The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings
IntroductionAccurate measurement of dietary intake without interfering in natural eating habits is a long-standing problem in nutritional epidemiology. We explored the applicability of hyperspectral imaging and machine learning for dietary assessment of home-prepared meals, by building a proof-of-co...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Nutrition |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnut.2024.1520674/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841525272622399488 |
|---|---|
| author | Esther Kok Aneesh Chauhan Michele Tufano Edith Feskens Guido Camps |
| author_facet | Esther Kok Aneesh Chauhan Michele Tufano Edith Feskens Guido Camps |
| author_sort | Esther Kok |
| collection | DOAJ |
| description | IntroductionAccurate measurement of dietary intake without interfering in natural eating habits is a long-standing problem in nutritional epidemiology. We explored the applicability of hyperspectral imaging and machine learning for dietary assessment of home-prepared meals, by building a proof-of-concept, which automatically detects food ingredients inside closed sandwiches.MethodsIndividual spectra were selected from 24 hyperspectral images of assembled closed sandwiches, measured in a spectral range of 1116.14 nm to 1670.62 nm over 108 bands, pre-processed with Standard Normal Variate filtering, derivatives, and subsampling, and fed into multiple algorithms, among which PLS-DA, multiple classifiers, and a simple neural network.ResultsThe resulting best performing models had an accuracy score of ~80% for predicting type of bread, ~60% for butter, and ~ 28% for filling type. We see that the main struggle in predicting the fillings lies with the spreadable fillings, meaning the model may be focusing on structural aspects and not nutritional composition.DiscussionFurther analysis on non-homogeneous mixed food items, using computer vision techniques, will contribute toward a generalizable system. While there are still significant technical challenges to overcome before such a system can be routinely implemented in studies of free-living subjects, we believe it holds promise as a future tool for nutrition research and population intake monitoring. |
| format | Article |
| id | doaj-art-0ec994b875fb41fe88f611f15a7d4ce4 |
| institution | Kabale University |
| issn | 2296-861X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Nutrition |
| spelling | doaj-art-0ec994b875fb41fe88f611f15a7d4ce42025-01-17T15:11:39ZengFrontiers Media S.A.Frontiers in Nutrition2296-861X2025-01-011110.3389/fnut.2024.15206741520674The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillingsEsther Kok0Aneesh Chauhan1Michele Tufano2Edith Feskens3Guido Camps4Division of Human Nutrition and Health, Wageningen University and Research, Wageningen, NetherlandsWageningen Food and Biobased Research, Wageningen University and Research, Wageningen, NetherlandsDivision of Human Nutrition and Health, Wageningen University and Research, Wageningen, NetherlandsDivision of Human Nutrition and Health, Wageningen University and Research, Wageningen, NetherlandsDivision of Human Nutrition and Health, Wageningen University and Research, Wageningen, NetherlandsIntroductionAccurate measurement of dietary intake without interfering in natural eating habits is a long-standing problem in nutritional epidemiology. We explored the applicability of hyperspectral imaging and machine learning for dietary assessment of home-prepared meals, by building a proof-of-concept, which automatically detects food ingredients inside closed sandwiches.MethodsIndividual spectra were selected from 24 hyperspectral images of assembled closed sandwiches, measured in a spectral range of 1116.14 nm to 1670.62 nm over 108 bands, pre-processed with Standard Normal Variate filtering, derivatives, and subsampling, and fed into multiple algorithms, among which PLS-DA, multiple classifiers, and a simple neural network.ResultsThe resulting best performing models had an accuracy score of ~80% for predicting type of bread, ~60% for butter, and ~ 28% for filling type. We see that the main struggle in predicting the fillings lies with the spreadable fillings, meaning the model may be focusing on structural aspects and not nutritional composition.DiscussionFurther analysis on non-homogeneous mixed food items, using computer vision techniques, will contribute toward a generalizable system. While there are still significant technical challenges to overcome before such a system can be routinely implemented in studies of free-living subjects, we believe it holds promise as a future tool for nutrition research and population intake monitoring.https://www.frontiersin.org/articles/10.3389/fnut.2024.1520674/fullhyperspectral imagingimage classificationmachine learningdietary assessmentchemometrics |
| spellingShingle | Esther Kok Aneesh Chauhan Michele Tufano Edith Feskens Guido Camps The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings Frontiers in Nutrition hyperspectral imaging image classification machine learning dietary assessment chemometrics |
| title | The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings |
| title_full | The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings |
| title_fullStr | The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings |
| title_full_unstemmed | The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings |
| title_short | The potential of short-wave infrared hyperspectral imaging and deep learning for dietary assessment: a prototype on predicting closed sandwiches fillings |
| title_sort | potential of short wave infrared hyperspectral imaging and deep learning for dietary assessment a prototype on predicting closed sandwiches fillings |
| topic | hyperspectral imaging image classification machine learning dietary assessment chemometrics |
| url | https://www.frontiersin.org/articles/10.3389/fnut.2024.1520674/full |
| work_keys_str_mv | AT estherkok thepotentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT aneeshchauhan thepotentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT micheletufano thepotentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT edithfeskens thepotentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT guidocamps thepotentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT estherkok potentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT aneeshchauhan potentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT micheletufano potentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT edithfeskens potentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings AT guidocamps potentialofshortwaveinfraredhyperspectralimaginganddeeplearningfordietaryassessmentaprototypeonpredictingclosedsandwichesfillings |