Single-Subject Multi-View MRI Super-Resolution via Implicit Neural Representations

2026-03-23

AI Summary

This work addresses the challenge of low through-plane resolution in clinical MRI, which arises from acquisition time constraints. Conventional multi-view fusion methods rely on image registration and interpolation, often compromising fine anatomical details, while existing deep learning-based super-resolution approaches typically require large-scale training data or pre-aligned inputs. To overcome these limitations, we propose SIMS-MRI, a novel framework that—without external training data or pre-alignment assumptions—achieves spatially consistent isotropic high-resolution reconstruction using only multi-view anisotropic scans from a single subject. Our method leverages implicit neural representation with multi-resolution hash encoding, a learnable view alignment module, and a self-supervised optimization strategy. Experiments on simulated brain and clinical prostate MRI demonstrate its effectiveness in significantly enhancing anatomical fidelity. The code is publicly released to ensure reproducibility.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Clinical MRI frequently acquires anisotropic volumes with high in-plane resolution and low through-plane resolution to reduce acquisition time. Multiple orientations are therefore acquired to provide complementary anatomical information. Conventional integration of these views relies on registration followed by interpolation, which can degrade fine structural details. Recent deep learning-based super-resolution (SR) approaches have demonstrated strong performance in enhancing single-view images. However, their clinical reliability is often limited by the need for large-scale training datasets, resulting in increased dependence on cohort-level priors. Self-supervised strategies offer an alternative by learning directly from the target scans. Prior work either neglects the existence of multi-view information or assumes that in-plane information can supervise through-plane reconstruction under the assumption of pre-alignment between images. However, this assumption is rarely satisfied in clinical settings. In this work, we introduce Single-Subject Implicit Multi-View Super-Resolution for MRI (SIMS-MRI), a framework that operates solely on anisotropic multi-view scans from a single patient without requiring pre- or post-processing. Our method combines a multi-resolution hash-encoded implicit representation with learned inter-view alignment to generate a spatially consistent isotropic reconstruction. We validate the SIMS-MRI pipeline on both simulated brain and clinical prostate MRI datasets. Code will be made publicly available for reproducibility: https://github.com/abhshkt/SIMS-MRI

Problem

• MRI super-resolution
• multi-view integration
• anisotropic MRI
• single-subject reconstruction
• inter-view alignment

Innovation

• Implicit Neural Representation
• Multi-View Super-Resolution
• Self-Supervised Learning
• Learned Inter-View Alignment
• Hash Encoding