{"id":"W4288039947","doi":"10.1101/2022.07.25.501438","title":"Unsupervised determination of lung tumor margin with widefield polarimetric second-harmonic generation microscopy","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Fluorescence Microscopy Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; European Regional Development Fund; Lietuvos Mokslo Taryba","keywords":"Extracellular matrix; Microscopy; Margin (machine learning); Pathology; Polarimetry; Second-harmonic generation; Lung cancer; Ultrastructure; H&E stain; Matrix (chemical analysis); Anatomy; Biomedical engineering; Biology; Materials science; Optics; Staining; Medicine; Computer science; Physics; Cell biology; Laser","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003442684,0.0005181583,0.000466334,0.0003675845,0.0001604365,0.00008016866,0.0006253947,0.000407153,0.0001215782],"category_scores_gemma":[0.0001192066,0.0005741046,0.0001421522,0.0005085687,0.0001363798,0.00002165315,0.0006270235,0.0006161518,0.000002182228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000213522,"about_ca_system_score_gemma":0.000650223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005042434,"about_ca_topic_score_gemma":0.000008454277,"domain_scores_codex":[0.9974918,0.0001553126,0.0005446994,0.001059676,0.0003161384,0.0004323765],"domain_scores_gemma":[0.9975901,0.0000189038,0.000589057,0.001268236,0.0004135651,0.0001201394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008750599,0.0001016091,0.008744921,0.0002923624,0.00006123319,0.0000149438,0.000004024558,0.00001340832,0.990378,0.00002134334,0.0002775626,0.000003102298],"study_design_scores_gemma":[0.0004256747,0.0002856684,0.00583456,0.0001068421,0.00008039405,9.494639e-8,0.000002555096,0.0002263719,0.990872,7.472406e-7,0.001555379,0.000609719],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9331068,0.002262122,0.06276886,0.00002777293,0.0003320054,0.0009694868,0.0004119358,0.0001138601,0.000007174257],"genre_scores_gemma":[0.8856264,0.0002470035,0.1133164,0.0001794922,0.0001913299,0.0002683939,0.00001352605,0.0001433483,0.000014128],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0505475,"threshold_uncertainty_score":0.999671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00908615322753674,"score_gpt":0.24367871445289,"score_spread":0.2345925612253533,"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."}}