Journal highlights
The following are highlights from the current issues of RSNA’s peer-reviewed journals.
Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
Despite the increasing use of CT and MRI, chest radiography remains the most performed radiologic examination worldwide. It is still widely used because of its cost-effectiveness and low radiation dose. However, the interpretation of chest radiographs can be challenging and make it difficult to detect abnormalities in some locations, especially if these abnormalities are small or subtle.
Because there is often high variability in chest radiograph analysis, AI-based computer-aided detection (CAD) systems have been developed. Advantages of automated chest radiograph analysis are numerous and include an increased sensitivity for subtle findings, prioritization of urgent cases and automation of tedious daily tasks. The use of CAD systems can also help emergency physicians and radiologists-in-training when senior radiologists are unavailable.
In an article published in Radiology, Souhail Bennani, MD, Cochin Hospital, Paris, and colleagues conducted a study that aimed to explore the potential benefit of AI assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, both with and without AI assistance.
This retrospective study consisted of 500 patients with 522 abnormalities visible on 241 radiographs. All patients underwent chest radiography and thoracic CT. AI-assisted chest radiography interpretation resulted in increased sensitivity of 6%–26% for all readers, including thoracic radiologists, general radiologists and radiology residents.
“AI assistance in chest radiograph interpretation may enhance sensitivity without affecting specificity for all readers, regardless of their level of expertise or seniority or the type of abnormality and may reduce the reading times for radiographs with and those without abnormalities,” the authors conclude.
Read the full article, “Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs.” Follow the Radiology editor on X @RadiologyEditor.
Multimodality Imaging in Metabolic Syndrome
Metabolic syndrome is a constellation of risk factors associated with the development of atherosclerotic cardiovascular disease and type 2 diabetes, as well as liver disease, renal impairment, neurologic dysfunction and malignancies. It is estimated that 20%–25% of the worldwide adult population has metabolic syndrome.
Lifestyle modifications and targeted treatment of specific risk factors can minimize downstream complications of metabolic syndrome. Hence, early recognition of these risk factors is imperative. While imaging is not typically used to diagnose metabolic syndrome or its risk factors, it plays a significant role in assessing the effects of the disease.
In an article published in RadioGraphics, Kevin Kalisz, MD, Mayo Clinic, Rochester, MN, and colleagues explain how current and emerging imaging techniques provide insight into metabolic syndrome risk factors and target organ damage.
The authors note that CT and MRI are the primary tools for evaluating cardiovascular risk through the quantification of excess fat in tissue and organs in the body. PET is used to detect signs of insulin resistance. CT angiography provides comprehensive evaluation of the coronary and systemic arteries, while cardiac MRI assesses cardiac structure and function.
The authors also comment on the utility of US, CT and MRI in assessing liver damage. “Metabolic syndrome is a common entity with causes and risk factors apparent at routine imaging. A multimodality imaging approach can offer comprehensive evaluation of its adverse effects. Imaging can also provide many useful biomarkers to potentially monitor effects of therapies,” the authors conclude.
Read the full article, “Multimodality Imaging in Metabolic Syndrome: State-of-the-Art Review,” and invited commentary at RSNA.org/RadioGraphics. This article is also available for CME at RSNA.org/Learning-Center-RG. Follow the RadioGraphics editor on X @RadG_Editor.
Disparities in the Demographic Composition of the Cancer Imaging Archive
Disparities in cancer incidence and mortality across race, ethnicity and socioeconomic status may reflect health inequalities in the U.S. Cancer health disparities result from several factors, including differences in health care coverage, socioeconomic status, exposure to risk factors and genetic ancestry.
Notably, the biorepositories and data archives that help us better understand and treat cancer are largely composed of data from individuals with European ancestry. This leads to inadequate representation of racial and ethnic minorities and hinders the generalizability of studies using them, thus perpetuating disparities across marginalized groups.
In an article published in Radiology: Imaging Cancer, Aidan Dulaney, BS, and John Virostoko, PhD, MSCI, Dell Medical School, University of Texas at Austin, sought to characterize the demographic distribution of The Cancer Imaging Archive (TCIA) studies and compare them with those of the U.S. cancer population.
Of 189 studies in TCIA up until April 2023, a total of 83 human cancer studies contained supporting demographic data. The researchers calculated the median patient age, and the sex, race and ethnicity proportions of each study. The median age of the TCIA patients was 6.84 years lower than that of the U.S. cancer population.
There were more female than male patients, and American Indian and Alaska Native, Black or African American, and Hispanic patients were underrepresented in TCIA studies by 47.7%, 35.8% and 14.7%, respectively.
“The results demonstrate that the patient demographics of TCIA data sets do not reflect those of the U.S. cancer population, which may decrease the generalizability of artificial intelligence radiology tools developed using these imaging data sets,” the authors conclude.
Read the full study, “Disparities in the Demographic Composition of The Cancer Imaging Archive,” and invited commentary at RSNA.org/ImagingCancer. Follow the Radiology: Imaging Cancer editor on X @RadIC_Editor.
Elevate Your Impact: Submit for Recognition and Reach
Enhance the influence of your work and make it more accessible to accelerate progress in the field. Submit your research to Radiology Advances, RSNA’ new open access, peer reviewed journal.
Published in partnership with Oxford University Press, Radiology Advances focuses on the timely publication of a broad spectrum of high-quality radiology and medical imaging research. It is a global, open access forum offering compelling research related to the emerging technologies and clinical innovations that will affect the future of radiology practice and patient outcomes.
The Radiology Advances editorial board is led by Susanna I. Lee, MD, PhD, and represents three continents and boasts expertise in more than 20 subspecialty areas. Submissions to the journal undergo a rigorous review process that includes double-anonymized peer review, ensuring the highest quality research for this growing publication.
Learn more about submissions to Radiology Advances at RSNA.org/Journals.