2D Dense-UNet

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical4 results

Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
Dice· 2017-09-21
0.4741
best: 0.5349 (D-UNet)
SOTA
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes arXiv:1709.07330
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
IoU· 2017-09-21
0.3559
SOTA
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes arXiv:1709.07330
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
Recall· 2017-09-21
0.4875
best: 0.5243 (D-UNet)
SOTA
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes arXiv:1709.07330
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
Precision· 2017-09-21
0.5613
best: 0.6331 (D-UNet)
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes arXiv:1709.07330