Lab on a Chip, Год журнала: 2024, Номер 24(4), С. 924 - 932
Опубликована: Янв. 1, 2024
Unbiased learning pipeline for label-free single-cell classification.
Язык: Английский
Advanced Science, Год журнала: 2022, Номер 9(34)
Опубликована: Окт. 18, 2022
Identification of novel non-invasive biomarkers is critical for the early diagnosis lung adenocarcinoma (LUAD), especially accurate classification pulmonary nodule. Here, a multiplexed assay developed on an optimized nanoparticle-based laser desorption/ionization mass spectrometry platform sensitive and selective detection serum metabolic fingerprints (SMFs). Integrative SMFs based multi-modal platforms are constructed LUAD The dual modal model, with protein tumor marker neural network (MP-NN), integrating carcinoembryonic antigen (CEA) via deep learning, shows superior performance compared single model Met-NN (p < 0.001). Based MP-NN, tri MPI-RF SMFs, CEA, image features random forest demonstrates significantly higher than clinical models (Mayo Clinic Veterans Affairs) artificial intelligence in nodule would be promising tools screening management, paving conceptual practical foundation application omics tools.
Язык: Английский
Процитировано
49
The Science of The Total Environment, Год журнала: 2022, Номер 815, С. 152708 - 152708
Опубликована: Янв. 3, 2022
Язык: Английский
Процитировано
41
Scientific Reports, Год журнала: 2023, Номер 13(1)
Опубликована: Апрель 13, 2023
Abstract Image-based identification of circulating tumor cells in microfluidic cytometry condition is one the most challenging perspectives Liquid Biopsy scenario. Here we show a machine learning-powered tomographic phase imaging flow system capable to provide high-throughput 3D phase-contrast tomograms each single cell. In fact, that discrimination against white blood potentially achievable with aid artificial intelligence label-free flow-cyto-tomography method. We propose hierarchical learning decision-maker, working on set features calculated from cells’ refractive index. prove morphological are adequately distinctive identify versus cell background first stage and, moreover, recognizing type at second decision step. Proof-of-concept experiments shown, which two different lines, namely neuroblastoma cancer and ovarian cells, used monocytes. The reported results allow claiming success rate higher than 97% an accuracy over discriminating between types, thus opening near future route new tool for detecting classifying by stain-free
Язык: Английский
Процитировано
32
Biochimie, Год журнала: 2024, Номер 220, С. 122 - 143
Опубликована: Янв. 3, 2024
Язык: Английский
Процитировано
10
Nano-Micro Letters, Год журнала: 2021, Номер 13(1)
Опубликована: Март 22, 2021
A zero-reflection-induced phase singularity is achieved through precisely controlling the resonance characteristics using two-dimensional nanomaterials. An atomically thin nano-layer having a high absorption coefficient exploited to enhance zero-reflection dip, which has led subsequent and thus giant lateral position shift. We have improved detection limit of low molecular weight molecules by more than three orders magnitude compared current state-of-art nanomaterial-enhanced plasmonic sensors. Detection small cancer biomarkers with concentration range always been challenging yet urgent in many clinical applications such as diagnosing early-stage cancer, monitoring treatment detecting relapse. Here, highly enhanced biosensor that can overcome this challenge developed change nanomaterial. By engineering configuration materials, successfully significantly shift effect. Based on our knowledge, it first experimental demonstration signal > 340 μm at sensing interface from all optical techniques. With effect, experimentally demonstrated be 10-15 mol L-1 for TNF-α marker, found various human diseases including inflammatory different kinds cancer. The as-reported novel integration Ge2Sb2Te5 substrate, results shift, enables markers femtomolar level. These will definitely hold promising potential biomedical application diagnostics.
Язык: Английский
Процитировано
47
ACS Photonics, Год журнала: 2021, Номер 8(7), С. 2148 - 2157
Опубликована: Июнь 18, 2021
Water plastic pollution is a serious problem affecting sealife, marine habitats, and the food chain. Artificial intelligence-enabled coherent imaging has recently shown exciting advances in field of environmental monitoring, portable holographic microscopes are good candidates to map microparticles content waters. The "holographic fingerprint" due light diffraction rich information, fully encoded into complex wavefront scattered by sample. Hence, proper analysis wavefronts reconstructed from digital holograms can unlock new possibilities fields diagnostics monitoring. Fractal geometry well describes natural objects allows inferring added-value information on way these fill 2D spaces 3D volumes. most abundant micron-scale class that populate waters consists microalgae named diatoms, which interest as bioindicators water quality. Here we investigate fractal properties patterns diatoms microplastics, considering heterogeneous mixture five types materials 55 different species microalgae. We show that, case weak scattering objects, small set parameters able characterize two large ensembles. As an applicative example, carry out classification tests possibility identify classes with high accuracy. This description micro-objects could be used near future for situ automatic mapping microplastic pollutants taxonomy quality bioindicators, screened onboard systems.
Язык: Английский
Процитировано
45
Journal of Materials Chemistry B, Год журнала: 2021, Номер 9(17), С. 3622 - 3639
Опубликована: Янв. 1, 2021
This comprehensive review highlights the recent research on a material-assisted mass spectrometric analysis of low molecular weight compounds, including material types, preparation approaches, and biomedical applications.
Язык: Английский
Процитировано
44
Biosensors and Bioelectronics, Год журнала: 2022, Номер 201, С. 113945 - 113945
Опубликована: Янв. 4, 2022
Язык: Английский
Процитировано
35
Deleted Journal, Год журнала: 2022, Номер 3(1), С. 151 - 151
Опубликована: Янв. 1, 2022
The appearance of the first laser approximately 12 years after invention holography by Gabor (1948) revolutionized field optical metrology. In fact, holographic interferometry enabled exploitation on non-mirror surfaces and full-scale objects. holography-based measurement methods has been implemented to several industrial systems or in support R&D with aim improving new products many fields (automotive, aerospace, electronics, etc.). To date, considered an important tool for non-destructive inspection (NDI), strain-stress measurement, vibration analysis at various engineering sites. Recently, paradigm Industry4.0 seen introduction technologies processing materials as well development manufacturing approaches realization innovative products. For example, direct printing, additive, bottom-up processes are expected involve ways making future, most fabrication will be based manipulation soft matter (e.g., starting from liquid phase) that shaped nanoscale. inherent characteristics digital (DH) make it a powerful accurate visualization testing final products, situ real-time monitoring quantitative characterization involved during cycle. This review aims report useful applications matter, where capabilities offered DH, such three-dimensional (3D) imaging, extended focus, 3D tracking, full-field analysis, high sensitivity, wide range measurements nanometers centimeters, permit completely non-invasive characterizations full-scale. Several experimental results typical samples reported discussed DH plays primary role gauge matter.
Язык: Английский
Процитировано
32
Small, Год журнала: 2020, Номер 16(46)
Опубликована: Окт. 26, 2020
Abstract Monitoring milk quality is of fundamental importance in food industry, because the nutritional value and resulting position daily diet. The detection small nutrients toxins challenging, considering high sample complexity low analyte abundance. In addition, slow analysis tedious preparation hinder large‐scale application conventional techniques. Herein, zirconia hybrid nanoshells are constructed to enhance performance laser desorption/ionization mass spectrometry (LDI MS). Zirconia with optimized structures compositions used as matrices LDI MS achieve direct molecules from 5 nL native ≈1 min, without any purification or separation. Accurate quantitation nutrient achieved by introducing isotope into nanoshell‐assisted internal standard, offering good consistency biochemical (BCA) R 2 = 0.94. Further, trace toxin enriched identified limit‐of‐detection (LOD) down 4 p m , outperforming current analytical methods. This work sheds light on personalized design material‐based tool for real‐case bioanalysis opens up new opportunities simple, fast, cost‐effective various a broad field.
Язык: Английский
Процитировано
43