基于深度学习的脑梗死性中风欠采样扩散加权磁共振成像超分辨率重建：与传统迭代重建的比较

Deep Learning-Based Super-Resolution Reconstruction on Undersampled Brain Diffusion-Weighted MRI for Infarction Stroke: A Comparison to Conventional Iterative Reconstruction.

作者信息

Zhang Shuo, Zhong Meimeng, Shenliu Hanxu, Wang Nan, Hu Shuai, Lu Xulun, Lin Liangjie, Zhang Haonan, Zhao Yan, Yang Chao, Feng Hongbo, Song Qingwei

机构信息

From the Department of Nuclear Medicine (S.Z., H.F.), The First Affiliated Hospital of Dalian Medical University, Dalian, China.

Department of Radiology (M.Z., N.W., S.H., X.L., H.Z., C.Y., Q.S.), The First Affiliated Hospital of Dalian Medical University, Dalian, China.

出版信息

AJNR Am J Neuroradiol. 2025 Jan 8;46(1):41-48. doi: 10.3174/ajnr.A8482.

DOI:10.3174/ajnr.A8482

PMID:39779291

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11735436/

Abstract

BACKGROUND AND PURPOSE

DWI is crucial for detecting infarction stroke. However, its spatial resolution is often limited, hindering accurate lesion visualization. Our aim was to evaluate the image quality and diagnostic confidence of deep learning (DL)-based super-resolution reconstruction for brain DWI of infarction stroke.

MATERIALS AND METHODS

This retrospective study enrolled 114 consecutive participants who underwent brain DWI. The DWI images were reconstructed with 2 schemes: 1) DL-based super-resolution reconstruction (DWI); and 2) conventional compressed sensing reconstruction (DWI). Qualitative image analysis included overall image quality, lesion conspicuity, and diagnostic confidence in infarction stroke of different lesion sizes. Quantitative image quality assessments were performed by measurements of SNR, contrast-to-noise ratio (CNR), ADC, and edge rise distance. Group comparisons were conducted by using a paired test for normally distributed data and the Wilcoxon test for non-normally distributed data. The overall agreement between readers for qualitative ratings was assessed by using the Cohen coefficient. A value less than .05 was considered statistically significant.

RESULTS

A total of 114 DWI examinations constituted the study cohort. For the qualitative assessment, overall image quality, lesion conspicuity, and diagnostic confidence in infarction stroke lesions (lesion size <1.5 cm) improved by DWI compared with DWI (all < .001). For the quantitative analysis, edge rise distance of DWI was reduced compared with that of DWI ( < .001), and no significant difference in SNR, CNR, and ADC values (all > .05).

CONCLUSIONS

Compared with the conventional compressed sensing reconstruction, the DL-based super-resolution reconstruction demonstrated superior image quality and was feasible for achieving higher diagnostic confidence in infarction stroke.

摘要

背景与目的

扩散加权成像（DWI）对于检测梗死性卒中至关重要。然而，其空间分辨率往往有限，阻碍了病变的准确可视化。我们的目的是评估基于深度学习（DL）的超分辨率重建用于梗死性卒中脑DWI的图像质量和诊断信心。

材料与方法

这项回顾性研究纳入了114名连续接受脑DWI检查的参与者。DWI图像采用两种方案进行重建：1）基于DL的超分辨率重建（DWI）；2）传统压缩感知重建（DWI）。定性图像分析包括整体图像质量、病变清晰度以及对不同病变大小梗死性卒中的诊断信心。通过测量信噪比（SNR）、对比噪声比（CNR）、表观扩散系数（ADC）和边缘上升距离进行定量图像质量评估。对于正态分布数据，采用配对t检验进行组间比较；对于非正态分布数据，采用Wilcoxon检验。使用Cohen κ系数评估读者之间定性评分的总体一致性。P值小于0.05被认为具有统计学意义。

结果

共有114次DWI检查构成研究队列。对于定性评估，与DWI相比，DWI的整体图像质量、病变清晰度以及对梗死性卒中病变（病变大小<1.5 cm）的诊断信心均有所提高（均P<0.001）。对于定量分析，与DWI相比，DWI的边缘上升距离减小（P<0.001），而SNR、CNR和ADC值无显著差异（均P>0.05）。