BARL: Bilateral Alignment in Representation and Label Spaces for Semi-Supervised Volumetric Medical Image Segmentation

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 $\mathbf{\text{Bilateral}}\mathbf{\text{Alignment}}\mathbf{\text{in}}\mathbf{\text{Representation}}\mathbf{\text{and}}\mathbf{\text{Label}}\mathbf{\text{spaces}}\mathbf{\text{(BARL)}}$, 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 $\mathbf{\text{Dual-Path}}\mathbf{\text{Regularization}}\mathbf{\text{(DPR)}}$ and $\mathbf{\text{Progressively}}\mathbf{\text{Cognitive}}\mathbf{\text{Bias}}\mathbf{\text{Correction}}\mathbf{\text{(PCBC)}}$ 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.