Shape in Medical Imaging

This book constitutes the proceedings of the International Workshop on Shape in Medical Imaging, ShapeMI 2024, which took place in Marrakesh, Morocco, on October 6, 2024, held in conjunction with MICCAI 2024.

The 16 full papers included in this book were carefully reviewed and selected from 24 submissions. They focus on shape and spectral analysis, geometric learning and modeling algorithms, and application-driven research.

Inhalt

Weakly Supervised Bayesian Shape Modeling from Unsegmented Medical Images.- PSGMM: Pulmonary Segment Segmentation Based on Gaussian Mixture Model.- Deformable vertebra 3D/2D registration from biplanar X-rays using particle-based shape modelling.- Deep Combined Computing of Vascular Images with Tubular Shape-Guided Convolution.- Implicitly Explicit: Segmenting Vertebrae with Deep Implicit Statistical Shape Models.- 3D Body Twin: Improving Human Gait Visualizations Using Personalized Avatars.- Robust Curve Detection in Volumetric Medical Imaging via Attraction Field.- A Critical Comparison Between Template-Based and Architecture-Reused Deep Learning Methods for Generic 3D Landmarking of Anatomical Structures.- Adaptive Bi-ventricle Surface Reconstruction from Cardiovascular Imaging.- Application of Deep Statistical Shape Modeling for Analysis of Obstructive Sleep Apnea from MRI Data.- Leveraging Expert Knowledge for Real-time Online Adaptation of Intraoperative Liver Registration.- MASSM: An End-to-End Deep Learning Framework for Multi-Anatomy Statistical Shape Modeling Directly From Images.- LaMoD: Latent Motion Diffusion Model For Myocardial Strain Generation.- Enhancing Multimodal Image-Based Classification of Alzheimer's Disease with Surface Information.- Fast Medical Shape Reconstruction via Meta-learned Implicit Neural Representations.- Towards Point Cloud-Based Medical Image Registration for Dynamic 4D-CT Imaging.