List your company

Brain Tumor Segmentation on BraTS 2019

94WT Segmentation ScoreReFRM3D
74.13679.29384.4589.607Jul 14, 2025Aug 10, 2025Sep 7, 2025Oct 5, 2025Nov 1, 2025Nov 29, 2025Dec 27, 2025

Evaluation results

MethodLinks
ReFRM3D2025.129492.693.6———————————
ReFRM3D2025.129492.693.6———————————
GMLN-BTSParams (M)=4.58⋆2025.0791.384.99289.4——————————
SegFormer3DParams (M)=4.512025.0789.682.491.887.9——————————
Barzegar and Jamzad2025.1288.78990.1———————————
Ullah et al.2025.1287.286.790.1———————————
SwinUNETRParams (M)=62.192025.0787.283.174.581.6——————————
Li et al.2025.1283.480.286.7———————————
Xu et al.2025.12827490———————————
nnFormerParams (M)=150.502025.0781.481.673.178.7——————————
SuperLightNetParams (M)=2.972025.0781.280.991.384.5——————————
Liu et al.2025.1281.176.789.2———————————
Tong and Wang2025.1277.476.788.6———————————
Liu et al.suffix=a2025.1276.781.189.2———————————
UNETRParams (M)=92.492025.0774.964.253.964.4——————————
ADRUwAMS2026.04————————90.682.7972.9392.05523.221723.7989
BCPL/U=25/2252026.03————77.0618.166.025.33——————
Brats 2019 WinnerImage size=4× 128× 128× 128, Encoder endpoint=128× 16× 16× 16, Loss Function=L(dice), Optimizer=Adam, Learning rate=1e−4, No of Epochs=4052025.02————88.7964.6181————————
CAMLL/U=25/2252026.03————78.3513.3467.023.85——————
Cascaded 3D U-Net and 3D U-Net++2026.04————————86.783.480.2———
CSE-Light-UNETRL/U=25/2252026.03————79.7311.6568.762.25——————
dual supervision guided attentional network2026.04————————88.277.172.78.0910.36.6
Fully SupervisedL/U=250/02026.03————79.9311.4469.332.26——————
heuristic approach for segmentation2026.04————————85.9877.2871.53———
Inception-v3Image size=128× 128× 128× 4, Encoder endpoint=8×8×8×256, Loss Function=L(dice)+ L(CF), Optimizer=Adam, Learning rate=0.0001, No of Epochs=100, Time Taken=4min2025.02————98.0711.1141————————
Inception-v4Image size=128× 128× 128× 4, Encoder endpoint=8×8×8×256, Loss Function=L(dice)+ L(CF), Optimizer=Adam, Learning rate=0.0001, No of Epochs=100, Time Taken=4min2025.02————98.0711.1141————————
Light-UNETRL/U=25/02026.03————75.9112.9364.83.86——————
MLRPL/U=25/2252026.03————78.112.567.513.79——————
Multiscale lightweight 3D segmentation with attention mechanism2026.04————————89.9483.4977.915.456.564.03
RAAGR2-Net2026.04————————88.481.476.3———
ResNetImage size=128× 128× 128× 4, Encoder endpoint=8×8×8×256, Loss Function=L(dice)+ L(CF), Optimizer=Adam, Learning rate=0.0001, No of Epochs=100, Time Taken=4min2025.02————98.6610.8453————————
SS-NetL/U=25/2252026.03————78.7913.6567.963.96——————
Swinbts2026.04————————89.7579.2874.43———
UA-MTL/U=25/2252026.03————74.1316.2362.454.42——————
UNETImage size=128× 128× 128× 4, Encoder endpoint=8×8×8×256, Loss Function=L(dice)+ L(CF), Optimizer=Adam, Learning rate=0.0001, No of Epochs=100, Time Taken=4min2025.02————98.8410.625————————