High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approach

2026-06-16

AI Summary

High-fidelity MRI-based 3D reconstruction of pelvic organs—specifically the bladder, uterus, and rectum—remains hindered by cumbersome pipelines and a lack of standardization. This work proposes a deformable shape modeling framework that synergistically integrates deep learning with iterative optimization: a geometry-aware multi-level network first rapidly predicts the global organ morphology, followed by a two-stage amortized optimization strategy to refine local surface details. The approach innovatively couples deep learning with iterative surface optimization, significantly enhancing surface accuracy and mesh quality while preserving topological consistency. Experimental results demonstrate that the method outperforms existing approaches in both Chamfer Distance and Dice coefficient, and achieves notable improvements in computational efficiency and overall volumetric mesh quality, as measured by metrics such as minSICN and minSIGE.

Abstract

Patient-specific 3D reconstruction of pelvic organ geometry from MRI is important for pelvic floor modeling and downstream patient-specific analysis. However, while previous studies have focused primarily on either image segmentation or downstream use of 3D models, the reconstruction of high-fidelity, high-quality geometries remains labor-intensive and poorly standardized. The study introduced a hybrid deformable shape modeling framework that integrates deep learning prediction with iterative optimization for the reconstruction of the bladder, uterus, and rectum. The framework consists of three core components: a geometry-aware multi-level deep learning architecture that preserves topological consistency of pelvic organs; a two-stage amortized optimization training strategy that balances global shape capture and local surface refinement; and a holistic synergy mechanism--where iterative optimization provides supervision for deep learning during the training phase, and during inference, deep learning rapidly predicts the global organ morphology, followed by iterative optimization to refine local surfaces and mesh quality. This framework demonstrated marked superiority in geometric fidelity than current mainstream deep learning-based organ reconstruction models. For individual anatomical structures, the reconstructed 3D geometries for the bladder, rectum, and uterus achieved significantly lower Chamfer Distance values and higher Dice Similarity Coefficient scores. In addition, while maintaining high computational efficiency, the proposed architecture yielded superior overall volumetric mesh quality. At the patient level, the framework achieved higher mean values for the 10 worst elements for both minSICN and minSIGE compared to traditional geometric post-processing algorithms.

Problem

• 3D geometric reconstruction
• pelvic organs
• MRI
• high-fidelity
• patient-specific

Innovation

• hybrid deep learning
• iterative optimization
• 3D geometric reconstruction
• topological consistency
• amortized optimization