Fundus Image Segmentation Using Step Time Signal Polynomial Fitting

Yan, Songlin; Huang, Ju; Tang, Xiaoying; Chi, Xuebing

doi:10.1109/ipec51340.2021.9421169

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other research groups have proposed fundus image enhancing techniques which are based on a mathematical model for processing fundus images. Experimental investigation has shown that the regional illumination and the refinement strategy can make the diagnostic process more precise [ 12 ], [ 13 ]. Yen et al, presented a segmentation method for blood vessels: optic disc and cup segmentation.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Microaneurysms in Fundus Images Using an Ensemble-Based Segmentation Method

Raudonis

Kairys

Verkauskienė

et al. 2023

Sensors

View full text Add to dashboard Cite

In this study, a novel method for automatic microaneurysm detection in color fundus images is presented. The proposed method is based on three main steps: (1) image breakdown to smaller image patches, (2) inference to segmentation models, and (3) reconstruction of the predicted segmentation map from output patches. The proposed segmentation method is based on an ensemble of three individual deep networks, such as U-Net, ResNet34-UNet and UNet++. The performance evaluation is based on the calculation of the Dice score and IoU values. The ensemble-based model achieved higher Dice score (0.95) and IoU (0.91) values compared to other network architectures. The proposed ensemble-based model demonstrates the high practical application potential for detection of early-stage diabetic retinopathy in color fundus images.

show abstract

Section: Introductionmentioning

confidence: 99%