Breast ultrasound finds many cancers missed by mammography, even when reviewed retrospectively.
Most breast cancers detected by ultrasound screening were not seen at mammography, even in retrospect, according to a study published in the journal Radiology.
Researchers from Korea retrospectively reviewed mammograms of 335 ultrasound-depicted cancers in 329 women (mean age 47) to determine the reasons the cancer was not seen at mammography.
Five blinded radiologists independently reviewed the mammograms to determine whether the findings on negative mammograms should be recalled. Three unblinded radiologists re-reviewed the mammograms to determine the reasons for nondetection by using the reference location of the cancer on mammograms obtained after ultrasound-guided wire localization or breast magnetic resonance imaging. The number of cancers recalled by the blinded radiologists were compared with the reasons for nondetection determined by the unblinded radiologists.
In the blinded review, 19 percent of the ultrasound-depicted cancers were recalled by three or more of the five radiologists, and 81 percent showed no mammographic findings that required immediate action.
In the unblinded repeat review, 78 percent of the cancers were obscured by overlapping dense breast tissue, and 3 percent were not included at mammography owing to difficult anatomic location or poor positioning.
Sixty-three (19 percent) of the cancers were considered interpretive errors. Of these, 82 percent were seen as subtle findings (46 asymmetries, six calcifications) and 18 percent were evident (six focal asymmetries, one distortion, four calcifications).
The authors concluded that 81 percent of the breast cancers found through screening ultrasound were missed in mammography, even when re-reviewed. In addition, 19 percent of the breast cancers had subtle or evident findings missed at mammography.
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.