Research Article
TSHVNet: Simultaneous Nuclear Instance Segmentation and Classification in Histopathological Images Based on Multiattention Mechanisms
Table 3
Quantitative comparison of nuclear classification results performed by different models on the CoNSeP and PanNuke datasets.
| Model | Dataset metrics | CoNSeP | PanNuke | | | | | | | | | | | |
| Dist | 0.732 | 0.626 | 0.554 | 0.509 | 0.025 | 0.741 | 0.402 | 0.391 | 0.000 | 0.137 | 0.518 | Micro-Net | 0.721 | 0.601 | 0.550 | 0.495 | 0.105 | 0.787 | 0.464 | 0.401 | 0.104 | 0.448 | 0.580 | HoVer-Net | 0.738 | 0.618 | 0.564 | 0.532 | 0.348 | 0.790 | 0.465 | 0.413 | 0.153 | 0.463 | 0.591 | TSHVNet | 0.763 | 0.669 | 0.621 | 0.583 | 0.358 | 0.820 | 0.531 | 0.460 | 0.179 | 0.536 | 0.623 |
|
|