Volume 36, Issue 2

In this paper, we propose DeepCut , a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in our case bounding boxes. It extends the approach of the well-known GrabCut [1] method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naïve approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.

在本文中，我们提出了DeepCut，一种从带有弱标注（即边界框）的图像数据集中获得逐像素对象分割的方法。它扩展了著名的GrabCut[1]方法，通过从边界框标注中训练神经网络分类器，将机器学习纳入其中。我们将问题表述为在密集连接的条件随机场上的能量最小化问题，并迭代更新训练目标以获得逐像素对象分割。此外，我们提出了DeepCut方法的变体，并将其与弱监督下CNN训练的朴素方法进行比较。我们在一个具有挑战性的胎儿磁共振数据集上测试了其解决脑和肺分割问题的适用性，并在准确性方面获得了令人鼓舞的结果。

Spatial regularization is essential in image registration, which is an ill-posed problem. Regularization can help to avoid both physically implausible displacement fields and local minima during optimization. Tikhonov regularization (squared $\ell _{2}$ -norm) is unable to correctly represent non-smooth displacement fields, that can, for example, occur at sliding interfaces in the thorax and abdom...

空间正则化在图像配准中至关重要，这是一个不适定问题。正则化有助于避免物理上不合理的位移场以及优化过程中的局部最小值。Tikhonov正则化（平方ℓ2范数）无法正确表示非平滑位移场，例如在胸部和腹部滑动界面处出现的位移场...

Robotic ultrasound has the potential to assist and guide physicians during interventions. In this work, we present a set of methods and a workflow to enable autonomous MRI-guided ultrasound acquisitions. Our approach uses a structured-light 3D scanner for patient-to-robot and image-to-patient calibration, which in turn is used to plan 3D ultrasound trajectories. These MRI-based trajectories are fo...

在这项工作中，我们提出了一套方法和工作流程，以实现自主MRI引导的超声采集。我们的方法使用结构光3D扫描仪进行患者-机器人以及图像-患者的标定，进而用于规划3D超声轨迹。这些基于MRI的轨迹用于...

We demonstrate the usefulness of utilizing a segmentation step for improving the performance of sparsity based image reconstruction algorithms. In specific, we will focus on retinal optical coherence tomography (OCT) reconstruction and propose a novel segmentation based reconstruction framework with sparse representation, termed segmentation based sparse reconstruction (SSR). The SSR method uses a...

我们展示了利用分割步骤提高基于稀疏性的图像重建算法性能的有用性。具体而言，我们将关注视网膜光学相干断层扫描（OCT）重建，并提出一种新颖的基于分割的稀疏表示重建框架，称为基于分割的稀疏重建（SSR）。SSR方法使用……

We present MRiLab, a new comprehensive simulator for large-scale realistic MRI simulations on a regular PC equipped with a modern graphical processing unit (GPU). MRiLab combines realistic tissue modeling with numerical virtualization of an MRI system and scanning experiment to enable assessment of a broad range of MRI approaches including advanced quantitative MRI methods inferring microstructure...

我们介绍了MRiLab，一种新的综合性模拟器，用于在配备现代图形处理单元（GPU）的常规PC上进行大规模真实MRI模拟。MRiLab将真实组织建模与MRI系统和扫描实验的数值虚拟化相结合，以评估广泛的MRI方法，包括推断微结构的先进定量MRI方法。

Accurate reconstruction of anatomical connections between neurons in the brain using electron microscopy (EM) images is considered to be the gold standard for circuit mapping. A key step in obtaining the reconstruction is the ability to automatically segment neurons with a precision close to human-level performance. Despite the recent technical advances in EM image segmentation, most of them rely ...

使用电子显微镜（EM）图像准确重建大脑神经元之间的解剖连接被认为是电路映射的金标准。获得重建的一个关键步骤是能够以接近人类水平的精度自动分割神经元。尽管最近在EM图像分割方面取得了技术进展，但大多数方法依赖于...

Multi-Line Transmission (MLT) was recently demonstrated as a valuable tool to increase the frame rate of ultrasound images. In this approach, the multiple beams that are simultaneously transmitted may determine cross-talk artifacts that are typically reduced, although not eliminated, by the use of Tukey apodization on both transmission and reception apertures, which unfortunately worsens the image...

多线传输（MLT）最近被证明是提高超声图像帧率的有价值工具。在这种方法中，同时传输的多束波可能会产生串扰伪影，通常通过同时在发射和接收孔径上使用Tukey切趾来减少（尽管不能消除），但这却不幸地降低了图像...

In biological tissue, an increase in elasticity is often a marker of abnormalities. Techniques such as quasi-static ultrasound elastography have been developed to assess the strain distribution in soft tissues in two dimensions using a quasi-static compression. However, as abnormalities can exhibit very heterogeneous shapes, a three dimensional approach would be necessary to accurately measure the...

在生物组织中，弹性增加通常是异常的标志。已开发出准静态超声弹性成像等技术，通过准静态压缩评估软组织的二维应变分布。然而，由于异常可能呈现非常不均匀的形状，三维方法对于准确测量是必要的...

We focus on the challenging problem of filamentary structure segmentation in both 2D and 3D images, including retinal vessels and neurons, among others. Despite the increasing amount of efforts in learning based methods to tackle this problem, there still lack proper data-driven feature construction mechanisms to sufficiently encode contextual labelling information, which might hinder the segmenta...

我们关注在2D和3D图像中分割丝状结构的挑战性问题，包括视网膜血管和神经元等。尽管基于学习的方法在处理此问题上付出了越来越多的努力，但仍然缺乏适当的数据驱动特征构建机制来充分编码上下文标记信息，这可能阻碍分割...

One of the major challenges in array-based medical ultrasound imaging is the image quality degradation caused by sidelobes and off-axis clutter, which is an inherent limitation of the conventional delay-and-sum (DAS) beamforming operating on a finite aperture. Ultrasound image quality is further degraded in imaging applications involving strong tissue attenuation and/or low transmit power. In orde...

基于阵列的医学超声成像的主要挑战之一是旁瓣和离轴杂波导致的图像质量下降，这是传统延迟求和（DAS）波束形成在有限孔径上运行的固有限制。超声图像质量在涉及强组织衰减和/或低发射功率的成像应用中进一步降低。

We analyze the principles underlying minimum variance distortionless response (MVDR) beamforming in order to integrate it into a pixel-based algorithm. There is a challenge posed by the low echo signal-to-noise ratio (eSNR) when calculating beamformer contributions at pixels far away from the beam centreline. Together with the well-known scarcity of samples for covariance matrix estimation, this r...

我们分析了最小方差无失真响应（MVDR）波束形成的基本原理，以便将其集成到基于像素的算法中。在计算远离波束中心线的像素的波束形成贡献时，存在低回波信噪比（eSNR）带来的挑战。加之协方差矩阵估计中众所周知的样本稀缺问题，这...

Electrical Impedance Tomography (EIT) aims to recover the internal conductivity and permittivity distributions of a body from electrical measurements taken on electrodes on the surface of the body. The reconstruction task is a severely ill-posed nonlinear inverse problem that is highly sensitive to measurement noise and modeling errors. Regularized D-bar methods have shown great promise in produci...

电阻抗断层成像（EIT）旨在从放置在体表电极上的电测量中恢复人体内部的电导率和介电常数分布。重建任务是一个严重病态的非线性逆问题，对测量噪声和建模误差高度敏感。正则化D-bar方法在生成鲁棒重建方面显示出巨大潜力。

Strain evaluation is of major interest in clinical cardiology as it can quantify the cardiac function. Myocardial elastography, a radio-frequency (RF)-based cross-correlation method, has been developed to evaluate the local strain distribution in the heart in vivo. However, inhomogeneities such as RF ablation lesions or infarction require a three-dimensional approach to be measured accurately. In ...

应变评估在临床心脏病学中具有重要意义，因为它可以量化心脏功能。心肌弹性成像是一种基于射频（RF）的互相关方法，已被开发用于评估体内心脏的局部应变分布。然而，不均匀性如射频消融灶或梗死需要三维方法才能准确测量。在……

Despite widespread availability of ultrasound and a need for personalised muscle diagnosis (neck/back pain-injury, work related disorder, myopathies, neuropathies), robust, online segmentation of muscles within complex groups remains unsolved by existing methods. For example, Cervical Dystonia (CD) is a prevalent neurological condition causing painful spasticity in one or multiple muscles in the c...

尽管超声技术广泛可用且需要个性化的肌肉诊断（颈/背痛损伤、工作相关疾病、肌病、神经病变），现有方法仍未能解决复杂肌群内肌肉的稳健在线分割问题。例如，颈肌张力障碍（CD）是一种常见的神经系统疾病，导致一个或多个肌肉出现疼痛性痉挛……

Two-dimensional-to-three-dimensional (2D-3D) deformation has emerged as a new technique to estimate cone-beam computed tomography (CBCT) images. The technique is based on deforming a prior high-quality 3D CT/CBCT image to form a new CBCT image, guided by limited-view 2D projections. The accuracy of this intensity-based technique, however, is often limited in low-contrast image regions with subtle ...

二维到三维（2D-3D）变形已成为一种估算锥形束计算机断层扫描（CBCT）图像的新技术。该技术基于对先验的高质量三维CT/CBCT图像进行变形，以形成新的CBCT图像，并由有限视角的二维投影引导。然而，这种基于强度的技术的准确性通常在低对比度图像区域中受到限制，这些区域具有细微的...

We investigate uncertainty quantification under a sparse Bayesian model of medical image registration. Bayesian modelling has proven powerful to automate the tuning of registration hyperparameters, such as the trade-off between the data and regularization functionals. Sparsity-inducing priors have recently been used to render the parametrization itself adaptive and data-driven. The sparse prior on...

我们研究在图像配准的稀疏贝叶斯模型下的不确定性量化。贝叶斯建模已被证明能有效自动调整配准超参数，例如数据项和正则化项之间的权衡。稀疏诱导先验最近被用于使参数化本身具有自适应性和数据驱动性。稀疏先验在...

A millimeter (mm) wave radio is presented in this work to support wireless MRI data transmission. High path loss and availability of wide bandwidth make mm-waves an ideal candidate for short range, high data rata communication required for wireless MRI. The proposed system uses a custom designed integrated chip (IC) mm-wave radio with 60 GHz as radio frequency carrier. In this work, we assess perf...

本文提出了一种毫米波无线电，以支持无线 MRI 数据传输。高路径损耗和宽带宽的可用性使得毫米波成为无线 MRI 所需的短距离、高数据速率通信的理想候选。所提出的系统使用定制设计的集成芯片 (IC) 毫米波无线电，以 60 GHz 作为射频载波。本文中，我们评估了性能...

Photon counting detector (PCD)-based computed tomography exploits spectral information from a transmitted x-ray spectrum to estimate basis line-integrals. The recorded spectrum, however, is distorted and deviates from the transmitted spectrum due to spectral response effect (SRE). Therefore, the SRE needs to be compensated for when estimating basis line-integrals. One approach is to incorporate th...

基于光子计数探测器（PCD）的计算机断层扫描利用透射X射线光谱的光谱信息来估计基底线积分。然而，由于光谱响应效应（SRE），记录的光谱会发生失真并偏离透射光谱。因此，在估计基底线积分时需要补偿SRE。一种方法是考虑...

Fluorescence Molecular Tomography (FMT) is a powerful imaging modality for the research of cancer diagnosis, disease treatment and drug discovery. Via three-dimensional (3-D) imaging reconstruction, it can quantitatively and noninvasively obtain the distribution of fluorescent probes in biological tissues. Currently, photon propagation of FMT is conventionally described by the Finite Element Metho...

荧光分子断层成像(FMT)是一种用于癌症诊断、疾病治疗和药物发现研究的强大成像模态。通过三维(3-D)成像重建，它可以定量且无创地获得生物组织中荧光探针的分布。目前，FMT的光子传播通常由有限元方法描述...

In quantitative MR $T_{1}$ mapping, the spin-lattice relaxation time $T_{1}$ of tissues is estimated from a series of $T_{1}$ -weighted images. As the $T_{1}$ estimation is a voxel-wise estimation procedure, correct spatial alignment of the $T_{1}$ -weighted images is crucial. Conventionally, the $T_{1}$ -weighted images are first registered based on a general-purpose registration metric,...

在定量MR T1映射中，组织的自旋-晶格弛豫时间T1是从一系列T1加权图像中估计的。由于T1估计是逐体素的估计过程，因此正确对齐T1加权图像的空间位置至关重要。传统上，首先基于通用配准度量对T1加权图像进行配准，...

Rapid, reliable quantification of MR relaxation parameters $\textit{T}_{1}$ and $\textit{T}_{2}$ is desirable for many clinical applications. Steady-state sequences such as Spoiled Gradient-Recalled Echo (SPGR) and Dual-Echo Steady-State (DESS) are fast and well-suited for relaxometry because the signals they produce are quite sensitive to $\textit{T}_{1}$ and $\textit{T}_{2}$ variation. H...

快速、可靠的MR弛豫参数T1和T2定量对许多临床应用非常理想。稳态序列如扰相梯度回波(SPGR)和双回波稳态(DESS)速度快且非常适合弛豫测量，因为其产生的信号对T1和T2变化非常敏感。

Interference effects in the transmit B1+ field can severely degrade the image quality in high-field Magnetic Resonance Imaging (MRI). High-permittivity pads are increasingly used to counteract these effects, but designing such pads is not trivial. In this paper, we present an efficient solution methodology for this dielectric RF shimming problem. By exploiting the fact that dielectric pads form a ...

在高场磁共振成像中，发射B1+场的干扰效应会严重降低图像质量。高介电常数垫片被越来越多地用于抵消这些效应，但设计此类垫片并非易事。本文提出了一种针对介电射频匀场问题的高效求解方法。通过利用介电垫片形成...

We present a new method for rigid registration of CT datasets in 3D Radon space based on sparse sampling of scanning projections. The inputs are the two 3D Radon transforms of the CT scans, one densely sampled and the other sparsely sampled (limited number of scan angles/ranges). The output is the rigid transformation that best matches them. The method first finds the best matching between each pr...

我们提出了一种基于扫描投影稀疏采样的CT数据集三维拉东空间刚性配准新方法。输入是两个CT扫描的三维拉东变换，一个密集采样，另一个稀疏采样（有限数量的扫描角度/范围）。输出是使它们最佳匹配的刚性变换。该方法首先找到每个...

SS-FSE is a fast technique that does not suffer from off-resonance distortions to the degree that EPI does. Unlike EPI, SS-FSE is ill-suited to diffusion weighted imaging (DWI) due to the Carr-Purcell-Meiboom-Geill (CPMG) condition. Non-CPMG phase cycling does accommodate SS-FSE and DWI but places constraints on reconstruction, which are resolved here through parallel imaging. Additionally, improv...

SS-FSE是一种快速技术，其离共振畸变程度不如EPI严重。与EPI不同，由于Carr-Purcell-Meiboom-Geill（CPMG）条件，SS-FSE不适合扩散加权成像（DWI）。非CPMG相位循环可以适应SS-FSE和DWI，但对重建施加了限制，本文通过并行成像解决了这些限制。此外，改进...

Functional imaging provides hemodynamic and metabolic information and is increasingly being incorporated into clinical diagnostic and research studies. Typically functional images have reduced signal-to-noise ratio and spatial resolution compared to other non-functional cross sectional images obtained as part of a routine clinical protocol. We hypothesized that enhancing visualization and interpre...

功能成像提供血流动力学和代谢信息，并越来越多地纳入临床诊断和研究中。通常，与常规临床方案中获取的其他非功能性横断面图像相比，功能图像的信噪比和空间分辨率较低。我们假设增强可视化和解释...