Welcome to the first installment of this year’s Road to RSNA preview for RSNA 2025. We’re once again providing a modality-by-modality overview of select scientific presentations to serve as your guide to events at McCormick Place.
In what has become an annual tradition at AuntMinnie, AI is our first stop on our journey along the Road to RSNA. This section will focus on pixel-based AI; stay tuned for coverage of AI in reporting and other workflow applications in our upcoming Imaging Informatics section. Breast imaging AI research will also be included in our Women’s Imaging preview.
Opportunistic screening research has really expanded this year, with studies demonstrating, for example, how AI-powered body composition analysis can be used to predict future risk of diabetes, osteoporosis, and major adverse cardiovascular events on routine imaging studies. Postdeployment monitoring of AI is also drawing interest, as researchers explore techniques for maintaining quality assurance.
Triage applications remain a key use case for radiology AI. Look for several presentations that assess performance for detecting critical findings such as intracranial hemorrhage. Prostate MRI also continues to be a fertile area of research, with a number of talks sharing its benefits for bolstering the performance of less-experienced readers and detailing results in a variety of imaging settings.
See below for previews of AI-related scientific talks we’re highlighting at this year's RSNA meeting. These are just a sample of the content on offer, however. Attendees can also look forward to a plethora of other scientific presentations, scientific posters, plenary sessions, and educational courses and exhibits on AI topics, including the always-popular AI Showcase in the South Exhibit Hall. For more information on those presentations and other abstracts, check out the RSNA 2025 meeting program.
Postdeployment monitoring needed for AI software updates
Sunday, November 30 | 11:20 a.m.-11:30 a.m. | SSCA01-6 | Room E353C
If this scientific presentation is any indication, AI software updates should undergo local validation and performance monitoring following deployment.
AI approach may lead to earlier PDAC detection
Sunday, November 30 | 1:40 p.m.-1:50 p.m. | SSIN01-5 | Room E450A
Johns Hopkins University researchers will share an update on their work to advance AI algorithms for detecting early-stage pancreatic ductal adenocarcinoma (PDAC).
AI boosts performance of nonexpert radiologists on prostate MRI
Sunday, November 30 | 2:40 p.m.-2:50 p.m. | S5-SSGU02-2 | Room E353B
An AI algorithm can increase the accuracy of nonexpert radiologists and decrease interreader variability, according to this scientific presentation.
Opportunistic screening predicts risk of diabetes
Sunday, November 30 | 3:20 p.m.-3:30 p.m. | S5-SSCA02-6 | Room S503
In this presentation, researchers will describe how AI-powered analysis of coronary artery calcium (CAC) on lung CT exams can enable early identification of individuals at risk for diabetes.
Automated CT body composition analysis predicts mRCC prognosis
Monday, December 1 | 8:30 a.m.-8:40 a.m. | M1-SSGU03-4 | Room E353B
In this talk, researchers will share how AI analysis of sarcopenia and myosteatosis parameters from routine CT exams can stratify risk in patients with metastatic renal cell carcinoma (mRCC).
AI makes the grade for opportunistic assessment of BMD
Monday, December 1 | 9:30 a.m.-9:40 a.m. | M3-SSCH03-1 | Room S501
An international trial has confirmed the strong performance of AI software for opportunistically detecting osteopenia and osteoporosis from chest radiographs.
ML enables early coronary atherosclerosis management
Monday, December 1 | 1:40 p.m.-1:50 p.m. | SSVA02-2 | Room S503
This vascular imaging session presents an AI-facilitated management strategy for early-stage coronary atherosclerosis in asymptomatic populations.
Model monitors radiology AI tools for potential failures
Tuesday, December 2 | 3:10 p.m.-3:20 p.m. | SSIN04-2 | Room E450B
This session will introduce a method for post-deployment monitoring of commercial radiology AI software and flagging potential failures across multiple products.
Model supports pancreatic cancer surgical risk stratification
Tuesday, December 2 | 3:20 p.m.-3:30 p.m. | SSGI08-3 | Room E353A
For this study, researchers developed an automated framework that may be useful for surgical planning and resection assessment in patients with pancreatic ductal adenocarcinoma (PDAC).
U.K. group evaluates CE-marked AI tools for pneumothorax accuracy
Wednesday, December 3 | 9:30 a.m.-9:40 a.m. | SSER02 | Room N228
In this scientific presentation, researchers from the U.K. will share performance analysis of nine AI tools for detecting pneumothorax on chest radiographs.
Study reinforces radiologist role in ICH diagnosis
Wednesday, December 3 | 9:50 a.m.-10:00 a.m. | SSER02-3 | Room N228
Although AI can reduce the number of missed intracranial hemorrhages (ICH) in emergencies, radiologists remain the gold standard for diagnosis, researchers have found.
AI-driven triage alerts in the ED deemed 'effective safety net'
Wednesday, December 3 | 10:10 a.m.-10:20 a.m. | SSER02-5 | Room N228
French researchers have found that AI-driven triage alerts serve as "effective safety nets," improving the detection of missed critical findings in emergency departments (EDs).
How are adult-trained radiology AI models faring in pediatrics?
Wednesday, December 3 | 3:20 p.m.-3:30 p.m. | SSPD04-3 | Room E350
Researchers are looking for safe ways to repurpose adult radiology AI models across pediatric imaging, but we're not there yet, according to this afternoon presentation.
AI shows promise in liver contrast-enhanced ultrasound
Wednesday, December 3 | 3:30 p.m.-3:40 p.m. | W7-SSGI13-4 | Room E451B
In this talk, researchers will update attendees on their efforts to apply AI to summarize liver contrast-enhanced ultrasound exams and characterize lesions.
Can AI predict major adverse cardiac events from chest CT studies?
Thursday, December 4 | 8:40 a.m.-8:50 a.m. | R1-SSCA09-5 | Room E353C
An AI algorithm shows potential for utilizing routine chest CT exams to opportunistically predict patient risk of having a major adverse cardiac event (MACE), according to this scientific presentation.
Can AI MRI support population-based screening for prostate cancer?
Thursday, December 4 | 8:40 a.m.-8:50 a.m. | R6-SSGU07-2 | Room E353B
In this session, researchers will present results from an international study assessing the performance of prostate MRI AI software in a variety of practice settings.
AI could enhance diagnosis of multiple sclerosis
Thursday, December 4 | 9:30 a.m.-9:40 a.m. | SSNR13-1 | Room N228
In this award-winning presentation, researchers will show how a deep-learning model can be useful in diagnosing multiple sclerosis.
Large radiology practice likes generative AI report tool
Thursday, December 4 | 9:50 a.m.-10:00 a.m. | SSCH09-3 | Room E451A
Radiologists found that a generative AI model for interpreting chest x-rays was useful for worklist prioritization and quality assurance at their large radiology practice.
Widget helps alleviate false-positive AI results for ICH
Thursday, December 4 | 10:10 a.m.-10:20 a.m. | SSNR13-5 | Room N228
This session addresses the challenge of high false-positive rates associated with using AI to detect intracranial hemorrhage (ICH).
Model may aid adrenal mass classification
Thursday, December 4 | 2:20 p.m.-2:30 p.m. | SSGU07-6 | Room E353B
Researchers have developed an automated machine-learning tool that they say can detect adrenal masses at scale in routine clinical practice.
