MK-ResRecon: Multi-Kernel Residual Framework for Texture-Aware 3D MRI Refinement from Sparse 2D Slices

TL;DR

This paper introduces MK-ResRecon, a novel multi-kernel residual framework that reconstructs high-quality 3D MRI images from only 12.5% of the original slices, significantly reducing scan time and patient discomfort.

Contribution

The work presents a new framework with two models that effectively reconstruct detailed 3D MRI volumes from sparse 2D slices, enabling faster and more patient-friendly MRI procedures.

Findings

Reconstructed 3D MRI volumes from only 12.5% slices.

Preserved fine anatomical details with multi-kernel texture-aware loss.

Validated on large, heterogeneous brain MRI datasets.

Abstract

Magnetic Resonance Imaging (MRI) acquisition remains a time-intensive and patient-straining process, as prolonged scan dura- tions increase the likelihood of motion artifacts, which degrade image quality and frequently require repeated scans. To address these chal- lenges, we propose a novel framework with two models MK-ResRecon and IdentityRefineNet3D to reconstruct high-fidelity 3D MRI volumes from sparsely sampled 2D slices-requiring only 12.5% of the axial slices for full resolution 3D reconstruction. MK-ResRecon predicts missing in- termediate 2D slices using a multi-kernel texture-aware loss, preserving fine anatomical details. IdentityRefineNet3D refines the predicted slices and the original sparse slices as a single 3D volume to obtain a smooth anatomical structure. We train the models on a large T1-sequence POST- contrast brain MRI dataset and evaluate on a large heterogeneous brain MRI cohort. The work provides accurate, hallucination-free, generaliz- able and clinically validated framework for 3D MRI reconstruction from highly sparse inputs and enables a clinically viable path towards faster and more patient-friendly MRI imaging.