Multi Tissue Nucleus Segmentation On Kumar
Metriken
Dice
Hausdorff Distance (mm)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Dice | Hausdorff Distance (mm) |
|---|---|---|
| dense-steerable-filter-cnns-for-exploiting | 0.826 | 60 |
| roto-translation-equivariant-convolutional | 0.814 | 53.4 |
| learning-steerable-filters-for-rotation | 0.791 | 51.0 |
| cia-net-robust-nuclei-instance-segmentation | 0.818 | 57.7 |
| mask-r-cnn | 0.760 | 50.9 |
| xy-network-for-nuclear-segmentation-in-multi | 0.826 | 59.7 |
| learning-steerable-filters-for-rotation | 0.818 | 54.3 |
| roto-translation-equivariant-convolutional | 0.811 | 51.9 |
| u-net-convolutional-networks-for-biomedical | 0.758 | 47.8 |
| rotation-equivariant-vector-field-networks | 0.800 | 49.9 |
| micro-net-a-unified-model-for-segmentation-of | 0.797 | 51.9 |
| learning-steerable-filters-for-rotation | 0.809 | 54.2 |
| rotation-equivariant-vector-field-networks | 0.808 | 50.7 |
| rotation-equivariant-vector-field-networks | 0.813 | 51.4 |
| group-equivariant-convolutional-networks | 0.793 | 49.0 |
| mrl-learning-to-mix-with-attention-and | 0.843 | - |
| fully-convolutional-networks-for-semantic-1 | 0.797 | 31.2 |
| learning-steerable-filters-for-rotation | 0.820 | 55.8 |