文献速递心血管MR

形变编码深度学习Transformer用于高帧率心脏电影MRI

Deformation-encoding Deep Learning Transformer for High-Frame-Rate Cardiac Cine MRI.
PubMed 文献 · Radiol Cardiothorac Imaging · 2024-01-01

研究在9个中心5840例回顾性心脏电影图像上训练并测试基于Transformer的深度学习模型,将25 fps电影图像插值至50 fps;模型插值误差低于线性和双三次插值(P < .001),前瞻性49例临床受试者和12名健康受试者中读者对实际与插值50 fps电影图像的偏好以「无偏好」为主(122次中84次),差值的90%CI为-0.01至0.14,达到非劣效。

要点

  • 模型可在不增加扫描时间、不降低空间分辨率的前提下将心脏电影帧率由25 fps提升至50 fps。
  • 模型插值图像无伪影,误差低于线性和双三次插值(P < .001)。
  • 读者对实际与插值50 fps电影图像的偏好以「无偏好」为主,非劣效成立。

核心结论

  • 基于Transformer的深度学习模型可提高心脏电影帧率,同时保留空间分辨率和扫描时间,图像质量与实际高帧率采集的图像相当。

研究设计与样本

  • 回顾性样本来自2003至2021年9个中心因临床心脏MRI转诊的5840例患者(平均年龄55岁±19,男性3527例),使用3个厂商的1.5 T和3 T扫描仪采集。
  • 其中3个中心的数据按4:1比例用于训练和测试,其余数据用于外部测试。
  • 对帧率降采样的电影图像分别用线性、双三次和基于模型的插值进行恢复,并以普通最小二乘回归对插值图像与原始电影图像的均方根误差建模。
  • 前瞻性研究纳入49例临床心脏MRI转诊受试者(平均年龄56岁±13,男性25例)和12名健康受试者(平均年龄51岁±16,男性8例),将模型应用于25 fps采集的电影图像使帧率加倍,并与实际50 fps电影图像比较。
  • 由两名读者根据感知时间平滑度和图像质量评价偏好,非劣效界值为10%。

关键影像表现/征象

  • 模型生成的插值图像无伪影。
  • 在校正厂商和场强后,基于模型的插值误差在内部和外部测试集中均低于线性和双三次插值(P < .001)。

诊断标准与关键数值

  • 读者偏好中占比最高的是实际与插值50 fps电影图像之间「无偏好」(122次中84次)。
  • 偏好采集的高帧率电影图像为122次中15次,偏好插值的为122次中23次,两者读者比例差值的90%CI为-0.01至0.14,提示非劣效。

临床应用与阅片要点

  • 模型可将25 fps心脏电影插值至50 fps,用于在不增加扫描时间的情况下获得时间平滑度与图像质量 comparable 于实际高帧率采集的电影图像。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Purpose To develop a deep learning model for increasing cardiac cine frame rate while maintaining spatial resolution and scan time. Materials and Methods A transformer-based model was trained and tested on a retrospective sample of cine images from 5840 patients (mean age, 55 years ± 19 [SD]; 3527 male patients) referred for clinical cardiac MRI from 2003 to 2021 at nine centers; images were acquired using 1.5- and 3-T scanners from three vendors. Data from three centers were used for training and testing (4:1 ratio). The remaining data were used for external testing. Cines with downsampled frame rates were restored using linear, bicubic, and model-based interpolation. The root mean square error between interpolated and original cine images was modeled using ordinary least squares regression. In a prospective study of 49 participants referred for clinical cardiac MRI (mean age, 56 years ± 13; 25 male participants) and 12 healthy participants (mean age, 51 years ± 16; eight male participants), the model was applied to cines acquired at 25 frames per second (fps), thereby doubling the frame rate, and these interpolated cines were compared with actual 50-fps cines. The preference of two readers based on perceived temporal smoothness and image quality was evaluated using a noninferiority margin of 10%. Results The model generated artifact-free interpolated images. Ordinary least squares regression analysis accounting for vendor and field strength showed lower error (P < .001) with model-based interpolation compared with linear and bicubic interpolation in internal and external test sets. The highest proportion of reader choices was "no preference" (84 of 122) between actual and interpolated 50-fps cines. The 90% CI for the difference between reader proportions favoring collected (15 of 122) and interpolated (23 of 122) high-frame-rate cines was -0.01 to 0.14, indicating noninferiority. Conclusion A transformer-based deep learning model increased cardiac cine frame rates while preserving both spatial resolution and scan time, resulting in images with quality comparable to that of images obtained at actual high frame rates. Keywords: Functional MRI, Heart, Cardiac, Deep Learning, High Frame Rate Supplemental material is available for this article. © RSNA, 2024.

来源:Radiol Cardiothorac Imaging,查看原文。版权归原作者所有。

引用

  1. Morales MA, Ghanbari F, Nakamori S, et al. Deformation-encoding Deep Learning Transformer for High-Frame-Rate Cardiac Cine MRI. Radiol Cardiothorac Imaging. 2024. PMID: 38722232. doi:10.1148/ryct.230177

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。