The Roadie awards are presented to researchers whose abstracts receive the most page views in our Road to RSNA previews of scientific sessions at the annual RSNA show. Roadie awards are presented in each of our eight areas of focus, from Artificial Intelligence to Imaging Informatics.
Below are the Roadie winners for 2019. To view our entire Road to RSNA preview, visit our RADCast @ RSNA.
Holographic light-field displays enabled radiologists to examine virtual 3D models based on medical images directly on a computer screen without having to wear a specialized headset in a study detailed in this Monday poster presentation. The technology could bring 3D viewing directly to the radiologist's workstation.
In this presentation, researchers from India will describe how a deep-learning algorithm shows potential for producing accurate reports of chest radiographs. The researchers set out to study the effects of artificial intelligence (AI) for reducing hedging in radiology reports.
Photon-counting CT can match the image quality of conventional sinus and temporal bone CT at approximately one-sixth the radiation dose, according to researchers from the Mayo Clinic in Rochester, MN. They investigated the extent to which a whole-body photon-counting CT scanner at their institution could reduce radiation dose without noticeably altering the image quality of head CT scans.
A novel triple-layer flat-panel digital detector design could solve current deficiencies in dual-energy digital radiography. The detector features three stacked sensors, each with its own cesium iodide scintillator, that generate three images per exposure.
Researchers from Massachusetts will describe how the combination of structured reporting and reader expertise can improve the diagnosis and staging of endometriosis on MRI. The researchers sought to understand the current gaps in imaging in a real clinical setting by comparing the diagnostic yield for presurgical pelvic MRI scans with three different review methods: routine, structured, and expert review.
Should clinicians proceed with an MRI scan if a patient refuses to remove a metal piercing? Researchers from the University of Rochester put that question to the test. They found that the answer depends on the accessory in a test performed on a 3-tesla MRI scanner.
In this poster presentation, researchers will discuss how ultrasound tomography is a feasible and accurate tool for characterizing stiffness of breast lesions. The findings offer an alternative to handheld ultrasound, which does provide tissue stiffness and elasticity information but can be operator dependent.
An artificial intelligence (AI) algorithm can be used for standalone interpretation of mammograms that have a low probability of being malignant, researchers from the University of Southern California will report in this presentation.