Impact of super-resolution deep learning-based reconstruction for hippocampal MRI: A volunteer and phantom study

IF 3.2 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Pub Date : 2025-07-05 DOI:10.1016/j.ejrad.2025.112289

Sentaro Takada , Takeshi Nakaura , Naofumi Yoshida , Hiroyuki Uetani , Kaori Shiraishi , Naoki Kobayashi , Kensei Matsuo , Kosuke Morita , Yasunori Nagayama , Masafumi Kidoh , Yuichi Yamashita , Ryohei Takayanagi , Toshinori Hirai

{"title":"Impact of super-resolution deep learning-based reconstruction for hippocampal MRI: A volunteer and phantom study","authors":"Sentaro Takada , Takeshi Nakaura , Naofumi Yoshida , Hiroyuki Uetani , Kaori Shiraishi , Naoki Kobayashi , Kensei Matsuo , Kosuke Morita , Yasunori Nagayama , Masafumi Kidoh , Yuichi Yamashita , Ryohei Takayanagi , Toshinori Hirai","doi":"10.1016/j.ejrad.2025.112289","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and Purpose</h3><div>To evaluate the effects of super-resolution deep learning-based reconstruction (SR-DLR) on thin-slice T2-weighted hippocampal MR image quality using 3 T MRI, in both human volunteers and phantoms.</div></div><div><h3>Materials and Methods</h3><div>Thirteen healthy volunteers underwent hippocampal MRI at standard and high resolutions. Original (standard-resolution; StR) images were reconstructed with and without deep learning-based reconstruction (DLR) (Matrix = 320 × 320), and with SR-DLR (Matrix = 960 × 960). High-resolution (HR) images were also reconstructed with/without DLR (Matrix = 960 × 960). Contrast, contrast-to-noise ratio (CNR), and septum slope were analyzed. Two radiologists evaluated the images for noise, contrast, artifacts, sharpness, and overall quality. Quantitative and qualitative results are reported as medians and interquartile ranges (IQR). Comparisons used the Wilcoxon signed-rank test with Holm correction. We also scanned an American College of Radiology (ACR) phantom to evaluate the ability of our SR-DLR approach to reduce artifacts induced by zero-padding interpolation (ZIP).</div></div><div><h3>Results</h3><div>SR-DLR exhibited contrast comparable to original images and significantly higher than HR-images. Its slope was comparable to that of HR images but was significantly steeper than that of StR images (p < 0.01). Furthermore, the CNR of SR-DLR (10.53; IQR: 10.08, 11.69) was significantly superior to the StR-images without DLR (7.5; IQR: 6.4, 8.37), StR-images with DLR (8.73; IQR: 7.68, 9.0), HR-images without DLR (2.24; IQR: 1.43, 2.38), and HR-images with DLR (4.84; IQR: 2.99, 5.43) (p < 0.05). In the phantom study, artifacts induced by ZIP were scarcely observed when using SR-DLR.</div></div><div><h3>Conclusion</h3><div>SR-DLR for hippocampal MRI potentially improves image quality beyond that of actual HR-images while reducing acquisition time.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"191 ","pages":"Article 112289"},"PeriodicalIF":3.2000,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0720048X25003754","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Background and Purpose

To evaluate the effects of super-resolution deep learning-based reconstruction (SR-DLR) on thin-slice T2-weighted hippocampal MR image quality using 3 T MRI, in both human volunteers and phantoms.

Materials and Methods

Thirteen healthy volunteers underwent hippocampal MRI at standard and high resolutions. Original (standard-resolution; StR) images were reconstructed with and without deep learning-based reconstruction (DLR) (Matrix = 320 × 320), and with SR-DLR (Matrix = 960 × 960). High-resolution (HR) images were also reconstructed with/without DLR (Matrix = 960 × 960). Contrast, contrast-to-noise ratio (CNR), and septum slope were analyzed. Two radiologists evaluated the images for noise, contrast, artifacts, sharpness, and overall quality. Quantitative and qualitative results are reported as medians and interquartile ranges (IQR). Comparisons used the Wilcoxon signed-rank test with Holm correction. We also scanned an American College of Radiology (ACR) phantom to evaluate the ability of our SR-DLR approach to reduce artifacts induced by zero-padding interpolation (ZIP).

Results

SR-DLR exhibited contrast comparable to original images and significantly higher than HR-images. Its slope was comparable to that of HR images but was significantly steeper than that of StR images (p < 0.01). Furthermore, the CNR of SR-DLR (10.53; IQR: 10.08, 11.69) was significantly superior to the StR-images without DLR (7.5; IQR: 6.4, 8.37), StR-images with DLR (8.73; IQR: 7.68, 9.0), HR-images without DLR (2.24; IQR: 1.43, 2.38), and HR-images with DLR (4.84; IQR: 2.99, 5.43) (p < 0.05). In the phantom study, artifacts induced by ZIP were scarcely observed when using SR-DLR.

Conclusion

SR-DLR for hippocampal MRI potentially improves image quality beyond that of actual HR-images while reducing acquisition time.

查看原文本刊更多论文

基于超分辨率深度学习的海马MRI重建的影响：一项志愿者和幻像研究

背景与目的评价基于超分辨率深度学习的重建（SR-DLR）对人类志愿者和幻影的3t MRI薄层t2加权海马MR图像质量的影响。材料与方法对13名健康志愿者进行了标准分辨率和高分辨率的海马核磁共振成像。原始(标准分辨率;分别使用深度学习重建（DLR）（矩阵= 320 × 320）和使用SR-DLR（矩阵= 960 × 960）重建StR图像。采用/不采用DLR重建高分辨率（HR）图像（矩阵= 960 × 960）。对比，对比噪声比（CNR）和隔膜斜率进行分析。两名放射科医生对图像的噪声、对比度、伪影、清晰度和整体质量进行了评估。定量和定性结果以中位数和四分位数范围（IQR）报告。比较采用Wilcoxon符号秩检验和Holm校正。我们还扫描了一个美国放射学会（ACR）假体，以评估我们的SR-DLR方法减少零填充插值（ZIP）引起的伪影的能力。结果ssr - dlr的对比度与原始图像相当，明显高于hr图像。其斜率与HR图像相当，但明显大于StR图像(p <；0.01)。SR-DLR的CNR为10.53；IQR: 10.08, 11.69)明显优于无DLR的str图像(7.5；IQR: 6.4, 8.37)，带DLR的str图像(8.73；IQR: 7.68, 9.0)，无DLR的hr图像(2.24；IQR: 1.43, 2.38)，带DLR的hr图像(4.84；IQR: 2.99, 5.43) (p <；0.05)。在假体研究中，使用SR-DLR时几乎没有观察到ZIP引起的伪影。结论sr - dlr对海马核磁共振成像的成像质量比实际hr图像有提高的潜力，同时减少了采集时间。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

European Journal of Radiology 医学-核医学

CiteScore

6.70

自引率

3.00%

发文量

398

审稿时长

42 days

期刊介绍： European Journal of Radiology is an international journal which aims to communicate to its readers, state-of-the-art information on imaging developments in the form of high quality original research articles and timely reviews on current developments in the field. Its audience includes clinicians at all levels of training including radiology trainees, newly qualified imaging specialists and the experienced radiologist. Its aim is to inform efficient, appropriate and evidence-based imaging practice to the benefit of patients worldwide.