Table 1.
Image processing time
| Single GPU | Dual GPUs | |||
|---|---|---|---|---|
| Processing step | Time per image sequence (ms) Blood/CSF | Total time per test (min) Blood/CSF | Time per image sequence (ms) Blood/CSF | Total time per test (min) Blood/CSF |
| Copy data from CPU memory to GPU memory | 316.7/212.7 | 1.14/0.77 | 346.2/231.7 | 0.62/0.42 |
| Image normalization | 44.3/30.0 | 0.16/0.11 | 49.0/32.5 | 0.09/0.06 |
| Autofocusing | 523.0/NA | 1.88/NA | 680.8/NA | 1.23/NA |
| Computational motion analysis | 6205.0/5515.7 | 22.34/19.86 | 6137.8/5561.5 | 11.05/10.01 |
| Post-image filtering | 106.7/136.0 | 0.38/0.49 | 108.2/138.3 | 0.19/0.25 |
| Segmentation | 10.1/10.1 | 0.04/0.04 | 10.1/10.1 | 0.02/0.02 |
| Deep learning-based classification | 9.8/10.3 | 0.04/0.04 | 9.8/10.3 | 0.02/0.02 |
| Total | 7215.6/5914.8 | 25.98/21.29 | 7341.9/5984.4 | 13.22/10.77 |