Medical　image　segmentation　is　crucial　in　medical　image　analysis.　In　recent　years,　deep　learning,　particularly　convolutional　neural　networks　(CNNs)　and　Transformer　models,　has　significantly　advanced　this　field.　To　fully　leverage　the　abilities　of　CNNs　and　Transformers　in　extracting　local　and　global　information,　we　propose　HSINet,　which　employs　Swin　Transformer　and　the　newly　introduced　Deep　Dense　Feature　Extraction　(DFE)　block　to　construct　dual　encoders.　A　Swin　Transformer　and　DFE　Encoded　Feature　Fusion　(TDEF)　module　is　designed　to　merge　features　from　the　two　branches,　and　the　Multi-Scale　Semantic　Fusion　(MSSF)　module　further　promotes　the　full　utilization　of　low-level　and　high-level　features　from　the　encoders.　We　evaluated　the　proposed　network　on　the　familial　cerebral　cavernous　malformations　private　dataset　(SG-FCCM)　and　the　ISIC-2017　challenge　dataset.　The　experimental　results　indicate　that　the　proposed　HSINet　outperforms　several　other　advanced　segmentation　methods,　demonstrating　its　superiority　in　medical　image　segmentation.　©　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.　2025.