{"id":"W4205830467","doi":"10.1038/s41598-021-03972-8","title":"Automated food intake tracking requires depth-refined semantic segmentation to rectify visual-volume discordance in long-term care homes","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Nutrition and Health in Aging","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Research Institute for Aging; Toronto Rehabilitation Institute; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Limiting; Segmentation; RGB color model; Deep learning; Convolutional neural network; Volume (thermodynamics); Computer vision","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004046662,0.0006527381,0.0003989866,0.0006013514,0.0001982071,0.0007605905,0.0008349916,0.000598878,0.001502095],"category_scores_gemma":[0.002044725,0.0002531385,0.0003637893,0.0003611759,0.0002864602,0.0005132188,0.000765715,0.0006499097,0.0007609316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006959779,"about_ca_system_score_gemma":0.0005478614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01254029,"about_ca_topic_score_gemma":0.02080934,"domain_scores_codex":[0.9997525,0.00004839412,0.00001124589,0.00007699904,0.00007673134,0.00003419863],"domain_scores_gemma":[0.999718,0.00008730386,0.0000401678,0.00003233461,0.0001027644,0.00001949646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00164412,0.0002981883,0.07394783,0.0007452523,0.0002612387,0.001195217,0.0006038251,0.06300417,0.06015017,0.00140774,0.01975649,0.7769857],"study_design_scores_gemma":[0.00006001671,0.0004242366,0.07239728,0.0002931985,0.0001576726,0.001356774,0.0006914776,0.8604405,0.05051094,0.004288798,0.009292091,0.00008701347],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7360136,0.00255554,0.2450671,0.0008194032,0.0001518155,0.0001538278,0.002887302,0.005592309,0.006759143],"genre_scores_gemma":[0.8830862,0.0008454151,0.1093344,0.0003741331,0.00003910771,0.00008656694,0.003344538,0.0001957119,0.002693939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01254029,"threshold_uncertainty_score":0.02493459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03344687079584848,"score_gpt":0.3607721565157859,"score_spread":0.3273252857199374,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}