Google's AI photoscanner can determine body fat through selfies

Researchers at Google developed PhotoScan, a deep learning method that estimates body composition from smartphone selfies, achieving a mean absolute error of 2.15% for total body fat percentage against DXA in a validation cohort of 677 participants. In a separate cohort of 132, adding PhotoScan metrics to baseline demographics improved insulin resistance classification AUROC from 69.2% to 76.0% (p=0.002), nearly matching the 77.3% achieved with DXA data, offering a scalable alternative to DXA for cardiometabolic risk assessment.

Quantitative Biology Quantitative Methods Submitted on 27 Mar 2026 v1 https://arxiv.org/abs/2603.27017v1 , last revised 6 Apr 2026 this version, v2 Title:Beyond BMI: Smartphone Body Composition Phenotyping for Cardiometabolic Risk Assessment View PDF /pdf/2603.27017 HTML experimental https://arxiv.org/html/2603.27017v2 Abstract:Body Mass Index BMI is a widely accessible but imprecise proxy of cardiometabolic health. While assessing true body composition is superior, gold-standard methods like Dual-Energy X-ray Absorptiometry DXA are not scalable. We address this gap by developing and validating "PhotoScan," a method to estimate body composition from smartphone imagery. We pretrained a deep learning model on UK Biobank participants N=35,323 and fine-tuned on a newly recruited clinical cohort PhotoBIA cohort, N=677 with diverse ethnicity, age, and body fat distribution, achieving high accuracy against DXA for total body fat percentage BF%, MAE = 2.15% , Android-to-Gynoid fat ratio A/G, MAE = 0.11 , and visceral-to-subcutaneous fat area ratio V/S, MAE = 0.09 . Generalizability of the model was demonstrated on an independent metabolic health study cohort MetabolicMosaic cohort, N=132 participants , achieving MAEs of 2.13% for BF%, 0.09 for A/G, and 0.09 for V/S. We then evaluated the clinical utility of these metrics in the MetabolicMosaic cohort by predicting insulin resistance IR . Adding PhotoScan-derived body composition metrics to baseline demographics model Age, Sex, BMI significantly improved insulin resistance classification Area Under the Receiver Operating Characteristic Curve "AUROC" 76.0% vs 69.2%, DeLong test p=0.002, Net Reclassification Index "NRI" 0.593 . Crucially, this accessible smartphone method achieved performance nearly equivalent to adding clinical-grade DXA data to baseline demographics model AUROC 77.3% vs 69.2%, DeLong test p=0.004, NRI 0.748 . These findings demonstrate that smartphone-based phenotyping captures clinically meaningful risk signals missed by BMI and anthropometrics, offering a scalable alternative to DXA for cardiometabolic risk stratification. Submission history From: Menglian Zhou view email /show-email/b601205d/2603.27017 Fri, 27 Mar 2026 22:12:16 UTC 7,454 KB v1 /abs/2603.27017v1 v2 Mon, 6 Apr 2026 23:23:21 UTC 7,452 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .