Research
RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
arXiv:2604.11164v1 Announce Type: new Abstract: Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotat
arXiv:2604.11164v1 Announce Type: new Abstract: Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and time-consuming for 3D volumetric scans. Barely-supervised learning reduces annotation burden by using only a few labeled slices per volume. Existing methods typically propagate sparse annotations to unlabeled slices through geometric continuity to generate pseudo-labels, but this strategy lacks semantic understanding, often resulting in low-quality pseudo-labels. Furthermore, medical image segmentation is inherently a pixel-level visual understanding task, where accuracy fundamentally depends on the quality of local, fine-grained visual features. Inspired by this, we propose RADA, a novel Region-Aware Dual-encoder Auxiliary learning pipeline which introduces a dual-encoder framework pre-trained on Alpha-CLIP to extract fine-grained, region-specific visual features from the original images and limited annotations. The framework combines image-level fine-grained visual features with text-level semantic guidance, providing region-aware semantic supervision that bridges image-level semantics and pixel-level segmentation. Integrated into a triple-view training framework, RADA achieves SOTA performance under extremely sparse annotation settings on LA2018, KiTS19 and LiTS, demonstrating robust generalization across diverse datasets.
Related
- FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
- Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
- Detecting and refurbishing ground truth errors during training of deep learning-based echocardiography segmentation models
- SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation
- TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
- Improving Deep Learning-Based Target Volume Auto-Delineation for Adaptive MR-Guided Radiotherapy in Head and Neck Cancer: Impact of a Volume-Aware Dice Loss
Source: arXiv cs.CV | 2026-04-14