Skip to main content

View full-text article in PMC

. Author manuscript; available in PMC: 2023 Jun 2.

Published in final edited form as: Med Image Anal. 2021 Apr 5;71:102048. doi: 10.1016/j.media.2021.102048

TABLE V.

Quantitative Result of Empirical Validation

Method	Metric	Data-Set
Method	Metric	PhC-C2DL-PSC	Fluo-C2DL-MSC	Fluo-N2DL-HeLa
Original(CPU) [16], [36]	Time Cost (s/frame)	288.78	17.24	487.78
Original(CPU) [16], [36]	GPU Memory (GB)	5.92	5.92	5.92
GPU_H [21]	Time Cost (s/frame)	89.94	7.89	121.45
GPU_H [21]	GPU Memory (GB)	6.16	6.16	6.16
GPU_P [22]	Time Cost (s/frame)	-	-	-
GPU_P [22]	GPU Memory (GB)	overflow	overflow	overflow
Ours	Time Cost (s/frame)	32.24s	1.54	63.61
Ours	GPU Memory (GB)	7.49	6.21	8.58

^*

5.92GB is the minimal GPU memory consumption for the deep learning based feature extraction.

^*

Due to the GPU overflow, the time-cost is not available(−)