病理图像的高效配准：一种主成分分析/图像重建联合方法。
EFFICIENT REGISTRATION OF PATHOLOGICAL IMAGES: A JOINT PCA/IMAGE-RECONSTRUCTION APPROACH.
作者信息
Han Xu, Yang Xiao, Aylward Stephen, Kwitt Roland, Niethammer Marc
机构信息
University of North Carolina (UNC) at Chapel Hill, USA.
Kitware Inc., USA.
出版信息
Proc IEEE Int Symp Biomed Imaging. 2017 Apr;2017:10-14. doi: 10.1109/ISBI.2017.7950456. Epub 2017 Jun 19.
Abstract
Registration involving one or more images containing pathologies is challenging, as standard image similarity measures and spatial transforms cannot account for common changes due to pathologies. Low-rank/Sparse (LRS) decomposition removes pathologies prior to registration; however, LRS is memory-demanding and slow, which limits its use on larger data sets. Additionally, LRS blurs normal tissue regions, which may degrade registration performance. This paper proposes an efficient alternative to LRS: (1) normal tissue appearance is captured by principal component analysis (PCA) and (2) blurring is avoided by an integrated model for pathology removal and image reconstruction. Results on synthetic and BRATS 2015 data demonstrate its utility.
摘要
涉及一个或多个包含病变的图像的配准具有挑战性，因为标准的图像相似性度量和空间变换无法考虑病变引起的常见变化。低秩/稀疏（LRS）分解在配准之前去除病变；然而，LRS对内存要求高且速度慢，这限制了它在更大数据集上的使用。此外，LRS会模糊正常组织区域，这可能会降低配准性能。本文提出了一种LRS的有效替代方法：（1）通过主成分分析（PCA）捕获正常组织外观，（2）通过用于病变去除和图像重建的集成模型避免模糊。在合成数据和BRATS 2015数据上的结果证明了其效用。
相似文献
1
EFFICIENT REGISTRATION OF PATHOLOGICAL IMAGES: A JOINT PCA/IMAGE-RECONSTRUCTION APPROACH.病理图像的高效配准：一种主成分分析/图像重建联合方法。
Proc IEEE Int Symp Biomed Imaging. 2017 Apr;2017:10-14. doi: 10.1109/ISBI.2017.7950456. Epub 2017 Jun 19.
2
Brain extraction from normal and pathological images: A joint PCA/Image-Reconstruction approach.从正常和病理性图像中提取脑区：一种联合 PCA/图像重建的方法。
Neuroimage. 2018 Aug 1;176:431-445. doi: 10.1016/j.neuroimage.2018.04.073. Epub 2018 May 4.
3
Registration of Pathological Images.病理图像的登记
Simul Synth Med Imaging. 2016 Oct;9968:97-107. doi: 10.1007/978-3-319-46630-9_10. Epub 2016 Sep 23.
4
Improving residue-residue contact prediction via low-rank and sparse decomposition of residue correlation matrix.通过残基相关矩阵的低秩和稀疏分解改进残基-残基接触预测。
Biochem Biophys Res Commun. 2016 Mar 25;472(1):217-22. doi: 10.1016/j.bbrc.2016.01.188. Epub 2016 Feb 23.
5
A Deep Network for Joint Registration and Reconstruction of Images with Pathologies.一种用于联合配准和重建病变图像的深度网络。
Mach Learn Med Imaging. 2020 Oct;12436:342-352. doi: 10.1007/978-3-030-59861-7_35. Epub 2020 Sep 29.
6
Low-Rank Based Image Analyses for Pathological MR Image Segmentation and Recovery.基于低秩的医学磁共振图像分割与恢复的图像分析
Front Neurosci. 2019 Apr 9;13:333. doi: 10.3389/fnins.2019.00333. eCollection 2019.
7
PCA-based groupwise image registration for quantitative MRI.基于主成分分析的定量 MRI 组间图像配准。
Med Image Anal. 2016 Apr;29:65-78. doi: 10.1016/j.media.2015.12.004. Epub 2015 Dec 19.
8
Improved medical image fusion based on cascaded PCA and shift invariant wavelet transforms.基于级联 PCA 和位移不变小波变换的改进型医学图像融合。
Int J Comput Assist Radiol Surg. 2018 Feb;13(2):229-240. doi: 10.1007/s11548-017-1692-4. Epub 2017 Dec 18.
9
Patient-Specific Registration of Pre-operative and Post-recurrence Brain Tumor MRI Scans.术前及复发后脑肿瘤磁共振成像扫描的患者特异性配准
Brainlesion. 2019;11383:105-114. doi: 10.1007/978-3-030-11723-8_10. Epub 2019 Jan 26.
10
Correction of motion artifacts in cone-beam CT using a patient-specific respiratory motion model.使用患者特定的呼吸运动模型校正锥形束 CT 中的运动伪影。
Med Phys. 2010 Jun;37(6):2901-9. doi: 10.1118/1.3397460.
引用本文的文献
1
Stepwise Corrected Attention Registration Network for Preoperative and Follow-Up Magnetic Resonance Imaging of Glioma Patients.用于胶质瘤患者术前和随访磁共振成像的逐步校正注意力配准网络
Bioengineering (Basel). 2024 Sep 23;11(9):951. doi: 10.3390/bioengineering11090951.
2
Deep learning-based simultaneous registration and unsupervised non-correspondence segmentation of medical images with pathologies.基于深度学习的医学图像病理同时配准和无监督非对应分割。
Int J Comput Assist Radiol Surg. 2022 Apr;17(4):699-710. doi: 10.1007/s11548-022-02577-4. Epub 2022 Mar 3.
3
A Deep Network for Joint Registration and Reconstruction of Images with Pathologies.一种用于联合配准和重建病变图像的深度网络。
Mach Learn Med Imaging. 2020 Oct;12436:342-352. doi: 10.1007/978-3-030-59861-7_35. Epub 2020 Sep 29.
4
Registration quality filtering improves robustness of voxel-wise analyses to the choice of brain template.登记质量过滤提高了体素分析对大脑模板选择的鲁棒性。
Neuroimage. 2021 Feb 15;227:117657. doi: 10.1016/j.neuroimage.2020.117657. Epub 2020 Dec 15.
5
Patient-Specific Registration of Pre-operative and Post-recurrence Brain Tumor MRI Scans.术前及复发后脑肿瘤磁共振成像扫描的患者特异性配准
Brainlesion. 2019;11383:105-114. doi: 10.1007/978-3-030-11723-8_10. Epub 2019 Jan 26.
6
Brain extraction from normal and pathological images: A joint PCA/Image-Reconstruction approach.从正常和病理性图像中提取脑区：一种联合 PCA/图像重建的方法。
Neuroimage. 2018 Aug 1;176:431-445. doi: 10.1016/j.neuroimage.2018.04.073. Epub 2018 May 4.
本文引用的文献
1
Registration of Pathological Images.病理图像的登记
Simul Synth Med Imaging. 2016 Oct;9968:97-107. doi: 10.1007/978-3-319-46630-9_10. Epub 2016 Sep 23.
2
Low-Rank Atlas Image Analyses in the Presence of Pathologies.存在病变情况下的低秩图谱图像分析
IEEE Trans Med Imaging. 2015 Dec;34(12):2583-91. doi: 10.1109/TMI.2015.2448556. Epub 2015 Jun 22.
3
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS).多模态脑肿瘤图像分割基准（BRATS）。
IEEE Trans Med Imaging. 2015 Oct;34(10):1993-2024. doi: 10.1109/TMI.2014.2377694. Epub 2014 Dec 4.
4
PORTR: Pre-operative and post-recurrence brain tumor registration.PORTR：术前和复发后脑肿瘤配准。
IEEE Trans Med Imaging. 2014 Mar;33(3):651-67. doi: 10.1109/TMI.2013.2293478.
5
Neuroimaging of structural pathology and connectomics in traumatic brain injury: Toward personalized outcome prediction.创伤性脑损伤的结构病理学和连接组学神经影像学：迈向个体化预后预测。
Neuroimage Clin. 2012 Aug 24;1(1):1-17. doi: 10.1016/j.nicl.2012.08.002. eCollection 2012.
6
Geometric metamorphosis.几何变形
Med Image Comput Comput Assist Interv. 2011;14(Pt 2):639-46. doi: 10.1007/978-3-642-23629-7_78.
7
Non-rigid registration with missing correspondences in preoperative and postresection brain images.术前和切除术后脑图像中存在对应关系缺失的非刚性配准。
Med Image Comput Comput Assist Interv. 2010;13(Pt 1):367-74. doi: 10.1007/978-3-642-15705-9_45.
8
Open access series of imaging studies: longitudinal MRI data in nondemented and demented older adults.开放获取成像研究系列：非痴呆和痴呆老年人大脑中的纵向 MRI 数据。
J Cogn Neurosci. 2010 Dec;22(12):2677-84. doi: 10.1162/jocn.2009.21407.
9
Fast free-form deformation using graphics processing units.基于图形处理单元的快速自由变形。
Comput Methods Programs Biomed. 2010 Jun;98(3):278-84. doi: 10.1016/j.cmpb.2009.09.002. Epub 2009 Oct 8.
10
Spatial normalization of brain images with focal lesions using cost function masking.使用代价函数掩膜对伴有局灶性病变的脑图像进行空间归一化。
Neuroimage. 2001 Aug;14(2):486-500. doi: 10.1006/nimg.2001.0845.
Zotero 插件