Imaging Informatics

“For radiologists, who generally perform routine activities, involvement in clinical trials increases their workload and raises human resources issues at hospitals which are already running chronic medical deficits,” wrote authors of a new study published in the European Journal of Radiology.

A deep learning platform created by researchers at the Dana-Farber Cancer Institute can identify cancer in radiology reports as well as clinicians, but in a fraction of the time, according to new research published July 25 in JAMA Oncology.

Clinical decision support (CDS) tools can improve the appropriateness scores of advanced imaging orders when used in clinical practice, according to a single-center analysis published in the American Journal of Roentgenology.

A newly created three-dimensional (3D) neural network can improve the detection of pulmonary nodules on CT scans, according to a study published July 12 in PLOS ONE. 

The updated LR-5 criteria for Liver Imaging Reporting and Data System (LI-RADS) version 2018 can improve sensitivity for diagnosing small hepatocellular carcinomas (HCC) compared to LI-RADS 2017.

While AI wasn’t the only topic discussed during the SIIM 2019 annual meeting, every issue seemed to be tied to the emerging technology in one way or another.

Data security has become a serious issue in the U.S., not only for big tech companies like Facebook, but for vendors and institutions looking to use patient imaging information to develop AI platforms.

In the first five months of the EHR, radiology information system (RIS) and PACS deployment project, Robert Paul, a radiology informatics manager at Mayo Clinic in Arizona, lost 60% of his team. He described his efforts to reduce burnout among his staff during a presentation at the SIIM annual conference.

Blockchain could be used to streamline preauthorization, share images between institutions and empower patients. But if healthcare as a whole isn't interested in sharing data, no technology can solve the industry's imaging informatics problems.

 

In order to properly train and validate algorithms, developers need high volumes of quality-labeled data. But such datasets are not easy to obtain.

A new CT- and PET-imaging-based approach—one that entails applying big data to personalizing treatment protocols—is needed to better identify which head and neck carcinoma (HNC) patient subgroups respond to which specific therapies.

A recent study validating the 2017 version of the ultrasound Liver Imaging Reporting and Data System (US LI-RADS) for detecting hepatocellular carcinoma (HCC) identified a few limitations in its scoring.