BARL: Bilateral Alignment in Representation and Label Spaces for Semi-Supervised Volumetric Medical Image Segmentation
This work addresses the challenge of reducing annotation costs for volumetric medical image segmentation, which is crucial for healthcare applications, though it appears incremental by building on existing semi-supervised approaches.
The paper tackles the problem of semi-supervised medical image segmentation by addressing the oversight of representation-space alignment in existing methods, introducing BARL to enforce alignment in both representation and label spaces, resulting in consistent outperformance over state-of-the-art methods on multiple benchmarks.
Semi-supervised medical image segmentation (SSMIS) seeks to match fully supervised performance while sharply reducing annotation cost. Mainstream SSMIS methods rely on \emph{label-space consistency}, yet they overlook the equally critical \emph{representation-space alignment}. Without harmonizing latent features, models struggle to learn representations that are both discriminative and spatially coherent. To this end, we introduce \textbf{Bilateral Alignment in Representation and Label spaces (BARL)}, a unified framework that couples two collaborative branches and enforces alignment in both spaces. For label-space alignment, inspired by co-training and multi-scale decoding, we devise \textbf{Dual-Path Regularization (DPR)} and \textbf{Progressively Cognitive Bias Correction (PCBC)} to impose fine-grained cross-branch consistency while mitigating error accumulation from coarse to fine scales. For representation-space alignment, we conduct region-level and lesion-instance matching between branches, explicitly capturing the fragmented, complex pathological patterns common in medical imagery. Extensive experiments on four public benchmarks and a proprietary CBCT dataset demonstrate that BARL consistently surpasses state-of-the-art SSMIS methods. Ablative studies further validate the contribution of each component. Code will be released soon.