{"id":"W4414788238","doi":"10.1038/s41416-025-03150-x","title":"Machine learning-based prediction of luminal breast cancer subtypes using polarised light microscopy","year":2025,"lang":"en","type":"article","venue":"British Journal of Cancer","topic":"Optical Polarization and Ellipsometry","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; University of British Columbia; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Universiteit Gent; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Princess Margaret Hospital Foundation","keywords":"Breast cancer; Microscopy; Cancer; Human breast; Mammary gland","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001269874,0.00009256556,0.0002290477,0.0001912774,0.00006394977,0.00004740868,0.00009765659,0.00008764904,0.0002369267],"category_scores_gemma":[0.00002770756,0.0001077425,0.00009114025,0.0003785313,0.00003972048,0.0001464462,0.000009411471,0.0003566301,7.766209e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001562782,"about_ca_system_score_gemma":0.0001637886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005777187,"about_ca_topic_score_gemma":0.0001470682,"domain_scores_codex":[0.9991696,0.00002906167,0.0003882046,0.00007521322,0.000183443,0.0001544302],"domain_scores_gemma":[0.9994984,0.00001888537,0.0001232269,0.00004978799,0.0002374022,0.00007224262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002659106,0.000159762,0.3243288,0.0006055501,0.0004594347,0.0000453869,0.0000749161,0.4139404,0.2144158,0.00002402474,0.002751679,0.04292835],"study_design_scores_gemma":[0.005026923,0.0001537838,0.4744023,0.0058886,0.000663175,0.0004059094,0.00007527557,0.3306548,0.1359006,0.00006495707,0.04623998,0.000523761],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8958441,0.06881604,0.03017006,0.0005624468,0.003178804,0.0001430501,0.0004932086,0.00008761445,0.0007046746],"genre_scores_gemma":[0.9971561,0.001795876,0.0005068711,0.0000810386,0.0002654485,0.000001379824,0.000003821993,0.00002129853,0.0001682072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1500735,"threshold_uncertainty_score":0.4393611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005449196015842769,"score_gpt":0.2448359748662717,"score_spread":0.2393867788504289,"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."}}