Search PubMedSearch

SEARCH · Search PubMed

Results for “polyp detection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

340 recordsLinked to original sources

Comparative Efficacy of Different AI Systems for Polyp Detection by Size During Colonoscopy: Systematic Review and Network Meta-Analysis.

BACKGROUND: Colorectal cancer remains a leading cause of death despite being largely preventable through polypectomy. AI systems designed to enhance polyp detection during colonoscopy have shown promise, but the extent to which they improve detection of different-sized polyps remains unclear. OBJECTIVE: This study compared the size-stratified efficacy of AI-assisted colonoscopy vs standard colonoscopy using the Hartung-Knapp-Sidik-Jonkman (HKSJ) method, and generated exploratory rankings while acknowledging all cross-platform comparisons are indirect. METHODS: This systematic review and network meta-analysis (NMA) searched PubMed, Embase, Cochrane CENTRAL, and Web of Science from inception to July 25, 2026, supplemented by citation searching. We included randomized controlled trials (RCTs) comparing AI-assisted vs standard colonoscopy in adults (≥18 years of age), reporting mean polyp detection counts stratified by size (≤5 mm, 6-9 mm, and ≥10 mm). Two reviewers screened studies, extracted data, and assessed risk of bias using the Cochrane Risk of Bias 2.0. We conducted frequentist NMA using the HKSJ method with restricted maximum likelihood estimation, calculated 95% prediction intervals (PIs), and assessed heterogeneity using I2 and τ2. Certainty of evidence was rated using the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) framework. RESULTS: A total of 13 RCTs (4156 participants) compared 8 AI systems to standard colonoscopy, forming a network without direct AI comparisons. For diminutive polyps (≤5 mm), AI showed a modest advantage (standardized mean difference [SMD] 0.21, 95% CI 0.07 to 0.35, 95% PI -1.12 to 1.54), but substantial heterogeneity (I2=86.6%) and wide PI crossing the null indicated high uncertainty. EndoScreener showed the most consistent evidence (SMD 0.36, 95% CI 0.18-0.54). For small and large polyps, effects were minimal (SMD 0.02, 95% CI -0.02 to 0.06, 95% PI -0.03 to 0.07; SMD 0.01, 95% CI 0.00-0.02, 95% PI -0.01 to 0.03). GRADE certainty was very low for diminutive polyps and low for small and large polyps. Sensitivity analysis excluding Tianjin YuJin did not materially change findings. CONCLUSIONS: AI may modestly enhance diminutive polyp detection, but effects on small and large polyps are minimal, with no platform superiority. Given very low to low certainty, findings are hypothesis-generating. This exploratory NMA provides size-stratified comparisons that can inform future head-to-head trial design. Unlike prior reviews aggregating all polyp sizes, we show the overall AI benefit is driven by diminutive polyp detection, providing a framework for targeted deployment-prioritizing AI for diminutive polyp screening, with limited value for larger lesions. Head-to-head trials are urgently needed. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD420251266932; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251266932.

Colonoscopy

Linked-color imaging with computer-aided detection and the proximal adenoma miss rate: a randomized tandem trial.

BACKGROUND AND AIMS: Linked-color imaging (LCI) aids the detection and characterization of lesions. Computer-aided detection (CADe) systems have been introduced to improve lesion detection during colonoscopy. Although several studies have been reported regarding LCI, few have investigated the combination of LCI and CADe. This study aimed to evaluate the efficacy of LCI with CADe colonoscopy compared to conventional white-light colonoscopy. METHODS: A single-center, randomized tandem trial was conducted. Participants referred for first-time colonoscopy after fecal immunochemical test (FIT)-positive, asymptomatic screening, or surveillance colonoscopy were randomized (1:1) to undergo CADe-assisted colonoscopy of LCI or white-light imaging (WLI) in the right side of the colon. The primary outcome was adenoma miss rate (AMR) in the right side of the colon. Secondary outcomes included polyp miss rate (PMR), diminutive adenoma miss rate (dAMR), sessile serrated lesion miss rate (SSLMR), advanced adenoma miss rate, advanced neoplasia miss rate, flat-type lesion miss rate (FMR), and the differences in miss rates based on expertise. RESULTS: Among 232 randomized participants, 209 were analyzed (LCI/CADe: 102; WLI: 107). AMR (WLI: 39% vs LCI/CADe: 20%; P = .001), PMR (42% vs 18%; P < .001), and dAMR (42% vs 21%; P = .003) were significantly lower in the LCI/CADe arm, particularly among experts. SSLMR (46% vs 0%), advanced AMR (30% vs 0%), advanced neoplasia miss rate (25% vs 0%), and FMR (27% vs 5.6%) were lower in LCI/CADe, although without statistical significance. CONCLUSIONS: Compared to conventional colonoscopy, LCI with CADe colonoscopy resulted in a statistically significant decrease, especially in AMR. (UMIN 000050685).

Humans

Bacterial Lysates Add-On Therapy to Reduce Postoperative Recurrence in Nasal Polyps.

OBJECTIVE: This study aimed to investigate the potential role of OM-85 in reducing polyp recurrence (PR). METHODS: A single-center randomized, prospective study was performed to compare the inter-group PR rate, patient-reported outcome measures (PROMs), CT and endoscopic scores. Hundred patients were randomized to receive either add-on OM-85 (34/50) or control group (43/50); 77 participants completed the 12-month follow-up. The OM-85 group received oral treatment for 10&#x2009;days, followed by a 20-day washout (Months 1-3 and 7-9). Primary outcome was the PR rate. Secondary outcomes included PROMs, Lund-Kennedy (L-K) scores, Lund-Mackay (L-M) scores, and complete blood count (CBC) parameters. RESULTS: The PR rate was significantly lower in the OM-85 group (8.82%) than in the control group (27.91%, &#x3c7; 2&#x2009;=&#x2009;4.408, p&#x2009;=&#x2009;0.036). Univariable analysis identified pre-operative Lund-Mackay (L-M) score (p&#x2009;=&#x2009;0.008) and hyposmia VAS score (p&#x2009;=&#x2009;0.031) as significant predictors of PR. In multivariable analysis, the L-M score remained an independent predictor (OR&#x2009;=&#x2009;1.15, p&#x2009;=&#x2009;0.012), with an optimal cutoff of 10. The OM-85 group showed significant improvements in nasal obstruction, olfactory dysfunction, and mucopurulent discharge at 6 and 12&#x2009;months (p&#x2009;<&#x2009;0.05). Lund-Kennedy (L-K) score and 22-item Sinonasal Outcome Test (SNOT-22) score were also significantly improved (p&#x2009;<&#x2009;0.05). Furthermore, the OM-85 group exhibited elevated white blood cell counts and lymphocyte percentages from 6&#x2009;months onward (p&#x2009;<&#x2009;0.05). CONCLUSION: Adjuvant OM-85 may reduce postoperative PR, with improved endoscopic and symptom scores, potentially mediated by enhanced systemic immune function.

Humans

SGLF-Net:Staged Global-to-Local Cross-Scale Fusion Network for Colonoscopic Polyp Segmentation.

Polyp segmentation in colonoscopy images plays a pivotal role in computer-aided medical diagnosis and the early prevention of colorectal cancer. However, existing methods often suffer from performance degradation when confronted with extreme polyp scale variation and polyp boundary ambiguity. To address these challenges, we propose the Staged Global-to-Local Cross-Scale Fusion Network (SGLF-Net), which adopts a novel staged global-to-local learning paradigm to progressively refine segmentation from coarse global semantics to fine-grained local details. Specifically, the Global Semantic Perception Stage integrates a Swin Transformer Encoder and a Dynamic Attentive Decoder (DAD) to construct comprehensive multi-scale contextual representations. The Local Detail Refinement Stage employs an Edge-aware Dynamic Attentive Decoder (E-DAD) to enhance structural fidelity and boundary precision through explicit edge-guided supervision. Furthermore, we introduce the Cross Spatial-Scale Feature Aggregation and Reconstitution (CSSAR) module, equipped with hybrid attention mechanisms, to facilitate efficient semantic structural interaction between the two cascaded stages. Extensive experiments on five public benchmark datasets demonstrate that SGLF-Net consistently outperforms state-of-the-art methods in both segmentation accuracy and boundary preservation.

Journal Article

Endoscopic mucosal resection with precutting vs. anchoring technique using snare tip for 10-25&#x2009;mm nonpedunculated colorectal polyps: a randomized controlled trial.

BACKGROUND AND AIMS: Modified endoscopic mucosal resection (EMR) techniques using a snare tip, precutting EMR (P-EMR) and anchoring EMR (A-EMR), have been developed for the effective resection of nonpedunculated colorectal polyps measuring 10-25&#x2005;mm. Although previous studies have compared either P-EMR or A-EMR with conventional EMR, no study has directly compared these two snare tip-assisted techniques within modified EMR. This study aimed to evaluate P-EMR and A-EMR in terms of the R0 resection rate and procedure duration. METHODS: This prospective randomized controlled trial enrolled patients with nonpedunculated colorectal polyps measuring 10-25&#x2005;mm. The patients were randomly assigned to the P-EMR or A-EMR groups. The primary outcome was R0 resection rate, defined as en bloc resection with histologically tumor-free margins. Secondary outcomes included the injection-to-snaring time, total procedure time, and adverse events. RESULTS: Each group included 63 polyps, of which 126 were analyzed in the final evaluation. Both groups achieved high R0 resection rates (93.7% for P-EMR and 88.9% for A-EMR), with no significant difference ( P &#x2005;=&#x2005;0.344). However, the A-EMR group demonstrated significantly shorter injection-to-snaring time (181.8&#x2005;&#xb1;&#x2005;81.9 vs. 320.9&#x2005;&#xb1;&#x2005;143.5&#x2005;s, P &#x2005;<&#x2005;0.001) and total procedure time (259.7&#x2005;&#xb1;&#x2005;139.7 vs. 479.8&#x2005;&#xb1;&#x2005;249.0&#x2005;s, P &#x2005;<&#x2005;0.001). Adverse events, including intraprocedural and delayed bleeding, were comparable between the groups. CONCLUSION: Both P-EMR and A-EMR demonstrated high R0 resection rates for nonpedunculated polyps measuring 10-25&#x2005;mm. However, A-EMR achieved these outcomes with a shorter procedure time than P-EMR.

Humans

A MIL-88@Ru-based molecularly imprinted electrochemiluminescence sensor for highly selective and sensitive detection of enrofloxacin residues in animal-derived foods.

Using a metal-organic framework (MOF) - supported Ru(bpy)32+ (MIL-88@Ru) composite luminescent material, this study innovatively adopted electropolymerization to fabricate a molecularly imprinted polymer-based electrochemiluminescent (MIP-ECL) sensor for enrofloxacin (ENR) detection in animal-derived foods. Systematic investigation of the ECL luminescence and ENR's quenching mechanism confirmed that the sensor integrates ECL's high sensitivity and MIP's high specificity, enabling rapid and accurate recognition of ENR. Experimental results show a good linear response in the range of 1&#xa0;nmol/L-20&#xa0;&#x3bc;mol/L (R2&#xa0;=&#xa0;0.99), a limit of detection (LOD) as low as 0.28&#xa0;nmol/L, as well as excellent selectivity and stability. Recoveries of ENR in all investigated matrices ranged from 97.7% to 106.4%, confirming the reliability of the established method. This ECL-MIP coupling strategy provides a new technical approach and application references for the efficient detection of trace pollutants in food safety and environmental monitoring fields.

Enrofloxacin

An RPA-assisted homogeneous electrochemical DNA sensor for on-site eDNA detection toward early warning of crown-of-thorns starfish outbreaks.

Crown-of-thorns starfish (COTS) outbreaks seriously threaten coral reef ecosystems, while conventional monitoring approaches are time-consuming and often lack sufficient sensitivity for early warning. Existing electrochemical DNA sensors usually require complex electrode-surface immobilization procedures, which can lead to uneven probe distribution, significant steric hindrance, and poor stability. Meanwhile, the low concentration of environmental DNA (eDNA) in marine environments further complicates detection. To overcome these challenges, this study developed a homogeneous electrochemical DNA sensor assisted by recombinase polymerase amplification (RPA) for COTS eDNA detection. Target DNA was first amplified by RPA, and the amplification products were then hybridized in solution with capture probe (CP)-modified magnetic beads (MB) and biotin-labeled signal probe (SP) to form sandwich-structured MB complexes. These complexes were subsequently magnetically enriched and immobilized on the electrode surface for electrochemical signal readout. Under optimized conditions, the sensor displayed a linear response to COTS genomic DNA from 3.77&#xa0;fg/&#x3bc;L to 1&#xa0;ng/&#x3bc;L, with an LOD of 2.02&#xa0;fg/&#x3bc;L and an LOQ of 3.77&#xa0;fg/&#x3bc;L. The sensor was applied to Xisha Islands samples, and the results agreed with droplet digital PCR (ddPCR) (P&#xa0;>&#xa0;0.05), demonstrating its potential for sensitive and reliable on-site COTS eDNA detection.

Animals

PdIr bimetallic nanozyme engineered metal-organic frameworks integrated dual-mode sensor toward Stx2 detection in food.

Shiga toxin II (Stx2) has attracted extensive attention due to its toxicity and pathogenicity, making the development of sensitive detection methods urgent. This study constructed a dual-mode sensing platform for the sensitive detection of Stx2 in food. Composite material UIO-66@PdIr with peroxidase-like activity and fluorescent properties was synthesized and combined with cDNA as the signal probe, while aptamer-modified magnetic beads served as the capture probe. Specific binding of Stx2 to the aptamer triggered the release of the signal probe, enabling colorimetric and fluorescence signal readout. The colorimetric mode showed a linear range of 0.05-100&#xa0;ng/mL with an LOD of 0.039&#xa0;ng/mL, and the fluorescence mode exhibited 0.01-1000&#xa0;ng/mL with an LOD of 0.0097&#xa0;ng/mL. Additionally, this method was successfully applied to the detection of Stx2 in food, and the recovery rates were 94.33%&#xa0;&#x223c;&#xa0;102.20%. It indicated that the constructed sensor holds great practical potential for Stx2 detection.

Food Contamination

Dual signal-enhanced immunochromatographic test strip based on Au@PtNPs: From sensitive detection of thiamethoxam to multiplex pesticide screening in vegetables.

Immunochromatographic test strip (ICTS) is a rapid analytical technique widely used in environmental and food detection owing to its merits of simple operation and short analysis time. Herein, three-dimensional nanoflower-structured gold&#x2011;platinum nanoparticles (Au@PtNPs) were synthesized via a seed-growth method. Compared with conventional gold nanoparticles (AuNPs), Au@PtNPs exhibited stronger signal intensity, excellent catalytic performance, and efficient antibody binding efficiency. Colorimetric Au@PtNPs-ICTS and catalytic colorimetric Au@PtNPs-ICTS were developed for the sensitive detection of thiamethoxam (THI) in vegetables. The limits of detection (LODs) for colorimetric Au@PtNPs-ICTS and catalytic colorimetric Au@PtNPs-ICTS quantitative analysis were 0.18&#xa0;ng/mL and 0.093&#xa0;ng/mL, respectively, representing approximately 3-fold and 6-fold improvement compared to AuNPs-ICTS (0.56&#xa0;ng/mL). Furthermore, highly sensitive detection of multiple pesticide residues (chlorpyrifos, acetamiprid, and imidacloprid) was achieved by replacing the corresponding target antigens and antibodies, which further verified the universality of this immunochromatographic strategy.

Thiamethoxam

Artificial neural network data fusion-mediated dual-mode sensor based on Fe3O4@PdIr for Salmonellatyphimurium detection in food.

Salmonella Typhimurium (S. typhimurium) is a major foodborne pathogen that poses a serious threat to public health. In this study, a colorimetric/electrochemical dual-mode biosensor assisted by artificial neural network (ANN) was developed for the sensitive detection of S. typhimurium. Fe3O4@PdIr nanocomposites with enhanced peroxidase-like activity and electrochemical performance were prepared and conjugated with an aptamer specific to S. typhimurium to obtain Fe3O4@PdIr-Apt. Through the sandwich binding of Fe3O4@PdIr-Apt and Apt to the target, the nanocomposites were attached to microplates or Au electrodes, thereby generating colorimetric and electrochemical signals. The ANN model deeply resolved the complex nonlinear relationship between the dual signals, enabling mutual correction and ultimately performing data fusion to output a single detection result, which significantly reduced the mean square error while improving detection sensitivity and reliability. This sensor exhibited a wide linear range of 2.7-2.7&#xa0;&#xd7;&#xa0;108&#xa0;CFU/mL and a low detection limit of 1.66&#xa0;CFU/mL. Additionally, this method was successfully applied to the detection of S. typhimurium in pork and milk, with a recovery rate of 95.19%&#xa0;&#x223c;&#xa0;104.07%. It indicated that the constructed sensor holds great practical potential for S. typhimurium detection.

Neural Networks, Computer

Peptide molecular lock-engineered nanobodies enable an oriented dual-modal immunoassay for reliable detection of Cronobacter sakazakii.

Conventional nanobody ELISAs for trace Cronobacter sakazakii in powdered infant formula suffer from random orientation and low signal output. We developed an oriented dual-modal immunoassay that combines site-specific biotinylation via a C-terminal AviTag and a peptide molecular lock, enabling controlled surface orientation while preserving nanobody structural integrity. This strategy was further integrated with phage-displayed nanobodies for multivalent amplification and both fluorescent and colorimetric readouts. The assay exhibited a broad linear range of 103-106&#xa0;CFU/mL, with limits of detection (LODs) of 6.70&#xa0;&#xd7;&#xa0;102&#xa0;CFU/mL for fluorescence and 1.55&#xa0;&#xd7;&#xa0;103&#xa0;CFU/mL for colorimetry, showing improved sensitivity compared with the conventional passive adsorption-based Nb-ELISA evaluated in this study. XGBoost-based multimodal fusion improved quantitative accuracy, and SHAP analysis elucidated modality contributions. In spiked powdered infant formula samples, recoveries ranged from 92.1% to 118% with coefficients of variation below 5.98%, confirming acceptable matrix tolerance and analytical reliability.

Cronobacter sakazakii

Assessing the threat of Bacillus cereus: From toxin characterization to modern detection strategies.

Bacillus cereus is a spore-forming pathogen responsible for both diarrheal and emetic foodborne illnesses worldwide. Its significance in food safety has received growing attention. Recent advances, including the discovery of novel virulence factors and the development of emerging detection technologies, have provided new insights into its pathogenic mechanisms and surveillance strategies. This review critically examines the global burden of B. cereus infections, and molecular mechanisms of its major virulence factors, and the performance characteristics of current detection knowledge gaps such as the viable-but-non-culturable state and regulatory blind spots for emetic toxins, and discuss unresolved challenges in clinical management. By integrating epidemiological, microbiological, and technological perspectives with critical lens, this review aims to provide a valuable reference for future research and food safety practices.

Bacillus cereus

Spatially confined electrochemical strategy with DNA-assembled nanogaps for SNP detection.

Accurate detection of low-abundance single nucleotide polymorphisms (SNPs) against a large excess of homologous wild-type sequences requires both selective molecular recognition and effective transduction of small sequence differences into measurable signals. Here, we report a spatially confined electrochemical strategy that couples sequence-selective recognition with size-dependent mass-transport gating. DNA-hybridization-driven self-assembly of gold nanoparticles (AuNPs) forms a three-dimensional self-assembled electrode (3D-SAE) with a DNA-defined interparticle architecture. Competitive probes (SP/WP) convert single-base recognition into distinct molecular-size states: the SNP-associated pathway preferentially triggers a hybridization chain reaction (HCR), generating bulky AuNP-anchored HCR/methylene blue complexes (Au@HCR/MB) with reduced electrochemical accessibility through the porous 3D-SAE, whereas the wild-type pathway does not trigger HCR and maintains a high-current response from more readily accessible MB-containing species. Thus, sequence recognition is translated into a molecular-size difference and subsequently into an electrochemical signal through differential mass transport. Under buffer conditions, the platform achieved a statistically estimated detection limit of &#x223c;0.47&#x202f;fM and a quantitative range of 1&#x202f;fM-100 pM. It discriminated a 0.1% mutant abundance in a fragmented genomic-DNA background. The downstream signal-transduction chemistry is enzyme-free and isothermal. This work establishes a mechanistical recognition-size-conversion-mass-transport-gating architecture for electrochemical nucleic acid analysis.

Polymorphism, Single Nucleotide

Machine learning-assisted Mn-N-C nanozyme colorimetric sensor array for trace-level detection of biogenic amines in meat.

Accurate detection of biogenic amines (BAs) in meat remains challenging due to their high structural similarity and co-occurrence. Herein, an Mn-N-C nanozyme was synthesized via a metal-organic framework confined pyrolysis strategy, possessing excellent oxidase (OXD)- and peroxidase (POD)-like activities. The dual enzyme-like activity showed Km values of 0.1584&#xa0;mM (OXD) and 0.1498&#xa0;mM (POD), respectively, in detection system. Leveraging these properties, a colorimetric sensor array was constructed, enabling the detection of four representative BAs within a concentration range of 2-10&#xa0;ppm with 100% classification accuracy. In addition, a concentration independent recognition model based on an artificial neural network was developed to address signal nonlinearity interference in meat. The integrated system achieved accurate trace-level identification of BAs in perishable fish, pork, and chicken, demonstrating its applicability for early-stage BAs monitoring and quality deterioration warning during storage and transportation.

Biogenic Amines

Viral surveillance beyond detection: JMTV and the need for ensemble approaches in emerging virus discovery.

The recent report by T. Murillo, L. E. Enrique Chaves-Gonz&#xe1;lez, S. Temmam, S. Berm&#xfa;dez, et al. (Microbiol Spectr 14:e04078-25, 2026, https://doi.org/10.1128/spectrum.04078-25) expands the known geographic and ecological range of Jingmen tick virus (JMTV) by detecting the virus in Amblyomma mixtum ticks collected from horses in Costa Rica. This is an important finding because A. mixtum can feed on wildlife, domestic animals, and humans, creating a possible interface for virus movement across various hosts. The study also places the Costa Rican virus in a wider phylogenetic context, linking it to JMTV diversity reported from other regions. However, the detection of viral RNA in ticks should not be interpreted as proof of local disease, human infection, or active transmission, especially in the absence of supporting results. Instead, it reflects an important signal for careful viral surveillance. Here, I discuss how JMTV illustrates the need for ensemble approaches that combine field sampling, phylogeny, segment-level genome analysis, serology, experimental validation, and data-driven virus discovery tools.

emerging viruses

Simultaneous determination of imiquimod and terbinafine in skin permeation studies: Validation of a liquid chromatography method with fluorescence detection.

Chromoblastomycosis is a chronic, neglected subcutaneous mycosis posing significant therapeutic challenges. A topical strategy combining terbinafine (TBF), an antifungal, with imiquimod (IMQ), a TLR-7/8 agonist immunomodulator, has emerged a promising alternative. However, no validated analytical method is currently available to simultaneously quantify both drugs in skin, which is crucial for novel formulation development. This study reports the development and validation of a simple HPLC method with fluorescence detection (excitation 236&#xa0;nm, emission 340&#xa0;nm) for the simultaneous determination of TBF and IMQ extracted from porcine skin. Separation was achieved on a C8 reversed-phase column (125&#xa0;&#xd7;&#xa0;4.0&#xa0;mm, 5&#xa0;&#x3bc;m) using a mobile phase of methanol and water (60,40, v/v), both containing 0.1% formic acid at a flow rate of 0.8&#xa0;mL/min. The method showed excellent linearity (r&#xa0;>&#xa0;0.999) over 0.01-1.0&#xa0;&#x3bc;g/mL for IMQ and 0.1-2.0&#xa0;&#x3bc;g/mL for TBF. Intra- and inter-day precision demonstrated coefficients of variation below 5%, and recovery rates from skin (79-105%) confirmed accuracy. Limits of detection were 0.001&#xa0;&#x3bc;g/mL for IMQ and 0.004&#xa0;&#x3bc;g/mL for TBF, with quantification limits of 0.02&#xa0;&#x3bc;g/mL and 0.16&#xa0;&#x3bc;g/mL, respectively. This selective, sensitive, and reproducible method represents a valuable analytical tool for supporting the development and quality control of topical formulations for chromoblastomycosis and other fungal skin diseases.

Animals

A Meta-learning-driven strategy for adulteration detection in sweet potato starch and vermicelli using Raman spectroscopy.

To address the widespread adulteration of sweet potato starch and its vermicelli with cheaper starches and overcome conventional supervised learning's dependency on large labeled datasets, this study developed a few-shot discrimination method integrating Raman spectroscopy with meta-learning. We constructed a meta-learning framework using cassava- and wheat-adulterated sweet potato starch as the source domain for training, with potato-adulterated sweet potato starch and cassava-adulterated sweet potato vermicelli as two target domains for testing. Raman spectra showed high consistency between sweet potato vermicelli and its raw starch, laying the foundation for cross-domain detection. Testing yielded comprehensive classification accuracies of 95.33% and 98.00% for the two target domains, significantly outperforming SVM, RF, and CNN (max. 85.24%). This approach effectively identifies subtle starch variety differences in complex adulteration, providing novel food quality inspection solutions and verifying the feasibility of raw material-to-finished product cross-domain detection.

Ipomoea batatas

Interfacial engineering of cobalt tungstate-halloysite nanotube nanocomposite for electrochemical detection of synthetic vanillin in food matrices.

In processed foods and medicine, synthetic vanillin is widely used, although excessive intake poses toxicological risks. Due to the rising usage of synthetic vanillin in food products and associated health hazards, quick, sensitive, and reliable analytical methods are needed to precisely measure vanillin in complex food matrices. This work introduces a CoWO4@F-HNT/GCE nanocomposite as an efficient electrocatalytic modifier for glassy carbon electrodes aimed at trace-level synthetic vanillin detection. Structural and microscopic analyses confirmed phase-pure monoclinic CoWO4, preservation of the tubular aluminosilicate framework, and homogeneous nanoparticle anchoring on F-HNT. Differential pulse voltammetry provided a broad linear range from 0.01 to 372.14&#xa0;&#x3bc;M and a low detection limit of 4.3&#xa0;nM, together with excellent selectivity against common interferents, good cycling stability, and high inter-electrode reproducibility. These characteristics position the CoWO4@F-HNT-modified electrode as a cost-effective and reliable platform for on-site quality control of synthetic vanillin in complex food matrices.

Benzaldehydes