Medical Image Segmentation On Automatic

Metriken

Avg DSC

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Avg DSC	Paper Title	Repository
R50-ViT-CUP	87.57	TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
MERIT-GCASCADE	92.23	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation
LHU-Net	92.65	LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image Segmentation
TransCASCADE	91.63	Medical Image Segmentation via Cascaded Attention Decoding
PVT-GCASCADE	91.95	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation
SwinUnet	90.00	Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
nnFormer	92.06	nnFormer: Interleaved Transformer for Volumetric Segmentation	-
FCT	93.02	The Fully Convolutional Transformer for Medical Image Segmentation
Interactive AI-SAM gt box	93.89	AI-SAM: Automatic and Interactive Segment Anything Model
R50-AttnUNet	86.75	TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Automatic AI-SAM	92.06	AI-SAM: Automatic and Interactive Segment Anything Model
TransUNet	90.4	S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging
FCT	94.26	Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation
TransUNet	89.71	TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
MIST	92.56	MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder
MERIT	92.32	Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation
EMCAD	92.12	EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation
SegFormer3D	90.96	SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation	-
MISSFormer	87.9	MISSFormer: An Effective Medical Image Segmentation Transformer
PVT-CASCADE	91.46	Medical Image Segmentation via Cascaded Attention Decoding

0 of 20 row(s) selected.