期刊
GENES
卷 13, 期 11, 页码 -出版社
MDPI
DOI: 10.3390/genes13112127
关键词
spectroscopy; machine learning; non-linear optics
资金
- Secom Science and Technology Foundation
- Japan Agency for Medical Research and Development [17bm0804008]
- MEXT [JP18H0540]
This article reviews the basics of Raman spectroscopy and imaging for cancer tissue discrimination, as well as recent attempts to estimate gene expression profiles using machine learning. With advances in machine learning techniques, it is speculated that cancer type discrimination using Raman spectroscopy will be possible in the future.
Normal and tumor regions within cancer tissue can be distinguished using various methods, such as histological analysis, tumor marker testing, X-ray imaging, or magnetic resonance imaging. Recently, new discrimination methods utilizing the Raman spectra of tissues have been developed and put into practical use. Because Raman spectral microscopy is a non-destructive and non-labeling method, it is potentially compatible for use in the operating room. In this review, we focus on the basics of Raman spectroscopy and Raman imaging in live cells and cell type discrimination, as these form the bases for current Raman scattering-based cancer diagnosis. We also review recent attempts to estimate the gene expression profile from the Raman spectrum of living cells using simple machine learning. Considering recent advances in machine learning techniques, we speculate that cancer type discrimination using Raman spectroscopy will be possible in the near future.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据