High Resolution of Plasmonic Resonance Scattering Imaging with Deep Learning

Song, Ming Ke; Peng, Yun; Liu, Hui; Hu, Ping; Huang, Chengzhi; Zhou, Jun

doi:10.1021/acs.analchem.1c04330

Cited by 10 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For complex image changes involved in technologies such as SPRM, artificial neural networks, the main workhorse in deep learning and computer vision, appear to augment the whole process. [202,210] In 2019, Kim et al proposed a convolutional neural network (CNN) in SPRM to tackle the problem of simultaneous imaging of multiple scatterers (up to 9). [211] 10000 SPM images of randomly distributed scattering particles were divided into the set of training (70%), validation (15%), and test (15%).…”

Section: Machine Learning-driven Data Analyticsmentioning

confidence: 99%

Refractometric Imaging and Biodetection Empowered by Nanophotonics

Geng

Shum

et al. 2023

Laser & Photonics Reviews

View full text Add to dashboard Cite

Advancing clinical and nonclinical diagnostic technologies is particularly crucial for improved preparedness for the next pandemic and other global healthcare challenges. To this end, marrying advanced microscopic imaging with chip‐scale bioanalytical systems provides fresh modalities by analyzing signals of transmitted, reflected, or scattered light waves. This review brings clarity to the latest progress of refractometric imaging and biodetections on a chip, in which interferences and resonances as cornerstones of optics and plasmonics are breaking new ground. A vast range of nanophotonic and plasmonic transducers are discussed, ranging from planar films, nanoarrays, and waveguiding resonators to holistic designs. The augmented bioanalyses cover immunoassays, single‐molecule analysis, and motion tracking of bacterial pathogens and cells. Compared to single‐point spectroscopic measurements, imaging‐empowered approaches are rapidly evolving with greatly promoted signal‐noise ratio, spatial‐temporal resolutions, multiplexability, and throughput, which can be accomplished in a compact cradle system with minimized bulky components in a spectrometer‐free manner. Besides, advances in machine learning technologies applied for data analytics and transducer designs are highlighted. All in all, there are unlimited opportunities for new optical structures, principles, and ways of data retrieval to tap in, which will raise technological impacts on unveiling fundamental issues in life science and advancing global healthcare technologies.

show abstract

Section: Machine Learning-driven Data Analyticsmentioning

confidence: 99%

Refractometric Imaging and Biodetection Empowered by Nanophotonics

Geng

Shum

et al. 2023

Laser & Photonics Reviews

View full text Add to dashboard Cite

show abstract

“…Additionally, we aim to use a more efficient approach to establish these relationships . In recent years, deep learning has become one of the most widely used methods for image processing. − This popularity is primarily due to the deeper network structures of deep learning models, which allow them to extract more complex and abstract feature representations from images, utilizing richer image information to establish accurate regression relationships. − However, the multilayered network structures of deep learning models result in a large number of internal parameters that require adjustment through extensive data. Furthermore, the complexity of these models often leads to overfitting.…”

Section: Introductionmentioning

confidence: 99%

Efficient and Accurate pH Determination with pH Test Strips Based on Machine Learning

Xiong,

Ma,

Liu

et al. 2024

Anal. Chem.

Self Cite

View full text Add to dashboard Cite

The determination of pH values is crucial in various fields, such as analytical chemistry, medical diagnostics, and biochemical research. pH test strips, renowned for their convenience and cost-effectiveness, are commonly utilized for pH qualitative estimation. Recently, quantitative methods for determining pH values using pH test strips have been developed. However, these methods can be prone to errors due to environmental factors, such as lighting conditions, which affect the imaging quality of the pH test strips. To address these challenges, we developed an innovative approach that combines machine learning techniques with pH test strips for the quantitative determination of pH values. Our method involves extracting artificial features from the pH test strip images and combining them across multiple dimensions for comprehensive analysis. To ensure optimal feature selection, we developed a feature selection strategy based on SHAP importance. This strategy helps in identifying the most relevant features that contribute to accurate pH prediction. Furthermore, we integrated multiple machine learning algorithms, employing a robust stacking fusion strategy to establish a highly reliable pH value prediction model. Our proposed method automates the determination of pH values through pH test strips, effectively overcoming the limitations associated with environmental lighting interference. Experimental results demonstrate that this method is convenient, effective, and highly reliable for the determination of pH values.

show abstract

“…It is difficult to avoid random selection and obtain representative particles for single particle analysis with high confidence. In recent years, machine learning has been successfully used to analyze the patterns hidden in data. − By introducing machine learning in single particle analysis, it is possible to select particles that are both representative and diverse by analyzing a huge amount of data. It can significantly reduce errors caused by particle selection and better reveal reaction mechanisms.…”

Section: Introductionmentioning

confidence: 99%

High Confidence Single Particle Analysis with Machine Learning

Wu,

Ma,

Liu

et al. 2023

Anal. Chem.

Self Cite

View full text Add to dashboard Cite

Single particle analysis can effectively determine the heterogeneity between particles based on the local information on a single particle, which is utilized extensively for monitoring chemical reactions and biological activities. However, the study of obtaining ensemble reaction information at the single particle level, which can obtain both the structural and functional heterogeneity of particles as well as the ensemble reaction information, is challenging because the selection of a single particle mainly depends on experience, which will lead to a certain randomness when analyzing the ensemble reaction with single particles. Using machine learning, it is demonstrated that the proposed intelligent single particle analysis strategy can provide single particle and ensemble analyses with high confidence. Convolutional neural network and Gaussian mixture model were utilized to develop a machine learning model for resonance scattering imaging analysis of plasmonic nanoparticles. It can identify the scattered light of single particles and select representative or diverse particles. When single particle scattering imaging is used to obtain ensemble information on the reaction, the error caused by the selection of individual particles can be significantly reduced by selecting representative particles. In addition, the real situation of the reaction can be better revealed by selecting diverse particles. These results indicate that the intelligent single particle analysis strategy has great potential for imaging analysis and biological sensing.

show abstract

High Resolution of Plasmonic Resonance Scattering Imaging with Deep Learning

Cited by 10 publications

References 32 publications

Refractometric Imaging and Biodetection Empowered by Nanophotonics

Refractometric Imaging and Biodetection Empowered by Nanophotonics

Efficient and Accurate pH Determination with pH Test Strips Based on Machine Learning

High Confidence Single Particle Analysis with Machine Learning

Contact Info

Product

Resources

About