FDA Clears Gleamer’s ChestView AI Software for CXR
Adjunctive use of the AI-powered software led to an average 38.6 percent increase in the detection of pneumothorax by general radiologists, according to a 2023 study.
The Food and Drug Administration (FDA) has granted 510(k) clearance for ChestView, an artificial intelligence (AI)-enabled software, which may enhance detection of a variety of abnormalities on chest X-rays (CXRs).
In a 2023 retrospective study involving 500 patients, researchers found that adjunctive use of the ChestView software led to an average increased detection of 26.2 percent for pneumothorax, 8.5 percent for pleural effusion and 14.1 percent for consolidation.
Without AI assistance, only two out of 12 reviewing radiologists were able to detect a right paravertebral mass in the case above. With the use of the newly FDA cleared AI software ChestView, all 12 radiologists detected the mass. (Images courtesy of Radiology.)
The authors of the study, published in Radiology, also noted an overall mean 31 percent reduction in CXR reading time with the use of ChestView. Specifically, researchers pointed out a 27 percent reduction in CXR reading time for thoracic radiologists and a 30 percent reduction for radiology residents.
"We believe ChestView will transform how chest X-rays are analyzed, making healthcare delivery faster, safer, and more effective for millions of patients,” noted Christian Allouche, the chief executive officer at Gleamer.
Predicting Diabetes on CT Scans: What New Research Reveals with Pancreatic Imaging Biomarkers
March 25th 2025Attenuation-based biomarkers on computed tomography (CT) scans demonstrated a 93 percent interclass correlation coefficient (ICC) agreement across three pancreatic segmentation algorithms for predicting diabetes, according to a study involving over 9,700 patients.
AI-Initiated Recalls After Screening Mammography Demonstrate Higher PPV for Breast Cancer
March 18th 2025While recalls initiated by one of two reviewing radiologists after screening mammography were nearly 10 percent higher than recalls initiated by an AI software, the AI-initiated recalls had an 85 percent higher positive predictive value for breast cancer, according to a new study.
