{"id":"W4389054294","doi":"10.1007/s00521-023-09172-x","title":"VolPAM: Volumetric Phenotype-Activation-Map for data-driven discovery of 3D imaging phenotypes and interpretability","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University Health Network; University of Manitoba","funders":"","keywords":"Interpretability; Phenotype; Convolutional neural network; Phenotypic screening; Artificial intelligence; Computational biology; Computer science; Autoencoder; Clinical phenotype; Machine learning; Deep learning; Pattern recognition (psychology); Biology; Genetics; Gene","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":[0.001090296,0.001643809,0.001322747,0.001895606,0.0005407899,0.001938232,0.002472255,0.001590693,0.00709219],"category_scores_gemma":[0.006998671,0.0008822591,0.002202987,0.001171356,0.0005691899,0.001122181,0.002394268,0.001856199,0.002495818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006477,"about_ca_system_score_gemma":0.001129098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003762703,"about_ca_topic_score_gemma":0.005517282,"domain_scores_codex":[0.9996446,0.00006357321,0.00001603599,0.0001084903,0.0001302127,0.00003691675],"domain_scores_gemma":[0.9990247,0.0005709377,0.00007219762,0.0001539637,0.0001218925,0.00005628416],"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":[0.001243489,0.0004358869,0.008081611,0.001544252,0.0008735781,0.0009721644,0.0005043643,0.2452984,0.04922132,0.03336963,0.08492269,0.5735325],"study_design_scores_gemma":[0.00005484338,0.00006883298,0.001049977,0.00004434635,0.000047093,0.0002545899,0.000042322,0.9469891,0.01117385,0.03288598,0.007353511,0.0000355923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01102128,0.0003201355,0.9313527,0.0003270287,0.00008575636,0.0001367884,0.006814619,0.04906499,0.0008766699],"genre_scores_gemma":[0.2581982,0.0006236479,0.7109742,0.0005036849,0.0001235618,0.0009837071,0.01822331,0.007622178,0.00274755],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00709219,"threshold_uncertainty_score":0.02372569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02691022167415851,"score_gpt":0.3003529253605365,"score_spread":0.273442703686378,"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."}}