Malnutrition among newborns is a top public health concern in developing countries. Identification and subsequent growth monitoring are key to successful interventions. However, this is challenging in rural communities where health systems tend to be inaccessible and under-equipped, with poor adherence to protocol. Our goal is to equip health workers and public health systems with a solution for contactless newborn anthropometry in the community. We propose NurtureNet, a multi-task model that fuses visual information (a video taken with a low-cost smartphone) with tabular inputs to regress multiple anthropometry estimates including weight, length, head circumference, and chest circumference. We show that visual proxy tasks of segmentation and keypoint prediction further improve performance. We establish the efficacy of the model through several experiments and achieve a relative error of 3.9% and mean absolute error of 114.3 g for weight estimation. Model compression to 15 MB also allows offline deployment to low-cost smartphones.
@article{arxiv.2405.05530,
title = {NurtureNet: A Multi-task Video-based Approach for Newborn Anthropometry},
author = {Yash Khandelwal and Mayur Arvind and Sriram Kumar and Ashish Gupta and Sachin Kumar Danisetty and Piyush Bagad and Anish Madan and Mayank Lunayach and Aditya Annavajjala and Abhishek Maiti and Sansiddh Jain and Aman Dalmia and Namrata Deka and Jerome White and Jigar Doshi and Angjoo Kanazawa and Rahul Panicker and Alpan Raval and Srinivas Rana and Makarand Tapaswi},
journal= {arXiv preprint arXiv:2405.05530},
year = {2024}
}