From 2D to 3D, Deep Learning-based Shape Reconstruction in Magnetic Resonance Imaging: A Review

2025-10-01

AI Summary

This study addresses the challenge of reconstructing high-fidelity 3D anatomical structures from 2D MRI scans to enhance disease diagnosis, treatment planning, and computational modeling. We systematically review four dominant deep learning paradigms for cardiac, neurological, and pulmonary applications: point cloud generation, mesh deformation, anatomy-aware shape modeling, and voxel-based reconstruction. Notably, we present the first unified survey of multimodal fusion and cross-modal 3D reconstruction frameworks. Our key contribution is a novel anatomy-specific model adaptability assessment framework, which—leveraging public benchmarks and standardized metrics—quantitatively evaluates trade-offs among reconstruction accuracy, robustness, computational cost, and clinical deployability. Empirical analysis reveals critical insights into method selection under varying clinical constraints. The findings provide both methodological foundations and practical guidelines for developing generalizable, clinically viable 3D reconstruction systems.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Deep learning-based 3-dimensional (3D) shape reconstruction from 2-dimensional (2D) magnetic resonance imaging (MRI) has become increasingly important in medical disease diagnosis, treatment planning, and computational modeling. This review surveys the methodological landscape of 3D MRI reconstruction, focusing on 4 primary approaches: point cloud, mesh-based, shape-aware, and volumetric models. For each category, we analyze the current state-of-the-art techniques, their methodological foundation, limitations, and applications across anatomical structures. We provide an extensive overview ranging from cardiac to neurological to lung imaging. We also focus on the clinical applicability of models to diseased anatomy, and the influence of their training and testing data. We examine publicly available datasets, computational demands, and evaluation metrics. Finally, we highlight the emerging research directions including multimodal integration and cross-modality frameworks. This review aims to provide researchers with a structured overview of current 3D reconstruction methodologies to identify opportunities for advancing deep learning towards more robust, generalizable, and clinically impactful solutions.

Problem

• Reconstructing 3D anatomical shapes from 2D MRI scans
• Surveying deep learning methods for medical imaging reconstruction
• Addressing clinical applicability and limitations in 3D MRI models

Innovation

• Deep learning reconstructs 3D shapes from 2D MRI
• Methods include point cloud and mesh-based models
• Focuses on clinical applications and data influence