EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating Vision‐Language Models for Accelerated High‐Throughput Nutrition Screening

Peihua Ma iD, Yixin Wu, Ning Yu, Xiaoxue Jia iD, Yiyang He, Yang Zhang, Michael Backes iD, Qin Wang, Cheng-I Wei iD

Advanced Science · 2024-09 · 11 (34)

DOI: 10.1002/advs.202403578 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 08.07.2024. Verfasst von Peihua Ma und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nutrition and Food Science, College of Agriculture and Natural Resources, University of Maryland, College Park, MD, 20742, USA. Hauptthemen laut MEDLINE: High-Throughput Screening Assays. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Maryland Agricultural Experiment Station, Pamela Pehrsson and Jaspreet Ahuja.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Addressing the critical need for swift and precise nutritional profiling in healthcare and in food industry, this study pioneers the integration of vision‐language models (VLMs) with chemical analysis techniques. A cutting‐edge VLM is unveiled, utilizing the expansive UMDFood‐90k database, to significantly improve the speed and accuracy of nutrient estimation processes. Demonstrating a macro‐AUCROC of 0.921 for lipid quantification, the model exhibits less than 10% variance compared to traditional chemical analyses for over 82% of the analyzed food items. This innovative approach not only accelerates nutritional screening by 36.9% when tested amongst students but also sets a new benchmark in the precision of nutritional data compilation. This research marks a substantial leap forward in food science, employing a blend of advanced computational models and chemical validation to offer a rapid, high‐throughput solution for nutritional analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

High-Throughput Screening AssaysHumansNutrition AssessmentFood Analysis

Stichwörter der Autor:innen

food analysishigh‐throughput screeningmachine learningprecision nutritionvision‐language model

Autor:innen und Institutionen

  • Department of Nutrition and Food Science, College of Agriculture and Natural Resources, University of Maryland, College Park, MD, 20742, USA.
  • CISPA Helmholtz Center for Information Security, 66123, Saarbrucken, Germany.
  • Netflix Eyeline Studios, Los Angeles, CA, 90028, USA.

ORCID-Profile: Peihua Ma, Xiaoxue Jia, Michael Backes, Cheng-I Wei

Förderung

  • Maryland Agricultural Experiment Station
  • Pamela Pehrsson and Jaspreet Ahuja

Zitieren

APA

Ma, P., Wu, Y., Yu, N., Jia, X., He, Y., Zhang, Y., Backes, M., Wang, Q., & Wei, C. I. (2024). Integrating Vision‐Language Models for Accelerated High‐Throughput Nutrition Screening. Advanced Science, 11(34). https://doi.org/10.1002/advs.202403578

Vancouver

Ma P, Wu Y, Yu N, Jia X, He Y, Zhang Y, et al. Integrating Vision‐Language Models for Accelerated High‐Throughput Nutrition Screening. Advanced Science. 2024;11(34). doi:10.1002/advs.202403578

BibTeX
@article{Ma2024,
  author = {Ma, Peihua and Wu, Yixin and Yu, Ning and Jia, Xiaoxue and He, Yiyang and Zhang, Yang and Backes, Michael and Wang, Qin and Wei, Cheng-I},
  title = {Integrating Vision‐Language Models for Accelerated High‐Throughput Nutrition Screening},
  journal = {Advanced Science},
  year = {2024},
  volume = {11},
  number = {34},
  doi = {10.1002/advs.202403578}
}
Kostenlos starten →