{"id":"W4405098987","doi":"10.22215/etd/2024-16302","title":"Opening the Black Box: Utilizing Everyday Textures as Concept-Based Explanations for Deep Learning Model Prediction of Glioma Biomarker Status","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Deep learning; Context (archaeology); Computer science; Artificial intelligence; Comprehension; Black box; Artificial neural network; Machine learning; Biomarker; Isocitrate dehydrogenase; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002159417,0.00100413,0.0003545016,0.0007182649,0.0002978238,0.00172041,0.001125357,0.001045986,0.003678962],"category_scores_gemma":[0.01366862,0.000312159,0.0007178878,0.000353039,0.0007774337,0.002637843,0.001232898,0.002181058,0.0004109032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006991043,"about_ca_system_score_gemma":0.0005860249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002078779,"about_ca_topic_score_gemma":0.002910882,"domain_scores_codex":[0.9993426,0.0003490557,0.00002914502,0.0001344054,0.0000925441,0.00005212183],"domain_scores_gemma":[0.9928765,0.005480037,0.0005687692,0.000460425,0.000434901,0.0001794235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002412023,0.0007479797,0.04141036,0.0007074507,0.0004320962,0.0007722193,0.005074249,0.2635122,0.02112456,0.03916896,0.008601825,0.6160362],"study_design_scores_gemma":[0.00004870606,0.0002217874,0.003529024,0.000140589,0.00008367594,0.00008390465,0.0003691755,0.9444944,0.005871126,0.04218441,0.002929408,0.00004374481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5110125,0.00111504,0.4757112,0.004461176,0.0002428146,0.0002433943,0.0009776379,0.001904337,0.004331896],"genre_scores_gemma":[0.8903939,0.0002725169,0.1072735,0.0002990493,0.00005210646,0.00009960702,0.0005103102,0.0000532344,0.001045752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003678962,"threshold_uncertainty_score":0.01230729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02233524759337414,"score_gpt":0.3342377055185044,"score_spread":0.3119024579251303,"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."}}