基于稀疏数据的有效且高效的生物医学图像分割学习方法。
Sparse Data-Driven Learning for Effective and Efficient Biomedical Image Segmentation.
机构信息
Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut 06520, USA; email:
Department of Urology, Yale School of Medicine, New Haven, Connecticut 06520, USA.
出版信息
Annu Rev Biomed Eng. 2020 Jun 4;22:127-153. doi: 10.1146/annurev-bioeng-060418-052147. Epub 2020 Mar 13.
Abstract
Sparsity is a powerful concept to exploit for high-dimensional machine learning and associated representational and computational efficiency. Sparsity is well suited for medical image segmentation. We present a selection of techniques that incorporate sparsity, including strategies based on dictionary learning and deep learning, that are aimed at medical image segmentation and related quantification.
摘要
稀疏性是用于高维机器学习以及相关表示和计算效率的强大概念。稀疏性非常适合医学图像分割。我们介绍了一些利用稀疏性的技术，包括基于字典学习和深度学习的策略，这些技术旨在用于医学图像分割和相关的量化。
相似文献
1
Sparse Data-Driven Learning for Effective and Efficient Biomedical Image Segmentation.基于稀疏数据的有效且高效的生物医学图像分割学习方法。
Annu Rev Biomed Eng. 2020 Jun 4;22:127-153. doi: 10.1146/annurev-bioeng-060418-052147. Epub 2020 Mar 13.
2
Cross-dimensional transfer learning in medical image segmentation with deep learning.深度学习在医学图像分割中的跨维度迁移学习。
Med Image Anal. 2023 Aug;88:102868. doi: 10.1016/j.media.2023.102868. Epub 2023 Jun 17.
3
TernaryNet: faster deep model inference without GPUs for medical 3D segmentation using sparse and binary convolutions.TernaryNet：使用稀疏和二值卷积实现更快的无 GPU 医疗 3D 分割的深度学习模型推断
Int J Comput Assist Radiol Surg. 2018 Sep;13(9):1311-1320. doi: 10.1007/s11548-018-1797-4. Epub 2018 May 30.
4
Machine learning techniques for biomedical image segmentation: An overview of technical aspects and introduction to state-of-art applications.机器学习技术在生物医学图像分割中的应用：技术方面的综述及最新应用介绍。
Med Phys. 2020 Jun;47(5):e148-e167. doi: 10.1002/mp.13649.
5
Variability and reproducibility in deep learning for medical image segmentation.深度学习在医学图像分割中的可变性和可重复性。
Sci Rep. 2020 Aug 13;10(1):13724. doi: 10.1038/s41598-020-69920-0.
6
Improving segmentation and classification of renal tumors in small sample 3D CT images using transfer learning with convolutional neural networks.利用卷积神经网络的迁移学习提高小样本三维 CT 图像中肾肿瘤的分割和分类。
Int J Comput Assist Radiol Surg. 2022 Jul;17(7):1303-1311. doi: 10.1007/s11548-022-02587-2. Epub 2022 Mar 15.
7
A Novel Sparse Dictionary Learning Separation (SDLS) Model With Adaptive Dictionary Mutual Incoherence Constraint for fMRI Data Analysis.一种用于功能磁共振成像（fMRI）数据分析的具有自适应字典互不相干性约束的新型稀疏字典学习分离（SDLS）模型。
IEEE Trans Biomed Eng. 2016 Nov;63(11):2376-2389. doi: 10.1109/TBME.2016.2533722. Epub 2016 Feb 23.
8
Machine learning and deep learning for brain tumor MRI image segmentation.机器学习和深度学习在脑肿瘤 MRI 图像分割中的应用。
Exp Biol Med (Maywood). 2023 Nov;248(21):1974-1992. doi: 10.1177/15353702231214259. Epub 2023 Dec 16.
9
NiftyNet: a deep-learning platform for medical imaging.NiftyNet：一个用于医学成像的深度学习平台。
Comput Methods Programs Biomed. 2018 May;158:113-122. doi: 10.1016/j.cmpb.2018.01.025. Epub 2018 Jan 31.
10
Fast and Precise Hippocampus Segmentation Through Deep Convolutional Neural Network Ensembles and Transfer Learning.通过深度卷积神经网络集成和迁移学习实现快速准确的海马体分割。
Neuroinformatics. 2019 Oct;17(4):563-582. doi: 10.1007/s12021-019-09417-y.
引用本文的文献
1
Machine Learning-Based Classification of Cervical Lymph Nodes in HNSCC: A Radiomics Approach with Feature Selection Optimization.基于机器学习的头颈部鳞状细胞癌颈淋巴结分类：一种具有特征选择优化的放射组学方法
Cancers (Basel). 2025 Aug 20;17(16):2711. doi: 10.3390/cancers17162711.
2
HDS-Net: Achieving fine-grained skin lesion segmentation using hybrid encoding and dynamic sparse attention.HDS-Net：使用混合编码和动态稀疏注意力实现细粒度皮肤病变分割。
PLoS One. 2024 Mar 21;19(3):e0299392. doi: 10.1371/journal.pone.0299392. eCollection 2024.
3
Machine Learning for Cardiovascular Biomechanics Modeling: Challenges and Beyond.机器学习在心血管生物力学建模中的应用：挑战与超越。
Ann Biomed Eng. 2022 Jun;50(6):615-627. doi: 10.1007/s10439-022-02967-4. Epub 2022 Apr 20.
本文引用的文献
1
Liver Tissue Classification Using an Auto-context-based Deep Neural Network with a Multi-phase Training Framework.使用具有多阶段训练框架的基于自动上下文的深度神经网络进行肝脏组织分类
Patch Based Tech Med Imaging (2018). 2018 Sep;11075:59-66. doi: 10.1007/978-3-030-00500-9_7. Epub 2018 Sep 15.
2
Segmenting the Brain Surface From CT Images With Artifacts Using Locally Oriented Appearance and Dictionary Learning.基于局部方向外观和字典学习从带伪影 CT 图像中分割脑表面。
IEEE Trans Med Imaging. 2019 Feb;38(2):596-607. doi: 10.1109/TMI.2018.2868045. Epub 2018 Aug 30.
3
Liver tissue classification in patients with hepatocellular carcinoma by fusing structured and rotationally invariant context representation.通过融合结构化和旋转不变上下文表示对肝细胞癌患者的肝脏组织进行分类
Med Image Comput Comput Assist Interv. 2017 Sep;10435:81-88. doi: 10.1007/978-3-319-66179-7_10. Epub 2017 Sep 4.
4
Deep Learning in Medical Image Analysis.医学图像分析中的深度学习
Annu Rev Biomed Eng. 2017 Jun 21;19:221-248. doi: 10.1146/annurev-bioeng-071516-044442. Epub 2017 Mar 9.
5
Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation.用于基于图谱的脑磁共振成像分割的特定主题稀疏字典学习
IEEE J Biomed Health Inform. 2015 Sep;19(5):1598-609. doi: 10.1109/JBHI.2015.2439242.
6
Sparsity techniques in medical imaging.医学成像中的稀疏技术。
Comput Med Imaging Graph. 2015 Dec;46 Pt 1(Pt 1):1. doi: 10.1016/j.compmedimag.2015.07.002. Epub 2015 Jul 16.
7
Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images.用于乳腺癌组织病理学图像细胞核检测的堆叠稀疏自动编码器（SSAE）
IEEE Trans Med Imaging. 2016 Jan;35(1):119-30. doi: 10.1109/TMI.2015.2458702. Epub 2015 Jul 20.
8
A homotopy-based sparse representation for fast and accurate shape prior modeling in liver surgical planning.一种基于同伦的稀疏表示方法，用于在肝外科规划中快速准确地建立形状先验模型。
Med Image Anal. 2015 Jan;19(1):176-86. doi: 10.1016/j.media.2014.10.003. Epub 2014 Oct 23.
9
BioImage Suite: An integrated medical image analysis suite: An update.生物图像套件：一个集成的医学图像分析套件：最新进展。
Insight J. 2006;2006:209.
10
Multi-atlas segmentation with augmented features for cardiac MR images.基于增强特征的多图谱分割方法在心脏磁共振图像中的应用。
Med Image Anal. 2015 Jan;19(1):98-109. doi: 10.1016/j.media.2014.09.005. Epub 2014 Sep 19.
Zotero 插件