Road to RSNA 2023: AI Preview – AuntMinnie

Welcome to the first installment of this year’s Road to RSNA preview of the RSNA 2023 meeting. We’re once again providing a modality-by-modality overview of select scientific presentations to serve as your guide to events at McCormick Place.
Our journey along the Road to RSNA begins again with our preview of AI, a topic that has dominated the annual meeting for the past seven years. Research on AI topics will be omnipresent, featuring both in dedicated sessions as well as throughout the scientific program. In fact, it’s hard to find a scientific session without at least one AI-related presentation.
AI’s capability and potential to enhance the practice of radiology will take center stage at RSNA 2023. AI scientific presentations will demonstrate continued progress in areas such as improving and accelerating image reconstruction; triaging critical cases; exploring potential applications for generative AI;  detecting findings initially missed by the radiologist, and, in perhaps one of the potentially more impactful applications for AI, opportunistic screening for risk assessment and incidental disease detection on exams performed for other indications.
Of course, AI also continues to advance in breast imaging, and we’ll provide coverage of key sessions in our upcoming Women’s Imaging section of the Road to RSNA.
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; many other scientific presentations, scientific posters, educational courses and exhibits, and plenary sessions on AI topics also await attendees. For more information on those presentations and other abstracts, check out the RSNA 2023 meeting program.
No trip to the RSNA meeting would be complete without visiting the technical exhibits to get up to speed on the latest commercial developments. And you won’t want to miss the AI Showcase, a dedicated exhibition space in the South Hall for AI firms. The AI Showcase is also the home of the AI Theater, which will host the AI Challenge Recognition Event at 4 p.m. Central Standard Time on November 27 as well as daily presentations from vendors.
Interested in a hands-on educational AI experience suitable for beginners? You’ll want to register for classes in the RSNA’s AI Deep Learning Lab. These sessions, which will be held in the Lakeside Learning Center, will cover a wide range of AI topics, such as basics of natural language processing in radiology, data processing and curation for deep learning, and using ChatGPT for DICOM deidentification.
RSNA attendees focused on practical AI matters will likely appreciate the RSNA’s Imaging AI in Practice interoperability demonstration, which will demonstrate at the AI Showcase how the technology can be integrated into radiology workflow in real-world clinical scenarios. Meanwhile, visitors can stop by the RSNAI Resource Center at the AI Showcase to get up to speed on the society’s Imaging AI certificate program, the Medical Imaging and Data Resource Center (MIDRC), and other RSNA-led imaging AI education and research activities.

AI highlights clinically significant prostate cancer on MRI
Sunday, November 26 | 9:30 a.m.-9:40 a.m. | S1-SSGU01-3 | Room S404
This session features an update on research toward clinical translation of AI in detecting clinically significant prostate cancer on MRI.

How multiple -omics merge to predict Gleason grading

Sunday, November 26 | 9:50 a.m.-10:00 a.m. | S1-SSNMMI01-6 | Room E350
A new multi-omics machine learning model may perform better for the prediction of Gleason grading than current methods used to determine the prognosis and management of prostate cancer, according to this scientific paper.

Generative AI enables patient-specific THA surgical templating
Sunday, November 26 | 1:00 p.m.-1:10 p.m. | S4-SSMK02-2 | Room E353C
Generative AI technology shows potential for making surgical planning for total hip arthroplasty (THA) more efficient, according to researchers from the Mayo Clinic.

Large language-image model segments organs, detects cancer
Sunday, November 26 | 1:50 p.m.-2:00 p.m. | S4-SSIN01-6 | Room S401
In this presentation, researchers from Arizona State University will share how large language-image models can automatically segment 25 abdominal organs on CT exams and detect six tumor types.

AI methods improve detection of Parkinson’s disease
Sunday, November 26 | 1:50 p.m.-2:00 p.m. | S4-SSNR02-6 | Room E352
A systematic review has found that machine-learning and deep-learning techniques are highly sensitive and specific for detecting Parkinson’s disease on dopamine transporter (DaT) SPECT exams.

Can AI opportunistically detect gastric cancer on noncontrast CT? 
Sunday, November 26 | 3:20 p.m.-3:30 p.m. | S5-SSGI04-6 | Room S405
This gastrointestinal imaging-related session will discuss the effectiveness of using an AI model in combination with noncontrast CT exams for the detection of gastric cancer tumors.

AI sharply reduces radiologist reading times on chest CT
Monday, November 27 | 1:30 p.m.-1:40 p.m. | M6-SSNPM01-1 | Room E351

With help from an AI algorithm, radiologists can detect and classify lung nodules on routine clinical chest CT exams faster and more effectively, according to this new study.

AI algorithm helps to spot overlooked fractures
Monday, November 27 | 1:40 p.m.-1:50 p.m. | M6-SSNPM01-2 | Room E351
In this talk, researchers will highlight the potential for AI software in detecting fractures that are often missed on radiographs.

Team studies CT image features for lung adenocarcinoma prognostication
Monday, November 27 | 3:40 p.m.-3:50 p.m. | M7-SSCH04-5 | Room E352
Deep learning-based analysis of morphological and histopathological features on CT can successfully predict survival in lung adenocarcinomas, according to this retrospective dual-institution study.
Machine-learning model detects, characterizes rib fractures on CT
Tuesday, November 28 | 9:30 a.m.-9:40 a.m. | T3-SSER01-1 | Room E351
A machine-learning model can detect traumatic rib fractures on CT scans and automatically provide a fracture severity score, according to this scientific presentation.

CT body composition metrics portend post-TIPS mortality
Tuesday, November 28 | 9:40 a.m.-9:50 a.m. | T3-SSIR02-2 | Room S501
CT body composition metrics calculated by an AI model can improve mortality predictions in patients receiving a transjugular intrahepatic portosystemic shunt (TIPS), according to this presentation.

AI algorithm predicts morbidity, mortality on spine DEXA exams
Tuesday, November 28 | 10:00 a.m.-10:10 a.m. | T3-SSMK05-4 | Room E352
In this Tuesday morning talk, researchers will describe how a deep-learning algorithm’s assessment of biological age on dual-energy x-ray absorptiometry (DEXA) exams can facilitate morbidity and mortality predictions.

CT radiomics can help classify indeterminate solitary pulmonary nodules
Tuesday, November 28 | 10:00 a.m.-10:10 a.m. | T3-SSMS02-4 | Room N228
CT radiomics analysis can be a viable noninvasive option for aiding management decisions of indeterminate solitary lung nodules found on detected by noncontrast chest CT scans in colorectal cancer patients, this study has found.

Can CAD software reduce missed fractures in the ED?
Tuesday, November 28 | 10:10 a.m.-10:20 a.m. | T3-SSMK06-5 | Room E351
Deep learning-based computer-aided detection (CAD) software shows potential for helping to avoid missed fractures on radiographs in the emergency department (ED), according to this talk.

AI analysis of chest CT exams predicts cardiovascular disease
Tuesday, November 28 | 3:00 p.m.-3:10 p.m. | T7-SSCA06-1 | Room E353B
A deep-learning algorithm can predict a patient’s risk of atherosclerotic cardiovascular disease (ASCVD) from analysis of a single chest CT image, according to a group of researchers from Harvard Medical School.

Algorithm classifies patients with autism spectrum disorder
Wednesday, November 29 | 9:40 a.m.-9:50 a.m. | W3-SSNR11-2 | Room E353B
A machine learning-based method for brain MRI exams can classify patients with autism spectrum disorder, according to this scientific paper.

Opportunity for osteoporosis check on lumbar spine plain radiographs
Wednesday, November 29 | 10:00 a.m.-10:10 a.m. | W3-SSMK08-4 | Room E450A
A deep learning-based framework for automated screening of osteoporosis on lumbar spine plain radiographs shows potential as another way to opportunistically make use of imaging studies performed for other indications, according to this presentation.

Deep-learning model can spot patients at high risk of COPD
Thursday, November 30 | 8:20 a.m.-8:30 a.m. | R1-SSCH09-3 | Room E352
This scientific presentation will present external validation results for a deep-learning model in identifying individuals at high risk of incident chronic obstructive pulmonary disease (COPD) on routine outpatient chest x-rays (CXR).

Algorithm hunts for unreported osteoporosis markers on chest x-rays
Thursday, November 30 | 8:50 a.m.-9:00 a.m. | R1-SSCH09-5 | Room E352
An AI algorithm can find radiographic markers for osteoporosis that are common but often not reported on radiology reports, according to this scientific paper.

AI software flags missed intracranial aneurysms on CTA
Thursday, November 30 | 9:40 a.m.-9:50 a.m. | R3-SSNR15-2 | Room S402
In this talk, researchers from Tel Aviv University in Israel will describe how an AI algorithm can retrospectively detect intracranial aneurysms that had been missed on CT angiography (CTA) exams.