Retinal Vessel Segmentation On Drive

評価指標

AUC

F1 score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	AUC	F1 score	Paper Title	Repository
IterNet	0.9816	0.8205	IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks	-
ConvMixer	-	0.8245	Deep Learning Architectures for Diagnosis of Diabetic Retinopathy
BCDU-Net (d=3)	0.9789	0.8224	Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions	-
Study Group Learning	0.9886	0.8316	Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels	-
ConvMixer-Light	-	0.8215	Deep Learning Architectures for Diagnosis of Diabetic Retinopathy
ET-Net	-	-	ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation	-
MERIT-GCASCADE	-	0.8290	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation	-
U-Net	0.9755	0.8142	U-Net: Convolutional Networks for Biomedical Image Segmentation	-
SA-UNet	0.9864	0.8263	SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation	-
RV-GAN	-	-	RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network	-
VGN	0.9802	0.8263	Deep Vessel Segmentation By Learning Graphical Connectivity	-
U-Net	0.9855	-	Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation	-
PVT-GCASCADE	-	0.8210	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation	-
FR-UNet	0.9889	0.8316	Full-Resolution Network and Dual-Threshold Iteration for Retinal Vessel and Coronary Angiograph Segmentation
DUNet	0.9802	0.8237	DUNet: A deformable network for retinal vessel segmentation	-
FSG-Net	0.9823	0.8322	Full-scale Representation Guided Network for Retinal Vessel Segmentation	-
LadderNet	0.9793	0.8202	LadderNet: Multi-path networks based on U-Net for medical image segmentation	-
CE-Net	0.9779	-	CE-Net: Context Encoder Network for 2D Medical Image Segmentation	-
Swin-Res-Net	0.9931	-	Enhancing Retinal Vascular Structure Segmentation in Images With a Novel Design Two-Path Interactive Fusion Module Model	-
Residual U-Net	0.9779	0.8149	Road Extraction by Deep Residual U-Net	-

0 of 21 row(s) selected.