3D肺部片段的重建在肺癌的外科治疗计划中起着重要作用,这有助于保存肺功能并有助于确保低复发率。但是,在深度学习时代,肺部段的自动重建仍未得到探索。在本文中,我们研究了是什么使肺部段自动重建。首先,我们在临床和几何上表达了肺部段的解剖学定义,并提出了遵守这些定义的评估指标。其次,我们提出了脉冲(隐式肺部段),这是一种旨在肺部段重建的深层隐式表面模型。通过脉冲自动重建肺部段的指标和视觉吸引力是准确的。与规范分割方法相比,冲动输出连续预测任意分辨率具有较高的训练效率和更少的参数。最后,我们尝试不同的网络输入,以分析肺部段重建任务中重要的事情。我们的代码可在https://github.com/m3dv/impulse上找到。
translated by 谷歌翻译
U-NET一直是医疗图像分割任务的首选架构,但是将U-NET体系结构扩展到3D图像时会出现计算挑战。我们提出了隐式U-NET体系结构,该体系结构将有效的隐式表示范式适应监督的图像分割任务。通过将卷积特征提取器与隐式定位网络相结合,我们隐式U-NET的参数比等效的U-NET少40%。此外,我们提出了培训和推理程序,以利用稀疏的预测。与等效的完全卷积U-NET相比,隐式U-NET减少了约30%的推理和训练时间以及训练记忆足迹,同时在我们的两个不同的腹部CT扫描数据集中取得了可比的结果。
translated by 谷歌翻译
最近关于Covid-19的研究表明,CT成像提供了评估疾病进展和协助诊断的有用信息,以及帮助理解疾病。有越来越多的研究,建议使用深度学习来使用胸部CT扫描提供快速准确地定量Covid-19。兴趣的主要任务是胸部CT扫描的肺和肺病变的自动分割,确认或疑似Covid-19患者。在这项研究中,我们使用多中心数据集比较12个深度学习算法,包括开源和内部开发的算法。结果表明,合并不同的方法可以提高肺部分割,二元病变分割和多种子病变分割的总体测试集性能,从而分别为0.982,0.724和0.469的平均骰子分别。将得到的二元病变分段为91.3ml的平均绝对体积误差。通常,区分不同病变类型的任务更加困难,分别具有152mL的平均绝对体积差,分别为整合和磨碎玻璃不透明度为0.369和0.523的平均骰子分数。所有方法都以平均体积误差进行二元病变分割,该分段优于人类评估者的视觉评估,表明这些方法足以用于临床实践中使用的大规模评估。
translated by 谷歌翻译
医学成像的病变分割是临床研究中的一个重要课题。研究人员提出了各种检测和分段算法来解决这项任务。最近,基于深度学习的方法显着提高了传统方法的性能。然而,大多数最先进的深度学习方法需要手动设计多个网络组件和培训策略。在本文中,我们提出了一种新的自动化机器学习算法T-Automl,不仅搜索最佳神经结构,而且还可以同时找到超参数和数据增强策略的最佳组合。该方法采用现代变压器模型,引入了适应搜索空间嵌入的动态长度,并且可以显着提高搜索能力。我们在几个大型公共病变分割数据集上验证T-Automl并实现最先进的性能。
translated by 谷歌翻译
人类注释是不完美的,尤其是在初级实践者生产的时候。多专家共识通常被认为是黄金标准,而这种注释协议太昂贵了,无法在许多现实世界中实施。在这项研究中,我们提出了一种完善人类注释的方法,称为神经注释细化(接近)。它基于可学习的隐式函数,该函数将潜在向量解码为表示形状。通过将外观整合为隐式函数的输入,可以固定注释人工制品的外观可见。我们的方法在肾上腺分析的应用中得到了证明。我们首先表明,可以在公共肾上腺细分数据集上修复扭曲的金标准。此外,我们开发了一个新的肾上腺分析(ALAN)数据集,其中拟议的附近,每个病例都由专家分配的肾上腺及其诊断标签(正常与异常)组成。我们表明,经过近距离修复的形状训练的型号比原始的肾上腺更好地诊断肾上腺。 Alan数据集将是开源的,具有1,594个用于肾上腺诊断的形状,它是医学形状分析的新基准。代码和数据集可在https://github.com/m3dv/near上找到。
translated by 谷歌翻译
Segmentation of lung tissue in computed tomography (CT) images is a precursor to most pulmonary image analysis applications. Semantic segmentation methods using deep learning have exhibited top-tier performance in recent years. This paper presents a fully automatic method for identifying the lungs in three-dimensional (3D) pulmonary CT images, which we call it Lung-Net. We conjectured that a significant deeper network with inceptionV3 units can achieve a better feature representation of lung CT images without increasing the model complexity in terms of the number of trainable parameters. The method has three main advantages. First, a U-Net architecture with InceptionV3 blocks is developed to resolve the problem of performance degradation and parameter overload. Then, using information from consecutive slices, a new data structure is created to increase generalization potential, allowing more discriminating features to be extracted by making data representation as efficient as possible. Finally, the robustness of the proposed segmentation framework was quantitatively assessed using one public database to train and test the model (LUNA16) and two public databases (ISBI VESSEL12 challenge and CRPF dataset) only for testing the model; each database consists of 700, 23, and 40 CT images, respectively, that were acquired with a different scanner and protocol. Based on the experimental results, the proposed method achieved competitive results over the existing techniques with Dice coefficient of 99.7, 99.1, and 98.8 for LUNA16, VESSEL12, and CRPF datasets, respectively. For segmenting lung tissue in CT images, the proposed model is efficient in terms of time and parameters and outperforms other state-of-the-art methods. Additionally, this model is publicly accessible via a graphical user interface.
translated by 谷歌翻译
Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not scale to more complicated or large-scale scenes. The key limiting factor of implicit methods is their simple fullyconnected network architecture which does not allow for integrating local information in the observations or incorporating inductive biases such as translational equivariance. In this paper, we propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We investigate the effectiveness of the proposed representation by reconstructing complex geometry from noisy point clouds and low-resolution voxel representations. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.
translated by 谷歌翻译
准确的几何表示对于开发有限元模型至关重要。尽管通常只有很少的数据在准确细分精美特征,例如缝隙和薄结构方面,虽然只有很少的数据就有良好的深度学习分割方法。随后,分段的几何形状需要劳动密集型手动修改,以达到可用于模拟目的的质量。我们提出了一种使用转移学习来重复使用分段差的数据集的策略,并结合了交互式学习步骤,其中数据对数据进行微调导致解剖上精确的分割适合模拟。我们使用改良的多平台UNET,该UNET使用下髋关节分段和专用损耗函数进行预训练,以学习间隙区域和后处理,以纠正由于旋转不变性而在对称类别上的微小不准确性。我们证明了这种可靠但概念上简单的方法,采用了临床验证的髋关节扫描扫描的临床验证结果。代码和结果3D模型可在以下网址提供:\ url {https://github.com/miccai2022-155/autoseg}
translated by 谷歌翻译
自动化的腹部多器官分割是计算机辅助诊断腹部器官相关疾病的至关重要但具有挑战性的任务。尽管许多深度学习模型在许多医学图像分割任务中取得了显着的成功,但由于腹部器官的不同大小以及它们之间的含糊界限,腹部器官的准确分割仍然具有挑战性。在本文中,我们提出了一个边界感知网络(BA-NET),以分段CT扫描和MRI扫描进行腹部器官。该模型包含共享编码器,边界解码器和分割解码器。两个解码器都采用了多尺度的深度监督策略,这可以减轻可变器官尺寸引起的问题。边界解码器在每个量表上产生的边界概率图被用作提高分割特征图的注意。我们评估了腹部多器官细分(AMOS)挑战数据集的BA-NET,并获得了CT扫描的多器官分割的平均骰子分数为89.29 $ \%$,平均骰子得分为71.92 $ \%$ \%$ \% MRI扫描。结果表明,在两个分割任务上,BA-NET优于NNUNET。
translated by 谷歌翻译
气道分割对于检查,诊断和预后的肺部疾病至关重要,而其手动描述则不当。为了减轻这种耗时且潜在的主观手动程序,研究人员提出了从计算机断层扫描(CT)图像自动分割气道的方法。但是,一些小型气道分支(例如,支气管和终末支气管)显着加剧了通过机器学习模型的自动分割难度。特别是,气道分支中体素值和严重的数据失衡的方差使计算模块容易导致不连续和假阴性预测。注意机制表明了分割复杂结构的能力,而模糊逻辑可以减少特征表示的不确定性。因此,由模糊注意力层给出的深度注意力网络和模糊理论的整合应该是升级的解决方案。本文提出了一种有效的气道分割方法,包括一个新型的模糊注意力神经网络和全面的损失函数,以增强气道分割的空间连续性。深层模糊集由特征图中的一组体素和可学习的高斯成员功能制定。与现有的注意机制不同,所提出的特异性模糊注意力解决了不同渠道中异质特征的问题。此外,提出了一种新的评估指标来评估气道结构的连续性和完整性。该方法的效率已通过在包括精确的09和LIDC数据集在内的开放数据集上进行测试,以及我们的内部Covid-19和纤维化肺病数据集证明了这一建议的效率。
translated by 谷歌翻译
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learningbased 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.
translated by 谷歌翻译
用于图像分割的深卷卷卷神经网络不会明确学习标签结构,并且可能会在类似树状结构(例如气道或血管)分割的圆柱形结构中产生不正确的结构(例如,具有断开的圆柱形结构)的分割。在本文中,我们提出了一种新型的标签改进方法,以从初始分割中纠正此类错误,并隐含地包含有关标签结构的信息。该方法具有两个新颖的部分:1)生成合成结构误差的模型,以及2)产生合成分割(带有误差)的标签外观仿真网络,其外观与实际初始分段相似。使用这些合成分割和原始图像,对标签改进网络进行了训练,以纠正错误并改善初始分割。该方法对两个分割任务进行了验证:来自胸部计算机断层扫描(CT)扫描和大脑3D CT血管造影(CTA)图像的脑血管分割的气道分割。在这两种应用中,我们的方法都大大优于标准的3D U-NET和其他先前的改进方法。当使用其他未标记的数据进行模型培训时,改进甚至更大。在消融研究中,我们证明了所提出方法的不同组成部分的值。
translated by 谷歌翻译
迄今为止,迄今为止,众所周知,对广泛的互补临床相关任务进行了全面比较了医学图像登记方法。这限制了采用研究进展,以防止竞争方法的公平基准。在过去五年内已经探讨了许多新的学习方法,但优化,建筑或度量战略的问题非常适合仍然是开放的。 Learn2reg涵盖了广泛的解剖学:脑,腹部和胸部,方式:超声波,CT,MRI,群体:患者内部和患者内部和监督水平。我们为3D注册的培训和验证建立了较低的入境障碍,这帮助我们从20多个独特的团队中汇编了65多个单独的方法提交的结果。我们的互补度量集,包括稳健性,准确性,合理性和速度,使得能够独特地位了解当前的医学图像登记现状。进一步分析监督问题的转移性,偏见和重要性,主要是基于深度学习的方法的优越性,并将新的研究方向开放到利用GPU加速的常规优化的混合方法。
translated by 谷歌翻译
主要的神经影像学研究推动了1.0 mm以下的3T MRI采集分辨率,以改善结构定义和形态学。然而,只有很少的时间 - 密集的自动化图像分析管道已被验证为高分辨率(雇用)设置。另一方面,有效的深度学习方法很少支持多个固定分辨率(通常1.0 mm)。此外,缺乏标准的杂交数据分辨率以及具有足够覆盖的扫描仪,年龄,疾病或遗传方差的多样化数据的有限可用性会带来额外的,未解决的挑战培训网络。将分辨率独立于基于深度学习的分割,即在一系列不同的体素大小上以其本地分辨率进行分辨率的能力,承诺克服这些挑战,但目前没有这种方法。我们现在通过向决议独立的分割任务(VINN)引入VINOSEIZED独立的神经网络(VINN)来填补这个差距,并呈现FastSurfervinn,(i)建立并实施决议独立,以获得深度学习作为同时支持0.7-1.0 mm的第一种方法分割,(ii)显着优于跨决议的最先进方法,(iii)减轻雇用数据集中存在的数据不平衡问题。总体而言,内部分辨率 - 独立性相互益处雇用和1.0 mm MRI分割。通过我们严格验证的FastSurfervinn,我们将为不同的神经视线镜分析分发一个快速工具。此外,VINN架构表示更广泛应用的有效分辨率的分段方法
translated by 谷歌翻译
神经隐式功能的最新发展已在高质量的3D形状重建方面表现出巨大的成功。但是,大多数作品将空间分为形状的内部和外部,从而将其代表力量限制为单层和水密形状。这种局限性导致乏味的数据处理(将非紧密的原始数据转换为水密度),以及代表现实世界中一般对象形状的无能。在这项工作中,我们提出了一种新颖的方法来表示一般形状,包括具有多层表面的非水平形状和形状。我们介绍了3D形状(GIF)的一般隐式函数,该功能建模了每两个点之间的关系,而不是点和表面之间的关系。 GIF没有将3D空间分为预定义的内部区域,而是编码是否将两个点分开。 Shapenet上的实验表明,在重建质量,渲染效率和视觉保真度方面,GIF的表现优于先前的最先进方法。项目页面可从https://jianglongye.com/gifs获得。
translated by 谷歌翻译
视觉变形金刚(VIT)S表现出可观的全球和本地陈述的自我监督学习表现,可以转移到下游应用程序。灵感来自这些结果,我们介绍了一种新的自我监督学习框架,具有用于医学图像分析的定制代理任务。具体而言,我们提出:(i)以新的3D变压器为基础的型号,被称为往返变压器(Swin Unet),具有分层编码器,用于自我监督的预训练; (ii)用于学习人类解剖学潜在模式的定制代理任务。我们展示了来自各种身体器官的5,050个公共可用的计算机断层扫描(CT)图像的提出模型的成功预培训。通过微调超出颅穹窿(BTCV)分割挑战的预先调整训练模型和来自医疗细分牌组(MSD)数据集的分割任务,通过微调训练有素的模型来验证我们的方法的有效性。我们的模型目前是MSD和BTCV数据集的公共测试排行榜上的最先进的(即第1号)。代码:https://monai.io/research/swin-unetr.
translated by 谷歌翻译
Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture long-range dependencies, compared to the local convolutional-based design. However, the self-attention operation has quadratic complexity which proves to be a computational bottleneck, especially in volumetric medical imaging, where the inputs are 3D with numerous slices. In this paper, we propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters and compute cost. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features using a pair of inter-dependent branches based on spatial and channel attention. Our spatial attention formulation is efficient having linear complexity with respect to the input sequence length. To enable communication between spatial and channel-focused branches, we share the weights of query and key mapping functions that provide a complimentary benefit (paired attention), while also reducing the overall network parameters. Our extensive evaluations on three benchmarks, Synapse, BTCV and ACDC, reveal the effectiveness of the proposed contributions in terms of both efficiency and accuracy. On Synapse dataset, our UNETR++ sets a new state-of-the-art with a Dice Similarity Score of 87.2%, while being significantly efficient with a reduction of over 71% in terms of both parameters and FLOPs, compared to the best existing method in the literature. Code: https://github.com/Amshaker/unetr_plus_plus.
translated by 谷歌翻译
Training parts from ShapeNet. (b) t-SNE plot of part embeddings. (c) Reconstructing entire scenes with Local Implicit Grids Figure 1:We learn an embedding of parts from objects in ShapeNet [3] using a part autoencoder with an implicit decoder. We show that this representation of parts is generalizable across object categories, and easily scalable to large scenes. By localizing implicit functions in a grid, we are able to reconstruct entire scenes from points via optimization of the latent grid.
translated by 谷歌翻译
Implicit fields have been very effective to represent and learn 3D shapes accurately. Signed distance fields and occupancy fields are the preferred representations, both with well-studied properties, despite their restriction to closed surfaces. Several other variations and training principles have been proposed with the goal to represent all classes of shapes. In this paper, we develop a novel and yet fundamental representation by considering the unit vector field defined on 3D space: at each point in $\mathbb{R}^3$ the vector points to the closest point on the surface. We theoretically demonstrate that this vector field can be easily transformed to surface density by applying the vector field divergence. Unlike other standard representations, it directly encodes an important physical property of the surface, which is the surface normal. We further show the advantages of our vector field representation, specifically in learning general (open, closed, or multi-layered) surfaces as well as piecewise planar surfaces. We compare our method on several datasets including ShapeNet where the proposed new neural implicit field shows superior accuracy in representing any type of shape, outperforming other standard methods. The code will be released at https://github.com/edomel/ImplicitVF
translated by 谷歌翻译