{"id":"W4362576897","doi":"10.1364/boe.487087","title":"Nonlinear microscopy and deep learning classification for mammary glandmicroenvironment studies","year":2023,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre; Institut National de la Recherche Scientifique","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Canadian Cancer Society","keywords":"Second-harmonic generation; Extracellular matrix; Microscopy; Artificial intelligence; Deep learning; Tumor microenvironment; Benchmark (surveying); Mammary tumor; Computer science; Mammary gland; Pathology; Biomedical engineering; Materials science; Cancer; Biology; Optics; Medicine; Cell biology; Physics; Internal medicine; Breast cancer","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":[0.0002322016,0.0001132233,0.0001427702,0.00006331259,0.00009080528,0.0000278054,0.0001359333,0.0001238187,0.00000161445],"category_scores_gemma":[0.0001770431,0.0001036153,0.00005680993,0.00008549022,0.0001874298,0.00000400138,0.0002377597,0.00006519336,0.000005087984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001206082,"about_ca_system_score_gemma":0.00001107735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001015643,"about_ca_topic_score_gemma":7.307437e-7,"domain_scores_codex":[0.9991536,0.00003002773,0.0001863899,0.000324331,0.000112114,0.0001935526],"domain_scores_gemma":[0.9995511,0.00003994958,0.00006251816,0.0002242667,0.00004302129,0.00007920068],"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":[0.00002022372,0.00004158545,0.0002382705,0.0000456183,0.0000784771,0.000003008568,0.00005403662,0.000001901932,0.9889137,0.00001607777,0.003875227,0.006711925],"study_design_scores_gemma":[0.0006291583,0.0004172278,0.0005345895,0.00002583915,0.00006994464,0.000006527202,0.0003784773,0.009320695,0.5916564,0.0001149638,0.3965847,0.0002614875],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8303841,0.004686485,0.162785,0.001153762,0.0001041812,0.000565098,0.00002145312,0.0001677714,0.0001320795],"genre_scores_gemma":[0.691767,0.05650488,0.2414963,0.0006399192,0.00101903,0.00050125,0.003416249,0.0001170117,0.004538372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3972573,"threshold_uncertainty_score":0.4225309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01784760328564821,"score_gpt":0.3117710640034278,"score_spread":0.2939234607177796,"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."}}