Ductal　carcinoma　in　situ　with　microinvasion　(DCISM)　is　a　challenging　subtype　of　breast　cancer　with　controversial　invasiveness　and　prognosis.　Accurate　diagnosis　of　DCISM　from　ductal　carcinoma　in　situ　(DCIS)　is　crucial　for　optimal　treatment　and　improved　clinical　outcomes.　However,　there　are　often　some　suspicious　small　cancer　nests　in　DCIS,　and　it　is　difficult　to　diagnose　the　presence　of　intact　myoepithelium　by　conventional　hematoxylin　and　eosin　(H&E)　stained　images.　Although　a　variety　of　biomarkers　are　available　for　immunohistochemical　(IHC)　staining　of　myoepithelial　cells,　no　single　biomarker　is　consistently　sensitive　to　all　tumor　lesions.　Here,　we　introduced　a　new　diagnostic　method　that　provides　rapid　and　accurate　diagnosis　of　DCISM　using　multiphoton　microscopy　(MPM).　Suspicious　foci　in　H&E-stained　images　were　labeled　as　regions　of　interest　(ROIs),　and　the　nuclei　within　these　ROIs　were　segmented　using　a　deep　learning　model.　MPM　was　used　to　capture　images　of　the　ROIs　in　H&E-stained　sections.　The　intensity　of　two-photon　excitation　fluorescence　(TPEF)　in　the　myoepithelium　was　significantly　different　from　that　in　tumor　parenchyma　and　tumor　stroma.　Through　the　use　of　MPM,　the　myoepithelium　and　basement　membrane　can　be　easily　observed　via　TPEF　and　second-harmonic　generation　(SHG),　respectively.　By　fusing　the　nuclei　in　H&E-stained　images　with　MPM　images,　DCISM　can　be　differentiated　from　suspicious　small　cancer　clusters　in　DCIS.　The　proposed　method　demonstrated　good　consistency　with　the　cytokeratin　5/6　(CK5/6)　myoepithelial　staining　method　(kappa　coefficient　=　0.818).　©　2024　UICC.