{"id":"W4385431541","doi":"10.1016/j.compmedimag.2023.102276","title":"Invasion depth estimation of carcinoma cells using adaptive stain normalization to improve epidermis segmentation accuracy","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Epidermis (zoology); Stain; Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Pathology; Computer vision; Biology; Anatomy; Medicine; Staining","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":[0.0007280762,0.0001532313,0.0002169605,0.0004211242,0.0001680495,0.00009262904,0.0003000372,0.00007201434,0.000001490755],"category_scores_gemma":[0.0002078565,0.0001548951,0.00004862254,0.001267212,0.00009259358,0.0006122696,0.0003529453,0.0001488226,0.000002934823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006527027,"about_ca_system_score_gemma":0.000148747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001674318,"about_ca_topic_score_gemma":0.000007317281,"domain_scores_codex":[0.9982074,0.0001537898,0.0003993382,0.0004123019,0.0005745484,0.0002525697],"domain_scores_gemma":[0.9988118,0.0003262364,0.0002073316,0.0002801228,0.0001623767,0.0002121478],"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":[0.00004864912,0.0001069095,0.001191609,0.0002211359,0.00002773926,0.00003836512,0.00257233,0.006750562,0.03504993,0.002347808,0.0005064839,0.9511385],"study_design_scores_gemma":[0.001056015,0.00007555385,0.00213173,0.0001297224,0.00001247629,0.00001685905,0.0000739346,0.9713562,0.0231367,0.001822143,0.00003756377,0.0001511248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2536053,0.00004180396,0.7447636,0.0005863728,0.0006088678,0.0002340242,0.000002608888,0.0001515314,0.000005913679],"genre_scores_gemma":[0.9099604,0.00008091152,0.0893191,0.0005190938,0.00007526523,0.00001490868,0.00001413916,0.00001341624,0.000002788173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646056,"threshold_uncertainty_score":0.631644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02803492667397791,"score_gpt":0.3012182966454943,"score_spread":0.2731833699715164,"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."}}