X-ray absorption spectroscopy combined with deep learning for auto and rapid illicit drug detection.

IF 2.7 3区 医学 Q2 PSYCHOLOGY, CLINICAL
Zheng Fang, Xiefeng Zhan, Bichao Ye
{"title":"X-ray absorption spectroscopy combined with deep learning for auto and rapid illicit drug detection.","authors":"Zheng Fang, Xiefeng Zhan, Bichao Ye","doi":"10.1080/00952990.2024.2377262","DOIUrl":null,"url":null,"abstract":"<p><p><i>Background:</i> X-ray absorption spectroscopy (XAS) is a widely used substance analysis technique. It bases on the different absorption coefficients at different energy level to achieve material identification. Additionally, the combination of spectral technology and deep learning can achieve auto detection and high accuracy in material identification.<i>Objectives:</i> Current methods are difficult to identify drugs quickly and nondestructively. Therefore, we explore a novel approach utilizing XAS for the detection of prohibited drugs with common X-ray tube source and photon-counting (PC) detector.<i>Method:</i> To achieve automatic, rapid, and accurate detection of drugs. A CdTe detector and a common X-ray source were used to collect data, then dividing the data into training and testing sets. Finally, the improved transformer encoder model was used for classification. LSTM and ResU-net models are selected for comparation.<i>Result:</i> Fifty substances, which are isomers or compounds with similar molecular formulas of drugs, were selected for experiment substances. The results showed that the improved transformer model achieving 1.4 hours for training time and 96.73% for accuracy, which is better than the LSTM (2.6 hours and 65%) and ResU-net (1.5 hours and 92.7%).<i>Conclusion:</i> It can be concluded that the attention mechanism is more accurate for spectral material identification. XAS combined with deep learning can achieve efficient and accurate drug identification, offering promising application in clinical drug testing and drug enforcement.</p>","PeriodicalId":48957,"journal":{"name":"American Journal of Drug and Alcohol Abuse","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Drug and Alcohol Abuse","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/00952990.2024.2377262","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/19 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"PSYCHOLOGY, CLINICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Background: X-ray absorption spectroscopy (XAS) is a widely used substance analysis technique. It bases on the different absorption coefficients at different energy level to achieve material identification. Additionally, the combination of spectral technology and deep learning can achieve auto detection and high accuracy in material identification.Objectives: Current methods are difficult to identify drugs quickly and nondestructively. Therefore, we explore a novel approach utilizing XAS for the detection of prohibited drugs with common X-ray tube source and photon-counting (PC) detector.Method: To achieve automatic, rapid, and accurate detection of drugs. A CdTe detector and a common X-ray source were used to collect data, then dividing the data into training and testing sets. Finally, the improved transformer encoder model was used for classification. LSTM and ResU-net models are selected for comparation.Result: Fifty substances, which are isomers or compounds with similar molecular formulas of drugs, were selected for experiment substances. The results showed that the improved transformer model achieving 1.4 hours for training time and 96.73% for accuracy, which is better than the LSTM (2.6 hours and 65%) and ResU-net (1.5 hours and 92.7%).Conclusion: It can be concluded that the attention mechanism is more accurate for spectral material identification. XAS combined with deep learning can achieve efficient and accurate drug identification, offering promising application in clinical drug testing and drug enforcement.

X 射线吸收光谱与深度学习相结合,用于自动快速检测非法药物。
背景:X 射线吸收光谱(XAS)是一种广泛应用的物质分析技术。它基于不同能级的不同吸收系数来实现物质识别。此外,光谱技术与深度学习相结合,可实现自动检测,实现物质识别的高准确性:目前的方法难以快速、无损地识别药物。因此,我们利用普通的 X 射线管源和光子计数(PC)探测器,探索一种利用 XAS 检测违禁药物的新方法:方法:实现自动、快速、准确地检测毒品。方法:为了实现自动、快速、准确地检测毒品,使用碲化镉探测器和普通 X 射线管源收集数据,然后将数据分为训练集和测试集。最后,使用改进的变压器编码器模型进行分类。结果:实验物质选取了 50 种物质,它们是药物的同分异构体或分子式相似的化合物。结果表明,改进后的变压器模型训练时间为 1.4 小时,准确率为 96.73%,优于 LSTM(2.6 小时和 65%)和 ResU-net(1.5 小时和 92.7%):可以得出结论,注意力机制在光谱材料识别方面的准确率更高。XAS与深度学习相结合,可以实现高效、准确的药物识别,在临床药物检测和禁毒执法中具有广阔的应用前景。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
4.70
自引率
3.70%
发文量
68
期刊介绍: The American Journal of Drug and Alcohol Abuse (AJDAA) is an international journal published six times per year and provides an important and stimulating venue for the exchange of ideas between the researchers working in diverse areas, including public policy, epidemiology, neurobiology, and the treatment of addictive disorders. AJDAA includes a wide range of translational research, covering preclinical and clinical aspects of the field. AJDAA covers these topics with focused data presentations and authoritative reviews of timely developments in our field. Manuscripts exploring addictions other than substance use disorders are encouraged. Reviews and Perspectives of emerging fields are given priority consideration. Areas of particular interest include: public health policy; novel research methodologies; human and animal pharmacology; human translational studies, including neuroimaging; pharmacological and behavioral treatments; new modalities of care; molecular and family genetic studies; medicinal use of substances traditionally considered substances of abuse.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信