{"id":"W2978969543","doi":"10.1109/ijcnn.2019.8851758","title":"Projectron – A Shallow and Interpretable Network for Classifying Medical Images","year":2019,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Radon; Computer science; MNIST database; Equidistant; Encoding (memory); Artificial intelligence; Radon transform; Pattern recognition (psychology); Layer (electronics); Image (mathematics); Artificial neural network; Medical imaging; Domain (mathematical analysis); Computer vision; Mathematics","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":[0.001495574,0.001115488,0.000793267,0.0007464421,0.0002994176,0.0009685955,0.001546103,0.001654033,0.003245766],"category_scores_gemma":[0.004280336,0.0004633426,0.0009069606,0.0006937651,0.0006582512,0.001930388,0.001372179,0.001662057,0.001079328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006259033,"about_ca_system_score_gemma":0.0006537507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002259595,"about_ca_topic_score_gemma":0.002550261,"domain_scores_codex":[0.9993677,0.0002530432,0.00003806165,0.0001304458,0.0001485184,0.00006230695],"domain_scores_gemma":[0.9990337,0.0005046661,0.00009359238,0.0001256343,0.000188954,0.0000534109],"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":[0.0004852356,0.0001657868,0.004219905,0.0003388715,0.0003067838,0.0003925145,0.0001995789,0.3629781,0.01866253,0.01553063,0.01110447,0.5856156],"study_design_scores_gemma":[0.0000103801,0.00007756694,0.0003685227,0.00003173862,0.00002580157,0.00009276042,0.00001880698,0.9848849,0.00358291,0.009504525,0.001386734,0.00001545103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02860692,0.0006135787,0.9650363,0.0005746403,0.0000939212,0.00007050894,0.0003777662,0.002694624,0.001931691],"genre_scores_gemma":[0.6144615,0.0009420249,0.3726116,0.0008554044,0.0001494789,0.0003158099,0.001711623,0.0002331475,0.008719401],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003245766,"threshold_uncertainty_score":0.01085818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008838301136692836,"score_gpt":0.2543384431975722,"score_spread":0.2455001420608793,"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."}}