The　development　of　genetically　engineered　mouse　models　for　neuronal　diseases　and　behavioural　disorders　have　generated　a　growing　need　for　small　animal　imaging.　High-resolution　magnetic　resonance　microscopy　(MRM)　provides　powerful　capabilities　for　noninvasive　studies　of　mouse　brains,　while　avoiding　some　limits　associated　with　the　histological　procedures.　Quantitative　comparison　of　structural　images　is　a　critical　step　in　brain　imaging　analysis,　which　highly　relies　on　the　performance　of　image　registration　techniques.　Nowadays,　there　is　a　mushrooming　growth　of　human　brain　registration　algorithms,　while　fine-tuning　of　those　algorithms　for　mouse　brain　MRMs　is　rarely　addressed.　Because　of　their　topology　preservation　property　and　outstanding　performance　in　human　studies,　diffeomorphic　transformations　have　become　popular　in　computational　anatomy.　In　this　study,　we　specially　tuned　five　diffeomorphic　image　registration　algorithms　[DARTEL,　geodesic　shooting,　diffeo-demons,　SyN　(Greedy-SyN　and　geodesic-SyN)]　for　mouse　brain　MRMs　and　evaluated　their　performance　using　three　measures　[volume　overlap　percentage　(VOP),　residual　intensity　error　(RIE)　and　surface　concordance　ratio　(SCR)].　Geodesic-SyN　performed　significantly　better　than　the　other　methods　according　to　all　three　different　measures.　These　findings　are　important　for　the　studies　on　structural　brain　changes　that　may　occur　in　wild-type　and　transgenic　mouse　brains.