{"id":"W3105158752","doi":"10.1007/s12553-020-00506-6","title":"Automatic suspicions lesions segmentation based on variable-size windows in mammography images","year":2020,"lang":"en","type":"article","venue":"Health and Technology","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Thresholding; False positive paradox; Mammography; Segmentation; Computer science; Artificial intelligence; Histogram; Pixel; Pattern recognition (psychology); False positives and false negatives; Variable (mathematics); Computer vision; Breast cancer; Image (mathematics); Mathematics; Cancer; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000132793,0.00008819882,0.0001457215,0.0003329423,0.0001344395,0.00002213038,0.0001992825,0.00009429099,0.00001220334],"category_scores_gemma":[0.0001045677,0.00008838322,0.00001373052,0.001564171,0.00005372922,0.0001013547,0.00005895257,0.0002243424,0.000005639344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006457222,"about_ca_system_score_gemma":0.0001966802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004933994,"about_ca_topic_score_gemma":0.00001854574,"domain_scores_codex":[0.9990816,0.00005918772,0.0002076303,0.0003059846,0.000100961,0.0002446085],"domain_scores_gemma":[0.9994342,0.0001173964,0.0000837259,0.00022657,0.00002091235,0.0001171949],"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":[0.00004320456,0.0002165269,0.02511119,0.0004844001,0.00001387441,0.00002921561,0.0008101282,0.0006132393,0.002081136,0.06307818,0.003699868,0.903819],"study_design_scores_gemma":[0.003987874,0.004570027,0.01661775,0.0003083109,0.000009916103,0.00003852388,0.0006520524,0.9223687,0.005602218,0.03725472,0.008016952,0.0005729335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05905735,0.0005833165,0.7068603,0.2302008,0.0003294659,0.001008646,0.00001387581,0.001543096,0.0004030832],"genre_scores_gemma":[0.9072506,0.00006091234,0.0854198,0.007136349,0.00001724367,0.0001020738,0.000002289914,0.000007238064,0.000003522263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9217555,"threshold_uncertainty_score":0.3604163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362925393999543,"score_gpt":0.2646073776066826,"score_spread":0.2509781236666871,"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."}}