This paper introduces a novel semi-supervised framework, the Multiscale Spatial Consistency Network (MSCNet), for robust semi-supervised skin lesion segmentation. MSCNet uses local and global spatial consistency to leverage a minimal set of labeled data, supplemented by a large number of unlabeled data, to improve segmentation. The model is is based on a single Encoder–Decoder (ED) network, augmented with a Spatially-Constrained Mixture Model (SCMM) to enforce spatial coherence in predictions. To encode the local spatial consistency, a hierarchical superpixel structure is used capture local region context (LRC), bolstering the model capacity to discern fine-grained lesion details. Global consistency is enforced through the SCMM module, which uses a larger context for lesion/background discrimination. In addition, it enables efficient leveraging of the unlabeled data through pseudo-label generation. Experiments demonstrate that the MSCNet outperforms existing state-of-the-art methods in segmenting complex lesions. The MSCNet has an excellent generalization capability, offering a promising direction for semi-supervised medical image segmentation, particularly in scenarios with limited annotated data. The code is available at https://github.com/AdamaTG/MSCNet.