"Two roads diverged in a yellow wood," Robert Frost wrote in "The Road Not Taken." That may be fitting this year for digital x-ray on the way to RSNA, where we see familiar paths and also those less traveled.
AI continues to be a significant area of research, with models based on pelvic x-rays and chest x-rays showing good performance in diagnosing sacroiliitis and fractures. Notably, a group pointed out that most software products on the market are approved for adults, and they’ve called for more development of models in pediatrics. To that end, we highlighted at least one effort to fill the gap in detecting medical devices in children’s chest x-rays.
Some studies highlight the value of dual-energy x-ray absorptiometry (DEXA), the gold standard for diagnosing osteoporosis based on bone mineral density measurements. AI now appears to be able to predict mortality and hip fractures from the scans. Yet the modality continues to face barriers due to limited availability to patients. In separate studies this year, researchers questioned just how useful DEXA is for screening for osteoporosis in women under the age of 65 and whether AI can help do the job using chest x-rays.
New technologies are advancing, with dynamic digital radiography and dynamic chest radiography inching closer to clinical use. Both techniques put x-rays in motion and show their capabilities in detecting lung cancer lesions and emphysema in patients with chronic obstructive pulmonary disease.
Finally, a few off-the-beaten-path studies demonstrate the real-world impact of x-rays, with researchers describing their use to meet rising demand in the care of homeless people and how to improve their utilization in detecting osteomyelitis. There are also new recommendations on their use in typically low-yield anatomic sites.
Most of the studies we’ve highlighted below are presented in scientific sessions, and these are just a small sample of digital x-ray research being presented at RSNA 2025. Aside, research in the modality is sprinkled throughout dozens of educational courses, exhibits, scientific poster sessions, and Learning Center Theater presentations. You can view the complete 2025 scientific and educational program on the RSNA website.
Sunday, November 30 | 1:20 p.m.-1:30 p.m. | S4-SSMK02-4 | Room E451A
In this session, a deep-learning model developed by a group in China will be presented that could help clinicians diagnose sacroiliitis from standard x-ray images.
Sunday, November 30 | 1:30 p.m.-1:40 p.m. | S4-SSMK01-4 | Room E451B
In this scientific session on musculoskeletal imaging, recommendations for the use of x-ray exams in 12 potentially low-yield anatomic sites will be presented.
Monday, December 1 | 9:50 a.m.-10:00 a.m. | M3-SSCH03-3 | Room S501
Dynamic chest radiography (DCR) can improve the detection of lung cancer lesions, particularly in cases where conventional chest x-ray is limited by anatomical overlap, according to a study in this session.
Monday, December 1 | 2:20 p.m.-2:30 p.m. | M6-SSMK03-6 | Room E450A
In this scientific session, an AI model will be presented that is designed to predict 10-year mortality and hip fractures on dual-energy x-ray absorptiometry (DEXA) scans.
Tuesday, December 2 | 9:50 a.m.-10:00 a.m. | T3-SSER01-3 | Room N228
In this session, data from a team at Massachusetts General Hospital in Boston will be presented on emergency imaging use among homeless patients over the age of 65.
Tuesday, December 2 | 10:20 a.m.-10:30 a.m. | T3-SSMK05-6 | Room E351
In this session, researchers will describe how reviewing clinical photographs of skin ulcerations alongside foot x-rays can enhance early osteomyelitis diagnosis.
Tuesday, December 2 | 3:10 p.m.-3:20 p.m. | T7-SSMK07-2 | Room E351
In this session, research will be presented on outcomes from a 15-year retrospective analysis of dual-energy x-ray absorptiometry (DEXA) scans of more than 4,500 women.
Tuesday, December 2 | 3:30 p.m.-3:40 p.m. | T7-SSMK07-4 | Room E351
A deep-learning model trained on chest x-rays significantly outperformed the Fracture Risk Assessment Tool (FRAX) in predicting major osteoporotic fractures, according to this presentation.
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.
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.
Thursday, December 4 | 9:40 a.m.-9:50 a.m. | R3-SSCH09-2 | Room E451A
While existing AI models have shown promise for detecting medical devices in adult populations, pediatric radiology remains underserved, according to this scientific presentation.
Thursday, December 4 | 11:20 a.m.-11:30 a.m. | R4-STCE2-3 | Learning Center Theater 2
Noninvasive methods are lacking for detecting reduced alveolar perfusion due to emphysema in patients with chronic obstructive pulmonary disease (COPD), and in this session, researchers present a study suggesting that dynamic digital radiography (DDR) holds promise for filling the role.
