{"id":"W3183458014","doi":"10.1016/j.compbiomed.2021.104699","title":"Sharp U-Net: Depthwise convolutional network for biomedical image segmentation","year":2021,"lang":"en","type":"preprint","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Encoder; Convolutional neural network; Pattern recognition (psychology); Sharpening; Feature (linguistics); Network architecture; Image segmentation; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003991124,0.001500731,0.0006481218,0.001129515,0.0003601708,0.0009334214,0.001722046,0.001598318,0.01291118],"category_scores_gemma":[0.001137853,0.0008522808,0.0007204078,0.0009989933,0.0004084331,0.001097041,0.001408777,0.001437236,0.004520738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008355065,"about_ca_system_score_gemma":0.001304615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01070511,"about_ca_topic_score_gemma":0.01800952,"domain_scores_codex":[0.9998093,0.00002150821,0.000008243344,0.00007135127,0.00005161007,0.00003798533],"domain_scores_gemma":[0.9997917,0.00005195132,0.00001894684,0.00005127492,0.00006259323,0.0000236047],"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":[0.0004726133,0.0001669354,0.000792187,0.0003497646,0.0001782429,0.000185427,0.00006655074,0.09758319,0.03494347,0.01788023,0.07577942,0.7716019],"study_design_scores_gemma":[0.00003008777,0.0000579869,0.0003981076,0.00002670662,0.0000261141,0.0001087763,0.0000103087,0.9445773,0.03259075,0.01182477,0.01033081,0.00001837062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01168635,0.0008661908,0.9519513,0.0003646797,0.0001793535,0.0001493136,0.003230893,0.0275583,0.004013653],"genre_scores_gemma":[0.1660867,0.0009481241,0.7925672,0.0005161463,0.0001153588,0.0003189702,0.007970148,0.002366751,0.02911059],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01291118,"threshold_uncertainty_score":0.04319215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02352291940269965,"score_gpt":0.3336563153983283,"score_spread":0.3101333959956287,"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."}}