Lung Segmentation on PadChest (five-fold cross-validation)
93.93DSC (%)S-MVD-CL
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| S-MVD-CLPre-training Method=S-MVD-CL, Supervision type=Supervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 93.93 | 97.75 | 92.43 | 7.3 | 2.05 | |
| CheXMaskPre-training Method=CheXMask, Supervision type=Supervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 93.65 | 97.81 | 92.02 | 7.3 | 2.46 | |
| S-DVD-CLPre-training Method=S-DVD-CL, Supervision type=Supervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 93.15 | 97.62 | 91.43 | 8 | 2.96 | |
| SSDCLPre-training Method=SSDCL, Supervision type=Supervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 92.91 | 97.58 | 91.1 | 15.3 | 3.31 | |
| DVD-CLPre-training Method=DVD-CL, Supervision type=Unsupervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 92.76 | 97.36 | 91.08 | 10.5 | 2.86 | |
| MVD-CLPre-training Method=MVD-CL, Supervision type=Unsupervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 92.27 | 97.18 | 90.36 | 9.1 | 2.61 | |
| VADeRPre-training Method=VADeR, Supervision type=Unsupervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 92.26 | 97.22 | 90.33 | 10.4 | 2.79 | |
| SimCLRPre-training Method=SimCLR, Supervision type=Unsupervised, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 90.9 | 96.71 | 88.61 | 11.9 | 3.64 | |
| NonePre-training Method=None, Supervision type=Baseline, Fine-tuning evaluation protocol=five-fold cross-validation2026.03 | 87.05 | 93.59 | 84.76 | 21.9 | 5.39 |