Medical Image Segmentation On Cvc Clinicdb

Métriques

mean Dice

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mean Dice	Paper Title	Repository
ResUNet++ + CRF	0.9203	Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
AG-CUResNeSt	0.9170	AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation
COMMA (Res2Net-50)	0.933	COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation	-
PraNet	0.8990	PraNet: Parallel Reverse Attention Network for Polyp Segmentation
ResUNet++	0.7955	ResUNet++: An Advanced Architecture for Medical Image Segmentation	-
ADSNet	0.938	Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation
UGCANet	0.950	UGCANet: A Unified Global Context-Aware Transformer-based Network with Feature Alignment for Endoscopic Image Analysis	-
DoubleUnet-DCA	0.9086	Dual Cross-Attention for Medical Image Segmentation
PVT-CASCADE	0.9434	Medical Image Segmentation via Cascaded Attention Decoding
MADGNet	0.9390	Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention
Yolo-SAM 2	0.951	Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model
COMMA (ResNet-50)	0.916	COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation	-
MEGANet(Res2Net-50)	0.938	MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation
ResUNet++ + TTA	0.9020	A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation
MEGANet(ResNet-34)	0.93	MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation
MSRF-Net	0.9420	MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation
KDAS	0.925	KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation
FANet	0.9355	FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation
DUCK-Net	0.9684	Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation
UACANet-S	0.916	UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation

0 of 45 row(s) selected.