Neural Network‐Enabled Multiparametric Impedance Signal Templating for High throughput Single‐Cell Deformability Cytometry Under Viscoelastic Extensional Flows DOI Creative Commons

Javad Jarmoshti,

Abdullah‐Bin Siddique,

Aditya Rane

et al.

Small, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 22, 2024

Abstract Cellular biophysical metrics exhibit systematic alterations during processes, such as metastasis and immune cell activation, which can be used to identify separate live subpopulations for targeting drug screening. Image‐based cytometry under extensional flows accurately quantify deformability based on shape but needs extensive image reconstruction, limits its inline utilization activate sorting. Impedance measure these electric field screening, while frequency response offers functional information viability interior structure, are difficult discern by imaging. Furthermore, 1‐D temporal impedance signal trains characteristic shapes that rapidly templated in near real‐time extract single‐cell We present a multilayer perceptron neural network templating approach utilizes raw signals from cells flow, alongside training with corresponding derive net electrical anisotropy over wide ranges minimal errors size distributions. Deformability physiology applied conjunction the same multiparametric classification of pancreatic cancer versus associated fibroblasts using support vector machine model.

Language: Английский

Advancing Healthcare: Synergizing Biosensors and Machine Learning for Early Cancer Diagnosis DOI Creative Commons
Mahtab Kokabi, Muhammad Nabeel Tahir, Darshan Singh

et al.

Biosensors, Journal Year: 2023, Volume and Issue: 13(9), P. 884 - 884

Published: Sept. 13, 2023

Cancer is a fatal disease and significant cause of millions deaths. Traditional methods for cancer detection often have limitations in identifying the its early stages, they can be expensive time-consuming. Since typically lacks symptoms only detected at advanced it crucial to use affordable technologies that provide quick results point care diagnosis. Biosensors target specific biomarkers associated with different types offer an alternative diagnostic approach care. Recent advancements manufacturing design enabled miniaturization cost reduction point-of-care devices, making them practical diagnosing various diseases. Furthermore, machine learning (ML) algorithms been employed analyze sensor data extract valuable information through statistical techniques. In this review paper, we details on how contribute ongoing development processing techniques biosensors, which are continually emerging. We also used along comparison performance ML sensing modalities terms classification accuracy.

Language: Английский

Citations

24
Progressive Approaches in Oncological Diagnosis and Surveillance: Real‐Time Impedance‐Based Techniques and Advanced Algorithms DOI
Viswambari Devi Ramaswamy, Michael Keidar

Bioelectromagnetics, Journal Year: 2025, Volume and Issue: 46(1)

Published: Jan. 1, 2025

ABSTRACT Cancer remains a formidable global health challenge, necessitating the development of innovative diagnostic techniques capable early detection and differentiation tumor/cancerous cells from their healthy counterparts. This review focuses on confluence advanced computational algorithms with noninvasive, label‐free impedance‐based biophysical methodologies—techniques that assess biological processes directly without need for external markers or dyes. elucidates diverse array state‐of‐the‐art technologies, illuminating distinct electrical signatures inherent to cancer vs tissues. Additionally, study probes transformative potential these modalities in recalibrating personalized treatment paradigms. These offer real‐time insights into tumor dynamics, paving way precision‐guided therapeutic interventions. By emphasizing quest continuous vivo monitoring, herald pivotal advancement overarching endeavor combat globally.

Language: Английский

Citations

1
Convolutional Neural Network-Driven Impedance Flow Cytometry for Accurate Bacterial Differentiation DOI

Shuaihua Zhang,

Ziyu Han,

H. Jerry Qi

et al.

Analytical Chemistry, Journal Year: 2024, Volume and Issue: 96(11), P. 4419 - 4429

Published: March 6, 2024

Impedance flow cytometry (IFC) has been demonstrated to be an efficient tool for label-free bacterial investigation obtain the electrical properties in real time. However, accurate differentiation of different species bacteria by IFC technology remains a challenge owing insignificant differences data. Here, we developed convolutional neural networks (ConvNet) deep learning approach enhance accuracy and efficiency toward distinguishing various bacteria. First, more than 1 million sets impedance data (comprising 42 characteristic features each set) groups were trained ConvNet model. To improve analysis, Spearman correlation coefficient mean decrease random forest algorithm introduced eliminate feature interaction extract opacity related wall membrane structure as predominant differentiation. Moreover, 25 optimized selected with accuracies >96% three (bacilli, cocci, vibrio) >95% two bacilli (Escherichia coli Salmonella enteritidis), compared machine algorithms (complex tree, linear discriminant, K-nearest neighbor algorithms) maximum 76.4%. Furthermore, was achieved on spiked samples mixing ratios. The proposed learning-assisted analysis method exhibits advantages analyzing huge number capacity extracting within multicomponent information will bring about progress advances fields both biosensing analysis.

Language: Английский

Citations

6
Three-dimensional inertial focusing based impedance cytometer enabling high-accuracy characterization of electrical properties of tumor cells DOI

Chen Ni,

Mingqi Yang,

Shuai Yang

et al.

Lab on a Chip, Journal Year: 2024, Volume and Issue: 24(18), P. 4333 - 4343

Published: Jan. 1, 2024

The differences in the cross-sectional positions of cells detection area have a severe negative impact on achieving accurate characterization impedance spectra cells. Herein, we proposed three-dimensional (3D) inertial focusing based cytometer integrating sheath fluid compression and for high-accuracy electrical identification tumor First, studied effects particle initial position focusing. Then, relationship height signal-to-noise ratio (SNR) signal was explored. results showed that efficient single-line 7-20 μm particles close to electrodes achieved signals with high SNR low coefficient variation (CV) were obtained. Finally, properties three types (A549, MDA-MB-231, UM-UC-3 cells) accurately characterized. Machine learning algorithms implemented identify amplitude phase opacities at multiple frequencies. Compared traditional two-dimensional (2D) focusing, accuracy A549, using our 3D increased by 57.5%, 36.4% 36.6%, respectively. enables wide size range without causing clogging obtains signals, improving applicability different complex biological samples cell accuracy.

Language: Английский

Citations

4
Dielectrophoretic enrichment of live chemo-resistant circulating-like pancreatic cancer cells from media of drug-treated adherent cultures of solid tumors DOI Creative Commons
Aditya Rane,

Javad Jarmoshti,

Abdullah‐Bin Siddique

et al.

Lab on a Chip, Journal Year: 2023, Volume and Issue: 24(3), P. 561 - 571

Published: Dec. 19, 2023

Due to low numbers of circulating tumor cells (CTCs) in liquid biopsies, there is much interest enrichment alternative circulating-like mesenchymal cancer cell subpopulations from

Language: Английский

Citations

10
A Label‐Free Approach for Cell‐Level Drug Dosage Response Tests With an Optimized Flow Cytometry Device DOI
Junwei Li, Huan Wang,

Wenjie Yang

et al.

Electrophoresis, Journal Year: 2025, Volume and Issue: unknown

Published: April 18, 2025

ABSTRACT Cancer is among the most significant health threats to humanity. As a critical front‐line treatment in early stages of disease, chemotherapy drugs provide positive effects on more than one disease. Traditional analytical methods for screening these are often marred by need intricate sample preparation and reliance costly equipment or reagents. In this study, we profiled biophysical properties cancer cells (MCF‐7) as they traversed detection region using high‐throughput seven‐electrode double‐differential biochip. To ensure precise reliable cell status assessment, optimized both electrode dimensions within assay system buffer's conductivities. Our findings indicated that an configuration E:F:G = 2:5:1 (E, F, G stand exciting/floating/gap, respectively), coupled with conductivity setting 1.6 S/m, was optimal probing electrical breast (MCF‐7). Utilizing refined system, achieved live–dead differentiation accuracy approximately 94.25%. Moreover, MCF‐7 displayed distinct impedance signatures response varying drug concentrations. Changes signal characteristics, such opacity phase, physiological shifts under exposure. This research considerable importance, offering novel efficient methodology dosage testing. It paves way personalized strategies, potentially enhancing patient outcomes quality life.

Language: Английский

Citations

0
Emerging artificial intelligence-driven precision therapies in tumor drug resistance: recent advances, opportunities, and challenges DOI Creative Commons
Yajun Mao,

Dangang Shangguan,

Qi Huang

et al.

Molecular Cancer, Journal Year: 2025, Volume and Issue: 24(1)

Published: April 23, 2025

Drug resistance is one of the main reasons for cancer treatment failure, leading to a rapid recurrence/disease progression cancer. Recently, artificial intelligence (AI) has empowered physicians use its powerful data processing and pattern recognition capabilities extract mine valuable drug information from large amounts clinical or omics data, study mechanisms, evaluate predict resistance, develop innovative therapeutic strategies reduce resistance. In this review, we proposed feasible workflow incorporating AI into tumor research, highlighted current AI-driven applications, discussed opportunities challenges encountered in process. Based on comprehensive literature analysis, systematically summarized role including development, mechanism elucidation, sensitivity prediction, combination therapy optimization, phenotype identification, biomarker discovery. With continuous advancement technology rigorous validation models are expected fuel development precision oncology by improving efficacy, guiding decisions, optimizing patient prognosis. summary, leveraging pioneer new mitigate improve efficacy survival, provide novel perspectives tools treatment.

Language: Английский

Citations

0
A review on intelligent impedance cytometry systems: Development, applications and advances DOI Creative Commons
Tao Tang, Trisna Julian,

Doudou Ma

et al.

Analytica Chimica Acta, Journal Year: 2023, Volume and Issue: 1269, P. 341424 - 341424

Published: May 29, 2023

Language: Английский

Citations

9
Label‐Free Impedance Analysis of Induced Pluripotent Stem Cell‐Derived Spinal Cord Progenitor Cells for Rapid Safety and Efficacy Profiling DOI
Linwei He, Jerome Tan, Shi‐Yan Ng

et al.

Advanced Materials Technologies, Journal Year: 2024, Volume and Issue: 9(20)

Published: July 5, 2024

Abstract Regenerative therapies, including the transplantation of spinal cord progenitor cells (SCPCs) derived from induced pluripotent stem (iPSCs), are promising treatment strategies for injuries. However, risk tumorigenicity residual iPSCs advocates an unmet need rapid SCPCs safety profiling. Herein, a (≈3000 min ‐1 ) electrical‐based microfluidic biophysical cytometer is reported to detect low‐abundance at single‐cell resolution. Based on multifrequency impedance measurements (0.3 12 MHz), features cell size, deformability, membrane, and nucleus dielectric properties simultaneously quantified as hydrodynamically stretched cross junction under continuous flow. A supervised uniform manifold approximation projection (UMAP) model further developed impedance‐based quantification undifferentiated with high sensitivity (≈1% spiked iPSCs) shows good correlations differentiation outcomes using two iPSC lines. Cell membrane opacity (day 1) also identified novel early intrinsic predictive biomarker that exhibits strong correlation SCPC efficiency 10). Overall, it envisioned this label‐free optic‐free platform technology can be versatile cost‐effective process analytical tool monitor or assess quality in regenerative medicine.

Language: Английский

Citations

2
An Effective Recognition Method for Particle Coincidence in Double Differential Impedance Cytometry DOI
Shanshan Li, Chao Wang, Bowen Yang

et al.

IEEE Sensors Journal, Journal Year: 2023, Volume and Issue: 23(16), P. 18070 - 18080

Published: July 14, 2023

As a label-free single cell analysis approach, impedance flow cytometry provides valuable information by differential signals. However, for high throughput purpose, particle coincidence is inevitable especially when the concentration or pumping rate too high. In this work, we proposed first numerical model and novel method coincidence. To investigate multiparticle events, double sensor used. From statistic of signal peaks, could determine threshold events then read out numbers. Compared with customized threshold, data-driven cutoff line fundamentally improves accuracy recognition. Herein, key operation parameters that influence including sample concentration, driven pressure (stands rate), configuration are elucidated. Moreover, guide to best practices avoid suggested real applications.

Language: Английский

Citations

4