Scholarlink

Background <p>Magnetic resonance imaging (MRI) plays an important role in the diagnosis and treatment of hippocampal sclerosis. However, this exam presents challenges due to long scan times and image quality variability in pediatric patients.</p> Objective <p>This study aims to compare conventional reconstructed MRI and accelerated sequences with and without deep learning-based reconstruction (DLR) with regard to image quality and diagnostic performance in pediatric hippocampal sclerosis patients.</p> Materials and methods <p>A total of 68 pediatric patients proven or suspected to have temporal lobe epilepsy with hippocampal sclerosis who underwent recommended epilepsy structural MRI were included in this study. MRI examination included standard sequences and accelerated sequences with and without DLR. Standard sequences were reconstructed using the conventional pipeline, while accelerated sequences were reconstructed using both the conventional pipeline and DLR pipeline. Two experienced pediatric radiologists independently evaluated the following parameters of three reconstructed image sets on a 5-point scale: image quality, anatomic structure visibility, motion artifact, truncation artifact, image noise, and detectability of hippocampal abnormalities. Signal-to-noise ratio (SNR) measurements of the hippocampus were performed in all sequences and compared between the three sets of images. Inter-reader agreement and agreement between image sets for detecting hippocampal abnormalities were assessed using Cohen’s kappa.</p> Results <p>Images reconstructed with DLR received significantly higher scores of overall image quality, presence of lesion, and image noise than with conventional or original accelerated reconstructions (all <i>P</i>&lt;0.05), while there was no statistical difference of artifacts between the three groups (all <i>P</i>&gt;0.05). The SNR for all sequences with DLR was significantly higher than conventional or original reconstructions without DLR (all <i>P</i>&lt;0.001). Inter-reader agreement showed almost perfect agreement (<i>κ</i>=0.803-0.963) of the imaging manifestations, while agreement between image sets showed substantial agreement to almost perfect agreement (<i>κ</i>=0.778-0.965) of the imaging manifestations.</p> Conclusion <p>Accelerated sequences with DLR provide a 44% scan time reduction with similar subjective image quality, artifacts, and diagnostic performance to conventional reconstruction sequences.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Accelerated magnetic resonance imaging of hippocampal sclerosis in pediatric patients with deep learning-based reconstruction: comparison of image quality and diagnostic performance with conventional reconstruction

  • 期刊论文

  • 发表日期：

    2025年10月13日

查看全文
  • Xuehua Peng,
  • Baiqi Zhu,
  • Jianbo Shao

摘要

Background

Magnetic resonance imaging (MRI) plays an important role in the diagnosis and treatment of hippocampal sclerosis. However, this exam presents challenges due to long scan times and image quality variability in pediatric patients.

Objective

This study aims to compare conventional reconstructed MRI and accelerated sequences with and without deep learning-based reconstruction (DLR) with regard to image quality and diagnostic performance in pediatric hippocampal sclerosis patients.

Materials and methods

A total of 68 pediatric patients proven or suspected to have temporal lobe epilepsy with hippocampal sclerosis who underwent recommended epilepsy structural MRI were included in this study. MRI examination included standard sequences and accelerated sequences with and without DLR. Standard sequences were reconstructed using the conventional pipeline, while accelerated sequences were reconstructed using both the conventional pipeline and DLR pipeline. Two experienced pediatric radiologists independently evaluated the following parameters of three reconstructed image sets on a 5-point scale: image quality, anatomic structure visibility, motion artifact, truncation artifact, image noise, and detectability of hippocampal abnormalities. Signal-to-noise ratio (SNR) measurements of the hippocampus were performed in all sequences and compared between the three sets of images. Inter-reader agreement and agreement between image sets for detecting hippocampal abnormalities were assessed using Cohen’s kappa.

Results

Images reconstructed with DLR received significantly higher scores of overall image quality, presence of lesion, and image noise than with conventional or original accelerated reconstructions (all P<0.05), while there was no statistical difference of artifacts between the three groups (all P>0.05). The SNR for all sequences with DLR was significantly higher than conventional or original reconstructions without DLR (all P<0.001). Inter-reader agreement showed almost perfect agreement (κ=0.803-0.963) of the imaging manifestations, while agreement between image sets showed substantial agreement to almost perfect agreement (κ=0.778-0.965) of the imaging manifestations.

Conclusion

Accelerated sequences with DLR provide a 44% scan time reduction with similar subjective image quality, artifacts, and diagnostic performance to conventional reconstruction sequences.

Graphical Abstract