Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

He, Hao; Yan, Sen; Lyu, Danya; Xu, Mengxi; Ye, Ruiqian; Zheng, Peng; Lu, Xinyu; Wang, Lei; Ren, Bin

doi:10.1021/acs.analchem.0c04671

Cited by 77 publications

(63 citation statements)

References 151 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the specific case studied here, the possibility of locating the presence of C. auris clades with a conspicuously reduced identification time could allow a prompt selection of the most appropriate cure. In line with the present state of the art in deep learning applied to biospectroscopy and biospectral imaging (He et al, 2021), we have proposed here a reliable and versatile Raman method to locate subtle variations and hidden features within big data collected on different Candida clades. Once translated into clinical practice, the speed of the presented Raman approach will provide a significant advantage for all those patients at immunological risk, who have limited ability to fight invasive fungal infections.…”

Section: Importance Of the Raman Approach To Candida Species Differentiationmentioning

confidence: 92%

Raman Imaging of Pathogenic Candida auris: Visualization of Structural Characteristics and Machine-Learning Identification

et al. 2021

View full text Add to dashboard Cite

Invasive fungal infections caused by yeasts of the genus Candida carry high morbidity and cause systemic infections with high mortality rate in both immunocompetent and immunosuppressed patients. Resistance rates against antifungal drugs vary among Candida species, the most concerning specie being Candida auris, which exhibits resistance to all major classes of available antifungal drugs. The presently available identification methods for Candida species face a severe trade-off between testing speed and accuracy. Here, we propose and validate a machine-learning approach adapted to Raman spectroscopy as a rapid, precise, and labor-efficient method of clinical microbiology for C. auris identification and drug efficacy assessments. This paper demonstrates that the combination of Raman spectroscopy and machine learning analyses can provide an insightful and flexible mycology diagnostic tool, easily applicable on-site in the clinical environment.

show abstract

Section: Importance Of the Raman Approach To Candida Species Differentiationmentioning

confidence: 92%

Raman Imaging of Pathogenic Candida auris: Visualization of Structural Characteristics and Machine-Learning Identification

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, the evolution of artificial intelligence (AI) provided a boost in real-time Raman data processing. The combination of AI tools with Raman spectroscopy can efficiently lead to adequate discrimination of cancerous tissues [ 57 ]. Machine learning (ML) and Deep learning (DL) constitute branches of the broader division of Artificial Intelligence (AI) [ 58 ].…”

Section: Machine Learning and Deep Learning As Tools Towards Raman Sp...mentioning

confidence: 99%

Raman Spectroscopy: A Personalized Decision-Making Tool on Clinicians’ Hands for In Situ Cancer Diagnosis and Surgery Guidance

Kouri

Spyratou

Karnachoriti

et al. 2022

Cancers

View full text Add to dashboard Cite

Accurate in situ diagnosis and optimal surgical removal of a malignancy constitute key elements in reducing cancer-related morbidity and mortality. In surgical oncology, the accurate discrimination between healthy and cancerous tissues is critical for the postoperative care of the patient. Conventional imaging techniques have attempted to serve as adjuvant tools for in situ biopsy and surgery guidance. However, no single imaging modality has been proven sufficient in terms of specificity, sensitivity, multiplexing capacity, spatial and temporal resolution. Moreover, most techniques are unable to provide information regarding the molecular tissue composition. In this review, we highlight the potential of Raman spectroscopy as a spectroscopic technique with high detection sensitivity and spatial resolution for distinguishing healthy from malignant margins in microscopic scale and in real time. A Raman spectrum constitutes an intrinsic “molecular finger-print” of the tissue and any biochemical alteration related to inflammatory or cancerous tissue state is reflected on its Raman spectral fingerprint. Nowadays, advanced Raman systems coupled with modern instrumentation devices and machine learning methods are entering the clinical arena as adjunct tools towards personalized and optimized efficacy in surgical oncology.

show abstract

“…To address this issue, we developed a machine-learning-based image processing method using convolutional neural network (CNN) visualization for particle counting (named “CNN method”). 44 − 46 Figure 2 a shows the algorithm architecture of the CNN method. It involves dark-field image data read-in/preprocessing (including noise filtering and contrast enhancement), detection signal/background image segmentation by pretrained CNN, postprocessing, and result output.…”

Section: Resultsmentioning

confidence: 99%

Machine-Learning-Assisted Microfluidic Nanoplasmonic Digital Immunoassay for Cytokine Storm Profiling in COVID-19 Patients

et al. 2021

View full text Add to dashboard Cite

Cytokine storm, known as an exaggerated hyperactive immune response characterized by elevated release of cytokines, has been described as a feature associated with life-threatening complications in COVID-19 patients. A critical evaluation of a cytokine storm and its mechanistic linkage to COVID-19 requires innovative immunoassay technology capable of rapid, sensitive, selective detection of multiple cytokines across a wide dynamic range at high-throughput. In this study, we report a machine-learning-assisted microfluidic nanoplasmonic digital immunoassay to meet the rising demand for cytokine storm monitoring in COVID-19 patients. Specifically, the assay was carried out using a facile one-step sandwich immunoassay format with three notable features: (i) a microfluidic microarray patterning technique for high-throughput, multiantibody-arrayed biosensing chip fabrication; (ii) an ultrasensitive nanoplasmonic digital imaging technology utilizing 100 nm silver nanocubes (AgNCs) for signal transduction; (iii) a rapid and accurate machine-learning-based image processing method for digital signal analysis. The developed immunoassay allows simultaneous detection of six cytokines in a single run with wide working ranges of 1–10,000 pg mL–1 and ultralow detection limits down to 0.46–1.36 pg mL–1 using a minimum of 3 μL serum samples. The whole chip can afford a 6-plex assay of 8 different samples with 6 repeats in each sample for a total of 288 sensing spots in less than 100 min. The image processing method enhanced by convolutional neural network (CNN) dramatically shortens the processing time ∼6,000 fold with a much simpler procedure while maintaining high statistical accuracy compared to the conventional manual counting approach. The immunoassay was validated by the gold-standard enzyme-linked immunosorbent assay (ELISA) and utilized for serum cytokine profiling of COVID-19 positive patients. Our results demonstrate the nanoplasmonic digital immunoassay as a promising practical tool for comprehensive characterization of cytokine storm in patients that holds great promise as an intelligent immunoassay for next generation immune monitoring.

show abstract

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

Cited by 77 publications

References 151 publications

Raman Imaging of Pathogenic Candida auris: Visualization of Structural Characteristics and Machine-Learning Identification

Raman Imaging of Pathogenic Candida auris: Visualization of Structural Characteristics and Machine-Learning Identification

Raman Spectroscopy: A Personalized Decision-Making Tool on Clinicians’ Hands for In Situ Cancer Diagnosis and Surgery Guidance

Machine-Learning-Assisted Microfluidic Nanoplasmonic Digital Immunoassay for Cytokine Storm Profiling in COVID-19 Patients

Contact Info

Product

Resources

About