the field of radiology depends on constant innovation and improvement. Radiology research by medical students fuels both innovation and the development of future academic radiologists and physician-scientists, helping to secure future growth for our field.

Impact of concurrent diagnostic level CT with PET/CT on the utilization of stand-alone CT and MRI in the management of head and neck cancer patients.

PURPOSE OF THE REPORT: This study aims to determine if the expansion of a PET/CT service to include simultaneous contrast-enhanced CT with PET (PET/DCT) leads to a reduction of supplemental diagnostic CT (sCT) performed within a 6-month period centered around PET/CT for initial treatment planning of patients with head and neck cancers. PATIENTS AND METHODS: There were 91 patients with head and neck cancers who had a non-contrast-enhanced PET/CT with CT (PET/aCT), and 153 patients had a PET/DCT. We compared the utilization of sCT before and after PET/aCT or PET/DCT. Logistic regression analysis, unpaired t test, and analysis of variance were performed. RESULTS: Among the 75 patients who had sCT scans in the 3 months before their PET/CT, 44 (58.7%) scans were performed in patients who had a PET/aCT and 31 (41.3%) scans were performed in patients who had a PET/DCT (P < 0.001). Among the 36 patients who had a CT in the 3 months after their baseline PET/CT, 23 (63.9%) were performed in patients who had a baseline PET/aCT and 13 (36.1%) were performed in patients who had a baseline PET/DCT (P < 0.001). The adjusted odds ratio for performing an sCT within 3 months before and after baseline PET/DCT scan as opposed to a PET/aCT scan was 0.24 (P < 0.001) and 0.31 (P < 0.01), respectively. CONCLUSIONS: The opportunity to order simultaneous diagnostic CT imaging with PET/CT (PET/DCT) reduced the referrals for stand-alone CT neck imaging in the initial treatment plan of head and neck cancer patients when compared to a service that only offered the PET/CT scan with CT for attenuation correction (PET/aCT).