Comparative evaluation of UNet, PSPNet, LinkNet and FPN with six encoders on three COVID-19 CT datasets reports up to 98% F1 for binary lesion segmentation and 75-77% for multi-class.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pixel Wised Lesion Prediction on COVID-19 CT Imagery: A Comparative Analysis of Automated Image Segmentation Architectures
Comparative evaluation of UNet, PSPNet, LinkNet and FPN with six encoders on three COVID-19 CT datasets reports up to 98% F1 for binary lesion segmentation and 75-77% for multi-class.