TRUST-Seg: Smooth Delta Attention for Weakly Supervised Brain Lesion Segmentation in MRI

Learning 3D brain lesion segmentation from bounding-box (bbox) annotations requires converting coarse spatial constraints into reliable voxel-wise supervision. We present TRUST-Seg (Teacher-Refined Uncertainty-aware Soft-label Training), a weakly supervised framework that combines heterogeneous pseudo-label generation with confidence-guided target refinement. Dataset-specific ensembles of frozen SAM-family vision foundation models and GrabCut generate reliability-weighted soft pseudo-labels, while inter-teacher disagreement weights the training of an initial 3D U-Net. The central contribution is Smooth Delta Attention (SDA), which computes a voxel-wise blending gate from the difference between student self-confidence and teacher-ensemble certainty. A student-confidence safeguard and bbox constraints regulate refinement, and a second 3D U-Net is trained from scratch on the refined targets. Both students receive MRI and bbox inputs during training and inference. Neither uses voxel-level masks as training targets, but dense validation masks calibrate teacher reliability and support model selection. Under an evaluation protocol using tight slice-wise boxes simulated from reference masks, TRUST-Seg achieves DSC scores of 85.47% on ISLES 2022 and 91.11% on BraTS 2019, exceeding the strongest evaluated weakly supervised methods by 3.26 and 0.38 Dice points, respectively. The corresponding gaps to matched fully supervised references (86.85% and 91.97%) are 1.38 and 0.86 Dice points. These results support confidence-guided pseudo-label refinement under the evaluated bbox-conditioned setting.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24345423
Primary Topic
Medical Image Segmentation Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

TRUST-Seg: Smooth Delta Attention for Weakly Supervised Brain Lesion Segmentation in MRI

Mohammad Alshurbaji, Naoufel Werghi, Taimur Hassan, Maregu Assefa et al.
4 links
Zenodo (CERN European Organization for Nuclear Research)
Medical Image Segmentation Techniques
preprint

TRUST-Seg: Smooth Delta Attention for Weakly Supervised Brain Lesion Segmentation in MRI

Mohammad Alshurbaji, Naoufel Werghi, Taimur Hassan, Maregu Assefa, Mohamed L Seghier, Kamal Taha
preprint en

Abstract

Learning 3D brain lesion segmentation from bounding-box (bbox) annotations requires converting coarse spatial constraints into reliable voxel-wise supervision. We present TRUST-Seg (Teacher-Refined Uncertainty-aware Soft-label Training), a weakly supervised framework that combines heterogeneous pseudo-label generation with confidence-guided target refinement. Dataset-specific ensembles of frozen SAM-family vision foundation models and GrabCut generate reliability-weighted soft pseudo-labels, while inter-teacher disagreement weights the training of an initial 3D U-Net. The central contribution is Smooth Delta Attention (SDA), which computes a voxel-wise blending gate from the difference between student self-confidence and teacher-ensemble certainty. A student-confidence safeguard and bbox constraints regulate refinement, and a second 3D U-Net is trained from scratch on the refined targets. Both students receive MRI and bbox inputs during training and inference. Neither uses voxel-level masks as training targets, but dense validation masks calibrate teacher reliability and support model selection. Under an evaluation protocol using tight slice-wise boxes simulated from reference masks, TRUST-Seg achieves DSC scores of 85.47% on ISLES 2022 and 91.11% on BraTS 2019, exceeding the strongest evaluated weakly supervised methods by 3.26 and 0.38 Dice points, respectively. The corresponding gaps to matched fully supervised references (86.85% and 91.97%) are 1.38 and 0.86 Dice points. These results support confidence-guided pseudo-label refinement under the evaluated bbox-conditioned setting.

Zenodo (CERN European Organization for Nuclear Research)
Abu Dhabi University (AE), Khalifa University of Science and Technology (AE)
Medical Image Segmentation Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon