{"id":"W3008562940","doi":"10.48550/arxiv.2002.08438","title":"Fine tuning U-Net for ultrasound image segmentation: which layers?","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Segmentation; Speckle noise; Artificial intelligence; Artifact (error); Modality (human–computer interaction); Computer vision; Speckle pattern; Noise (video); Salient; Ultrasound; Layer (electronics); Image (mathematics); Pattern recognition (psychology); Geology; Materials science; Acoustics; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00185807,0.002141383,0.00115733,0.0006457318,0.0006085505,0.001548701,0.002259324,0.002842833,0.003698113],"category_scores_gemma":[0.007557935,0.0008995561,0.0009726291,0.0004887081,0.0006868479,0.002666635,0.001022888,0.00252883,0.001325259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001159813,"about_ca_system_score_gemma":0.0009500862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00910558,"about_ca_topic_score_gemma":0.01178845,"domain_scores_codex":[0.9994748,0.0001208605,0.00003452774,0.0001839183,0.0000556938,0.0001302271],"domain_scores_gemma":[0.9982591,0.0009563843,0.0001188048,0.0003056132,0.0002325462,0.0001275989],"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":[0.001779576,0.0008916152,0.009384225,0.0005607909,0.0005144503,0.000431033,0.0002880544,0.3715128,0.05513548,0.003305951,0.01552418,0.5406719],"study_design_scores_gemma":[0.00008634785,0.0003021947,0.001941886,0.0001087122,0.0001203162,0.0001298993,0.0001231389,0.9595393,0.02964825,0.004570054,0.003391244,0.00003873637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4787896,0.006579449,0.473828,0.00271768,0.0009642182,0.0004930212,0.0007547117,0.02263773,0.01323562],"genre_scores_gemma":[0.7981574,0.0008195389,0.1915603,0.001350907,0.0001114296,0.000279516,0.001100937,0.001135102,0.00548492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00910558,"threshold_uncertainty_score":0.01810521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07502057494079693,"score_gpt":0.2127681324316353,"score_spread":0.1377475574908384,"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."}}