Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from quadratic computational complexity with respect to the number of tokens. Many architectures attempt to reduce model complexity by limiting the self-attention mechanism to local regions or by redesigning the tokenization process. In this paper, we propose DAE-Former, a novel method that seeks to provide an alternative perspective by efficiently designing the self-attention mechanism. More specifically, we reformulate the self-attention mechanism to capture both spatial and channel relations across the whole feature dimension while staying computationally efficient. Furthermore, we redesign the skip connection path by including the cross-attention module to ensure the feature reusability and enhance the localization power. Our method outperforms state-of-the-art methods on multi-organ cardiac and skin lesion segmentation datasets without requiring pre-training weights. The code is publicly available at https://github.com/mindflow-institue/DAEFormer.
translated by 谷歌翻译
多年来,卷积神经网络(CNN)已成为多种计算机视觉任务的事实上的标准。尤其是,基于开创性体系结构(例如具有跳过连接的U形模型)或具有金字塔池的Artous卷积的深度神经网络已针对广泛的医学图像分析任务量身定制。此类架构的主要优点是它们容易拘留多功能本地功能。然而,作为一般共识,CNN无法捕获由于卷积操作的固有性能的内在特性而捕获长期依赖性和空间相关性。另外,从全球信息建模中获利的变压器源于自我发项机制,最近在自然语言处理和计算机视觉方面取得了出色的表现。然而,以前的研究证明,局部和全局特征对于密集预测的深层模型至关重要,例如以不同的形状和配置对复杂的结构进行分割。为此,本文提出了TransDeeplab,这是一种新型的DeepLab样纯变压器,用于医学图像分割。具体而言,我们用移动的窗口利用层次旋转式变形器来扩展DeepLabV3并建模非常有用的空间金字塔池(ASPP)模块。对相关文献的彻底搜索结果是,我们是第一个用基于纯变压器模型对开创性DeepLab模型进行建模的人。关于各种医学图像分割任务的广泛实验证明,我们的方法在视觉变压器和基于CNN的方法的合并中表现出色或与大多数当代作品相提并论,并显着降低了模型复杂性。代码和训练有素的模型可在https://github.com/rezazad68/transdeeplab上公开获得
translated by 谷歌翻译
卷积神经网络(CNN)已成为医疗图像分割任务的共识。但是,由于卷积操作的性质,它们在建模长期依赖性和空间相关性时受到限制。尽管最初开发了变压器来解决这个问题,但它们未能捕获低级功能。相比之下,证明本地和全球特征对于密集的预测至关重要,例如在具有挑战性的环境中细分。在本文中,我们提出了一种新型方法,该方法有效地桥接了CNN和用于医学图像分割的变压器。具体而言,我们使用开创性SWIN变压器模块和一个基于CNN的编码器设计两个多尺度特征表示。为了确保从上述两个表示获得的全局和局部特征的精细融合,我们建议在编码器编码器结构的跳过连接中提出一个双层融合(DLF)模块。在各种医学图像分割数据集上进行的广泛实验证明了Hiformer在计算复杂性以及定量和定性结果方面对其他基于CNN的,基于变压器和混合方法的有效性。我们的代码可在以下网址公开获取:https://github.com/amirhossein-kz/hiformer
translated by 谷歌翻译
在过去的几年中,卷积神经网络(CNN),尤其是U-NET,一直是医学图像处理时代的流行技术。具体而言,开创性的U-NET及其替代方案成功地设法解决了各种各样的医学图像分割任务。但是,这些体系结构在本质上是不完美的,因为它们无法表现出长距离相互作用和空间依赖性,从而导致具有可变形状和结构的医学图像分割的严重性能下降。针对序列到序列预测的初步提议的变压器已成为替代体系结构,以精确地模拟由自我激进机制辅助的全局信息。尽管设计了可行的设计,但利用纯变压器来进行图像分割目的,可能导致限制的定位容量,导致低级功能不足。因此,一系列研究旨在设计基于变压器的U-NET的强大变体。在本文中,我们提出了Trans-Norm,这是一种新型的深层分割框架,它随同将变压器模块合并为标准U-NET的编码器和跳过连接。我们认为,跳过连接的方便设计对于准确的分割至关重要,因为它可以帮助扩展路径和收缩路径之间的功能融合。在这方面,我们从变压器模块中得出了一种空间归一化机制,以适应性地重新校准跳过连接路径。对医学图像分割的三个典型任务进行了广泛的实验,证明了透气的有效性。代码和训练有素的模型可在https://github.com/rezazad68/transnorm上公开获得。
translated by 谷歌翻译
基于CNN的方法已经实现了医学图像分割的令人印象深刻的结果,但由于卷积操作的内在局部,它们未能捕获远程依赖性。基于变压器的方法最近在愿景任务中流行,因为它们的远程依赖性和有希望的性能。但是,它缺乏建模本地背景。本文以医学图像分割为例,我们呈现了MissFormer,一种有效和强大的医学图像分割变压器。 MissFormer是具有两个吸引人设计的分层编码器 - 解码器网络:1)通过所提出的增强型变压器块重新设计前馈网络,该熵增强了远程依赖性并补充本地上下文,使得该特征更加辨别。 2)我们提出了增强的变压器上下文网桥,与以前的模拟全局信息的方法不同,所提出的上下文网桥与增强变压器块提取了由我们的层级变压器编码器产生的多尺度特征的远程依赖性和本地语境。由这两个设计驱动,MissFormer显示了捕获更多辨别性依赖性和在医学图像分割中的识别依赖性和上下文的牢固能力。多器官和心脏分割任务的实验表明了我们的错过更优越性,有效性和稳健性,训练了从划伤的痕迹甚至高于想象的最先进方法。核心设计可以推广到其他视觉分段任务。代码已在GitHub上发布:https://github.com/zhifangdeng/missformer
translated by 谷歌翻译
最新的语义分段方法采用具有编码器解码器架构的U-Net框架。 U-Net仍然具有挑战性,具有简单的跳过连接方案来模拟全局多尺度上下文:1)由于编码器和解码器级的不兼容功能集的问题,并非每个跳过连接设置都是有效的,甚至一些跳过连接对分割性能产生负面影响; 2)原始U-Net比某些数据集上没有任何跳过连接的U-Net更糟糕。根据我们的调查结果,我们提出了一个名为Uctransnet的新分段框架(在U-Net中的提议CTRANS模块),从引导机制的频道视角。具体地,CTRANS模块是U-NET SKIP连接的替代,其包括与变压器(命名CCT)和子模块通道 - 明智的跨关注进行多尺度信道交叉融合的子模块(命名为CCA)以指导熔融的多尺度通道 - 明智信息,以有效地连接到解码器功能以消除歧义。因此,由CCT和CCA组成的所提出的连接能够替换原始跳过连接以解决精确的自动医学图像分割的语义间隙。实验结果表明,我们的UCTRANSNET产生更精确的分割性能,并通过涉及变压器或U形框架的不同数据集和传统架构的语义分割来实现一致的改进。代码:https://github.com/mcgregorwwwww/uctransnet。
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
计算机辅助医学图像分割已广泛应用于诊断和治疗,以获得靶器官和组织的形状和体积的临床有用信息。在过去的几年中,基于卷积神经网络(CNN)的方法(例如,U-Net)占主导地位,但仍遭受了不足的远程信息捕获。因此,最近的工作提出了用于医学图像分割任务的计算机视觉变压器变体,并获得了有希望的表现。这种变压器通过计算配对贴片关系来模拟远程依赖性。然而,它们促进了禁止的计算成本,尤其是在3D医学图像(例如,CT和MRI)上。在本文中,我们提出了一种称为扩张变压器的新方法,该方法在本地和全球范围内交替捕获的配对贴片关系进行自我关注。灵感来自扩张卷积核,我们以扩张的方式进行全球自我关注,扩大接收领域而不增加所涉及的斑块,从而降低计算成本。基于这种扩展变压器的设计,我们构造了一个用于3D医学图像分割的U形编码器解码器分层体系结构。 Synapse和ACDC数据集的实验表明,我们的D-Ager Model从头开始培训,以低计算成本从划痕训练,优于各种竞争力的CNN或基于变压器的分段模型,而不耗时的每训练过程。
translated by 谷歌翻译
变压器在计算机视觉中的成功吸引了医学成像社区越来越多的关注。特别是对于医学图像细分,已经介绍了许多基于卷积神经网络(CNN)和变压器的出色混合体系结构,并取得了令人印象深刻的性能。但是,将模块化变压器嵌入CNN中的大多数方法都难以发挥其全部潜力。在本文中,我们提出了一种新型的医学图像分割的混合体系结构,称为Phtrans,该架构可与主要构建基块中的变形金刚和CNN杂交,以产生来自全球和本地特征的层次结构表示,并适应性地汇总它们,旨在完全利用其优势以获得更好的优势。细分性能。具体而言,phtrans遵循U形编码器编码器设计,并在深层阶段引入平行的Hybird模块,其中卷积块和经过修改的3D SWIN变压器分别学习本地特征和全局依赖性,然后统一尺寸,统一尺寸输出以实现特征聚合。超出颅库和自动化心脏诊断挑战数据集以外的多ATLA标签的广泛实验结果证实了其有效性,始终超过了最先进的方法。该代码可在以下网址获得:https://github.com/lseventeen/phtrans。
translated by 谷歌翻译
对医学图像的器官或病变的准确分割对于可靠的疾病和器官形态计量学的可靠诊断至关重要。近年来,卷积编码器解码器解决方案在自动医疗图像分割领域取得了重大进展。由于卷积操作中的固有偏见,先前的模型主要集中在相邻像素形成的局部视觉提示上,但无法完全对远程上下文依赖性进行建模。在本文中,我们提出了一个新型的基于变压器的注意力指导网络,称为Transattunet,其中多层引导注意力和多尺度跳过连接旨在共同增强语义分割体系结构的性能。受到变压器的启发,具有变压器自我注意力(TSA)和全球空间注意力(GSA)的自我意识注意(SAA)被纳入Transattunet中,以有效地学习编码器特征之间的非本地相互作用。此外,我们还使用解码器块之间的其他多尺度跳过连接来汇总具有不同语义尺度的上采样功能。这样,多尺度上下文信息的表示能力就可以增强以产生判别特征。从这些互补组件中受益,拟议的Transattunet可以有效地减轻卷积层堆叠和连续采样操作引起的细节损失,最终提高医学图像的细分质量。来自不同成像方式的多个医疗图像分割数据集进行了广泛的实验表明,所提出的方法始终优于最先进的基线。我们的代码和预培训模型可在以下网址找到:https://github.com/yishuliu/transattunet。
translated by 谷歌翻译
目的:在手术规划之前,CT图像中肝血管的分割是必不可少的,并引起了医学图像分析界的广泛兴趣。由于结构复杂,对比度背景下,自动肝脏血管分割仍然特别具有挑战性。大多数相关的研究采用FCN,U-Net和V-Net变体作为骨干。然而,这些方法主要集中在捕获多尺度局部特征,这可能导致由于卷积运营商有限的地区接收领域而产生错误分类的体素。方法:我们提出了一种强大的端到端血管分割网络,通过将SWIN变压器扩展到3D并采用卷积和自我关注的有效组合,提出了一种被称为电感偏置的多头注意船网(IBIMHAV-NET)的稳健端到端血管分割网络。在实践中,我们介绍了Voxel-Wise嵌入而不是修补程序嵌入,以定位精确的肝脏血管素,并采用多尺度卷积运营商来获得局部空间信息。另一方面,我们提出了感应偏置的多头自我关注,其学习从初始化的绝对位置嵌入的归纳偏置相对位置嵌入嵌入。基于此,我们可以获得更可靠的查询和键矩阵。为了验证我们模型的泛化,我们测试具有不同结构复杂性的样本。结果:我们对3Dircadb数据集进行了实验。四种测试病例的平均骰子和敏感性为74.8%和77.5%,超过现有深度学习方法的结果和改进的图形切割方法。结论:拟议模型IBIMHAV-Net提供一种具有交错架构的自动,精确的3D肝血管分割,可更好地利用CT卷中的全局和局部空间特征。它可以进一步扩展到其他临床数据。
translated by 谷歌翻译
Recently, many attempts have been made to construct a transformer base U-shaped architecture, and new methods have been proposed that outperformed CNN-based rivals. However, serious problems such as blockiness and cropped edges in predicted masks remain because of transformers' patch partitioning operations. In this work, we propose a new U-shaped architecture for medical image segmentation with the help of the newly introduced focal modulation mechanism. The proposed architecture has asymmetric depths for the encoder and decoder. Due to the ability of the focal module to aggregate local and global features, our model could simultaneously benefit the wide receptive field of transformers and local viewing of CNNs. This helps the proposed method balance the local and global feature usage to outperform one of the most powerful transformer-based U-shaped models called Swin-UNet. We achieved a 1.68% higher DICE score and a 0.89 better HD metric on the Synapse dataset. Also, with extremely limited data, we had a 4.25% higher DICE score on the NeoPolyp dataset. Our implementations are available at: https://github.com/givkashi/Focal-UNet
translated by 谷歌翻译
Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realize global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissues structures. Inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting anatomies of 133 structures in brain, 14 organs in abdomen, 4 hierarchical components in kidney, and inter-connected kidney tumors). We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in single network, outperforms prior state-of-the-art method SLANT27 ensembled with 27 network tiles, our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively.
translated by 谷歌翻译
变形金刚占据了自然语言处理领域,最近影响了计算机视觉区域。在医学图像分析领域中,变压器也已成功应用于全栈临床应用,包括图像合成/重建,注册,分割,检测和诊断。我们的论文旨在促进变压器在医学图像分析领域的认识和应用。具体而言,我们首先概述了内置在变压器和其他基本组件中的注意机制的核心概念。其次,我们回顾了针对医疗图像应用程序量身定制的各种变压器体系结构,并讨论其局限性。在这篇综述中,我们调查了围绕在不同学习范式中使用变压器,提高模型效率及其与其他技术的耦合的关键挑战。我们希望这篇评论可以为读者提供医学图像分析领域的读者的全面图片。
translated by 谷歌翻译
卷积神经网络(CNN)的深度学习体系结构在计算机视野领域取得了杰出的成功。 CNN构建的编码器架构U-Net在生物医学图像分割方面取得了重大突破,并且已在各种实用的情况下应用。但是,编码器部分中每个下采样层和简单堆积的卷积的平等设计不允许U-NET从不同深度提取足够的特征信息。医学图像的复杂性日益增加为现有方法带来了新的挑战。在本文中,我们提出了一个更深层,更紧凑的分裂注意U形网络(DCSAU-NET),该网络有效地利用了基于两个新颖框架的低级和高级语义信息:主要功能保护和紧凑的分裂注意力堵塞。我们评估了CVC-ClinicDB,2018 Data Science Bowl,ISIC-2018和SEGPC-2021数据集的建议模型。结果,DCSAU-NET在联合(MIOU)和F1-SOCRE的平均交点方面显示出比其他最先进的方法(SOTA)方法更好的性能。更重要的是,提出的模型在具有挑战性的图像上表现出了出色的细分性能。我们的工作代码以及更多技术细节,请访问https://github.com/xq141839/dcsau-net。
translated by 谷歌翻译
Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by learning both global and local features and contextual representations which can be utilized for semantic output prediction by the decoder. Despite their success, the locality of convolutional layers in FCNNs, limits the capability of learning long-range spatial dependencies. Inspired by the recent success of transformers for Natural Language Processing (NLP) in long-range sequence learning, we reformulate the task of volumetric (3D) medical image segmentation as a sequence-to-sequence prediction problem. We introduce a novel architecture, dubbed as UNEt TRansformers (UNETR), that utilizes a transformer as the encoder to learn sequence representations of the input volume and effectively capture the global multi-scale information, while also following the successful "U-shaped" network design for the encoder and decoder. The transformer encoder is directly connected to a decoder via skip connections at different resolutions to compute the final semantic segmentation output. We have validated the performance of our method on the Multi Atlas Labeling Beyond The Cranial Vault (BTCV) dataset for multiorgan segmentation and the Medical Segmentation Decathlon (MSD) dataset for brain tumor and spleen segmentation tasks. Our benchmarks demonstrate new state-of-the-art performance on the BTCV leaderboard. Code: https://monai.io/research/unetr
translated by 谷歌翻译
作为新一代神经体系结构的变形金刚在自然语言处理和计算机视觉方面表现出色。但是,现有的视觉变形金刚努力使用有限的医学数据学习,并且无法概括各种医学图像任务。为了应对这些挑战,我们将Medformer作为数据量表变压器呈现为可推广的医学图像分割。关键设计结合了理想的电感偏差,线性复杂性的层次建模以及以空间和语义全局方式以线性复杂性的关注以及多尺度特征融合。 Medformer可以在不预训练的情况下学习微小至大规模的数据。广泛的实验表明,Medformer作为一般分割主链的潜力,在三个具有多种模式(例如CT和MRI)和多样化的医学靶标(例如,健康器官,疾病,疾病组织和肿瘤)的三个公共数据集上优于CNN和视觉变压器。我们将模型和评估管道公开可用,为促进广泛的下游临床应用提供固体基线和无偏比较。
translated by 谷歌翻译
在广泛的实用应用中,需要进行远程感知的城市场景图像的语义细分,例如土地覆盖地图,城市变化检测,环境保护和经济评估。在深度学习技术的快速发展,卷积神经网络(CNN)的迅速发展。 )多年来一直在语义细分中占主导地位。 CNN采用层次特征表示,证明了局部信息提取的强大功能。但是,卷积层的本地属性限制了网络捕获全局上下文。最近,作为计算机视觉领域的热门话题,Transformer在全球信息建模中展示了其巨大的潜力,从而增强了许多与视觉相关的任务,例如图像分类,对象检测,尤其是语义细分。在本文中,我们提出了一个基于变压器的解码器,并为实时城市场景细分构建了一个类似Unet的变压器(UneTformer)。为了有效的分割,不显示器将轻量级RESNET18选择作为编码器,并开发出有效的全球关注机制,以模拟解码器中的全局和局部信息。广泛的实验表明,我们的方法不仅运行速度更快,而且与最先进的轻量级模型相比,其准确性更高。具体而言,拟议的未显示器分别在无人机和洛夫加数据集上分别达到了67.8%和52.4%的MIOU,而在单个NVIDIA GTX 3090 GPU上输入了512x512输入的推理速度最多可以达到322.4 fps。在进一步的探索中,拟议的基于变压器的解码器与SWIN变压器编码器结合使用,还可以在Vaihingen数据集上实现最新的结果(91.3%F1和84.1%MIOU)。源代码将在https://github.com/wanglibo1995/geoseg上免费获得。
translated by 谷歌翻译
最近,已经开发了各种视觉变压器作为对远程依赖性建模的能力。在当前的基于变压器的主骨用于医疗图像分割的骨架中,卷积层被纯变压器替换,或者将变压器添加到最深的编码器中以学习全球环境。但是,从规模的角度来看,主要有两个挑战:(1)尺度内问题:在每个尺度中提取局部全球线索所缺乏的现有方法,这可能会影响小物体的信号传播; (2)尺度间问题:现有方法未能从多个量表中探索独特的信息,这可能会阻碍表示尺寸,形状和位置广泛的对象的表示形式学习。为了解决这些局限性,我们提出了一个新颖的骨干,即比例尺形式,具有两个吸引人的设计:(1)尺度上的尺度内变压器旨在将基于CNN的本地功能与每个尺度中的基于变压器的全球线索相结合,在行和列的全局依赖项上可以通过轻巧的双轴MSA提取。 (2)一种简单有效的空间感知尺度变压器旨在以多个尺度之间的共识区域相互作用,该区域可以突出跨尺度依赖性并解决复杂量表的变化。对不同基准测试的实验结果表明,我们的尺度形式的表现优于当前最新方法。该代码可公开可用:https://github.com/zjugivelab/scaleformer。
translated by 谷歌翻译
Convolutional Neural Networks (CNNs) with U-shaped architectures have dominated medical image segmentation, which is crucial for various clinical purposes. However, the inherent locality of convolution makes CNNs fail to fully exploit global context, essential for better recognition of some structures, e.g., brain lesions. Transformers have recently proven promising performance on vision tasks, including semantic segmentation, mainly due to their capability of modeling long-range dependencies. Nevertheless, the quadratic complexity of attention makes existing Transformer-based models use self-attention layers only after somehow reducing the image resolution, which limits the ability to capture global contexts present at higher resolutions. Therefore, this work introduces a family of models, dubbed Factorizer, which leverages the power of low-rank matrix factorization for constructing an end-to-end segmentation model. Specifically, we propose a linearly scalable approach to context modeling, formulating Nonnegative Matrix Factorization (NMF) as a differentiable layer integrated into a U-shaped architecture. The shifted window technique is also utilized in combination with NMF to effectively aggregate local information. Factorizers compete favorably with CNNs and Transformers in terms of accuracy, scalability, and interpretability, achieving state-of-the-art results on the BraTS dataset for brain tumor segmentation and ISLES'22 dataset for stroke lesion segmentation. Highly meaningful NMF components give an additional interpretability advantage to Factorizers over CNNs and Transformers. Moreover, our ablation studies reveal a distinctive feature of Factorizers that enables a significant speed-up in inference for a trained Factorizer without any extra steps and without sacrificing much accuracy. The code and models are publicly available at https://github.com/pashtari/factorizer.
translated by 谷歌翻译