Diagnostic Reading #16: Five “Must Read” Articles on HIT and Radiology
Reading Time: 3 minutes read
News this week: increasing tech adoption in radiography; optical imaging in cancer detection.
This week’s articles in Diagnostic Reading include: deep learning with radiologist oversight can boost efficiency of liver lesion segmentation; a near-infrared imaging technique can detect deep tumors before the cancer grows beyond a few cells; a study identifies ways to increase adoption of new technologies in radiography; tracking follow-up imaging adherence rates can lead to better patient care; and natural language processing could help radiology providers anticipate demand.
When manually corrected by radiologists, an AI system for automatically detecting and segmenting colorectal metastases in the liver can improve interpretative efficiency, according to a study published in Radiology: Artificial Intelligence.
MIT researchers have developed a near-infrared imaging technique that can detect tumors deep in internal tissue before the cancer grows beyond a few hundred cells. The team hopes to take the technology to oncology imaging specialists who may be able to tap it for early diagnosis of ovarian and other cancers that are hard to find until they’ve progressed to late stages.
Guide to increasing adoption of new technology in radiography – Everything Rad
A recent study identified radiographers’ ideas, views and perceptions of technology. It also identified opportunities to increase adoption of new technology.
Tracking follow-up imaging adherence rates can lead to better patient care – Radiology Business
Follow-up imaging adherence rates vary based on a number of factors, according to research published in the American Journal of Roentgenology. Authors noted that closely monitoring patterns could help providers engage patients and minimize risk. Failure to comply with imaging follow-up recommendations in a timely manner is common and can lead to delayed treatment, poor patient outcomes, complications, unnecessary testing, lost revenue and medical malpractice risk.
Natural language processing could help radiology providers anticipate demand – Radiology Business
Natural language processing (NLP) could help radiology providers anticipate fluctuations in demand and provide better patient care, according to a new study published in the Journal of the American College of Radiology. The authors explore whether a NLP approach could be implemented that extracts data from free-text radiology reports and helps providers anticipate when demand for imaging resources may be higher than normal.