Colorectal Gland Segmentation On Crag

Metriken

Dice

F1-score

Hausdorff Distance (mm)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

				Paper Title
VF-CNN (C4)	0.721	0.711	318.9	Rotation equivariant vector field networks
VF-CNN (C8)	0.758	0.745	287.5	Rotation equivariant vector field networks
VF-CNN (C12)	0.782	0.776	251.9	Rotation equivariant vector field networks
FCN8 (e)	-	-	199.5	U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net (e)	0.844	-	196.9	U-Net: Convolutional Networks for Biomedical Image Segmentation
G-CNN (C12)	0.834	0.818	192.2	Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
Steerable G-CNN (e)	0.848	0.811	175.9	Learning Steerable Filters for Rotation Equivariant CNNs
G-CNN (C4)	0.856	0.833	170.4	Group Equivariant Convolutional Networks
Steerable G-CNN (C12)	0.869	0.837	164.8	Learning Steerable Filters for Rotation Equivariant CNNs
G-CNN (C8)	0.866	0.837	157.4	Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
Steerable G-CNN (C12)	0.870	0.855	156.2	Learning Steerable Filters for Rotation Equivariant CNNs
MILD-Net (e)	0.883	0.869	146.2	MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images
Steerable G-CNN (C8)	0.888	0.861	139.5	Learning Steerable Filters for Rotation Equivariant CNNs
DSF-CNN (C8)	0.891	0.874	138.4	Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images
PatchCL	0.892	0.881	119.5	Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

0 of 15 row(s) selected.