{"id":"W4401768890","doi":"10.18280/isi.290433","title":"Innovative: A Novel Deep Learning-Based Semantic Segmentation Architecture for Medical Applications","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Deep learning; Architecture; Computer science; Segmentation; Artificial intelligence; Computer architecture; Natural language processing; Data science; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001376519,0.0002042049,0.0002312328,0.0004621127,0.001237073,0.00009626386,0.0002127281,0.0003688374,0.0003033718],"category_scores_gemma":[0.00164402,0.0001863569,0.00007485681,0.001197381,0.0001602874,0.0008447107,0.00005141288,0.000842898,0.0005270353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006127362,"about_ca_system_score_gemma":0.0009846737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00025714,"about_ca_topic_score_gemma":0.0004187386,"domain_scores_codex":[0.9973696,0.0001747174,0.00124803,0.0002205014,0.0004841128,0.0005030107],"domain_scores_gemma":[0.9969897,0.001360388,0.0003235438,0.0002070339,0.0009675494,0.0001518108],"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":[0.0001690076,0.00006765948,0.007133807,0.01428436,0.00009103053,0.00000225528,0.05256186,0.009916081,0.000566883,0.04583281,0.001463886,0.8679104],"study_design_scores_gemma":[0.000584462,0.0002729311,0.001267812,0.002400619,0.00004491049,0.00001430948,0.01834417,0.7728424,0.001040815,0.01274655,0.1899382,0.0005027613],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01671995,0.0001987443,0.9754598,0.001512257,0.0006883902,0.00310925,0.00007259771,0.0006252444,0.001613783],"genre_scores_gemma":[0.9847056,0.00002026207,0.007130187,0.001589197,0.000473601,0.00487171,0.001028768,0.00004033447,0.000140337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9683296,"threshold_uncertainty_score":0.9514688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04710950111946562,"score_gpt":0.4032972452591072,"score_spread":0.3561877441396415,"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."}}