{"id":"W4403837039","doi":"10.1016/j.isci.2024.111273","title":"Deep learning-based hyperspectral image correction and unmixing for brain tumor surgery","year":2024,"lang":"en","type":"article","venue":"iScience","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Westfälische Wilhelms-Universität Münster; Carl Zeiss Meditec AG","keywords":"Hyperspectral imaging; Artificial intelligence; Protoporphyrin IX; Imaging phantom; Computer science; Visualization; Deep learning; Brain tissue; Pattern recognition (psychology); Fluorescence; Biomedical engineering; Radiology; Medicine; Physics; Optics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004628505,0.00007535876,0.0001255678,0.0001257544,0.0001102607,0.0001251405,0.00003197523,0.00002069643,0.00001684962],"category_scores_gemma":[0.0007887051,0.00006201409,0.00005737285,0.0002416771,0.0001979304,0.0001283186,0.00001007421,0.0001628733,0.000005999016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005384245,"about_ca_system_score_gemma":0.00008711179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001703983,"about_ca_topic_score_gemma":0.000001974301,"domain_scores_codex":[0.9992785,0.00001594266,0.00009732372,0.0002672324,0.0001229489,0.0002180934],"domain_scores_gemma":[0.9993209,0.0004703781,0.00001488248,0.00007581056,0.00003859536,0.0000794511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001463963,0.0001343647,0.008876955,0.0005137853,0.00001690799,0.0002489983,0.0006115072,0.00004540259,0.8879543,0.002111448,0.02107596,0.07826396],"study_design_scores_gemma":[0.0001738222,0.0004376767,0.003638906,0.0003899604,0.00003867126,0.0002190184,0.0001783579,0.7955598,0.1914516,0.000591859,0.007129274,0.0001910438],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2956693,0.001624785,0.6837195,0.01363912,0.0008506111,0.0003785268,0.000001725615,0.001158206,0.002958286],"genre_scores_gemma":[0.9633929,0.00001297396,0.03483691,0.000567461,0.0001046636,0.00002185448,0.000002805329,0.00001464425,0.001045844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7955144,"threshold_uncertainty_score":0.2528861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01294454695848364,"score_gpt":0.31408336852216,"score_spread":0.3011388215636763,"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."}}