Abstract:
The main objective of this work is to obtain reliable and detailed anatomical information for developing a quantitative 3-D tongue model. This work introduces a strategy for defining a set of landmark points in reference to a general 3-D representation of tongue structure. The landmarks define locations of anatomical significance that have identifiable geometric coordinates. They constitute common reference points for a mathematical mapping between any pair of data sets and indicate the anatomical correspondence, or homology, between the data sets. The integration of different data sets of the human tongue is based on this correspondence, and it is achieved by a method of nonuniform geometrical transformation (thin-plate spline mapping). We show the feasibility of these methods by mapping from muscle anatomy, according to a detailed hand-drawn dissection study [K. Miyawaki, Ann. Bul. RILP, Univ. Tokyo 8, 23--50 (1974)], against atlas images from freshly deep-frozen samples (Visible Man data) and MRI head scans of living subjects making a vowel articulatory gesture. As the result of this exercise, we have produced a tongue portion of the Visible Man data with muscle fiber direction identified. [Work supported in part by NSF grant RF 729550 and ATR/MIC Labs.]