VOTENET++：多图谱分割的配准优化
VOTENET++: REGISTRATION REFINEMENT FOR MULTI-ATLAS SEGMENTATION.
作者信息
Ding Zhipeng, Niethammer Marc
机构信息
Department of Computer Science, UNC Chapel Hill, USA.
出版信息
Proc IEEE Int Symp Biomed Imaging. 2021 Apr;2021:275-279. doi: 10.1109/isbi48211.2021.9434031. Epub 2021 May 25.
Abstract
Multi-atlas segmentation (MAS) is a popular image segmentation technique for medical images. In this work, we improve the performance of MAS by correcting registration errors before label fusion. Specifically, we use a volumetric displacement field to refine registrations based on image anatomical appearance and predicted labels. We show the influence of the initial spatial alignment as well as the beneficial effect of using label information for MAS performance. Experiments demonstrate that the proposed refinement approach improves MAS performance on a 3D magnetic resonance dataset of the knee.
摘要
多图谱分割（MAS）是一种用于医学图像的流行图像分割技术。在这项工作中，我们通过在标签融合之前校正配准误差来提高MAS的性能。具体而言，我们使用体积位移场基于图像解剖外观和预测标签来优化配准。我们展示了初始空间对齐的影响以及使用标签信息对MAS性能的有益效果。实验表明，所提出的优化方法在膝关节的三维磁共振数据集上提高了MAS的性能。
相似文献
1
VOTENET++: REGISTRATION REFINEMENT FOR MULTI-ATLAS SEGMENTATION.VOTENET++：多图谱分割的配准优化
Proc IEEE Int Symp Biomed Imaging. 2021 Apr;2021:275-279. doi: 10.1109/isbi48211.2021.9434031. Epub 2021 May 25.
2
VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation.VoteNet：一种用于多图谱分割的深度学习标签融合方法。
Med Image Comput Comput Assist Interv. 2019 Oct;11766:202-210. doi: 10.1007/978-3-030-32248-9_23. Epub 2019 Oct 10.
3
VOTENET+ : AN IMPROVED DEEP LEARNING LABEL FUSION METHOD FOR MULTI-ATLAS SEGMENTATION.VOTENET+：一种用于多图谱分割的改进深度学习标签融合方法。
Proc IEEE Int Symp Biomed Imaging. 2020 Apr;2020:363-367. doi: 10.1109/isbi45749.2020.9098493. Epub 2020 May 22.
4
Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion.基于深度配准和标签融合的跨模态多图谱分割。
IEEE J Biomed Health Inform. 2022 Jul;26(7):3104-3115. doi: 10.1109/JBHI.2022.3149114. Epub 2022 Jul 1.
5
Hierarchical multi-atlas label fusion with multi-scale feature representation and label-specific patch partition.具有多尺度特征表示和特定标签块划分的分层多图谱标签融合
Neuroimage. 2015 Feb 1;106:34-46. doi: 10.1016/j.neuroimage.2014.11.025. Epub 2014 Nov 20.
6
Multi-atlas segmentation with robust label transfer and label fusion.具有稳健标签传递和标签融合的多图谱分割
Inf Process Med Imaging. 2013;23:548-59. doi: 10.1007/978-3-642-38868-2_46.
7
Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection.使用条件熵进行图谱排序和选择的CT数据多图谱全心分割
Med Phys. 2015 Jul;42(7):3822-33. doi: 10.1118/1.4921366.
8
Discriminative confidence estimation for probabilistic multi-atlas label fusion.概率多图谱标签融合的判别置信估计。
Med Image Anal. 2017 Dec;42:274-287. doi: 10.1016/j.media.2017.08.008. Epub 2017 Sep 1.
9
A transversal approach for patch-based label fusion via matrix completion.一种基于矩阵补全的基于补丁的标签融合横向方法。
Med Image Anal. 2015 Aug;24(1):135-148. doi: 10.1016/j.media.2015.06.002. Epub 2015 Jun 20.
10
Deep label fusion: A generalizable hybrid multi-atlas and deep convolutional neural network for medical image segmentation.深度标签融合：一种可推广的混合多图谱和深度卷积神经网络的医学图像分割方法。
Med Image Anal. 2023 Jan;83:102683. doi: 10.1016/j.media.2022.102683. Epub 2022 Nov 5.
引用本文的文献
1
A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond.医学图像配准中的深度学习综述：新技术、不确定性、评估指标及其他
Med Image Anal. 2025 Feb;100:103385. doi: 10.1016/j.media.2024.103385. Epub 2024 Nov 10.
本文引用的文献
1
DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation.深度图谱：图像配准与分割的联合半监督学习
Med Image Comput Comput Assist Interv. 2019 Oct;11765:420-429. doi: 10.1007/978-3-030-32245-8_47. Epub 2019 Oct 10.
2
VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation.VoteNet：一种用于多图谱分割的深度学习标签融合方法。
Med Image Comput Comput Assist Interv. 2019 Oct;11766:202-210. doi: 10.1007/978-3-030-32248-9_23. Epub 2019 Oct 10.
3
VOTENET+ : AN IMPROVED DEEP LEARNING LABEL FUSION METHOD FOR MULTI-ATLAS SEGMENTATION.VOTENET+：一种用于多图谱分割的改进深度学习标签融合方法。
Proc IEEE Int Symp Biomed Imaging. 2020 Apr;2020:363-367. doi: 10.1109/isbi45749.2020.9098493. Epub 2020 May 22.
4
Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative.基于统计形状知识和卷积神经网络的膝关节骨和软骨自动分割：来自 Osteoarthritis Initiative 的数据。
Med Image Anal. 2019 Feb;52:109-118. doi: 10.1016/j.media.2018.11.009. Epub 2018 Nov 17.
5
Quicksilver: Fast predictive image registration - A deep learning approach.快银：快速预测图像配准 - 深度学习方法。
Neuroimage. 2017 Sep;158:378-396. doi: 10.1016/j.neuroimage.2017.07.008. Epub 2017 Jul 11.
6
Multi-atlas segmentation of biomedical images: A survey.生物医学图像的多图谱分割：一项综述。
Med Image Anal. 2015 Aug;24(1):205-219. doi: 10.1016/j.media.2015.06.012. Epub 2015 Jul 6.
7
A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement: application to cardiac MR images.基于概率补丁的配准细化标签融合模型在多图谱分割中的应用：在心脏磁共振图像中的应用。
IEEE Trans Med Imaging. 2013 Jul;32(7):1302-15. doi: 10.1109/TMI.2013.2256922. Epub 2013 Apr 5.
8
Multi-Atlas Segmentation with Joint Label Fusion.基于联合标签融合的多图谱分割
IEEE Trans Pattern Anal Mach Intell. 2013 Mar;35(3):611-23. doi: 10.1109/TPAMI.2012.143. Epub 2012 Jun 26.
9
Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation.基于补丁的分割使用专家先验：在海马体和脑室分割中的应用。
Neuroimage. 2011 Jan 15;54(2):940-54. doi: 10.1016/j.neuroimage.2010.09.018. Epub 2010 Sep 17.
10
Automatic anatomical brain MRI segmentation combining label propagation and decision fusion.结合标签传播和决策融合的自动脑部解剖磁共振成像分割
Neuroimage. 2006 Oct 15;33(1):115-26. doi: 10.1016/j.neuroimage.2006.05.061. Epub 2006 Jul 24.
Zotero 插件