Rapid species identification of pathogenic bacteria from a minute quantity exploiting three-dimensional quantitative phase imaging and artificial neural network.
Rapid species identification of pathogenic bacteria from a minute quantity exploiting three-dimensional quantitative phase imaging and artificial neural network.
复制标题
DOI：
10.1038/s41377-022-00881-x
复制
发表时间：
2022-06-23
影响因子：
19.4
通讯作者：
Park, YongKeun
中科院分区：
文献类型：
--
作者：
Kim, Geon;Ahn, Daewoong;Kang, Minhee;Park, Jinho;Ryu, DongHun;Jo, YoungJu;Song, Jinyeop;Ryu, Jea Sung;Choi, Gunho;Chung, Hyun Jung;Kim, Kyuseok;Chung, Doo Ryeon;Yoo, In Young;Huh, Hee Jae;Min, Hyun-seok;Lee, Nam Yong;Park, YongKeun
医疗保健行业迫切需要快速的微生物鉴定技术来治疗微生物感染。微生物感染是世界范围内的一个主要卫生保健问题，因为这些广泛传播的疾病经常发展成致命的症状。虽然研究表明，早期适当的抗生素治疗可显著降低感染的死亡率，但这种有效的治疗方法很难实施。早期适当抗生素治疗的主要障碍是常规微生物鉴定的周转时间长，其中包括耗时的样品生长。在这里，我们提出了一个基于显微镜的框架，从单个细胞到少数细胞识别病原体。我们的框架通过结合三维定量相位成像和人工神经网络来获取和利用有限样品的形态。我们展示了19种导致血液感染的细菌的鉴定，从单个细菌细胞或集群中获得了82.5%的准确性。在足够的样品量下，这种性能可与金标准质谱相媲美，巩固了我们的框架在临床应用中的有效性。此外，我们的精度随着多次测量而增加，在7次不同的细胞或簇测量中达到99.9%。我们相信，我们的框架可以作为一个有益的咨询工具，为临床医生在初期治疗感染。基于细菌种类的无标签快速深度学习识别，将3D折射率断层图分类为物种。
The healthcare industry is in dire need of rapid microbial identification techniques for treating microbial infections. Microbial infections are a major healthcare issue worldwide, as these widespread diseases often develop into deadly symptoms. While studies have shown that an early appropriate antibiotic treatment significantly reduces the mortality of an infection, this effective treatment is difficult to practice. The main obstacle to early appropriate antibiotic treatments is the long turnaround time of the routine microbial identification, which includes time-consuming sample growth. Here, we propose a microscopy-based framework that identifies the pathogen from single to few cells. Our framework obtains and exploits the morphology of the limited sample by incorporating three-dimensional quantitative phase imaging and an artificial neural network. We demonstrate the identification of 19 bacterial species that cause bloodstream infections, achieving an accuracy of 82.5% from an individual bacterial cell or cluster. This performance, comparable to that of the gold standard mass spectroscopy under a sufficient amount of sample, underpins the effectiveness of our framework in clinical applications. Furthermore, our accuracy increases with multiple measurements, reaching 99.9% with seven different measurements of cells or clusters. We believe that our framework can serve as a beneficial advisory tool for clinicians during the initial treatment of infections. Label-free rapid deep-learning-based identification of bacterial species that classifies 3D refractive index tomograms into the species.
登录
查看更多内容
影响因子：
10.4
作者：
Horstmeyer R;Chung J;Ou X;Zheng G;Yang C
通讯作者：
Yang C
影响因子：
4.6
作者：
Chen CL;Mahjoubfar A;Tai LC;Blaby IK;Huang A;Niazi KR;Jalali B
通讯作者：
Jalali B
影响因子：
21.3
作者：
Jo, YoungJu;Cho, Hyungjoo;Park, YongKeun
通讯作者：
Park, YongKeun
影响因子：
4.6
作者：
Bhattacharya A;Cui Y
通讯作者：
Cui Y
影响因子：
4.1
作者：
Hoyer, Juliane;Bartel, Juergen;Becher, Doerte
通讯作者：
Becher, Doerte