Medical Image Segmentation On Synapse Multi
Metriken
Avg DSC
Avg HD
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Avg DSC | Avg HD |
|---|---|---|
| agileformer-spatially-agile-transformer-unet | 86.11 | 12.88 |
| rethinking-attention-gated-with-hybrid-dual | 83.43 | 15.82 |
| nnformer-interleaved-transformer-for | 86.57 | 10.63 |
| medsegdiff-v2-diffusion-based-medical-image | 89.50 | - |
| nnu-net-self-adapting-framework-for-u-net | 88.80 | 10.78 |
| rethinking-semantic-segmentation-from-a | 79.60 | - |
| paratranscnn-parallelized-transcnn-encoder | 83.86 | 15.86 |
| emcad-efficient-multi-scale-convolutional | 83.63 | 15.68 |
| uctransnet-rethinking-the-skip-connections-in | 78.99 | 30.29 |
| ai-sam-automatic-and-interactive-segment | 90.66 | - |
| segformer3d-an-efficient-transformer-for-3d | 82.15 | - |
| s2s2-semantic-stacking-for-robust-semantic | 81.19 | - |
| multi-scale-hierarchical-vision-transformer-1 | 84.90 | 13.22 |
| transunet-transformers-make-strong-encoders | 77.48 | 31.69 |
| medical-sam-adapter-adapting-segment-anything | 89.80 | - |
| mist-medical-image-segmentation-transformer | 86.92 | 11.07 |
| ai-sam-automatic-and-interactive-segment | 84.21 | - |
| missformer-an-effective-medical-image | 81.96 | 18.20 |
| mednext-transformer-driven-scaling-of | 88.76 | - |
| adaptive-t-vmf-dice-loss-for-multi-class | 80.26 | - |
| selfreg-unet-self-regularized-unet-for | 80.54 | - |
| swin-unet-unet-like-pure-transformer-for | 79.13 | 21.55 |
| selfreg-unet-self-regularized-unet-for | 80.34 | - |