FDA Clears AI-Powered Breast Ultrasound Software from DeepHealth
Combining automated lesion detection and characterization, the DeepHealth Breast Ultrasound software reportedly offers greater than 98 percent sensitivity for localizing breast lesions and reduces interpretation time for radiologists by 37 percent.
The Food and Drug Administration (FDA) has granted 510(k) clearance for the AI-enabled DeepHealth Breast Ultrasound software, which may enhance detection, characterization and reporting of breast lesions.
DeepHealth, the developer of the software, said
• greater than 98 percent accuracy for localizing breast lesions;
• 8 percent improvement in sensitivity for breast cancer; and
• a 37 percent reduction in interpretation time with automated characterization of the shape, orientation, echo pattern and margin of breast lesions.
The company added that the DeepHealth Breast Ultrasound software also reduces reporting time for sonographers through automated and standardized formatting of relevant measurements, lesion characteristics and other pertinent findings.
“With DeepHealth’s breast ultrasound solution, we can achieve greater standardization of workflows, improving consistency while saving time for patients, sonographers and radiologists. By streamlining the examination process, we can help reduce exam times, enhance efficiency and ultimately improve patient outcomes,” noted Jason McKellop, the medical director of women’s imaging for RadNet California.













