基于拉曼光谱分析的轻链粉症和多发性骨髓瘤的非侵入性差异化,使用一维卷积神经网络
Yanling Zhang1, Chongxuan Tian2, Luyao An1
1State Key Laboratory for Innovation and Transformation of Luobing Theory; Key Laboratory of Cardiovascular Remodeling and Function Research of MOE, NHC, CAMS and Shandong Province; Department of Cardiology, Qilu Hospital of Shandong University, Jinan 250012, China.
概括
一项新的研究结合了血清拉曼光谱和1D-CNN模型,以准确区分轻链粉样性粉症 (AL) 和多发性骨髓瘤 (MM). 这种非侵入性方法显示出更快地诊断这些血细胞疾病的前景.
科学领域:
- 生物医学工程 生物医学工程
- 频谱学是一种光谱学.
- 机器学习 机器学习
- 在瘤学瘤学.
背景情况:
- 轻链 Amyloidosis (AL) 和多发性骨髓瘤 (MM) 是相关的血细胞疾病,具有不同的临床模式.
- 区分AL和MM是具有挑战性的,往往导致诊断延迟和患者预后较差,特别是在AL氨基粉症.
- 目前的诊断方法依赖于侵入性活检和漫长的血清学测试,突出需要快速,非侵入性的替代方案.
研究的目的:
- 开发和验证一个创新的分析框架,以精确区分AL和MM.
- 将血清拉曼光谱与一维卷积神经网络 (1D-CNN) 集成,以提高诊断能力.
- 建立一个快速的,非侵入性的辅助诊断方法,用于血细胞失色症.
主要方法:
- 从临床诊断的AL和MM患者收集了血清样本.
- 使用785nm激发拉曼系统 (光谱范围:200-2000厘米-1) 分析样品.
- 开发并应用了一种专门的1D-CNN模型,用于预处理后的光谱数据分类.
主要成果:
- 1D-CNN模型实现了高分类性能:AL的AUC为0.94和MM的0.96.
- 总体准确度达到92.5%,灵敏度为91.4%,特异性为93.1%.
- 该模型显著优于传统的机器学习 (例如SVM,AUC=0.78) 和其他深度学习架构 (p < 0.01).
结论:
- 综合的拉曼光谱和1D-CNN平台提供了一种快速,非侵入性的方法来区分AL和MM.
- 主要的光谱变化 (例如,在500,1150,1750厘米-1度) 提供了对诊断差异的分子洞察力.
- 这种方法对早期疾病查和加强诊断血细胞失分的临床决策支持具有重大潜力.
相关概念视频
Raman Spectroscopy: Overview
2.1K
The underlying principle of Raman spectroscopy is based on the interaction between light and matter, specifically molecules' inelastic scattering of photons. When a monochromatic beam of light, typically from a laser source, interacts with a sample, most scattered light has the same frequency as the incident light. This is known as Rayleigh scattering.
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
2.1K
Raman Spectroscopy Instrumentation: Overview
1.5K
A conventional Raman spectrophotometer includes a laser source, a sample holding system, a wavelength selector, and a detector.
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
1.5K


