Table 1.
Summary of test datasets used for evaluating the proposed high-throughput algorithm
DATASET | CELL LINE | IMAGES (N) | ISOLATED NUCLEI (N) | CLUSTERED NUCLEI (N) | PNCBEFORE (%) | FOREGROUND (%) |
---|---|---|---|---|---|---|
D1 | C1 | 16 | 865 | 767 | 47.0 | 24.1 |
D2 | C2 | 18 | 217 | 78 | 26.4 | 5.2 |
D3 | C3 | 12 | 380 | 121 | 24.2 | 12.7 |
D4 | C4 | 16 | 261 | 122 | 31.9 | 6.2 |
D5 | C1 | 17 | 120 | 146 | 54.9 | 7.4 |
D6 | C2 | 10 | 175 | 368 | 67.8 | 20.4 |
D7 | C3 | 15 | 190 | 371 | 66.1 | 9.8 |
Sum | 104 | 2,208 | 1,973 |
PNCbefore = percentage of nuclei in clusters in the input image(s) and foreground = percentage area occupied by nuclei in the inputimage (calculated from the ground truth data).