The　labyrinth　of　the　inner　ear　is　an　important　auditory　and　balanced　sensory　organ　and　is　closely　related　to　tinnitus,　hearing　loss,　vertigo,　and　Meniere　diseases.　Quantitative　description　and　measurement　of　the　labyrinth　is　a　challenging　task　in　both　clinical　practice　and　medical　research.　A　data-driven-based　labyrinth　morphological　modeling　method　is　proposed　for　extracting　simple　and　low-dimensional　representations　or　feature　vectors　to　quantify　the　normal　and　abnormal　labyrinths　in　morphology.　Firstly,　a　two-stage　pose　alignment　strategy　is　introduced　to　align　the　segmented　inner　ear　labyrinths.　Then,　an　energy-adaptive　spatial　and　inter-slice　dimensionality　reduction　strategy　is　adopted　to　extract　compact　morphological　features　via　a　variational　autoencoder　(VAE).　Finally,　a　statistical　model　of　the　compact　feature　in　the　latent　space　is　established　to　represent　the　morphology　distribution　of　the　labyrinths.　As　one　of　an　application　of　our　model,　a　reference-free　quality　evaluation　for　the　segmentation　of　the　labyrinth　is　explored.　The　experimental　results　show　that　the　consistency　between　the　proposed　method　and　the　Dice　similarity　coefficient　(DSC)　reaches　0.78.　Further　analysis　showed　that　the　model　also　has　a　high　potential　to　apply　to　morphological　analysis,　such　as　anomaly　detection,　of　the　labyrinths.