RSNA 2021 Imaging Informatics Preview

Road to RSNA 2021: Imaging Informatics Preview

By Erik L. Ridley, staff writer
November 22, 2021

Our next destination on the Road to RSNA is imaging informatics -- specifically, enterprise imaging, cybersecurity, structured reporting, clinical decision support (CDS), analytics, radiomics, and issues regarding patient access to radiology results. For information on artificial intelligence (AI) topics, you'll want to visit our Artificial Intelligence Preview.

Scientific presentations on imaging informatics at RSNA 2021 will encompass a range of topics, including the effect on radiologist workflow of patient access to imaging results, the effectiveness of using radiological reports and electronic medical record data to predict adverse cardiac events, and the benefits of structured reporting for improving turnaround times. The growing utility of radiomics will also be on display for a variety of clinical indications, including stratifying risk on CT in patients with non-small cell lung cancer and predicting rectal cancer treatment response on MRI.

Although Medicare rules mandating consultation of an approved CDS mechanism to order advanced imaging studies have been delayed -- again -- until January 1, 2023, it's certainly not too early to get up to speed if you haven't already. Scientific presentations this year will discuss, for example, the experience of a pediatric hospital in using CDS for ordering CT exams and the effect of incorporating AI-assisted indications on order appropriateness. You may also want to check out a Monday educational course on best practices to follow when rolling out CDS.

In other RSNA educational opportunities for imaging informatics topics, you can take in a Sunday morning refresher course on cybersecurity for radiology practices, as well as educational courses on the effect of recent legislation on radiology informatics and how to design your imaging platform to be fast, reliable, and ready for disaster recovery. On Monday, a refresher course will also review the imaging informatics clinical "interspace" between radiology and pathology.

What's more, a refresher course on Thursday will delve into the technical issues involved with remote reading and offer strategies for success. In addition, hot topic sessions on Thursday will discuss interactive multimedia reporting and share how imaging informatics tools can be leveraged to engage with patients. An ask-the-expert session will also feature a discussion on how to use informatics tools to measure, display, and monitor performance.

Are you interested in starting or maintaining a point-of-care 3D printing lab? You won't want to miss the RSNA 3D Printing Symposium taking place on Saturday, November 27, from 12:30 p.m. to 5:00 p.m. at McCormick Place. In addition to the Saturday symposium, the RSNA's 3D Printing Special Interest Group is also sponsoring two other sessions: a Sunday educational course on clinical applications for 3D printing and a Wednesday educational course that will enable attendees to have hands-on experience with 3D-printed anatomic models.

See below for our previews of select imaging informatics-related scientific presentations at RSNA 2021. For more information on those talks, as well as other scientific sessions, scientific posters, educational sessions, educational exhibits, refresher courses, and hot topic sessions, view the RSNA 2021 meeting program.

Combining radiomics, AI with PET/MRI helps assess nodal status
Sunday, November 28 | 10:30 a.m.-11:30 a.m. | SSNMMI01-3 | Room N226
Here, researchers will talk about how applying radiomics and machine learning to FDG-PET/MRI can noninvasively assess nodal status and treatment planning for breast cancer patients.
Radiomics helps predict rectal cancer treatment response
Sunday, November 28 | 10:30 a.m.-11:30 a.m. | SSGI01-1 | Room S404
The combination of radiologist assessment and a radiomics classifier can significantly improve the accuracy of MRI for predicting treatment response in cases of rectal cancer, according to this scientific presentation.
Clinical decision-support software gets a helping hand from AI
Sunday, November 28 | 10:30 a.m.-11:30 a.m. | SSIN01-2 | Room E350
In this talk, researchers will share positive results from providing clinicians with artificial intelligence (AI)-assisted clinical indications when ordering imaging studies using clinical decision-support software.
The future of reporting
Radiology imaging is almost entirely digitized, yet the outcome of the whole radiology process -- the report -- is still reliant on free-text dictation, a process that has changed little over the last 50 years.
Does patient image access affect radiologist workloads?
Sunday, November 28 | 10:30 a.m.-11:30 a.m. | SSIN01-6 | Room E350
In this study, a multi-institutional research team found that patient access to radiology images on online patient portals tended not to affect radiologists very much.
Models predict mortality risk on total-body DEXA exams
Sunday, November 28 | 1:00 p.m.-2:00 p.m. | SSMK03-3 | Room S402
Artificial intelligence can spot changes in body composition over time on total-body dual-energy x-ray absorptiometry (DEXA) exams and predict mortality risk, according to this presentation.
Structured reporting speeds up resident reports
Monday, November 29 | 9:30 a.m.-10:30 a.m. | SSIN02-2 | Room S401
Structured reporting can significantly speed up report turnaround times for neuroradiology residents, according to this scientific presentation.
Deep-learning tool can help in total hip arthroplasty surveillance
Tuesday, November 30 | 8:00 a.m.-9:00 a.m. | SSMK05-3 | Room S406B
Research to develop a fully automated deep-learning tool to measure femoral component subsidence on hip x-ray without any user input will be discussed in this Tuesday morning session.
'Plug-and-play' AI method helps with microcalcifications on DBT
Tuesday, November 30 | 9:30 a.m.-10:30 a.m. | SSPH09-6 | Room S405
Researchers will present results from a "plug-and-play" artificial intelligence (AI) algorithm that they say has the potential to improve detection of microcalcifications on digital breast tomosynthesis (DBT) images.
CT radiomics help stratify risk in NSCLC patients
Tuesday, November 30 | 3:00 p.m.-4:00 p.m. | SSIN05-1 | Room S401
In this session, researchers will share how CT radiomics can enable prognostic stratification in patients with non-small cell lung cancer (NSCLC).
Can AI predict radiology study volume and turnaround times?
Wednesday, December 1 | 9:30 a.m.-10:30 a.m. | SSIN06-5 | Room E350
Although an artificial intelligence (AI) algorithm can predict daily radiology study volume, it's still not ready to be used to optimize radiologist scheduling, according to this scientific presentation.
Machine learning predicts adverse cardiac events from reports, EMR
Wednesday, December 1 | 1:30 p.m.-2:00 p.m. | SSCA09-6 | Room E352
Adverse cardiac events can be predicted from machine learning-based analysis of radiology reports and electronic medical record (EMR) data, according to this scientific presentation.
Prediction model forecasts need for COVID-19 resources
Wednesday, December 1 | 1:30 p.m.-2:30 p.m. | SSMS05-5 | Room S405
In this talk, researchers will describe how data in the electronic medical record can be used to predict if a COVID-19 patient will need to be admitted to the hospital.
Deep-learning tool triages women with decreased breast density
Wednesday, December 1 | 3:00 p.m.-4:00 p.m. | SSBR09-4 | Room S406B
In this Wednesday talk, researchers will present findings from their study of nearly 2,700 women that used a convolutional neural network in predicting mammographic density percentage from MRI scans.
What factors affect liver metastasis detection performance?
Thursday, December 2 | 8:00 a.m.-9:00 a.m. | SSPH14-2 | Room S402
Image navigation patterns and subspecialization was associated with better performance of abdominal CT scans to detect liver metastasis, according to this scientific presentation.
What impedes follow-up of incidental lung nodules?
Prerecorded, available throughout the meeting | SPR-NPM-5
In this scientific talk, researchers will discuss how structured recommendations and electronic health record tracking affect the completion rate for follow-up of incidental lung nodules.