Table 3.
Average test accuracy scores for CNNs trained and tested on super-resolution imagery
| DataSet | Mask R-CNN | ANCIS | StarDist | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Train set | Test set | F1 | FN/FP | H | F1 | FN/FP | H | F1 | FN/FP | H |
| Colon tissue | Colon | 0.793 | 0.177/0.225 | 9.76 | 0.739 | 0.315/0.122 | 10.68 | 0.725 | 0.253/0.126 | 10.62 |
| Prostate | 0.646 | 0.221/0.121 | 8.82 | 0.505 | 0.496/0.118 | 9.64 | 0.673 | 0.357/0.071 | 9.17 | |
| Cell downsize | 0.872 | 0.053/0.17 | 5.65 | 0.601 | 0.201/0.134 | 13.21 | 0.847 | 0.137/0.105 | 6.39 | |
| Cell Line A (discrete) | Cell line | 0.832 | 0.11/0.3 | 8.21 | 0.902 | 0.101/0.078 | 7.05 | 0.799 | 0.107/0.263 | 8.87 |
| Cell Line B (all textures) | Cell line | 0.831 | 0.125/0.116 | 7.91 | 0.952 | 0.03/0.128 | 6.39 | 0.859 | 0.076/0.31 | 8.11 |
| Colon upsize | 0.423 | 0.607/0.424 | 17.43 | 0.489 | 0.551/0.076 | 14.51 | 0.39 | 0.467/0.645 | 17.06 | |
| Combined (Colon & Cell) | Colon | 0.676 | 0.169/0.564 | 10.59 | 0.753 | 0.305/0.11 | 11.13 | 0.612 | 0.396/0.397 | 11.39 |
| Cell line | 0.885 | 0.021/0.236 | 5.54 | 0.943 | 0.041/0.107 | 6.76 | 0.92 | 0.037/0.174 | 5.45 | |
| Colon Blur | Colon blur | 0.752 | 0.246/0.25 | 9.87 | 0.729 | 0.349/0.136 | 11.06 | 0.658 | 0.387/0.141 | 11.02 |
| Colon HEQ | Colon HEQ | 0.769 | 0.183/0.287 | 10.01 | 0.733 | 0.328/0.127 | 11.17 | 0.696 | 0.348/0.123 | 10.94 |
| Cell A Blur | Cell blur | 0.791 | 0.12/0.333 | 6.87 | 0.858 | 0.112/0.118 | 6.83 | 0.761 | 0.153/0.288 | 9.22 |
| Cell A HEQ | Cell HEQ | 0.81 | 0.105/0.363 | 6.64 | 0.867 | 0.098/0.126 | 6.57 | 0.785 | 0.14/0.285 | 8.99 |
F1-Score (F1), false negative percent and false positive percent (FN/FP), and Hausdorff distance (H) for Mask R-CNN, ANCIS and StarDist network models trained on the STORM colon tissue dataset, and cell line datasets A & B. An additional combined training dataset included downsized cell line dataset A, colon tissue and Kaggle datasets. Testing was conducted on the 512 × 512 colon and prostate tissue test sets as well as on the 512 × 512 cell line test set, downsized (256 × 256) cell line test set and upsized (1024 × 1024) colon test set. Training and testing were also conducted on histogram equalized (HEQ) and blurred (Blur) versions of the colon tissue and cell line A datasets. Pre-processing was conducted on the 512 × 512 versions of the colon tissue and cell line A datasets for both the training and test images. The results indicate that the original data provided the best test accuracy over the pre-processed images for all cases, suggesting no advantage to be gained by these processes. Top results for each test set are indicated by bold numbering