Dear Imaging Informatics Insider,
Artificial intelligence (AI) continues to show promise for a variety of radiology workflow-enhancing tasks. For example, Italian researchers have developed a software system that uses natural language processing and machine-learning techniques to automatically analyze and classify chest CT reports.
While the software still has room for improvement, the researchers believe it shows potential for improving clinical care and supporting radiology research. Click here to learn more.
Dr. Paul Chang from the University of Chicago recently shared his admiration for the strong emphasis in France on the ethical and humanistic aspects of AI in radiology. Speaking at a seminar in Lyon earlier this month, Chang discussed the marked differences between the views of the French and American radiology communities on AI.
While radiologists in the U.S. aren't ignoring ethical and human factors, they tend to take a more pragmatic -- and perhaps a more self-centered -- approach with respect to AI practices, he said. The French attitude, while also pragmatic, places ethics and patients at the top of the agenda. Click here for our coverage of his presentation.
Meanwhile, France's national professional council, G4, has launched a novel collaboration with other partners to develop a complete AI tool for medical imaging. What are the goals for this initiative? Click here to find out.
U.K. researchers have developed an AI algorithm that can accurately detect and grade the severity of brain lesions on CT scans of patients presenting with stroke or dementia. Click here for our report.
German researchers have trained AI algorithms that can generate a 3D liver model from MRI or CT scans. How did they do it? Click here for all the details.
In other news, social media has played a critical role in helping teleradiologists from all over the world to support local physicians in Syria. Click here for our article.
How can radiology reporting be improved? AuntMinnieEurope.com contributor Dr. Giles Maskell has some practical suggestions. Click here to access his 10 tips.
If you have any tips or suggestions for topics you'd like to see covered in the Imaging Informatics Community, please feel free to drop me a line.