一种用于多模态图像中脑肿瘤分割的生成模型。
A generative model for brain tumor segmentation in multi-modal images.
作者信息
Menze Bjoern H, Van Leemput Koen, Lashkari Danial, Weber Marc-André, Ayache Nicholas, Golland Polina
机构信息
1 Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA.
出版信息
Med Image Comput Comput Assist Interv. 2010;13(Pt 2):151-9. doi: 10.1007/978-3-642-15745-5_19.
Abstract
We introduce a generative probabilistic model for segmentation of tumors in multi-dimensional images. The model allows for different tumor boundaries in each channel, reflecting difference in tumor appearance across modalities. We augment a probabilistic atlas of healthy tissue priors with a latent atlas of the lesion and derive the estimation algorithm to extract tumor boundaries and the latent atlas from the image data. We present experiments on 25 glioma patient data sets, demonstrating significant improvement over the traditional multivariate tumor segmentation.
摘要
我们介绍了一种用于多维度图像中肿瘤分割的生成概率模型。该模型允许每个通道中有不同的肿瘤边界，反映了跨模态肿瘤外观的差异。我们用病变的潜在图谱增强健康组织先验的概率图谱，并推导估计算法以从图像数据中提取肿瘤边界和潜在图谱。我们展示了对25个神经胶质瘤患者数据集的实验，证明相对于传统的多变量肿瘤分割有显著改进。
相似文献
1
A generative model for brain tumor segmentation in multi-modal images.一种用于多模态图像中脑肿瘤分割的生成模型。
Med Image Comput Comput Assist Interv. 2010;13(Pt 2):151-9. doi: 10.1007/978-3-642-15745-5_19.
2
Combining generative models for multifocal glioma segmentation and registration.用于多灶性胶质瘤分割与配准的生成模型融合
Med Image Comput Comput Assist Interv. 2014;17(Pt 1):763-70. doi: 10.1007/978-3-319-10404-1_95.
3
Low-rank to the rescue - atlas-based analyses in the presence of pathologies.低秩来救援——存在病变时基于图谱的分析
Med Image Comput Comput Assist Interv. 2014;17(Pt 3):97-104. doi: 10.1007/978-3-319-10443-0_13.
4
A unified framework for cross-modality multi-atlas segmentation of brain MRI.用于脑 MRI 多模态多图谱分割的统一框架。
Med Image Anal. 2013 Dec;17(8):1181-91. doi: 10.1016/j.media.2013.08.001. Epub 2013 Aug 19.
5
Segmentation of image ensembles via latent atlases.通过潜在图谱对图像集进行分割。
Med Image Anal. 2010 Oct;14(5):654-65. doi: 10.1016/j.media.2010.05.004. Epub 2010 Jun 4.
6
Robust brain registration using adaptive probabilistic atlas.使用自适应概率图谱进行稳健的脑图谱配准。
Med Image Comput Comput Assist Interv. 2008;11(Pt 2):1041-9. doi: 10.1007/978-3-540-85990-1_125.
7
Groupwise segmentation with multi-atlas joint label fusion.基于多图谱联合标签融合的分组分割
Med Image Comput Comput Assist Interv. 2013;16(Pt 1):711-8. doi: 10.1007/978-3-642-40811-3_89.
8
Deformable atlas for multi-structure segmentation.用于多结构分割的可变形图谱
Med Image Comput Comput Assist Interv. 2013;16(Pt 1):743-50. doi: 10.1007/978-3-642-40811-3_93.
9
Statistical and topological atlas based brain image segmentation.基于统计和拓扑图谱的脑图像分割
Med Image Comput Comput Assist Interv. 2007;10(Pt 1):94-101. doi: 10.1007/978-3-540-75757-3_12.
10
Simulation of brain tumors in MR images for evaluation of segmentation efficacy.用于评估分割效果的磁共振图像中脑肿瘤的模拟
Med Image Anal. 2009 Apr;13(2):297-311. doi: 10.1016/j.media.2008.11.002. Epub 2008 Dec 3.
引用本文的文献
1
Automatic brain-tumor diagnosis using cascaded deep convolutional neural networks with symmetric U-Net and asymmetric residual-blocks.使用具有对称U-Net和非对称残差块的级联深度卷积神经网络进行脑肿瘤自动诊断。
Sci Rep. 2024 Apr 25;14(1):9501. doi: 10.1038/s41598-024-59566-7.
2
Development and Validation of a Deep Learning Model for Brain Tumor Diagnosis and Classification Using Magnetic Resonance Imaging.利用磁共振成像开发和验证用于脑肿瘤诊断和分类的深度学习模型。
JAMA Netw Open. 2022 Aug 1;5(8):e2225608. doi: 10.1001/jamanetworkopen.2022.25608.
3
Automated Detection of Brain Tumor through Magnetic Resonance Images Using Convolutional Neural Network.基于卷积神经网络的磁共振图像脑肿瘤自动检测
Biomed Res Int. 2021 Nov 30;2021:3365043. doi: 10.1155/2021/3365043. eCollection 2021.
4
Fully automated segmentation of brain tumor from multiparametric MRI using 3D context deep supervised U-Net.基于三维上下文深度监督 U-Net 的多参数 MRI 脑肿瘤全自动分割。
Med Phys. 2021 Aug;48(8):4365-4374. doi: 10.1002/mp.15032. Epub 2021 Jul 11.
5
LBTS-Net: A fast and accurate CNN model for brain tumour segmentation.LBTS-Net：一种用于脑肿瘤分割的快速且准确的卷积神经网络模型。
Healthc Technol Lett. 2021 Mar 16;8(2):31-36. doi: 10.1049/htl2.12005. eCollection 2021 Apr.
6
Analyzing magnetic resonance imaging data from glioma patients using deep learning.利用深度学习分析脑胶质瘤患者的磁共振成像数据。
Comput Med Imaging Graph. 2021 Mar;88:101828. doi: 10.1016/j.compmedimag.2020.101828. Epub 2020 Dec 2.
7
Survey of Image Processing Techniques for Brain Pathology Diagnosis: Challenges and Opportunities.脑病理学诊断的图像处理技术综述：挑战与机遇
Front Robot AI. 2018 Nov 2;5:120. doi: 10.3389/frobt.2018.00120. eCollection 2018.
8
BraTS Toolkit: Translating BraTS Brain Tumor Segmentation Algorithms Into Clinical and Scientific Practice.BraTS工具包：将BraTS脑肿瘤分割算法转化为临床和科研实践
Front Neurosci. 2020 Apr 29;14:125. doi: 10.3389/fnins.2020.00125. eCollection 2020.
9
Novel Volumetric Sub-region Segmentation in Brain Tumors.脑肿瘤中的新型体积子区域分割
Front Comput Neurosci. 2020 Jan 24;14:3. doi: 10.3389/fncom.2020.00003. eCollection 2020.
10
A New Approach for Brain Tumor Segmentation and Classification Based on Score Level Fusion Using Transfer Learning.基于迁移学习的基于分数级融合的脑肿瘤分割与分类新方法。
J Med Syst. 2019 Oct 23;43(11):326. doi: 10.1007/s10916-019-1453-8.
本文引用的文献
1
Segmenting brain tumors using pseudo-conditional random fields.使用伪条件随机场分割脑肿瘤。
Med Image Comput Comput Assist Interv. 2008;11(Pt 1):359-66.
2
A discriminative model-constrained graph cuts approach to fully automated pediatric brain tumor segmentation in 3-D MRI.一种基于判别模型约束图割的方法用于三维磁共振成像中儿童脑肿瘤的全自动分割。
Med Image Comput Comput Assist Interv. 2008;11(Pt 1):67-75. doi: 10.1007/978-3-540-85988-8_9.
3
ORBIT: a multiresolution framework for deformable registration of brain tumor images.ORBIT：一种用于脑肿瘤图像可变形配准的多分辨率框架。
IEEE Trans Med Imaging. 2008 Aug;27(8):1003-17. doi: 10.1109/TMI.2008.916954.
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
Atlas-based segmentation of pathological MR brain images using a model of lesion growth.基于图谱的病理性脑部磁共振图像分割，采用病变生长模型
IEEE Trans Med Imaging. 2004 Oct;23(10):1301-14. doi: 10.1109/TMI.2004.834618.
6
A brain tumor segmentation framework based on outlier detection.一种基于异常值检测的脑肿瘤分割框架。
Med Image Anal. 2004 Sep;8(3):275-83. doi: 10.1016/j.media.2004.06.007.
7
Automatic brain tumor segmentation by subject specific modification of atlas priors.通过对图谱先验进行特定于个体的修改实现脑肿瘤自动分割。
Acad Radiol. 2003 Dec;10(12):1341-8. doi: 10.1016/s1076-6332(03)00506-3.
8
Automated segmentation of multiple sclerosis lesions by model outlier detection.通过模型离群值检测实现多发性硬化症病变的自动分割。
IEEE Trans Med Imaging. 2001 Aug;20(8):677-88. doi: 10.1109/42.938237.
9
Automated model-based tissue classification of MR images of the brain.基于模型的脑磁共振图像自动组织分类
IEEE Trans Med Imaging. 1999 Oct;18(10):897-908. doi: 10.1109/42.811270.
Zotero 插件