{"id":"W4399558075","doi":"10.1364/boe.528535","title":"Spectral library and method for sparse unmixing of hyperspectral images in fluorescence guided resection of brain tumors","year":2024,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Carl Zeiss Meditec AG","keywords":"Endmember; Hyperspectral imaging; Overfitting; Artificial intelligence; Pattern recognition (psychology); Computer science; Data set; Mixture model; Multispectral image; Mathematics; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00127827,0.0007793973,0.0005309137,0.001935963,0.000542933,0.000611463,0.001024991,0.0007783066,0.002098757],"category_scores_gemma":[0.002214095,0.0004686943,0.001513187,0.001453749,0.0005459681,0.001072594,0.001371996,0.001112337,0.00133865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004450561,"about_ca_system_score_gemma":0.00111592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001960285,"about_ca_topic_score_gemma":0.002751057,"domain_scores_codex":[0.9993736,0.0001283504,0.00003901231,0.0001444748,0.0002714848,0.00004315815],"domain_scores_gemma":[0.999398,0.0001624985,0.0001004761,0.0001149231,0.0001923939,0.00003175935],"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":[0.000262672,0.0003151533,0.002136965,0.0002940543,0.000162419,0.0002384071,0.0003554401,0.2879722,0.09882175,0.01988982,0.004269644,0.5852814],"study_design_scores_gemma":[0.00001091464,0.00003981738,0.000745239,0.00001033025,0.00001910076,0.0001175425,0.00003051775,0.9638057,0.02730233,0.004148078,0.003735542,0.00003495309],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009188023,0.00008221243,0.9892929,0.00005354616,0.00001296894,0.00003339336,0.00007368919,0.0008173395,0.0004459219],"genre_scores_gemma":[0.08141418,0.0002220223,0.9151437,0.00008383857,0.00002546458,0.0002230869,0.0005885059,0.0004107507,0.001888403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002098757,"threshold_uncertainty_score":0.00702107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163984286238156,"score_gpt":0.3491756572171251,"score_spread":0.3275358143547435,"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."}}