{"id":"W4412525167","doi":"10.1038/s41598-025-11508-7","title":"AI-CMCA: a deep learning-based segmentation framework for capillary microfluidic chip analysis","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Microfluidic and Capillary Electrophoresis Applications","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alberta Innovates","keywords":"Segmentation; Computer science; Microfluidics; Chip; Microfluidic chip; Deep learning; Capillary action; Lab-on-a-chip; Artificial intelligence; Nanotechnology; Materials science; Telecommunications","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":[0.000624097,0.001535996,0.000731303,0.001052206,0.000455988,0.001096021,0.002774622,0.001502583,0.002669787],"category_scores_gemma":[0.001474656,0.0006053429,0.001243668,0.0006923322,0.0006479674,0.001058348,0.001107163,0.001740463,0.001112467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001831936,"about_ca_system_score_gemma":0.002529586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01276189,"about_ca_topic_score_gemma":0.01589717,"domain_scores_codex":[0.9996715,0.00003772383,0.00001501849,0.0001230088,0.0001055412,0.00004716973],"domain_scores_gemma":[0.9996438,0.0001305991,0.00004457642,0.00003533112,0.0001099375,0.00003569006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004040998,0.0002300194,0.001842273,0.0003994688,0.0002119241,0.000195421,0.0001161419,0.4983668,0.05479259,0.01147957,0.0197755,0.4121861],"study_design_scores_gemma":[0.000007517452,0.00002477581,0.0001292881,0.000009440343,0.00001046557,0.00002341113,0.000004213371,0.9885319,0.007145078,0.00230367,0.001800042,0.00001008167],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01208318,0.0008660371,0.9671987,0.0002787989,0.00009531919,0.0001009201,0.0008790077,0.01649804,0.001999936],"genre_scores_gemma":[0.2176251,0.0007389924,0.769756,0.0009986645,0.00006972293,0.0004585063,0.003538681,0.001116771,0.005697419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01276189,"threshold_uncertainty_score":0.02537519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005598697196989912,"score_gpt":0.2405561981059596,"score_spread":0.2349575009089697,"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."}}