OpenCodePapers

lesion-segmentation-on-isic-2018

Medical Image SegmentationLesion Segmentation
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodemean DiceF1-ScoreMean IoUModelNameReleaseDate
Training on Polar Image Transformations Improves Biomedical Image Segmentation✓ Link0.9253Polar Res-U-Net++2021-09-29
DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation✓ Link0.9230.867DuAT2022-12-21
ProMISe: Promptable Medical Image Segmentation using SAM✓ Link0.9210.850ProMISe2024-03-07
Automated skin lesion segmentation using multi-scale feature extraction scheme and dual-attention mechanism0.9152RMSM UNet + DF-RAM +EF-RAM2021-11-16
Boundary-aware Transformers for Skin Lesion Segmentation✓ Link0.9120.843BAT2021-10-08
From Semantic Segmentation of Natural Images to Medical Image Segmentation Using ViT-Based Architectures0.9110.841SegMed2025-01-31
MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer For Efficient Medical Image Segmentation✓ Link0.90740.8456MobileUNETR2024-09-04
DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation✓ Link0.9005DermoSegDiff-A2023-08-05
DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation✓ Link0.8962DoubleU-Net2020-06-08
Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation✓ Link0.895MCGU-Net2020-03-10
MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation✓ Link0.8813MSRF-Net2021-05-16
A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation✓ Link0.856Attn U-Net + Multi-Input + FTL2018-10-18
Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs✓ Link0.85AIM++ (256x256, 1.5m parameters, 10% labeled data, no pretraining)2024-01-25
Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions✓ Link0.847BCDU-net2019-08-31
A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation✓ Link0.829U-Net + FTL2018-10-18
A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation✓ Link0.806Attn U-Net + DL2018-10-18
Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions✓ Link0.851BCDU-Net (d=3)2019-08-31