Qualitative and quantitative detection of liver injury with terahertz time-domain spectroscopy
Yuqi Cao, Pingjie Huang, Jiani Chen, Weiting Ge, Dibo Hou, Guangxin Zhang
Abstract
Terahertz technology has been widely used as a nondestructive and effective detection method. Herein, terahertz time-domain spectroscopy was used to detect drug-induced liver injury in mice. Firstly, the boxplots were used to detect abnormal data. Then the maximal information coefficient method was used to search for the features strongly correlated with the degree of injury. After that, the liver injury model was built using the random forests method in machine learning. The results show that this method can effectively identify the degree of liver injury and thus provide an auxiliary diagnostic method for detecting minor liver injury.
Topics & Concepts
Terahertz radiationLiver injuryTerahertz spectroscopy and technologyTerahertz time-domain spectroscopySpectroscopyComputer scienceLiver tissueRandom forestDomain (mathematical analysis)Artificial intelligenceBiomedical engineeringPattern recognition (psychology)Materials scienceMedicineMathematicsPhysicsOpticsInternal medicineQuantum mechanicsMathematical analysisTerahertz technology and applicationsAdvanced Chemical Sensor TechnologiesSpectroscopy Techniques in Biomedical and Chemical Research