Although AI often generates headlines for its capabilities in image analysis, the technology arguably has its most significant impact on workflow applications, enabling improved efficiency and quality.
In today’s hectic radiology environment, radiologists could use all the help they can get in dealing with ever-increasing imaging volumes. The use of AI to help in reporting has drawn considerable interest -- and understandably so. A number of presentations will describe the efficiency improvements made possible by AI-assisted reporting.
The utility of large language models (LLMs) in radiology will also be a frequent topic of discussion. Look for studies highlighting progress in utilizing LLMs for applications such as patient communication, billing, and protocoling.
Of course, these are only a sample of the Imaging Informatics content available at McCormick Place this year. For more information on these and other related sessions, including scientific presentations, scientific posters, plenary sessions, and educational courses, visit the RSNA 2025 meeting program. You also won’t want to miss the technical exhibits, including the AI Showcase in the South Exhibit Hall.
Structured reporting tool cuts CCTA interpretation time
Sunday, November 30 | 11:10 a.m.-11:20 a.m. | S2-SSCA01-5 | Room E353C
This cardiac imaging session highlights a study investigating whether an integrated structured reporting (SR) tool for coronary CT angiography (CCTA) could increase reader efficiency and reproducibility -- and reduce cognitive load.
Can AI reduce radiation dose, improve workflow in chest CT?
Sunday, November 30 | 1:00 p.m.-1:10 p.m. | S4-SSIN01-1 | Room E450A
In this talk, researchers will report on the benefits of AI-based automatic positioning and scan range for chest CT exams.
LLMs perform well for annotating radiology reports
Monday, December 1 | 9:30 a.m.-9:40 a.m. | S4-SSIN02-1 | Room E450B
In this scientific presentation, researchers will exhibit a framework for deploying large language models (LLMs) in real-world radiology settings.
Good news, bad news about AI for knee MRI reports
Monday, December 1 | 2:00 p.m.-2:10 p.m. | M6-SSMK03-4 | Room E450A
When it comes to knee MRI exams, partial AI integration without workflow embedding came up short for reducing reporting time, according to researchers leading this Monday afternoon scientific session.
DICOM format 'ideal' for PACS in routine and high-volume clinical settings
Tuesday, December 2 | 3:10 p.m.-3:20 p.m. | T7-SSIN03-2 | Room S404
This session focuses on PACS image storage and AI visualization in DICOM formats, in particular, the storage and transfer efficiency of DICOM Grayscale Softcopy Presentation State (GSPS).
Integrated AI-PACS lightens chest imaging load
Tuesday, December 2 | 3:20 p.m.-3:30 p.m. | T7-SSIN04-3 | Room E450B
This imaging informatics reporting presentation discusses an integrated AI-PACS system designed to minimize workflow disruptions and reduce time to diagnosis for chest x-rays and CT exams.
What to do about imaging exam no-shows
Tuesday, December 2 | 3:20 p.m.-3:30 p.m. | T7-SSNPM02-3 | Room S402
This session tackles the problem of imaging exam no-shows and suggests that radiology administrators may be able to maintain scheduling efficiency and ensure high productivity using proactive, automated patient confirmation processes.
AI liver MRI model mimics radiologists' decision-making?
Tuesday, December 2 | 3:40 p.m.-3:50 p.m. | T7-SSIN03-5 | Room S404
Researchers have developed and tested a liver MRI model and system that first predicts liver tumor imaging features and then integrates them into structured LI-RADS reports.
Survey raises question of written consent to use radiology AI
Wednesday, December 3 | 8:10 a.m.-8:20 a.m. | W1-SSNPM03-2 | Room S402
This early morning session will appeal to those interested in creating a positive patient experience despite the pressure of increasing imaging volumes.
ChatGPT is fast, accurate for ICD-10 coding of PET/CT exams
Wednesday, December 3 | 8:20 a.m.-8:30 a.m. | W1-SSNPM03-3 | Room S402
In this presentation, attendees will learn how ChatGPT can assist radiologists with proper ICD-10 coding of PET/CT exams.
Group explores DL MRI reconstruction as a 'green pathway'
Wednesday, December 3 | 8:40 a.m.-8:50 a.m. | W1-SSNPM03-5 | Room S402
For radiology department leaders interested in sustainable imaging practices, AI-powered MRI offers a "green pathway" for routine clinical workflows, according to details of this Wednesday morning session.
AI image reconstruction in MRI satisfies radiologists and patients
Wednesday, December 3 | 8:50 a.m.-9:00 a.m. | W1-SSNPM03-6 | Room S402
Not only does AI-based MRI reconstruction enhance image quality and diagnostic confidence, but patients like it too, according to this scientific paper.
Mayo trains modified BigBird model for autoprotocoling
Wednesday, December 3 | 9:30 a.m.-9:40 a.m. | W3-SSIN06-1 | Room E450B
This session will provide a performance report for two different models for automatically generating protocols for imaging studies.
Generative AI-assisted CT reads cut reporting time
Thursday, December 4 | 9:40 a.m.-9:50 a.m. | R3-SSIN07-2 | Room E450B
In an example of a live clinical setting application, generative AI increased reporting efficiency for CT studies by nearly one-fourth, researchers have found.
