Radiology in public focus

Press releases were sent to the medical news media for the following articles appearing in recent issues of RSNA Journals.

Figure 2 Chae

Flow diagram for feature selection and deep-radiomics model development. LASSO = least absolute shrinkage and selection operator, MLP = multilayer perceptron, Model-C = model with clinical features, Model-T = model with texture features, Model-TC = model with texture and clinical features, Model-D = model with deep features, Model-DC = model with deep and clinical features, Model-DT = model with deep and texture features, Model-DTC = model with deep, clinical, and texture features.

https://doi.org/10.1148/ryai.210212 © RSNA 2022 

 

AI Can Diagnose Osteoporosis on Hip X-ray  

A new method that combines imaging information with AI can diagnose osteoporosis from hip X-rays, according to a study in Radiology: Artificial Intelligence. Researchers said the approach could help speed treatment to patients before fractures occur.

People with osteoporosis are susceptible to fracture associated with bone fragility, resulting in poor quality of life and increased mortality. According to statistics from the International Osteoporosis Foundation, one in three women worldwide over the age of 50 years and one in five men will experience osteoporotic fractures in their lifetime.

Early screening for osteoporosis with dual-energy X-ray absorptiometry (DXA) to assess bone mineral density is an important tool for timely treatment that can reduce the risk of fractures. However, the low availability of the scanners and the relatively high cost has limited its use for screening and post-treatment follow-up.

In contrast, plain X-ray is widely available and is used frequently in daily practice. Despite these attributes, it has been relatively underutilized in the management of osteoporosis because diagnosing osteoporosis using only X-rays is challenging even for an experienced radiologist.

Study author Hee-Dong Chae, MD, from the Department of Radiology at Seoul National University Hospital in Korea, and colleagues developed a model that can automatically diagnose osteoporosis from hip X-rays.

Using almost 5,000 hip X-rays from 4,308 patients obtained over more than 10 years, they developed the models with a variety of deep, clinical and texture features and then tested them externally on 444 hip X-rays from another institution.

The deep-radiomics model with deep, clinical and texture features was able to diagnose osteoporosis on hip X-rays with diagnostic performance that was superior to the models using either texture or deep features alone, thus enabling opportunistic diagnosis of osteoporosis.

“Our study shows that opportunistic detection of osteoporosis using these X-ray images is advantageous, and our model can serve as a triage tool recommending DXA in patients with highly suspected osteoporosis,” Dr. Chae said.

For More Information

Access the Radiology: Artificial Intelligence study, “Deep Radiomics-based Approach to the Diagnosis of Osteoporosis Using Hip Radiographs,” at RSNA.org/AI.

Fig 3 Vachani

Representative axial CT images of pulmonary nodules included in the study. (A) Malignant nodule with a lung cancer prediction score of 10. (B) Benign nodule with a lung cancer prediction score of 2.

https://doi.org/10.1148/radiol.212182 © RSNA 2022

Researchers Use AI to Predict Cancer Risk of Lung Nodules

An AI tool helps doctors predict the cancer risk in lung nodules seen on CT, according to a new study published in Radiology.

Pulmonary nodules appear as small spots on the lungs on chest imaging and have become a much more common finding as CT has gained favor over X-rays for chest imaging.

Study senior author Anil Vachani, MD, director of clinical research in the section of Interventional Pulmonology and Thoracic Oncology at the Perelman School of Medicine, University of Pennsylvania, Philadelphia, and colleagues evaluated an AI-based computer-aided diagnosis tool to assist clinicians in assessing pulmonary nodules on chest CT.

In the study, six radiologists and six pulmonologists made estimates of malignancy risk for nodules using CT imaging data alone. They also made management recommendations such as CT surveillance or a diagnostic procedure for each case without and with the AI tool.

A total of 300 chest CTs of indeterminant pulmonary nodules were used in the study. The researchers defined indeterminant nodules as those between five and 30 millimeters in diameter.

Analysis showed that the use of the AI tool improved estimation of nodule malignancy risk on chest CT. It also improved agreement among the different readers for both risk stratification and management recommendations.

“The readers judge malignant or benign with a reasonable level of accuracy based on imaging itself, but when you combine their clinical interpretation with the AI algorithm, the accuracy level improves significantly,” Dr. Vachani said.

For More Information

Access the Radiology study, “Artificial Intelligence Tool for Assessment of Indeterminate Pulmonary Nodules Detected with CT,” and the editorial, “Artificial Intelligence Improves Radiologist Performance for Predicting Malignancy at Chest CT,” at RSNA.org/Radiology.

Media Coverage of RSNA

In May, 993 RSNA-related news stories were tracked in the media. These stories had over 304 million audience impressions.

Coverage included KTTV-TV (Los Angeles), KCPQ-TV (Seattle), U.S. News & World Report, Pittsburgh Post-Gazette, MSN.com, MedPage Today, Drugs.com, HealthDay, ScienceDaily, Applied Radiology, Diagnostic Imaging, Health Imaging News and Radiology Business.

To view links to select RSNA-related news stories, visit RSNA.org/Media

A Trusted Patient Resource Has Fresh Content, New Look  

A cleaner, more modern look is just one of several recent updates to RadiologyInfo.org. The site, sponsored by RSNA and the American College of Radiology, is a unique resource that doctors can share with their patients to help guide them through their radiology experience.

RadiologyInfo.org contains over 260 procedure, exam and disease descriptions covering diagnostic and interventional radiology, nuclear medicine, radiation therapy and radiation safety. It undergoes routine content and accessibility review with new patient resources added regularly. Recent additions include new articles that are more targeted on specific diseases, conditions and related imaging procedures, as well as Spanish language captioning for many of the site’s informative videos.

There is also expanded pediatric content and new iconography to call out imaging tests and treatments with pediatric-specific information. A special section entitled RadInfo 4 Kids provides focused videos, games and activities for children. The video library includes several episodes of the “Story Time” series presented by Sherry Wang, MBBS, FRANCZR, with versions also available in Mandarin. According to Dr. Wang, the series is intended to be used in tandem with the site’s written material to help both children and their parents and guardians better understand what to expect during an imaging procedure.

Plans for RadiologyInfo.org include expansion into the post-service arena to help patients understand and navigate their radiology reports. Stay informed about the latest RadiologyInfo.org activities on Twitter @RadiologyInfo_ and on Facebook at Facebook.com/RadiologyInfo.

RadiologyInfo.org