Abstract | ||
---|---|---|
3D ultrasound is becoming common for noninvasive medical imaging because of its high accuracy, safety, and ease of use. Unlike other modalities, ultrasound transducers require little power, which makes handheld imaging platforms possible, and several low-resolution 2D devices are commercially available today. However, the extreme computational requirements (and associated power requirements) of 3D ultrasound image formation have, to date, precluded handheld 3D-capable devices. The authors describe the Sonic Millip3De, a new system architecture and accelerator for 3D ultrasound beamforming--the most computationally intensive aspect of image formation. Their three-layer die-stacked design combines a new approach to the ultrasound imaging algorithm better suited to hardware with a custom beamforming accelerator that employs massive data parallelism and a streaming pipeline architecture to achieve high-quality 3D ultrasound imaging within a full-system power of 15 W in 45-nm semiconductor technology (400× less than a conventional DSP solution). Under anticipated scaling trends, the authors project that Sonic Millip3De will achieve the target 5-W power budget by the 16-nm technology node. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/MM.2014.49 | Micro, IEEE |
Keywords | Field | DocType |
biomedical ultrasonics,graphics processing units,medical image processing,semiconductor technology,ultrasonic imaging,3D ultrasound beamforming,3D ultrasound imaging algorithm,SONIC MILLIP3DE,custom beamforming accelerator,handheld 3D ultrasound,hardware friendly approach,power 15 W,power 5 W,semiconductor technology,size 16 nm,size 45 nm,system architecture,three-layer die stacked design,3D ultrasound,Array signal processing,Biomedical imaging,Computer architecture,Random access memory,Three-dimensional displays,Transducers,Ultrasonic imaging,accelerators,beamforming,handheld ultrasound,hardware | Power budget,Digital signal processing,Computer science,Medical imaging,Image formation,Mobile device,Data parallelism,Systems architecture,3D ultrasound,Embedded system | Journal |
Volume | Issue | ISSN |
34 | 3 | 0272-1732 |
Citations | PageRank | References |
1 | 0.56 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Richard Sampson | 1 | 34 | 6.01 |
Ming Yang | 2 | 30 | 5.23 |
Siyuan Wei | 3 | 30 | 5.91 |
Chaitali Chakrabarti | 4 | 1978 | 184.17 |
Thomas F. Wenisch | 5 | 2112 | 105.25 |