• AI
  • Molecular Imaging
  • CT
  • X-Ray
  • Ultrasound
  • MRI
  • Facility Management
  • Mammography

Study Shows Benefits of AI in Detecting Lung Cancer Risk in Non-Smokers

News
Article

Artificial intelligence (AI) assessments of chest X-rays identified 28 percent of a 17,000 plus cohort of never-smokers as being at high-risk for lung cancer, according to research to be presented at the annual Radiological Society of North America (RSNA) conference next week.

In a large study of never-smokers, researchers found that artificial assessment of routine chest X-rays identified a high risk of lung cancer in 28 percent of patients who had over double the risk of those deemed to have low risk.

For the study, which will be presented at the annual Radiological Society of North America (RSNA) conference next week in Chicago, researchers evaluated the capability of a deep learning model to assess lung cancer risk based on routine outpatient chest X-rays from 17,407 never-smokers (mean age of 63).

The deep learning model detected a high risk for lung cancer in 28 percent of the cohort and 2.9 percent of these patients were subsequently diagnosed with lung cancer, according to the study authors.

Study Shows Benefits of AI in Detecting Lung Cancer Risk in Non-Smokers

ln a study of over 17,000 never-smokers, an emerging deep learning model detected a high risk for lung cancer in 28 percent of the cohort and 2.9 percent of these patients were subsequently diagnosed with lung cancer. (Images courtesy of RSNA.)

"This AI tool opens the door for opportunistic screening for never-smokers at high risk of lung cancer, using existing chest X-rays in the electronic medical record," said senior study author Michael T. Lu, M.D., M.P.H., the director of artificial intelligence and co-director of the Cardiovascular Imaging Research Center (CIRC) at Massachusetts General Hospital (MGH). "Since cigarette smoking rates are declining, approaches to detect lung cancer early in those who do not smoke are going to be increasingly important."

Never-smokers have 10 to 20 percent of lung cancers diagnosed in the United States, according to the American Cancer Society. This study’s high-risk group with subsequent lung cancer diagnosis in 2.9 percent of patients more than doubled the 1.3 percent six-year risk threshold for the use of CT lung cancer screening as recommended by the National Comprehensive Cancer Guidelines, according to the study authors.

However, as the researchers pointed out, screening guidelines are geared to current smokers or those who have smoked heavily in the past.

"Current Medicare and USPSTF guidelines recommend lung cancer screening CT only for individuals with a substantial smoking history. However, lung cancer is increasingly common in never-smokers and often presents at an advanced stage,” noted lead study author Anika S. Walia, B.A., a researcher at the CIRC at MGH and medical student at the Boston University School of Medicine.

(Editor’s note: For related content, see “FDA Clears AI-Powered Software for Lung Nodule Detection on X-Rays,” “Can Deep Learning Enhance Pulmonary Nodule Detection on Chest X-Rays?” and “Study: AI Assessment of Chest CT May Predict Multiple Mortality Risks.”)

In their research, the study authors also found that the high-risk patients identified with the deep learning model had more than double the risk of low-risk patients even after adjustments for conditions such as chronic obstructive pulmonary disease (COPD) and prior lower respiratory tract infection, and factors such as age, race, and sex.

The study authors noted that development of the deep learning model was based on a total of 147,497 chest X-rays from a cohort of 40,643 asymptomatic smokers and never-smokers from the Prostate, Lung, Colorectal and Ovarian (PLCO) cancer screening trial.

Click here for more coverage of RSNA 2023.

Related Videos
Does Initial CCTA Provide the Best Assessment of Stable Chest Pain?
Can Diffusion Microstructural Imaging Provide Insights into Long Covid Beyond Conventional MRI?
Assessing the Impact of Radiology Workforce Shortages in Rural Communities
Emerging MRI and PET Research Reveals Link Between Visceral Abdominal Fat and Early Signs of Alzheimer’s Disease
Reimbursement Challenges in Radiology: An Interview with Richard Heller, MD
Nina Kottler, MD, MS
The Executive Order on AI: Promising Development for Radiology or ‘HIPAA for AI’?
Emerging Innovations in Molecular Imaging
Ultra-High Resolution Brain PET: A ‘Quantum Leap’ for Neuroradiology
Related Content
© 2024 MJH Life Sciences

All rights reserved.