[论文解读] Active Phase-Encode Selection for Slice-Specific Fast MR Scanning Using a Transformer-Based Deep Reinforcement Learning Framework

Yiming Liu, Yanwei Pang+2 more|arXiv (Cornell University)|Mar 11, 2022

Advanced MRI Techniques and Applications被引用 4

一句话总结

本文提出 TITLE，一种基于轻量级Transformer的深度强化学习框架，通过主动选择特定切片的相位编码线来加速磁共振成像扫描。通过利用二值相位指示符和欠采样k空间数据预测Q值，该方法在推理速度上比以往的强化学习方法快150倍，同时在fastMRI数据集上显著提升了重建精度。

ABSTRACT

Purpose: Long scan time in phase encoding for forming complete K-space matrices is a critical drawback of MRI, making patients uncomfortable and wasting important time for diagnosing emergent diseases. This paper aims to reducing the scan time by actively and sequentially selecting partial phases in a short time so that a slice can be accurately reconstructed from the resultant slice-specific incomplete K-space matrix. Methods: A transformer based deep reinforcement learning framework is proposed for actively determining a sequence of partial phases according to reconstruction-quality based Q-value (a function of reward), where the reward is the improvement degree of reconstructed image quality. The Q-value is efficiently predicted from binary phase-indicator vectors, incomplete K-space matrices and their corresponding undersampled images with a light-weight transformer so that the sequential information of phases and global relationship in images can be used. The inverse Fourier transform is employed for efficiently computing the undersampled images and hence gaining the rewards of selecting phases. Results: Experimental results on the fastMRI dataset with original K-space data accessible demonstrate the efficiency and accuracy superiorities of proposed method. Compared with the state-of-the-art reinforcement learning based method proposed by Pineda et al., the proposed method is roughly 150 times faster and achieves significant improvement in reconstruction accuracy. Conclusions: We have proposed a light-weight transformer based deep reinforcement learning framework for generating high-quality slice-specific trajectory consisting of a small number of phases. The proposed method, called TITLE (Transformer Involved Trajectory LEarning), has remarkable superiority in phase-encode selection efficiency and image reconstruction accuracy.

研究动机与目标

• 通过最小化每一切片的相位编码线数量来减少磁共振成像扫描时间，同时不牺牲图像质量。
• 解决现有强化学习方法在磁共振成像相位编码选择中效率低下的问题。
• 开发一种快速、准确且切片特定的轨迹学习框架，用于欠采样k空间重建。
• 利用轻量级Transformer架构整合全局图像上下文信息与序列相位依赖关系。

提出的方法

• 一个深度强化学习智能体基于反映图像重建质量提升的Q值函数，按顺序学习选择相位编码线。
• Q值通过一个轻量级Transformer预测，该模型处理二值相位指示符向量和不完整的k空间矩阵。
• 通过在欠采样k空间数据上执行逆傅里叶变换计算图像质量奖励，以评估重建图像的质量。
• 该框架采用稀疏且自适应的采样策略，根据图像重建质量的实时反馈动态选择相位。
• 模型通过端到端训练，使用源自结构相似性（SSIM）和重建图像与完全采样图像之间均方误差（MSE）的奖励信号。
• 轻量级Transformer架构能够高效建模k空间中的长距离依赖关系以及全局图像特征。

实验结果

研究问题

• RQ1 深度强化学习智能体能否有效学习到选择最少数量的相位编码线，从而为单一切片生成高质量的磁共振成像重建？
• RQ2 与标准深度学习或强化学习基线相比，基于Transformer的架构在序列相位选择建模方面有何改进？
• RQ3 与最先进方法相比，该方法在保持或提升图像重建精度的同时，能在多大程度上减少扫描时间？
• RQ4 将逆傅里叶变换用于实时奖励计算，如何提升训练效率与性能？

主要发现

• 所提出的方法 TITLE 相较于 Pineda 等人提出的最先进强化学习方法，在相位编码选择推理速度上实现了150倍的加速。
• 该方法在使用原始k空间数据的 fastMRI 数据集上，显著提升了重建精度，表现为更高的SSIM和更低的MSE。
• 轻量级Transformer架构能够有效建模局部相位序列与全局图像关系，从而提升重建保真度。
• 该框架成功学习到针对切片的自适应、优化的采样轨迹，减少了扫描时间，同时不损害诊断潜力。
• 利用逆傅里叶变换实现实时奖励计算，使训练过程中能够获得高效且准确的反馈，从而提升策略收敛性。