PulseAugur
LIVE 13:04:43
research · [2 sources] ·
0
research

New AI framework reconstructs 3D MRI from sparse 2D slices

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have developed a novel framework, MK-ResRecon, designed to reconstruct high-fidelity 3D MRI volumes from significantly fewer 2D slices. This method utilizes a multi-kernel texture-aware loss to predict missing intermediate slices and a secondary model, IdentityRefineNet3D, to refine these predictions into a cohesive 3D structure. The framework has been trained and evaluated on brain MRI datasets, demonstrating its potential for faster and more patient-friendly MRI imaging by reducing scan times and motion artifacts. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Enables faster and more patient-friendly MRI imaging by reducing scan times and motion artifacts.

RANK_REASON This is a research paper describing a new framework for MRI reconstruction.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Prajyot Pyati, Sapna Sachan, Amulya Kumar Mahto, Pranjal Phukan ·

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

    arXiv:2605.03432v1 Announce Type: new 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 repea…

  2. arXiv cs.CV TIER_1 · Pranjal Phukan ·

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

    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 pro…

RELATED ENTITIES

RELATED TOPICS