الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Retinal Vessel Segmentation On Chase_Db1

المقاييس

AUC

Acc

F1 score

MCC

Sensitivity

mIOU

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	AUC	Acc	F1 score	MCC	Sensitivity	mIOU	Paper Title	Repository
FSG-Net	0.9937	0.9751	0.8101	0.7989	0.8599	0.8268	Full-scale Representation Guided Network for Retinal Vessel Segmentation
IterNet	0.9851	-	0.8073	-	-	-	IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks
MERIT-GCASCADE	-	-	0.8267	-	0.8493	0.7050	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation
LadderNet	0.9839	-	0.8031	-	-	-	LadderNet: Multi-path networks based on U-Net for medical image segmentation
U-Net ASPP	-	-	-	-	-	0.8959	Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks	-
SA-UNet	0.9905	-	0.8153	-	-	-	SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation
Residual U-Net	0.9779	-	0.7800	-	-	-	Road Extraction by Deep Residual U-Net
VGN	0.9830	-	0.8034	-	-	-	Deep Vessel Segmentation By Learning Graphical Connectivity
DUNet	0.9804	-	0.7883	-	-	-	DUNet: A deformable network for retinal vessel segmentation	-
R2U-Net	0.9815	-	0.7928	-	-	-	Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
RV-GAN	0.9914	-	0.8957	-	0.8199	0.9705	RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network
Study Group Learning	0.9920	-	0.8271	-	0.8690	-	Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels
U-Net	0.9772	-	-	-	-	-	U-Net: Convolutional Networks for Biomedical Image Segmentation
PVT-GCASCADE	-	-	0.8251	-	0.8584	0.7024	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation
FR-UNet	0.9913	-	0.8151	-	0.8798	-	Full-Resolution Network and Dual-Threshold Iteration for Retinal Vessel and Coronary Angiograph Segmentation

0 of 15 row(s) selected.