• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于细胞生物学图像分类的随机子窗口和极端随机树

Random subwindows and extremely randomized trees for image classification in cell biology.

作者信息

Marée Raphaël, Geurts Pierre, Wehenkel Louis

机构信息

GIGA Bioinformatics Platform, University of Liege, Liege, Belgium.

出版信息

BMC Cell Biol. 2007 Jul 10;8 Suppl 1(Suppl 1):S2. doi: 10.1186/1471-2121-8-S1-S2.

DOI:10.1186/1471-2121-8-S1-S2
PMID:17634092
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC1924507/
Abstract

BACKGROUND

With the improvements in biosensors and high-throughput image acquisition technologies, life science laboratories are able to perform an increasing number of experiments that involve the generation of a large amount of images at different imaging modalities/scales. It stresses the need for computer vision methods that automate image classification tasks.

RESULTS

We illustrate the potential of our image classification method in cell biology by evaluating it on four datasets of images related to protein distributions or subcellular localizations, and red-blood cell shapes. Accuracy results are quite good without any specific pre-processing neither domain knowledge incorporation. The method is implemented in Java and available upon request for evaluation and research purpose.

CONCLUSION

Our method is directly applicable to any image classification problems. We foresee the use of this automatic approach as a baseline method and first try on various biological image classification problems.

摘要

背景

随着生物传感器和高通量图像采集技术的进步，生命科学实验室能够开展越来越多涉及以不同成像方式/尺度生成大量图像的实验。这凸显了对能自动执行图像分类任务的计算机视觉方法的需求。

结果

我们通过在四个与蛋白质分布或亚细胞定位以及红细胞形状相关的图像数据集上对我们的图像分类方法进行评估，展示了其在细胞生物学中的潜力。在没有任何特定预处理和领域知识融入的情况下，准确率结果相当不错。该方法用Java实现，可应要求提供用于评估和研究目的。

结论

我们的方法可直接应用于任何图像分类问题。我们预计将这种自动方法用作基线方法，并首先尝试用于各种生物图像分类问题。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/e2904a01065f/1471-2121-8-S1-S2-8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/afb8d039c413/1471-2121-8-S1-S2-1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/a335431d9410/1471-2121-8-S1-S2-2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/7d8a1d9ce8aa/1471-2121-8-S1-S2-3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/22521acdf1dd/1471-2121-8-S1-S2-4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/a3d7a8b87658/1471-2121-8-S1-S2-5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/ad5c6a77984f/1471-2121-8-S1-S2-6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/eb716c163842/1471-2121-8-S1-S2-7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/e2904a01065f/1471-2121-8-S1-S2-8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/afb8d039c413/1471-2121-8-S1-S2-1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/a335431d9410/1471-2121-8-S1-S2-2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/7d8a1d9ce8aa/1471-2121-8-S1-S2-3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/22521acdf1dd/1471-2121-8-S1-S2-4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/a3d7a8b87658/1471-2121-8-S1-S2-5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/ad5c6a77984f/1471-2121-8-S1-S2-6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/eb716c163842/1471-2121-8-S1-S2-7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e815/1924507/e2904a01065f/1471-2121-8-S1-S2-8.jpg

相似文献

1
Random subwindows and extremely randomized trees for image classification in cell biology.用于细胞生物学图像分类的随机子窗口和极端随机树
BMC Cell Biol. 2007 Jul 10;8 Suppl 1(Suppl 1):S2. doi: 10.1186/1471-2121-8-S1-S2.
2
[An automatic fluorescence chemosensitivity analysis system for tumors].[一种用于肿瘤的自动荧光化学敏感性分析系统]
Zhongguo Yi Liao Qi Xie Za Zhi. 2005 May;29(3):167-9.
3
XML-based data model and architecture for a knowledge-based grid-enabled problem-solving environment for high-throughput biological imaging.用于基于知识的、支持网格的高通量生物成像问题解决环境的基于XML的数据模型和架构。
IEEE Trans Inf Technol Biomed. 2008 Mar;12(2):226-40. doi: 10.1109/TITB.2007.904153.
4
A reliable method for cell phenotype image classification.一种用于细胞表型图像分类的可靠方法。
Artif Intell Med. 2008 Jun;43(2):87-97. doi: 10.1016/j.artmed.2008.03.005. Epub 2008 Apr 28.
5
Automated classification of mitotic phenotypes of human cells using fluorescent proteins.利用荧光蛋白对人类细胞有丝分裂表型进行自动分类。
Methods Cell Biol. 2008;85:539-54. doi: 10.1016/S0091-679X(08)85023-6.
6
Active learning methods for interactive image retrieval.用于交互式图像检索的主动学习方法。
IEEE Trans Image Process. 2008 Jul;17(7):1200-11. doi: 10.1109/TIP.2008.924286.
7
Content based image retrieval using unclean positive examples.使用不纯净正例的基于内容的图像检索。
IEEE Trans Image Process. 2009 Oct;18(10):2370-5. doi: 10.1109/TIP.2009.2026669. Epub 2009 Jul 6.
8
Randomized clustering forests for image classification.用于图像分类的随机聚类森林
IEEE Trans Pattern Anal Mach Intell. 2008 Sep;30(9):1632-46. doi: 10.1109/TPAMI.2007.70822.
9
Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion.基于概率多类支持向量机分类器和自适应相似性融合的医学图像检索
Comput Med Imaging Graph. 2008 Mar;32(2):95-108. doi: 10.1016/j.compmedimag.2007.10.001. Epub 2007 Nov 26.
10
Geometry-based image retrieval in binary image databases.二值图像数据库中基于几何的图像检索
IEEE Trans Pattern Anal Mach Intell. 2008 Jun;30(6):1003-13. doi: 10.1109/TPAMI.2008.37.

引用本文的文献

1
AAGP integrates physicochemical and compositional features for machine learning-based prediction of anti-aging peptides.AAGP整合物理化学和组成特征，用于基于机器学习的抗衰肽预测。
Sci Rep. 2025 Aug 8;15(1):29036. doi: 10.1038/s41598-025-12759-0.
2
Early detection of pancreatic cancer by comprehensive serum miRNA sequencing with automated machine learning.基于自动化机器学习的综合血清 miRNA 测序对胰腺癌的早期检测。
Br J Cancer. 2024 Oct;131(7):1158-1168. doi: 10.1038/s41416-024-02794-5. Epub 2024 Aug 28.
3
Machine Learning for Multi-Vessel Coronary Artery Disease Prediction on Electrocardiogram Gated Single-Photon Emission Computed Tomography.

本文引用的文献

1
Automatic recognition and annotation of gene expression patterns of fly embryos.果蝇胚胎基因表达模式的自动识别与注释。
Bioinformatics. 2007 Mar 1;23(5):589-96. doi: 10.1093/bioinformatics/btl680. Epub 2007 Jan 19.
2
Automated subcellular location determination and high-throughput microscopy.自动亚细胞定位测定与高通量显微镜技术
Dev Cell. 2007 Jan;12(1):7-16. doi: 10.1016/j.devcel.2006.12.007.
3
Keypoint recognition using randomized trees.使用随机树进行关键点识别。
基于心电图门控单光子发射计算机断层扫描的多支冠状动脉疾病预测的机器学习
Ann Nucl Cardiol. 2023;9(1):11-18. doi: 10.17996/anc.22-00155. Epub 2023 Oct 31.
4
Machine learning of microvolt-level 12-lead electrocardiogram can help distinguish takotsubo syndrome and acute anterior myocardial infarction.微伏级12导联心电图的机器学习有助于区分应激性心肌病和急性前壁心肌梗死。
Cardiovasc Digit Health J. 2022 Jul 16;3(4):179-188. doi: 10.1016/j.cvdhj.2022.07.001. eCollection 2022 Aug.
5
RGB Three-Channel SWE-Based Ultrasomics Model: Improving the Efficiency in Differentiating Focal Liver Lesions.基于RGB三通道剪切波弹性成像的超声组学模型：提高局灶性肝病变鉴别诊断效率
Front Oncol. 2021 Sep 27;11:704218. doi: 10.3389/fonc.2021.704218. eCollection 2021.
6
Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches.基于药物相关网络搜索的机器学习实现药物过量死亡的精确时空映射。
PLoS One. 2020 Dec 7;15(12):e0243622. doi: 10.1371/journal.pone.0243622. eCollection 2020.
7
Variation in model performance by data cleanliness and classification methods in the prediction of 30-day ICU mortality, a US nationwide retrospective cohort and simulation study.数据清洁度和分类方法对美国全国回顾性队列和模拟研究中预测 30 天 ICU 死亡率的模型性能的影响变化。
BMJ Open. 2020 Dec 2;10(12):e041421. doi: 10.1136/bmjopen-2020-041421.
8
Extremely-randomized-tree-based Prediction of N-Methyladenosine Sites in .基于极端随机树的……中N-甲基腺苷位点预测
Curr Genomics. 2020 Jan;21(1):26-33. doi: 10.2174/1389202921666200219125625.
9
CT-based radiomics scores predict response to neoadjuvant chemotherapy and survival in patients with gastric cancer.基于 CT 的放射组学评分可预测胃癌患者对新辅助化疗的反应和生存。
BMC Cancer. 2020 May 25;20(1):468. doi: 10.1186/s12885-020-06970-7.
10
Pretreatment prediction of immunoscore in hepatocellular cancer: a radiomics-based clinical model based on Gd-EOB-DTPA-enhanced MRI imaging.基于钆塞酸二钠增强 MRI 成像的放射组学临床模型：肝细胞癌免疫评分的预处理预测。
Eur Radiol. 2019 Aug;29(8):4177-4187. doi: 10.1007/s00330-018-5986-x. Epub 2019 Jan 21.
IEEE Trans Pattern Anal Mach Intell. 2006 Sep;28(9):1465-79. doi: 10.1109/TPAMI.2006.188.
4
Automated segmentation, classification, and tracking of cancer cell nuclei in time-lapse microscopy.延时显微镜下癌细胞核的自动分割、分类与追踪
IEEE Trans Biomed Eng. 2006 Apr;53(4):762-6. doi: 10.1109/TBME.2006.870201.
5
Proteomic mass spectra classification using decision tree based ensemble methods.使用基于决策树的集成方法进行蛋白质组质谱分类。
Bioinformatics. 2005 Jul 15;21(14):3138-45. doi: 10.1093/bioinformatics/bti494. Epub 2005 May 12.
6
Boosting accuracy of automated classification of fluorescence microscope images for location proteomics.提高用于定位蛋白质组学的荧光显微镜图像自动分类的准确性。
BMC Bioinformatics. 2004 Jun 18;5:78. doi: 10.1186/1471-2105-5-78.
7
Automatic identification of subcellular phenotypes on human cell arrays.人类细胞阵列中亚细胞表型的自动识别。
Genome Res. 2004 Jun;14(6):1130-6. doi: 10.1101/gr.2383804.
8
Advances in molecular labeling, high throughput imaging and machine intelligence portend powerful functional cellular biochemistry tools.分子标记、高通量成像和机器智能方面的进展预示着强大的功能性细胞生物化学工具的出现。
J Cell Biochem Suppl. 2002;39:194-210. doi: 10.1002/jcb.10448.
9
A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells.一种能够识别HeLa细胞荧光显微镜图像中所有主要亚细胞结构模式的神经网络分类器。
Bioinformatics. 2001 Dec;17(12):1213-23. doi: 10.1093/bioinformatics/17.12.1213.
10
Systematic subcellular localization of novel proteins identified by large-scale cDNA sequencing.通过大规模cDNA测序鉴定的新型蛋白质的系统亚细胞定位
EMBO Rep. 2000 Sep;1(3):287-92. doi: 10.1093/embo-reports/kvd058.