Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Deep learning-empowered Raman spectroscopy for gastric cancer diagnosis: a review of data pipelines and algorithms.

The Analyst·2026
Same author

High confidence Raman spectroscopy of tumor biomarker proteins through experimental and theoretical cross-validation.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Methanogenesis inhibition by bacitracin via modulating rumen microbial composition as demonstrated in in vitro assays.

Journal of dairy science·2026
Same author

Phylogenetic diversity and divergent arsenite oxidation of photoarsenotrophs in geothermal springs.

Journal of hazardous materials·2025
Same author

An intelligent diagnostic algorithm for Raman spectroscopy of gastrointestinal cancer based on component modeling.

Analytical methods : advancing methods and applications·2025
Same author

Characteristics of atmospheric optical turbulence in the free atmosphere over China derived from radiosonde data using the Thorpe method.

Optics express·2025

相关实验视频

Updated: Jan 17, 2026

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

1.1K

深度拉曼定量分析和增强特征用于生物可解释的肠道癌症检测

Mingkun Wang1, Juan Li2, Wenbo Mo1

  • 1Department of Materials Science and Technology, Laser Fusion Research Center, China Academy of Engineering Physics, Mianyang 621900, China.

Analytical chemistry
|September 22, 2025
PubMed
概括

这项研究提出了一种使用拉曼光谱和深度学习的早期胃肠道癌症检测的新方法. 该方法通过分析分子变化准确地识别恶性组织,提供了一个有前途的非侵入性诊断工具.

更多相关视频

Glycomics-Guided Glycoproteomics Facilitates Comprehensive Profiling of the Glycoproteome in Complex Tumor Microenvironments
10:59

Glycomics-Guided Glycoproteomics Facilitates Comprehensive Profiling of the Glycoproteome in Complex Tumor Microenvironments

Published on: February 7, 2025

1.7K
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
15:17

Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing

Published on: September 25, 2011

14.4K

相关实验视频

Last Updated: Jan 17, 2026

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

1.1K
Glycomics-Guided Glycoproteomics Facilitates Comprehensive Profiling of the Glycoproteome in Complex Tumor Microenvironments
10:59

Glycomics-Guided Glycoproteomics Facilitates Comprehensive Profiling of the Glycoproteome in Complex Tumor Microenvironments

Published on: February 7, 2025

1.7K
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
15:17

Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing

Published on: September 25, 2011

14.4K

科学领域:

  • 生物医学光谱学 生物医学光谱学
  • 计算生物学 计算生物学
  • 在瘤学瘤学.

背景情况:

  • 胃肠道 (GI) 癌症的早期诊断对于改善患者的治疗结果至关重要.
  • 对于精确的癌症检测,需要使用非侵入性的分子量化方法.
  • 拉曼光谱为分析组织中的生化成分提供了一个潜在的方法.

研究的目的:

  • 开发和验证一个协同作用的框架,整合拉曼光谱和深度学习 (CNN) 以进行非侵入性肠胃癌检测.
  • 用光谱分解量化分析肠道组织中的分子变化.
  • 建立基于分子特征的胃肠道癌症强有力的诊断策略.

主要方法:

  • 拉曼光谱从927个胃肠道组织 (82个恶性,845个良性) 中获得.
  • 理论上计算了五种生化成分的参考光谱.
  • 一个LightGBM分类器被训练在10个特征 (5系数+5比特征) 来自光谱分解,使用SMOTE等级失衡.
  • 用SHAP分析和t-SNE进行特征重要性评估和可视化.

主要成果:

  • 轻GBM模型实现了高诊断性能:98.2%的准确性,99.4%的灵敏性,96.9%的特异性和0.996 AUC.
  • 鉴定出DNA及其比例特征是区分良性和恶性组织的最重要的指标.
  • 交叉验证证实了该模型的稳定性和通用性,平均AUC为0.996 ± 0.003.

结论:

  • 开发的框架通过定量分子变化分析为肠道癌症检测提供了强大而准确的策略.
  • 这种方法证明了复杂的生物谱应用的优良诊断性能和通用性.
  • 拉曼光谱和深度学习的整合对非侵入性癌症诊断具有重大前景.