Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

Procházka, David; Mazura, M.P.; Samek, Ota; Rebrošová, Katarína; Pořízka, Pavel; Klus, Jakub; Procházková, Petra; Novotný, Jan; Novotný, Karel; Kaiser, Jozef

doi:10.1016/j.sab.2017.11.004

Cited by 55 publications

(29 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, a recent study reported the combination of LIBS and Raman spectroscopy for the classification of bacteria. 11 For the case of melanoma, we reported in our recent study that melanoma and surrounding dermis could be distinguished by LIBS with high sensitivity using Mg and Ca emission peaks as the biomarkers. 12 Although it was an early stage of research yet, this study confirmed that LIBS can be an effective method to identify melanoma from normal tissue.…”

Section: Introductionmentioning

confidence: 99%

Mapping of cutaneous melanoma by femtosecond laser-induced breakdown spectroscopy

et al. 2018

View full text Add to dashboard Cite

Surgical excision (Mohs micrographic surgery) is the standard procedure to treat a melanoma, in which an in situ histologic examination of sectioned skin is carried out repeatedly until no cancer cells are detected. The possibility to identify melanoma from the surrounding skin by femtosecond laser-induced breakdown spectroscopy (fs-LIBS) is investigated. For experiments, melanoma induced on a hairless mouse by injection of B16/F10 murine melanoma cell was sampled in the form of frozen tissue sections as in Mohs surgery and analyzed by fs-LIBS (λ ¼ 1030 nm, τ ¼ 550 fs). For analysis, the magnesium signal normalized by carbon intensity was utilized to construct an intensity map around the cancer, including both melanoma and surrounding dermis. The intensity map showed a close match to the optically observed morphological and histological features near the cancer region. The results showed that when incorporated into the existing micrographic surgery procedure, fs-LIBS could be a useful tool for histopathologic interpretation of skin cancer possibly with significant reduction of histologic examination time.

show abstract

Section: Introductionmentioning

confidence: 99%

Mapping of cutaneous melanoma by femtosecond laser-induced breakdown spectroscopy

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The NN models indicated that LIBS could possibly be as sensitive or more sensitive than other methods available at the time. The study of NN models continues today [36,53,54] with many variants of the technique possible, including the use of a K-means classifier on the full-spectrum LIBS data for the discrimination of E. coli from S. aureus [55] and the use of a supervised technique utilizing self-organizing maps (SOM) upon spectra that were first preprocessed in a PCA [56]. In this last, while the first five PC's were seen to only retain 23% of the variance in the data, a plot of the scores of the first two PC's showed a fairly consistent discrimination between Staphylococcus sciuri, S. aureus, and E. coli.…”

Section: Neural Network/support Vector Machinesmentioning

confidence: 99%

“…Many authors have attempted to ablate live bacterial cells from culture directly on the surface of the growth medium (some form of culturing agar) used to grow them [43,53,54,56,66]. The approach is complicated as the colony produced during culturing is not controlled for size or cell number, is not "washed" clean of growth medium contaminants prior to ablation, and lacks the mechanical stability or rigidity required for high shot-to-shot repeatability.…”

Section: Aerosolsmentioning

confidence: 99%

A review of the use of laser-induced breakdown spectroscopy for bacterial classification, quantification, and identification

Rehse

2019

Spectrochimica Acta Part B: Atomic Spectroscopy

View full text Add to dashboard Cite

The use of laser-induced breakdown spectroscopy to determine the elemental composition of bacterial cells has been described in the peer-reviewed literature since 2003. Fifteen years on, significant accomplishments have been reported that have served to clarify and underscore the areas of bacteriological investigation that LIBS is well-suited for as well as the challenges that yet remain to be faced. This review will attempt to summarize the state of the field by surveying the available body of knowledge. The early days of these experiments, roughly from 2003 to 2007, in which many of the most fundamental experiments were initially conducted will be described. The more in-depth investigations that followed in the subsequent decade will then be detailed. Many important aspects of performing LIBS on bacterial cells were reported on and are summarized here including: the use of chemometric algorithms for statistical classification of unknown spectra; the influence of the mounting substrate on classification; the effect of the testing gas atmosphere and the choice of bacterial cell growth nutrient medium on the measured LIBS spectrum; the efficacy of a LIBS-based test as a genus-level or strainlevel discrimination test; the ability of LIBS to determine the cell titer or concentration of cells in the initial sample; the effects that possible contaminations or interferents within the sample would have on the LIBS spectrum; the influence that environmental stresses the cells may be exposed to during growth and the state of reproductive health of the cells could have on the LIBS spectrum; the use of standoff or remote apparatus to minimize the risk to the operators during bacteriological identification of unknown specimens; and the combination of other optical modalities with LIBS to enhance the sensitivity or specificity of identification. Lastly, tables are provided which summarize both every species of bacteria ever tested with LIBS as well as the major lessons learned by the community through 15 years of careful investigation. laser-induced breakdown spectroscopy; pathogens; bacteria

show abstract

“…LIBS spectra are usually complex and noisy signals, and conventional machine learning methods have proven to be effective in dealing with such data [13,14]. On one hand, three traditional supervised classification methods for performing multivariate classification, including support vector machine (SVM), radial basis function neural network (RBFNN), and extreme learning machine (ELM), were used to identify the spectral features of grape seeds in this study.…”

Section: Introductionmentioning

confidence: 99%

Discrimination of Grape Seeds Using Laser-Induced Breakdown Spectroscopy in Combination with Region Selection and Supervised Classification Methods

Zhao

Zhang

et al. 2020

Foods

View full text Add to dashboard Cite

The wine-making industry generates a considerable amount of grape pomace. Grape seeds, as an important part of pomace, are rich in bioactive compounds and can be reutilized to produce useful derivatives. The nutritional properties of grape seeds are largely influenced by the cultivar, which calls for effective identification. In the present work, the spectral profiles of grape seeds belonging to three different cultivars were collected by laser-induced breakdown spectroscopy (LIBS). Three conventional supervised classification methods and a deep learning method, a one-dimensional convolutional neural network (CNN), were applied to establish discriminant models to explore the relationship between spectral responses and cultivar information. Interval partial least squares (iPLS) algorithm was successfully used to extract the spectral region (402.74–426.87 nm) relevant for elemental composition in grape seeds. By comparing the discriminant models based on the full spectra and the selected spectral regions, the CNN model based on the full spectra achieved the optimal overall performance, with classification accuracy of 100% and 96.7% for the calibration and prediction sets, respectively. This work demonstrated the reliability of LIBS as a rapid and accurate approach for identifying grape seeds and will assist in the utilization of certain genotypes with desirable nutritional properties essential for production rather than their being discarded as waste.

show abstract

Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

Cited by 55 publications

References 22 publications

Mapping of cutaneous melanoma by femtosecond laser-induced breakdown spectroscopy

Mapping of cutaneous melanoma by femtosecond laser-induced breakdown spectroscopy

A review of the use of laser-induced breakdown spectroscopy for bacterial classification, quantification, and identification

Discrimination of Grape Seeds Using Laser-Induced Breakdown Spectroscopy in Combination with Region Selection and Supervised Classification Methods

Contact Info

Product

Resources

About