Academic Journal

Laser Light Scattering-Enhanced Deep Computer Vision Method for the Detection of Trace Mineral Oil in Vegetable Oils.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Laser Light Scattering-Enhanced Deep Computer Vision Method for the Detection of Trace Mineral Oil in Vegetable Oils.
Συγγραφείς: Wang XZ; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China., Yin XY; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China., Yang XH; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China., Chen Y; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China.; School of Biological Science and Medical Engineering, Hunan University of Technology, Zhuzhou 412007, China., Wang T; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China.; Yuelushan Laboratory, Changsha 410128, China., Wu HL; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China., Yu RQ; State Key Laboratory of Chemo and Biosensing, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China.
Πηγή: Analytical chemistry [Anal Chem] 2026 Jun 23; Vol. 98 (24), pp. 17777-17788. Date of Electronic Publication: 2026 Jun 11.
Τύπος έκδοσης: Journal Article; Research Support, Non-U.S. Gov't
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: American Chemical Society Country of Publication: United States NLM ID: 0370536 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1520-6882 (Electronic) Linking ISSN: 00032700 NLM ISO Abbreviation: Anal Chem Subsets: MEDLINE
Imprint Name(s): Original Publication: Washington, American Chemical Society.
Ιατρικοί όροι (MeSH): Mineral Oil*/analysis , Plant Oils*/chemistry , Plant Oils*/analysis , Food Contamination*/analysis , Lasers* , Light* , Deep Learning*, Scattering, Radiation
Περίληψη: Mineral oil contamination in vegetable oils poses a serious threat to food safety and consumer health. In this study, we reported an on-site compatible analytical strategy based on laser light scattering-enhanced deep computer vision for detecting mineral oil contamination in vegetable oils. The strategy integrates saponification-induced phase and turbidity contrast with laser-enhanced scattering visualization to transform trace mineral oil into visually discriminative signals. To accurately analyze these signals, we proposed a novel, lightweight, and efficient deep learning model (Oil-MobileNet). After optimizing chemical reaction conditions, the effects of three illumination sources (green laser, red laser, and laser-free) on image acquisition were systematically examined. Subsequently, Oil-MobileNet was evaluated on binary and multiclass classification. Comparative analyses with four baseline models demonstrated that the combination of green laser illumination and Oil-MobileNet achieved the best classification performance, enabling reliable discrimination of mineral oil contamination down to 0.05% (v/v) under the defined operational criteria. This practical detection capability outperformed human visual inspection with green laser (0.1%) and commercially available saponification-based kits (0.9-3%). The contaminated level prediction models were also established using these architectures. In addition, interpretability studies were conducted to elucidate the model's decision-making mechanism. Finally, the well-trained models were deployed in a user-friendly graphical user interface for the accurate determination of mineral oil contamination.
Substance Nomenclature: 8020-83-5 (Mineral Oil)
0 (Plant Oils)
Entry Date(s): Date Created: 20260611 Date Completed: 20260623 Latest Revision: 20260709
Update Code: 20260709
DOI: 10.1021/acs.analchem.6c00302
PMID: 42275108
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1520-6882
DOI:10.1021/acs.analchem.6c00302