用于协助非洲人群进行饮食评估的人工智能可穿戴相机。

AI-enabled wearable cameras for assisting dietary assessment in African populations.

作者信息

Lo Frank P-W, Qiu Jianing, Jobarteh Modou L, Sun Yingnan, Wang Zeyu, Jiang Shuo, Baranowski Tom, Anderson Alex K, McCrory Megan A, Sazonov Edward, Jia Wenyan, Sun Mingui, Steiner-Asiedu Matilda, Frost Gary, Lo Benny

机构信息

The Hamlyn Centre for Robotic Surgery, Imperial College London, London, UK.

Department of Population Health, London School of Hygiene & Tropical Medicine, London, UK.

出版信息

NPJ Digit Med. 2024 Dec 5;7(1):356. doi: 10.1038/s41746-024-01346-8.

We have developed a population-level method for dietary assessment using low-cost wearable cameras. Our approach, EgoDiet, employs an egocentric vision-based pipeline to learn portion sizes, addressing the shortcomings of traditional self-reported dietary methods. To evaluate the functionality of this method, field studies were conducted in London (Study A) and Ghana (Study B) among populations of Ghanaian and Kenyan origin. In Study A, EgoDiet's estimations were contrasted with dietitians' assessments, revealing a performance with a Mean Absolute Percentage Error (MAPE) of 31.9% for portion size estimation, compared to 40.1% for estimates made by dietitians. We further evaluated our approach in Study B, comparing its performance to the traditional 24-Hour Dietary Recall (24HR). Our approach demonstrated a MAPE of 28.0%, showing a reduction in error when contrasted with the 24HR, which exhibited a MAPE of 32.5%. This improvement highlights the potential of using passive camera technology to serve as an alternative to the traditional dietary assessment methods.

我们开发了一种使用低成本可穿戴摄像头进行饮食评估的群体层面方法。我们的方法EgoDiet采用基于自我中心视觉的流程来学习食物份量，解决了传统自我报告饮食方法的缺点。为了评估该方法的功能，在伦敦（研究A）和加纳（研究B）对加纳和肯尼亚裔人群进行了实地研究。在研究A中，将EgoDiet的估计值与营养师的评估进行了对比，结果显示食物份量估计的平均绝对百分比误差（MAPE）为31.9%，而营养师的估计值为40.1%。我们在研究B中进一步评估了我们的方法，将其性能与传统的24小时饮食回顾法（24HR）进行了比较。我们的方法显示MAPE为28.0%，与MAPE为32.5%的24HR相比，误差有所降低。这一改进凸显了使用被动式摄像头技术作为传统饮食评估方法替代方案的潜力。