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。
Non-rigid registration with missing correspondences in preoperative and postresection brain images.
作者信息
Chitphakdithai Nicha, Duncan James S
机构信息
Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
出版信息
Med Image Comput Comput Assist Interv. 2010;13(Pt 1):367-74. doi: 10.1007/978-3-642-15705-9_45.
Abstract
Registration of preoperative and postresection images is often needed to evaluate the effectiveness of treatment. While several non-rigid registration methods exist, most would be unable to accurately align these types of datasets due to the absence of tissue in one image. Here we present a joint registration and segmentation algorithm which handles the missing correspondence problem. An intensity-based prior is used to aid in the segmentation of the resection region from voxels with valid correspondences in the two images. The problem is posed in a maximum a posteriori (MAP) framework and optimized using the expectation-maximization (EM) algorithm. Results on both synthetic and real data show our method improved image alignment compared to a traditional non-rigid registration algorithm as well as a method using a robust error kernel in the registration similarity metric.
摘要
通常需要对术前和切除后图像进行配准，以评估治疗效果。虽然存在几种非刚性配准方法，但由于其中一幅图像中没有组织，大多数方法无法准确对齐这些类型的数据集。在此，我们提出一种联合配准和分割算法，该算法可处理对应关系缺失的问题。基于强度的先验用于辅助从两幅图像中具有有效对应关系的体素中分割出切除区域。该问题在最大后验概率（MAP）框架中提出，并使用期望最大化（EM）算法进行优化。合成数据和真实数据的结果均表明，与传统的非刚性配准算法以及在配准相似性度量中使用鲁棒误差核的方法相比，我们的方法改善了图像对齐效果。
相似文献
1
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.
2
A marginalized MAP approach and EM optimization for pair-wise registration.一种用于成对配准的边缘化最大后验概率方法和期望最大化优化
Inf Process Med Imaging. 2007;20:662-74. doi: 10.1007/978-3-540-73273-0_55.
3
Non-rigid image registration with uniform spherical structure patterns.具有均匀球形结构模式的非刚性图像配准
Inf Process Med Imaging. 2009;21:163-75. doi: 10.1007/978-3-642-02498-6_14.
4
A unifying approach to registration, segmentation, and intensity correction.一种用于配准、分割和强度校正的统一方法。
Med Image Comput Comput Assist Interv. 2005;8(Pt 1):310-8. doi: 10.1007/11566465_39.
5
Groupwise registration by hierarchical anatomical correspondence detection.通过分层解剖对应检测进行分组配准。
Med Image Comput Comput Assist Interv. 2010;13(Pt 2):684-91. doi: 10.1007/978-3-642-15745-5_84.
6
Hierarchical segmentation-assisted multimodal registration for MR brain images.基于层次分割的多模态磁共振脑图像配准方法。
Comput Med Imaging Graph. 2013 Apr;37(3):234-44. doi: 10.1016/j.compmedimag.2013.03.004. Epub 2013 Mar 29.
7
Simultaneous registration and segmentation of anatomical structures from brain MRI.基于脑部磁共振成像的解剖结构同步配准与分割
Med Image Comput Comput Assist Interv. 2005;8(Pt 1):17-25. doi: 10.1007/11566465_3.
8
Similarity metrics for groupwise non-rigid registration.用于逐组非刚性配准的相似性度量
Med Image Comput Comput Assist Interv. 2007;10(Pt 2):544-52. doi: 10.1007/978-3-540-75759-7_66.
9
Non-rigid registration of breast images using feature points.使用特征点的乳腺图像非刚性配准
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:4387-90. doi: 10.1109/IEMBS.2010.5627142.
10
Robust nonrigid multimodal image registration using local frequency maps.使用局部频率图的鲁棒非刚性多模态图像配准
Inf Process Med Imaging. 2005;19:504-15. doi: 10.1007/11505730_42.
引用本文的文献
1
A Systematic Review on the Use of Registration-Based Change Tracking Methods in Longitudinal Radiological Images.基于登记的变化跟踪方法在纵向放射影像中的应用系统评价
J Imaging Inform Med. 2024 Nov 22. doi: 10.1007/s10278-024-01333-1.
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
One shot PACS: Patient specific Anatomic Context and Shape prior aware recurrent registration-segmentation of longitudinal thoracic cone beam CTs.单次成像的PACS：基于患者特定解剖背景和形状先验的纵向胸部锥形束CT的递归配准分割
IEEE Trans Med Imaging. 2022 Feb 25;PP. doi: 10.1109/TMI.2022.3154934.
4
Development and Characterization of a Chest CT Atlas.胸部CT图谱的开发与特征描述
Proc SPIE Int Soc Opt Eng. 2021;2021. doi: 10.1117/12.2580800. Epub 2021 Feb 15.
5
A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections.一种模拟切除的术后脑腔分割的自监督学习策略。
Int J Comput Assist Radiol Surg. 2021 Oct;16(10):1653-1661. doi: 10.1007/s11548-021-02420-2. Epub 2021 Jun 13.
6
Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease.基于强度变换和缺失数据的微分同胚配准：在阿尔茨海默病三维数字病理学中的应用
Front Neurosci. 2020 Feb 11;14:52. doi: 10.3389/fnins.2020.00052. eCollection 2020.
7
Tracking Metastatic Brain Tumors in Longitudinal Scans via Joint Image Registration and Labeling.通过联合图像配准和标记在纵向扫描中追踪转移性脑肿瘤
Spatiotemporal Image Anal Longitud Time Ser Image Data (2012). 2012 Oct;7570:124-136. doi: 10.1007/978-3-642-33555-6_11.
8
REGISTRATION OF BRAIN RESECTION MRI WITH INTENSITY AND LOCATION PRIORS.基于强度和位置先验的脑切除MRI配准
Proc IEEE Int Symp Biomed Imaging. 2011 Mar-Apr;2011:1520-1523. doi: 10.1109/ISBI.2011.5872690. Epub 2011 Jun 9.
9
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.
10
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.
本文引用的文献
1
PAIRWISE REGISTRATION OF IMAGES WITH MISSING CORRESPONDENCES DUE TO RESECTION.针对因切除导致对应关系缺失的图像进行成对配准。
Proc IEEE Int Symp Biomed Imaging. 2010 Apr 14;2010:1025-1028. doi: 10.1109/ISBI.2010.5490164.
2
Partially resected gliomas: diagnostic performance of fluid-attenuated inversion recovery MR imaging for detection of progression.部分切除的脑胶质瘤：液体衰减反转恢复磁共振成像检测进展的诊断性能。
Radiology. 2010 Mar;254(3):907-16. doi: 10.1148/radiol09090893.
3
Refractory seizures: try additional antiepileptic drugs (after two have failed) or go directly to early surgery evaluation?难治性癫痫发作：尝试额外的抗癫痫药物（在两种药物治疗失败后）还是直接进行早期手术评估？
Epilepsia. 2009 Sep;50 Suppl 8:57-62. doi: 10.1111/j.1528-1167.2009.02237.x.
4
A non-rigid registration framework that accommodates resection and retraction.一种能够适应切除和牵拉的非刚性配准框架。
Inf Process Med Imaging. 2009;21:447-58. doi: 10.1007/978-3-642-02498-6_37.
5
Constrained non-rigid registration for use in image-guided adaptive radiotherapy.用于图像引导自适应放射治疗的约束非刚性配准
Med Image Anal. 2009 Oct;13(5):809-17. doi: 10.1016/j.media.2009.07.004. Epub 2009 Jul 16.
6
Non-diffeomorphic registration of brain tumor images by simulating tissue loss and tumor growth.通过模拟组织损失和肿瘤生长实现脑肿瘤图像的非微分同胚配准
Neuroimage. 2009 Jul 1;46(3):762-74. doi: 10.1016/j.neuroimage.2009.01.051.
7
De-enhancing the dynamic contrast-enhanced breast MRI for robust registration.降低动态对比增强乳腺MRI的对比度以实现稳健配准。
Med Image Comput Comput Assist Interv. 2007;10(Pt 1):933-41. doi: 10.1007/978-3-540-75757-3_113.
8
A Bayesian model for joint segmentation and registration.一种用于联合分割与配准的贝叶斯模型。
Neuroimage. 2006 May 15;31(1):228-39. doi: 10.1016/j.neuroimage.2005.11.044. Epub 2006 Feb 7.
9
Medical image registration with partial data.基于部分数据的医学图像配准
Med Image Anal. 2006 Jun;10(3):452-64. doi: 10.1016/j.media.2005.03.006. Epub 2005 Jun 23.
10
Nonrigid registration using free-form deformations: application to breast MR images.基于自由形式变形的非刚性配准：在乳腺磁共振图像中的应用。
IEEE Trans Med Imaging. 1999 Aug;18(8):712-21. doi: 10.1109/42.796284.
Zotero 插件