Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution

2026-06-25

AI Summary

This work addresses the ill-posed inverse problem in arbitrary-slice super-resolution of medical images by proposing a dual-prior-guided null-space learning framework that avoids anatomical distortion and preserves fidelity to observed data. The method integrates a deterministic observation prior with a geometric continuity prior, enabling content-adaptive modeling within the null space through a dynamically blended B-spline mixture-of-experts module. To strictly enforce exact reconstruction of the original slices, it combines a measurement consistency projection (MCP) with a local spatial consistency decoder (LSCD). Evaluated on three CT and one MRI benchmarks, the proposed approach significantly outperforms existing methods, achieving superior anatomical realism and spatial coherence while maintaining strict consistency with the input observations.

Abstract

Arbitrary slice super-resolution reconstructs isotropic volumes from anisotropic clinical acquisitions by synthesizing intermediate slices at arbitrary scales. However, treating this ill-posed inverse problem as unconstrained residual-based regression risks hallucinating anatomically implausible structures or altering the originally observed data. To address both concerns, this paper presents the Dual-Prior Null-space Learning (DP-NSL) framework, which reformulates the task as a constrained recovery process guided by two complementary priors. A Measurement-Consistent Projection (MCP) enforces a Deterministic Observation Prior: the reconstruction undergoes an exact orthogonal projection that reproduces every acquired slice with zero error, confining all learned details to the unobservable null space. Within this null space, a Mixture-of-Splines (MoS) module imposes a Geometric Continuity Prior by dynamically mixing B-spline experts of different analytic orders, allowing each anatomical region to be modeled with a content-aware level of continuity. To promote spatial coherence, a Local Spatial Consistency Decoder (LSCD) further injects local inductive bias. Experiments on three CT and one MRI benchmark show that DP-NSL outperforms existing approaches while strictly preserving measurement consistency. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.

Problem

• arbitrary slice super-resolution
• ill-posed inverse problem
• measurement consistency
• anatomical plausibility
• medical image reconstruction

Innovation

• Null-space Learning
• Measurement Consistency
• Mixture-of-Splines
• Geometric Continuity Prior
• Arbitrary Slice Super-Resolution