Skip to main content

Table 7 generalizability results of the models trained on CVC-Clinicdb and tested on Kvasir-SEG

From: EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation

Method

Year

mDice

mIoU

Recall

Precision

U-Net [5]

2015

0.5621

0.4050

0.4364

0.8466

U-Net++ [7]

2018

0.6783

0.5494

0.7311

0.6885

HRNetV2-W18-Smallv2 [44]

2020

0.2107

0.1363

0.2038

0.3347

HRNetV2-W48 [44]

2020

0.2349

0.2461

0.3372

0.1523

MSRF-Net [41]

2021

0.7575

0.6337

0.7197

0.8414

EG-TransUNet

–

0.8337

0.7647

0.8600

0.8698

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us