{"id":"W4386022050","doi":"10.1002/ima.22951","title":"RETRACTED: <scp>Multi‐classification</scp> of brain tumor by using deep convolutional neural network model in <scp>magnetic resonance imaging</scp> images","year":2023,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":37,"is_retracted":true,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Computer science; Hyperparameter; Artificial intelligence; Deep learning; Particle swarm optimization; Pattern recognition (psychology); Brain tumor; Magnetic resonance imaging; Glioma; Categorization; Artificial neural network; Machine learning; Radiology; Pathology; Medicine","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":[0.0007185905,0.001269871,0.0005368543,0.0009442614,0.0006766046,0.00117681,0.00164882,0.001557893,0.02054133],"category_scores_gemma":[0.004409835,0.0003321103,0.0008575856,0.0006093691,0.000542203,0.001063545,0.001332524,0.001887495,0.009655646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000924563,"about_ca_system_score_gemma":0.00159805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02654785,"about_ca_topic_score_gemma":0.02943888,"domain_scores_codex":[0.9995509,0.00004369838,0.00003106147,0.00007781273,0.0001988322,0.00009767043],"domain_scores_gemma":[0.9980997,0.0002610597,0.0001022939,0.00037708,0.0009863044,0.0001735851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005456578,0.0001105364,0.007715294,0.0004339327,0.0001223011,0.003792724,0.0001625747,0.03878875,0.02551077,0.001327247,0.6600519,0.2614383],"study_design_scores_gemma":[0.00007251324,0.0001672448,0.0151697,0.0001840486,0.00008136043,0.001745341,0.0002667912,0.7613586,0.07929108,0.004038987,0.1375187,0.0001057596],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2966777,0.003682799,0.3502148,0.03975095,0.03549623,0.001759339,0.03856985,0.1667082,0.06714012],"genre_scores_gemma":[0.7115565,0.001595528,0.1399833,0.004742945,0.001720411,0.0004119647,0.04100056,0.005843187,0.09314567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02654785,"threshold_uncertainty_score":0.0687176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02499700062316891,"score_gpt":0.2790211174422454,"score_spread":0.2540241168190766,"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."}}