You are here

Technology Management

 

During a 2016 simulation exercise, researchers evaluated the ability of 32 different deep learning algorithms to detect lymph node metastases in patients with breast cancer. Each algorithm’s performance was then compared to that of a panel of 11 pathologists with time constraint (WTC). Overall, the team found that seven of the algorithms outperformed the panel of pathologists, publishing an in-depth analysis in JAMA.

At RSNA 2017 in Chicago, artificial intelligence (AI) and deep learning technologies were everywhere. Attendees rushed to learn as much as possible about AI, countless educational sessions touched on the topic and exhibitors made sure to mention it in their booths as much as possible. I wouldn’t quite say AI took over the show like some have suggested, but it did make quite an impression on everyone walking through the doors of McCormick Place.

The buzz around social media in radiology has skyrocketed in recent years, with more and more departments, private practices and specialists starting to use using the various platforms to their advantage. Of course, it’s about more than just using sites such as Facebook, Twitter and Instagram; to get the most out of these resources, one must also learn the differences between them.

Interest in artificial intelligence (AI) and machine learning at RSNA 2017 seems like it’s unprecedented—but the increased attention is quantifiable. More than 100 sessions delve into the topic at this year’s show in Chicago. Two years ago, less than 10 touched on such concepts.

Social media platforms have quickly become dominant outlets to discuss healthcare, including lung cancer-specific topics across the cancer prevention and control continuum.

 

Recent Headlines

These deep learning algorithms outperformed a panel of 11 pathologists

During a 2016 simulation exercise, researchers evaluated the ability of 32 different deep learning algorithms to detect lymph node metastases in patients with breast cancer. Each algorithm’s performance was then compared to that of a panel of 11 pathologists with time constraint (WTC). Overall, the team found that seven of the algorithms outperformed the panel of pathologists, publishing an in-depth analysis in JAMA.

RSNA in review: Radiologists ready to make the most of AI

At RSNA 2017 in Chicago, artificial intelligence (AI) and deep learning technologies were everywhere. Attendees rushed to learn as much as possible about AI, countless educational sessions touched on the topic and exhibitors made sure to mention it in their booths as much as possible. I wouldn’t quite say AI took over the show like some have suggested, but it did make quite an impression on everyone walking through the doors of McCormick Place.

RSNA 2017: A radiologist’s guide to the differences between Facebook, Twitter and other social media platforms

The buzz around social media in radiology has skyrocketed in recent years, with more and more departments, private practices and specialists starting to use using the various platforms to their advantage. Of course, it’s about more than just using sites such as Facebook, Twitter and Instagram; to get the most out of these resources, one must also learn the differences between them.

RSNA 2017: AI has potential to match the hype

Interest in artificial intelligence (AI) and machine learning at RSNA 2017 seems like it’s unprecedented—but the increased attention is quantifiable. More than 100 sessions delve into the topic at this year’s show in Chicago. Two years ago, less than 10 touched on such concepts.

What do Twitter users have to say about lung cancer?

Social media platforms have quickly become dominant outlets to discuss healthcare, including lung cancer-specific topics across the cancer prevention and control continuum.

Interoperability in Radiology: A Game of Inches

The health IT holy grail of nationwide interoperability remains top of mind in theory yet miles away in practice. The daunting distance of the road ahead was thrown into sharp relief in early October, when Health Affairs published American Hospital Association (AHA) survey data from 2015 showing that two of three U.S. hospitals can’t locate, retrieve, send and/or meaningfully integrate the electronic medical records (EMRs) of patients who received care at other provider sites (Health Aff (Millwood). 2017 Oct 1;36(10):1820-1827). 

Examining AI’s Impact on Breast Imaging

By Working Closely with AI Technologies, Radiologists Are Making Considerable Strides in Breast Cancer Treatment

Just the beginning: 6 applications for machine learning in radiology beyond image interpretation

Discussions about machine learning’s impact on radiology might begin with image interpretation, but that’s only the tip of the iceberg. When it comes to realizing the technology’s full potential, it’s like Bachman Turner Overdrive sang many years ago: You ain’t seen nothing yet.

3 common complaints about using social media and how to overcome them

As social media continues to grow in popularity, radiologists and radiology practices alike are using platforms such as Facebook, Twitter and Instagram to provide additional value to patients. A recent analysis published in the Journal of the American College of Radiology explored some examples of how users can get the most out of these new technological tools, including a look at some of the most common complaints and problems associated with social media.

How deep learning may revolutionize image-based diagnosis

For years, medical researchers and vendors have tried their hand at involving computer aided diagnosis (CAD) into patient care. However, slow integration has allowed for newer cognitive technologies such as deep neural networks, or deep learning technology, to find an onramp into radiology imaging.  

Pages