磁共振成像2025，Vol.16Issue(9)：60-65,6.DOI:10.12015/issn.1674-8034.2025.09.010
基于深度学习的加速T1WI和T2WI序列在头颈部肿瘤中的应用价值
Application value of deep learning-based accelerated T1WI and T2WI sequences in head and neck tumors
摘要
Abstract
Objective:To evaluate the application value of deep learning(DL)-based accelerated T1-weighted imaging(T1WI)and T2-weighted imaging(T2WI)in head and neck tumors.Materials and Methods:Thirty-five untreated patients with head and neck tumors were prospectively enrolled and underwent head and neck MRI standard(T1WI,T2WI-Dixon)and DL sequences(DL-T1WI,DL-T2WI-Dixon).Image quality was subjectively rated by two radiologists using a five-point scale for overall image quality,artifacts and lesion conspicuity.Objective image quality was assessed by calculation of signal-to-noise ratio(SNR)of muscle,fat and tumor and contrast-to-noise ratio(CNR)of tumor in standard and DL sequences by one radiologist.Scan time and image quality scores were compared between standard and DL sequences using Kruskal-Wallis test.Results:DL-T1WI(89 s)and DL-T2WI-Dixon(101 s)sequences reduced 46%scan time compared to standard T1WI(164 s)and T2WI-Dixon(188 s)sequences,respectively.There were no significant difference in overall image quality,artifacts and lesion conspicuity between DL-T1WI,DL-T2WI-Dixon sequences and standard T1WI and T2WI-Dixon sequences(all P>0.05).SNR of fat and tumor and CNR of tumor in DL-T1WI sequence were comparable with that in standard T1WI sequence(all P>0.05),SNR of muscle,fat and tumor and CNR of tumor in DL-T2WI-Dixon sequence were comparable with that in standard T2WI-Dixon sequence(all P>0.05).Conclusions:DL-based accelerated MRI sequences could effectively reduce scanning time in patients with head and neck tumors.Except for the SNR of muscle in DL-T1WI sequence,the remaining objective image quality metrics of DL sequences are comparable to those in standard sequences.Moreover,compared to standard T1WI and T2WI-Dixon sequences,DL-T1WI and DL-T2WI-Dixon sequences could maintain excellent subjective image quality.关键词
头颈部肿瘤/深度学习重建技术/磁共振成像/信噪比/对比噪声比Key words
head and neck tumors/deep learning reconstruction/magnetic resonance imaging/signal-to-noise ratio/contrast-to-noise ratio分类
医药卫生引用本文复制引用
王天娇,付海鸿,冯逢,金征宇,王沄,陈钰,苏童,曲江明,徐振潭,王晓,张竹花,薛华丹..基于深度学习的加速T1WI和T2WI序列在头颈部肿瘤中的应用价值[J].磁共振成像,2025,16(9):60-65,6.基金项目
National Natural Science Foundation of China(No.82371962) （No.82371962）
National High Level Hospital Clinical Research Funding(No.2022-PUMCH-B-067). 国家自然科学基金项目(编号:82371962) （No.2022-PUMCH-B-067）
中央高水平医院临床科研专项(编号:2022-PUMCH-B-067) （编号:2022-PUMCH-B-067）
