Remarkable progress has been made by data-driven machine-learning methods in
the analysis of MRI scans. However, most existing MRI analysis approaches are
crafted for specific MR pulse sequences (MR contrasts) and usually require
nearly isotropic acquisitions. This limits their applicability to diverse
real-world clinical data, where scans commonly exhibit variations in
appearances due to being obtained with varying sequence parameters,
resolutions, and orientations -- especially in the presence of pathology. In
this paper, we propose PEPSI, the first pathology-enhanced, and
pulse-sequence-invariant feature representation learning model for brain MRI.
PEPSI is trained entirely on synthetic images with a novel pathology encoding
strategy, and enables co-training across datasets with diverse pathologies and
missing modalities. Despite variations in pathology appearances across
different MR pulse sequences or the quality of acquired images (e.g.,
resolution, orientation, artifacts, etc), PEPSI produces a high-resolution
image of reference contrast (MP-RAGE) that captures anatomy, along with an
image specifically highlighting the pathology. Our experiments demonstrate
PEPSI's remarkable capability for image synthesis compared with the
state-of-the-art, contrast-agnostic synthesis models, as it accurately
reconstructs anatomical structures while differentiating between pathology and
normal tissue. We further illustrate the efficiency and effectiveness of PEPSI
features for downstream pathology segmentations on five public datasets
covering white matter hyperintensities and stroke lesions. Code is available at
this https URL

提出了 PEPSI 方法，一种病理增强和脉冲序列不变的脑部 MRI 特征表示学习模型，它能够合成高分辨率的对比度参考图像和突出显示病变的图像，显示了其在图像合成和病变分割方面的出色能力。

PEPSI：病理学增强的脑 MRI 脉冲序列不变表示

PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for  Brain MRI

Magnetic resonance imaging (MRI) is being increasingly utilized to assess,
diagnose, and plan treatment for a variety of diseases. The ability to
visualize tissue in varied contrasts in the form of MR pulse sequences in a
single scan provides valuable insights to physicians, as well as enabling
automated systems performing downstream analysis. However many issues like
prohibitive scan time, image corruption, different acquisition protocols, or
allergies to certain contrast materials may hinder the process of acquiring
multiple sequences for a patient. This poses challenges to both physicians and
automated systems since complementary information provided by the missing
sequences is lost. In this paper, we propose a variant of generative
adversarial network (GAN) capable of leveraging redundant information contained
within multiple available sequences in order to generate one or more missing
sequences for a patient scan. The proposed network is designed as a
multi-input, multi-output network which combines information from all the
available pulse sequences, implicitly infers which sequences are missing, and
synthesizes the missing ones in a single forward pass. We demonstrate and
validate our method on two brain MRI datasets each with four sequences, and
show the applicability of the proposed method in simultaneously synthesizing
all missing sequences in any possible scenario where either one, two, or three
of the four sequences may be missing. We compare our approach with competing
unimodal and multi-modal methods, and show that we outperform both
quantitatively and qualitatively.

本篇研究提出了一种基于生成对抗网络的多输入、多输出的方法，通过利用多个序列的冗余信息，能够在单次扫描中生成患者缺失的磁共振成像序列，该方法在两个不同的 4 序列脑 MRI 数据集上进行了测试，并与单模态和多模态方法进行了比较，结果定量和定性上均优于其竞争方法。

使用多模式生成对抗网络进行 MRI 脉冲序列合成

Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative  Adversarial Network

We present experimental measurements on a model quantum system that
demonstrate our ability to dramatically suppress qubit error rates by the
application of optimized dynamical decoupling pulse sequences in a variety of
experimentally relevant noise environments. We provide the first demonstration
of an analytically derived pulse sequence developed by Uhrig, and find novel
sequences through active, real-time experimental feedback. These new sequences
are specially tailored to maximize error suppression without the need for a
priori knowledge of the ambient noise environment. We compare these sequences
against the Uhrig sequence, and the well established CPMG-style spin echo,
demonstrating that our locally optimized pulse sequences outperform all others
under test. Numerical simulations show that our locally optimized pulse
sequences are capable of suppressing errors by orders of magnitude over other
existing sequences. Our work includes the extension of a treatment to predict
qubit decoherence under realistic conditions, including the use of
finite-duration, square $\pi$ pulses, yielding strong agreement between
experimental data and theory for arbitrary pulse sequences. These results
demonstrate the robustness of qubit memory error suppression through dynamical
decoupling techniques across a variety of qubit technologies.

通过优化动力学解耦脉冲序列的应用，我们在模型量子系统上进行了实验测量，证明了我们能够显著抑制量子位的错误率。我们通过实时反馈找到新的序列，并将这些序列与已有的序列进行比较，证明了这些本地优化的脉冲序列在测试中表现优于其他所有序列。