Skip to main content
. 2021 Jan 28;21:14. doi: 10.1186/s12880-020-00528-6

Table 4.

The model segmentation results with and without Multi input, deeper network and post-processing

Method DRISHTI-GS dataset REFUGE dataset
DCdisc(mean) DCcup(mean) DCdisc(mean) DCcup(mean)
Without image pyramid input 0.9743 0.9076 0.9589 0.8880
Without multi-DDSC blocks 0.9746 0.8939 0.9575 0.8837
DDSC-Net 0.9779 0.9123 0.9592 0.8894
DDSC-NET + post-processing 0.9780 0.9123 0.9601 0.8903

Italics indicate the best results