ResUNet++ + CRF

Reported on 5 benchmarks across 1 task · 2 papers · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical5 results

Medical Image SegmentationonCVC-VideoClinicDB
Dice· 2021-07-26
0.8811
best: 0.926 (Meta-Polyp)
SOTA
A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation arXiv:2107.12435
Medical Image SegmentationonCVC-VideoClinicDB
mIoU· 2021-07-26
0.8739
SOTA
A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation arXiv:2107.12435
Medical Image SegmentationonCVC-VideoClinicDB
precision· 2021-07-26
0.6706
SOTA
A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation arXiv:2107.12435
Medical Image SegmentationonCVC-VideoClinicDB
Recall· 2021-07-26
0.7743
best: 0.7749 (ResUNet++)
A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation arXiv:2107.12435
Medical Image SegmentationonCVC-ClinicDB
mean Dice· 2020-11-15
0.9203
best: 0.9684 (DUCK-Net)
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning arXiv:2011.07631