Leveraging deep learning for nonlinear shape representation in anatomically parameterized statistical shape models.

Journal: International journal of computer assisted radiology and surgery
PMID:

Abstract

PURPOSE: Statistical shape models (SSMs) are widely used for morphological assessment of anatomical structures. However, a key limitation is the need for a clear relationship between the model's shape coefficients and clinically relevant anatomical parameters. To address this limitation, this paper proposes a novel deep learning-based anatomically parameterized SSM (DL-ANAT) by introducing a nonlinear relationship between anatomical parameters and bone shape information.

Authors

  • Behnaz Gheflati
    Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada. b_ghefla@encs.concordia.ca.
  • Morteza Mirzaei
    Applied Biotechnology Research Center, Baqiyatallah University of Medical Sciences, Tehran, Iran.
  • Sunil Rottoo
    Think Surgical Inc., Montreal, QC, Canada.
  • Hassan Rivaz