Food waste is one of the main problems contributing to climate change, as its piling up in landfills produces the greenhouse gas methane. Food waste occurs at every stage of food production; however, a major source of food waste occurs at businesses that supply food to consumers. Industry 4.0 technologies have shown promise in helping to reduce food waste in food supply chains. However, more innovative technologies, such as Raman spectroscopy, hold great promise in helping to reduce food waste, although this has largely been ignored in the literature. In this context, we propose a portable Raman platform to monitor food quality during transportation. The developed system was tested in conditions mimicking those present in a refrigerated truck by analyzing chicken samples stored at temperatures of 4 °C. Raman spectra were acquired for non-packaged and packaged samples over the duration of 30 days resulting in 6000 spectra. The analysis of Raman spectra revealed that the system was able to detect noticeable changes in chicken quality starting on day six. The main Raman bands contributing to this change are amide I and tyrosine. The proposed system will offer the potential to reduce food losses during transportation by consistently checking the food quality over time.

/pdf/raman-spectroscopy-application-in-food-waste-analysis-a-step-lljdmx88.pdf

Raman Spectroscopy Application in Food Waste Analysis: A Step towards a Portable Food Quality-Warning System

In the QuantERA project QURAMAN (Quantum Raman) are we aiming for a combination of breakthroughs and improvements of existing components and already existing setups for building a commercial quantum Raman microscope. By combining the project partners’ expertise and skills in quantum optics, nonlinear optics, Raman spectroscopy and medical device design we will develop the next-generation Raman microscope for bio-imaging with quantum-enhanced sensitivity. The background knowledge and idea behind the QuRAMAN project is described in our recent publications (Optica 7, 470-475 (2020)). Where we have demonstrated that the use of continuous wave (CW) squeezed light can improve the SNR of weak Raman signals. However, to beat the performance of state-of-the-art SRS microscopes by means of squeezed light, one must employ amplitude squeezed picosecond pulses in a strongly focusing configuration (using an objective with a numerical aperture above unity). This will enable the imaging of weak Raman features and will push the Raman technology beyond the state of the art by applying pulsed amplitude squeezed light for signal enhancement.

Towards quantum-enhanced Raman spectroscopy for bioimaging applications

Tuberculosis (TB) is the world's deadliest infectious disease, with 1.5 million annual deaths and half a million annual infections. Rapid TB diagnosis and antibiotic susceptibility testing (AST) are critical to improve patient treatment and to reduce the rise of new drug resistance. Here, we develop a rapid, label-free approach to identify Mycobacterium tuberculosis (Mtb) strains and antibiotic-resistant mutants. We collect over 20,000 single-cell Raman spectra from isogenic mycobacterial strains each resistant to one of the four mainstay anti-TB drugs (isoniazid, rifampicin, moxifloxacin and amikacin) and train a machine-learning model on these spectra. On dried TB samples, we achieve > 98% classification accuracy of the antibiotic resistance profile, without the need for antibiotic co-incubation; in dried patient sputum, we achieve average classification accuracies of ~ 79%. We also develop a low-cost, portable Raman microscope suitable for field-deployment of this method in TB-endemic regions. 

Predicting tuberculosis drug resistance with machine learning-assisted Raman spectroscopy.

Our research should be seen in the light of the worldwide increase of antimicrobial resistance (AMR), which is a serious threat to human health. To prevent the spread of AMR, fast reliable diagnostics tools that facilitate optimal antibiotic stewardship are of urgent need. Raman spectroscopy (RS) is a promising tool for rapid label- and culture-free identification and antimicrobial susceptibility testing (AST) in a single step. To take full advantage of RS for bacterial identification machine learning (ML) analysis is essential. Many limitations must be addressed before RS will be a practical platform for point-of-care diagnostics applications in clinics and hospitals. RS is sensitive to factors such as the growth stage, changes in measurement environment and inconsistency in sample preparation. We address the issues of sample preparation, changes in measurement environment and limited data availability. We reduce sample preparation to merely transferring the bacteria to the measurement environment, hereby minimizing the issue of sample inconsistency and the additional benefit of removing sample preparation. To alleviate the situation of limited data availability for ML model training, we have developed a novel spectral transformer (ST) ML model that is efficient after training on both small- and large RS bacteria datasets. We explicit demonstrated that our ST outperforms a state-of-the-art domain-specific residual CNN both in terms of accuracy with 7.5%. Where we attain more than 96% classification accuracy on a dataset consisting of 15 different classes and 95.6% classification accuracy for six MR–MS bacteria species.

Accurate identification of bacteria in a minimally prepared environment using Raman spectroscopy assisted by machine learning

Rapid and accurate detection of microorganisms is critical to clinical diagnosis. As Raman spectroscopy promises label-free and culture-free detection of biomedical objects, it holds the potential to rapidly identify microorganisms in a single step. To stabilize the microorganism for spectrum collection and to increase the accuracy of real-time identification, we propose an optofluidic method for single microorganism detection in microfluidics using optical-tweezing-based Raman spectroscopy with artificial neural network. A fiber optical tweezer was incorporated into a microfluidic channel to generate optical forces that trap different species of microorganisms at the tip of the tweezer and their Raman spectra were simultaneously collected. An artificial neural network was designed and employed to classify the Raman spectra of the microorganisms, and the identification accuracy reached 94.93%. This study provides a promising strategy for rapid and accurate diagnosis of microbial infection on a lab-on-a-chip platform. 

https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/bmm2.12007

Optofluidic identification of single microorganisms using fiber‐optical‐tweezer‐based Raman spectroscopy with artificial neural network

Abstract The worldwide increase of antimicrobial resistance (AMR) is a serious threat to human health. To avert the spread of AMR, fast reliable diagnostics tools that facilitate optimal antibiotic stewardship are an unmet need. In this regard, Raman spectroscopy promises rapid label- and culture-free identification and antimicrobial susceptibility testing (AST) in a single step. However, even though many Raman-based bacteria-identification and AST studies have demonstrated impressive results, some shortcomings must be addressed. To bridge the gap between proof-of-concept studies and clinical application, we have developed machine learning techniques in combination with a novel data-augmentation algorithm, for fast identification of minimally prepared bacteria phenotypes and the distinctions of methicillin-resistant (MR) from methicillin-susceptible (MS) bacteria. For this we have implemented a spectral transformer model for hyper-spectral Raman images of bacteria. We show that our model outperforms the standard convolutional neural network models on a multitude of classification problems, both in terms of accuracy and in terms of training time. We attain more than 96% classification accuracy on a dataset consisting of 15 different classes and 95.6% classification accuracy for six MR–MS bacteria species. More importantly, our results are obtained using only fast and easy-to-produce training and test data. 

/pdf/accurate-and-fast-identification-of-minimally-prepared-1ywg4la9.pdf

B. Thomsen

Papers

Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning

Accurate identification of bacteria in a minimally prepared environment using Raman spectroscopy assisted by machine learning