Lesion Segmentation On Isic 2018

Metriken

mean Dice

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
Polar Res-U-Net++	0.9253	Training on Polar Image Transformations Improves Biomedical Image Segmentation
DuAT	0.923	DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation
ProMISe	0.921	ProMISe: Promptable Medical Image Segmentation using SAM
RMSM UNet + DF-RAM +EF-RAM	0.9152	Automated skin lesion segmentation using multi-scale feature extraction scheme and dual-attention mechanism
BAT	0.912	Boundary-aware Transformers for Skin Lesion Segmentation
MobileUNETR	0.9074	MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer For Efficient Medical Image Segmentation
DermoSegDiff-A	0.9005	DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation
DoubleU-Net	0.8962	DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation
MCGU-Net	0.895	Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation
MSRF-Net	0.8813	MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation
Attn U-Net + Multi-Input + FTL	0.856	A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation
AIM++ (256x256, 1.5m parameters, 10% labeled data, no pretraining)	0.85	Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs
BCDU-net	0.847	Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions
U-Net + FTL	0.829	A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation
Attn U-Net + DL	0.806	A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation
BCDU-Net (d=3)	-	Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions

0 of 16 row(s) selected.