Liver Segmentation On Lits2017

Métriques

Dice

HD

IoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

				Paper Title
H-DenseUnet Liver	96.5	-	-	H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
KiU-Net 3D	94.23	-	-	KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
U-Net LiS (MICCAI 17)	94	-	-	Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function
Polar U-Net	93.02	-	89.85	Training on Polar Image Transformations Improves Biomedical Image Segmentation
Semantic Genesis	92.27	-	85.6	Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration
ModelGenesis	91.13	-	79.52	Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis
PVTFormer	86.78	3.50	78.46	CT Liver Segmentation via PVT-based Encoding and Refined Decoding
H-DenseUnet Lession	82.4	-	-	H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
KiU-Net 3D Liver	-	-	89.46	KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

0 of 9 row(s) selected.