Research Article
TSHVNet: Simultaneous Nuclear Instance Segmentation and Classification in Histopathological Images Based on Multiattention Mechanisms
Table 2
Quantitative comparison of instance segmentation results performed by different models on the CoNSeP and PanNuke datasets.
| Model | Dataset metrics | CoNSeP | PanNuke | DICE | AJI | DQ | SQ | PQ | DICE | AJI | DQ | SQ | PQ |
| Dist | 0.794 | 0.505 | 0.544 | 0.725 | 0.397 | 0.782 | 0.598 | 0.636 | 0.764 | 0.499 | Micro-Net | 0.780 | 0.513 | 0.560 | 0.709 | 0.415 | 0.810 | 0.654 | 0.740 | 0.794 | 0.599 | HoVer-Net | 0.849 | 0.556 | 0.687 | 0.772 | 0.532 | 0.818 | 0.651 | 0.757 | 0.783 | 0.609 | TSHVNet | 0.856 | 0.558 | 0.690 | 0.777 | 0.546 | 0.835 | 0.662 | 0.779 | 0.813 | 0.637 |
|
|