AI-based digital image dietary assessment methods compared to humans and ground truth: a systematic review.
AI-based digital image dietary assessment methods compared to humans and ground truth: a systematic review.
复制标题
DOI：
10.1080/07853890.2023.2273497
复制
发表时间：
2023
影响因子：
4.4
通讯作者：
中科院分区：
文献类型：
--
作者：
估计食物摄入量的人为错误是营养研究中偏见的主要来源。人工智能（AI）方法可能会减少偏见，但人工智能估计的整体准确性尚不清楚。本研究对同行评议的期刊文章进行了系统回顾，比较了基于人工智能（如深度学习）的全自动饮食评估方法，从数字图像到人类评估者和基本事实（如双重标签水）。截至2023年5月，在四个电子数据库中检索文献，并进行参考文献挖掘。符合条件的文章报告了人工智能估计的体积、能量或营养。独立调查人员筛选文章并提取数据。在没有适用的偏倚风险评估工具的情况下，记录了潜在的偏倚来源。数据库和手工检索确定了14,059种独特的出版物；保留2010 - 2023年间发表的52篇论文（研究）。对于食物检测和分类，79%的论文使用了卷积神经网络。共同的基础真相来源是使用营养表（51%）和称重食物（27%）进行计算。纳入的论文在食品图像数据库和结果报告中差异很大，因此无法进行元分析综合。从69%的论文中提取或计算出相对误差。热量计算的平均总体相对误差（人工智能与真实情况）在0.10%到38.3%之间，体积计算的平均相对误差在0.09%到33%之间，两者表现相似。当图像中有单一或简单的食物时，相对误差范围较低。体积和卡路里估算的相对误差表明，人工智能方法与人类估算的准确性保持一致，并有可能超过人类估算的准确性。然而，食物图像数据库和结果报告的可变性阻碍了meta分析综合。该领域可以通过在有限数量的大规模食品图像和营养数据库上测试人工智能架构来推进，该领域认为这些数据库足以进行培训和测试，并通过报告体积或卡路里估计的至少绝对和相对误差的准确性。这些结果表明，人工智能方法符合并有可能超过基于数字食物图像的人类对营养成分估计的准确性。所使用的食品图像数据库的可变性和报告的结果阻碍了meta分析综合。该领域可以通过在有限数量的大规模食品图像和营养数据库上测试人工智能架构来推进，该领域认为这些数据库是准确的，并通过报告体积或卡路里估计的至少绝对和相对误差的准确性来推进。总的来说，目前可用的工具在作为营养研究或临床实践中独立的饮食评估方法部署之前需要更多的开发。
Human error estimating food intake is a major source of bias in nutrition research. Artificial intelligence (AI) methods may reduce bias, but the overall accuracy of AI estimates is unknown. This study was a systematic review of peer-reviewed journal articles comparing fully automated AI-based (e.g. deep learning) methods of dietary assessment from digital images to human assessors and ground truth (e.g. doubly labelled water). Literature was searched through May 2023 in four electronic databases plus reference mining. Eligible articles reported AI estimated volume, energy, or nutrients. Independent investigators screened articles and extracted data. Potential sources of bias were documented in absence of an applicable risk of bias assessment tool. Database and hand searches identified 14,059 unique publications; fifty-two papers (studies) published from 2010 to 2023 were retained. For food detection and classification, 79% of papers used a convolutional neural network. Common ground truth sources were calculation using nutrient tables (51%) and weighed food (27%). Included papers varied widely in food image databases and results reported, so meta-analytic synthesis could not be conducted. Relative errors were extracted or calculated from 69% of papers. Average overall relative errors (AI vs. ground truth) ranged from 0.10% to 38.3% for calories and 0.09% to 33% for volume, suggesting similar performance. Ranges of relative error were lower when images had single/simple foods. Relative errors for volume and calorie estimations suggest that AI methods align with – and have the potential to exceed – accuracy of human estimations. However, variability in food image databases and results reported prevented meta-analytic synthesis. The field can advance by testing AI architectures on a limited number of large-scale food image and nutrition databases that the field determines to be adequate for training and testing and by reporting accuracy of at least absolute and relative error for volume or calorie estimations. These results suggest that AI methods are in line with – and have the potential to exceed – accuracy of human estimations of nutrient content based on digital food images. Variability in food image databases used and results reported prevented meta-analytic synthesis. The field can advance by testing AI architectures on a limited number of large-scale food image and nutrition databases that the field determines to be accurate and by reporting accuracy of at least absolute and relative error for volume or calorie estimations. Overall, the tools currently available need more development before deployment as stand-alone dietary assessment methods in nutrition research or clinical practice.
登录
查看更多内容
DOI：
10.1038/s41366-020-00693-2
发表时间：
2020-12
期刊：
International journal of obesity (2005)
影响因子：
--
作者：
Höchsmann C;Martin CK
通讯作者：
Martin CK
DOI：
10.1587/transinf.2017mvp0027
发表时间：
2018-05-01
影响因子：
0.7
作者：
Ege, Takumi;Yanai, Keiji
通讯作者：
Yanai, Keiji
影响因子：
2.7
作者：
Dai, Yanyan;Park, Subin;Lee, Kidong
通讯作者：
Lee, Kidong
影响因子：
2.3
作者：
Hassannejad, Hamid;Matrella, Guido;Cagnoni, Stefano
通讯作者：
Cagnoni, Stefano
影响因子：
5
作者：
Anthimopoulos, Marios;Dehais, Joachim;Mougiakakou, Stavroula
通讯作者：
Mougiakakou, Stavroula