2D Prediction of the Nutritional Composition of Dishes from Food Images: Deep Learning Algorithm Selection and Data Curation Beyond the Nutrition5k Project
Nutrients · 30.06.2025 · 17 (13) · 2196
DOI: 10.3390/nu17132196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nutrients, online erschienen am 30.06.2025. Verfasst von Rachele Bianco und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine-DMED, Università degli Studi di Udine, 33100 Udine, Italy. Hauptthemen laut MEDLINE: Deep Learning, Nutritive Value, Food Analysis. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministero dell'università e della ricerca, Italian Ministry of University and Research, Professor Valeria Edefonti.
Abstract (Originalsprache)
Background/Objectives: Deep learning (DL) has shown strong potential in analyzing food images, but few studies have directly predicted mass, energy, and macronutrient content from images. In addition to the importance of high-quality data, differences in country-specific food composition databases (FCDBs) can hinder model generalization.
Methods
We assessed the performance of several standard DL models using four ground truth datasets derived from Nutrition5k—the largest image–nutrition dataset with ~5000 complex US cafeteria dishes. In light of developing an Italian dietary assessment tool, these datasets varied by FCDB alignment (Italian vs. US) and data curation (ingredient–mass correction and frame filtering on the test set). We evaluated combinations of four feature extractors [ResNet-50 (R50), ResNet-101 (R101), InceptionV3 (IncV3), and Vision Transformer-B-16 (ViT-B-16)] with two regression networks (2+1 and 2+2), using IncV3_2+2 as the benchmark. Descriptive statistics (percentages of agreement, unweighted Cohen’s kappa, and Bland–Altman plots) and standard regression metrics were used to compare predicted and ground truth nutritional composition. Dishes mispredicted by ≥7 algorithms were analyzed separately.
Results
R50, R101, and ViT-B-16 consistently outperformed the benchmark across all datasets. Specifically, when replacing it with these top algorithms, reductions in median Mean Absolute Percentage Errors were 6.2% for mass, 6.4% for energy, 12.3% for fat, and 33.1% and 40.2% for protein and carbohydrates. Ingredient–mass correction substantially improved prediction metrics (6–42% when considering the top algorithms), while frame filtering had a more limited effect (
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine-DMED, Università degli Studi di Udine, 33100 Udine, Italy.
- Branch of Medical Statistics, Biometry and Epidemiology "G. A. Maccacaro", Department of Clinical Sciences and Community Health, Dipartimento di Eccellenza 2023-2027, Università degli Studi di Milano, 20133 Milano, Ital…
- Department of Mathematics, Computer Science and Physics-DMIF, Università degli Studi di Udine, 33100 Udine, Italy.
- Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, 20122 Milano, Italy.
ORCID-Profile: Rachele Bianco, Sergio Coluccia, Alex Falcon, Federica Fiori, Monica Ferraroni, Valeria Edefonti, Maria Parpinel
Förderung
- Ministero dell'università e della ricerca
- Italian Ministry of University and Research
- Professor Valeria Edefonti
Zitieren
APA
Bianco, R., Coluccia, S., Marinoni, M., Falcon, A., Fiori, F., Serra, G., Ferraroni, M., Edefonti, V., & Parpinel, M. (2025). 2D Prediction of the Nutritional Composition of Dishes from Food Images: Deep Learning Algorithm Selection and Data Curation Beyond the Nutrition5k Project. Nutrients, 17(13), 2196. https://doi.org/10.3390/nu17132196
Vancouver
Bianco R, Coluccia S, Marinoni M, Falcon A, Fiori F, Serra G, et al. 2D Prediction of the Nutritional Composition of Dishes from Food Images: Deep Learning Algorithm Selection and Data Curation Beyond the Nutrition5k Project. Nutrients. 2025;17(13):2196. doi:10.3390/nu17132196
BibTeX
@article{Bianco2025,
author = {Bianco, Rachele and Coluccia, Sergio and Marinoni, Michela and Falcon, Alex and Fiori, Federica and Serra, Giuseppe and Ferraroni, Monica and Edefonti, Valeria and Parpinel, Maria},
title = {2D Prediction of the Nutritional Composition of Dishes from Food Images: Deep Learning Algorithm Selection and Data Curation Beyond the Nutrition5k Project},
journal = {Nutrients},
year = {2025},
volume = {17},
number = {13},
pages = {2196},
doi = {10.3390/nu17132196}
}
EUVIMED