Statistical Shape
Statistical shape modeling (SSM) aims to quantitatively analyze and represent the variations in anatomical shapes within a population, facilitating applications in medical diagnosis and treatment planning. Current research heavily emphasizes deep learning approaches, including various neural network architectures, to directly learn SSMs from unsegmented medical images or point clouds, thereby reducing the need for time-consuming manual segmentation. This shift towards automated SSM construction is significantly improving the feasibility and accessibility of shape analysis, impacting fields like medical image analysis, computer-aided surgery, and personalized medicine.
Papers
Learning Population-level Shape Statistics and Anatomy Segmentation From Images: A Joint Deep Learning Model
Wenzheng Tao, Riddhish Bhalodia, Shireen Elhabian
A statistical shape model for radiation-free assessment and classification of craniosynostosis
Matthias Schaufelberger, Reinald Peter Kühle, Andreas Wachter, Frederic Weichel, Niclas Hagen, Friedemann Ringwald, Urs Eisenmann, Jürgen Hoffmann, Michael Engel, Christian Freudlsperger, Werner Nahm