Radiologists viewing supplemental breast ultrasounds should assess lesions separately to reduce the risk of missing a cancer.
Multiple breast lesions should be separately assessed during supplemental screening breast ultrasound (US), to reduce the number of missed cancers, according to a study published in Radiology.
Researchers from Korea performed a retrospective study to determine the features of undiagnosed breast cancers at previous supplemental screening US, and why there may be undiagnosed among women who were later diagnosed with breast cancer.
A total of 230 women (median age 49) who had been diagnosed with cancer were included in the study. There were 230 pairs of US examinations performed between December 2003 and August 2013. The median time for diagnosis was 12 months, ranging from two months to 24 months.
To determine which cancers may have been missed at the first ultrasound, the researchers compared the clinical-pathologic features of patients with negative findings on prior images with those of patients with visible findings on prior images. Blinded radiologists classified the findings as actionable or underthreshold.
The researchers found that among the 230 prior US examinations, 72 (31.3%) did show visible findings and 158 (68.7%) did show negative findings. “High-nuclear-grade cancers and triple-negative cancers were more common in patients with negative findings than in those with visible findings,” they wrote.
Fifty-seven of the 72 visible findings (79%) were actionable. The most common reasons for missing actionable findings were misinterpretation in 28 of 72 lesions (39%) and multiple distracting lesions in 12 of 72 lesions (17%), which showed more noncircumscribed margins than did underthreshold findings.
The researchers concluded that when radiologists are viewing supplemental screening breast ultrasounds, “close attention should be paid to the presence of a margin that is not circumscribed, and multiple lesions should be separately assessed to reduce the number of missed breast cancers.”
FDA Clears AI-Powered Ultrasound Software for Cardiac Amyloidosis Detection
November 20th 2024The AI-enabled EchoGo® Amyloidosis software for echocardiography has reportedly demonstrated an 84.5 percent sensitivity rate for diagnosing cardiac amyloidosis in heart failure patients 65 years of age and older.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.