LETT-NeXt uses RECIST line prompts in a cropped MedNeXt-v2 encoder-decoder to predict 3D lesion masks, reaching DSC 73.9 on hidden test data for a CVPR 2026 segmentation competition.
MedNeXt-v2: Scaling 3D ConvNeXts for Large-Scale Supervised Representation Learning in Medical Image Segmenta- tion, December 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CoMNet combines MedNeXt segmentation with corrective diffusion and fold ensembling to report the highest Dice scores on UTSW-Glioma and BraTS-SSA multi-site glioma datasets versus two baselines.
citing papers explorer
-
LETT-NeXt: A Lightweight RECIST-Guided Model for 3D CT Lesion Segmentation
LETT-NeXt uses RECIST line prompts in a cropped MedNeXt-v2 encoder-decoder to predict 3D lesion masks, reaching DSC 73.9 on hidden test data for a CVPR 2026 segmentation competition.
-
CoMNet: A MedNeXt-CorrDiff Framework for Multi-Site Brain Tumor Segmentation
CoMNet combines MedNeXt segmentation with corrective diffusion and fold ensembling to report the highest Dice scores on UTSW-Glioma and BraTS-SSA multi-site glioma datasets versus two baselines.