Research map / Detection and segmentation / Open-set and few-shot detection
Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the proposed one-shot framework with image-aligned style transformation and feature-aware content consistency | one-shot brain tissue segmentation · OASIS | average Dice: 0.819±0.018 -> 0.851±0.017 | Helped |
| use the proposed one-shot framework with image-aligned style transformation and feature-aware content consistency | one-shot brain tissue segmentation · CANDIShare | average Dice: 0.830±0.018 -> 0.839±0.012 | Helped |
| add feature-aware content consistency to the registration model (ablation) | the iterative registration-segmentation framework · OASIS, after 3 iterations | registration average Dice: 1.81% | Helped |
| add feature-aware content consistency to the registration model (ablation) | the iterative registration-segmentation framework · OASIS, after three iterations | segmentation average Dice: 2.69% | Helped |
| train the segmentation model using image-aligned style-transformed atlas-mask pairs instead of misaligned unlabeled-image and pseudo-mask pairs (ablation) | the iterative registration-segmentation framework · OASIS, after three iterations | segmentation average Dice: 2.51% | Helped |
| use the proposed method rather than 3D-UNet trained with 5 labeled images | one-shot segmentation · OASIS, 5 labeled atlases | average Dice: 7.91% | Helped |
| use the proposed method with one labeled atlas instead of supervised 3D-UNet trained with 50 annotated samples | brain tissue segmentation · OASIS | average Dice | Helped |
Closest papers by meaning
- Alternative Baselines for Low-Shot 3D Medical Image Segmentation—An Atlas Perspective (AAAI 2021 · similarity 0.88)
- Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains (NeurIPS 2025 · similarity 0.83)
- Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation (CVPR 2025 · similarity 0.83)
- MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling (CVPR 2024 · similarity 0.83)
- One-Prompt to Segment All Medical Images (CVPR 2024 · similarity 0.82)
- A Unified Degradation-Robust Approach to SSL and UDA for 3D Medical Images (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.