Reshapeit: reliable shape interaction with implicit template for medical anatomy reconstruction.

purposeShape modeling of volumetric medical images plays a crucial role in quantitative analysis and surgical planning for computer-aided diagnosis. However, automatic shape reconstruction from deep learning models often suffers from limited image resolution and the lack of shape prior constraints. This study aims to address these challenges by developing a method that enables reliable and accurate anatomical shape modeling in the continuous space.

methodsWe present the Reliable Shape Interaction with Implicit Template (ReShapeIT) network, which represents anatomical structures using continuous implicit fields rather than discrete voxel grids. The approach combines a category-specific implicit template field with a deformation network to encode anatomical shapes from training shapes. In addition, a Template Interaction Module (TIM) is designed to refine test cases by aligning learned template shapes with instance-specific latent codes.

resultsWe evaluated ReShapeIT on three anatomical datasets-Liver, Pancreas, and Lung Lobe. The proposed method outperforms state-of-the-art approaches in 3D shape reconstruction, achieving Chamfer Distance/Earth Mover's Distance scores of 0.225/0.318 for Liver, 0.125/0.067 for Pancreas, and 0.414/0.098 for Lung Lobe.

conclusionReShapeIT provides a reliable and generalizable solution for implicit anatomical shape modeling by leveraging shared template priors and instance-level deformations. The implementation is publicly available at: https://github.com/EndoluminalSurgicalVision-IMR/ReShapeIT .