基於幅度圖像並利用相位增強技術訓練生成式先驗模型以重建 MRI 圖像
使用從幅度圖像中訓練的生成式先驗模型，並結合相位增強技術，可以顯著提高 MRI 圖像的重建質量，尤其是在高度欠採樣的情況下。
マグニチュード画像のみから学習したMRI再構成のための生成的な事前分布：位相拡張を用いたアプローチ
本稿では、位相情報を含まないマグニチュード画像のみを用いて、高精度かつロバストなMRI画像再構成を実現する生成的な事前分布の構築手法を提案する。
Improving MRI Reconstruction Quality with Generative Priors Trained on Magnitude-Only Images Using Phase Augmentation
Training generative priors on magnitude-only MRI images augmented with synthetic phase information significantly improves image reconstruction quality, especially in high-undersampling scenarios.
빠른 MRI 재구성을 위한 이미지 안내를 사용한 연속 K 공간 복구 네트워크
본 논문에서는 암묵적 신경 표현(INR)과 이미지 안내를 활용하여 저해상도 MRI 이미지에서 고품질의 연속적인 k-공간을 복구하는 새로운 네트워크인 IGKR-Net을 제안합니다.
Image-Guided Continuous K-Space Recovery Network for Fast MRI Reconstruction using Implicit Neural Representation
This paper proposes a novel deep learning method for fast MRI reconstruction by leveraging implicit neural representations (INR) to recover undersampled k-space data with guidance from the image domain, leading to improved image quality compared to traditional methods.
Benchmarking Non-Cartesian 3D Multi-Coil MRI Reconstruction Using NC-PDNet and Comparing Various Undersampling Patterns
Extending NC-PDNet, a deep learning model, to reconstruct 3D multi-coil MRI data acquired with non-Cartesian undersampling, particularly showcasing the superior performance of the GoLF-SPARKLING trajectory and the practicality of channel-agnostic training with coil compression.
サブスペース拡散モデルを用いたMRI再構成のための直交分解を用いたサブスペース拡散モデル
本稿では、従来の拡散モデルよりも高速かつ高精度なMRI再構成を実現する、直交分解を用いたサブスペース拡散モデル（Sub-DM）を提案する。
MR-VAE 및 잠재 확산 사전을 활용한 언더샘플링된 MRI 재구성을 위한 LDPM: 품질과 충실도 사이의 균형
LDPM이라는 새로운 MRI 재구성 방법을 제안하며, 이는 잠재 확산 모델을 사용하여 제한된 계산 리소스로 고품질의 MRI 이미지를 생성하면서도 데이터 충실도를 유지하는 데 초점을 맞춥니다.
MR-VAEと潜在拡散事前分布を用いたアンダーサンプリングMRI再構成に向けたLDPM
本稿では、アンダーサンプリングされたMRI画像を高品質かつ高忠実度で再構成するために、MR-VAEと潜在拡散事前分布を用いた新しい手法LDPMを提案する。
LDPM: An Undersampled MRI Reconstruction Method Using MR-VAE and Latent Diffusion Prior
This paper introduces LDPM, a novel method for reconstructing undersampled MRI images by leveraging a latent diffusion model with an MRI-specific variational autoencoder (MR-VAE) and a dual-stage sampling technique for improved fidelity and reduced computational burden.
© 2024 by Linnk AI