Artificial intelligence-driven whole-brain cell mapping with highly multiplexed in situ hybridization

Recent advances in three-dimensional single-cell-resolution imaging have begun to link organ-wide and cellular-level research in development and disease. Although powerful, whole-organ imaging remains limited by the inability to stain a broad range of molecular markers and by the lack of an analytical scheme to precisely quantify cell populations. Here, we present a highly multiplexed whole-mount staining technique, utilizing the repeated application of fluorescence in situ hybridization. This technique, termed mFISH3D, enables the visualization of 10 types of mRNAs in an intact mouse brain and has been demonstrated in various biological specimens, including the human brain. To achieve higher levels of accuracy in spatial cell mapping, we developed an artificial intelligence (AI)-driven workflow that reduces the need for extensive manual annotations. This integration provides a systematic framework for analyzing complex cellular ecosystems across large tissue volumes and enables the comprehensive investigation of selective cellular vulnerabilities in disease.