{"id":"W2526499595","doi":"10.1007/978-3-319-46723-8_53","title":"Topology Aware Fully Convolutional Networks for Histology Gland Segmentation","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; ENCODE; Convolutional neural network; Prior probability; Dice; Pattern recognition (psychology); Deep learning; Object (grammar); Object detection; Network topology; Image segmentation; Computer vision; Pixel; Topology (electrical circuits); Mathematics; Computer network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000578977,0.0004052047,0.0004405928,0.0005420123,0.0003366508,0.0001436021,0.001783057,0.0004942725,0.00003942658],"category_scores_gemma":[0.00004103423,0.000357764,0.0001263255,0.0002475852,0.0009057648,0.0004606554,0.0005713617,0.0004215433,0.00002057398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001089609,"about_ca_system_score_gemma":0.0006459719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000126144,"about_ca_topic_score_gemma":0.0001260938,"domain_scores_codex":[0.9969055,0.00004246493,0.0004793232,0.00143211,0.0004800718,0.000660516],"domain_scores_gemma":[0.9975747,0.0007844844,0.0003768598,0.0007947753,0.0003501695,0.0001189802],"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":[0.00003546487,0.00001328907,0.00008372761,0.0000299455,0.00001990659,0.00001819797,0.0001679939,0.02560913,0.0001241383,0.05350042,0.0003164244,0.9200814],"study_design_scores_gemma":[0.0007757268,0.000488821,0.000107585,0.0001454683,0.00001286774,0.0001949738,1.236628e-7,0.7105572,0.0004943801,0.2779468,0.008641042,0.0006350304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001251098,0.0004794078,0.9882517,0.00255084,0.007167813,0.0005854998,0.00001427639,0.0001500049,0.0007878925],"genre_scores_gemma":[0.1341701,0.0001463728,0.8513325,0.005463613,0.006004717,0.0002213753,0.00004462139,0.000103009,0.002513762],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9194463,"threshold_uncertainty_score":0.9998874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01510039814091865,"score_gpt":0.2547135883113253,"score_spread":0.2396131901704067,"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."}}