{"id":"W3081619705","doi":"10.48550/arxiv.2008.12904","title":"On segmentation of pectoralis muscle in digital mammograms by means of deep learning","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":"University of Waterloo","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Mammography; Convolutional neural network; Digital mammography; Pattern recognition (psychology); Pectoralis major muscle; Graph; Shortest path problem; Pectoral muscle; Image segmentation; Computer vision; Anatomy; Medicine; Breast cancer","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":[0.0004193226,0.0006813997,0.000423053,0.001088049,0.0002036958,0.0005288989,0.0008601561,0.0008092564,0.0008308541],"category_scores_gemma":[0.0009590157,0.0002649839,0.0004347097,0.0006766046,0.0002814184,0.0005140167,0.0004518311,0.0004397867,0.0004722911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005077348,"about_ca_system_score_gemma":0.0007148457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008613174,"about_ca_topic_score_gemma":0.01263832,"domain_scores_codex":[0.9997855,0.00002707148,0.0000135883,0.00006211687,0.00008238681,0.00002939299],"domain_scores_gemma":[0.9997304,0.00009324128,0.00004461299,0.00003306149,0.00008203035,0.0000166942],"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":[0.000245284,0.000188953,0.003469437,0.0002233106,0.0000860459,0.0001719938,0.0001004722,0.2003019,0.05339217,0.001662677,0.002610914,0.7375467],"study_design_scores_gemma":[0.000006144694,0.00006162308,0.001826973,0.00001759869,0.00001481564,0.0001074777,0.0000166702,0.9825514,0.01358903,0.0008930226,0.000906199,0.00000914773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2096488,0.001719094,0.780075,0.000433931,0.00008838841,0.0001734952,0.0004834086,0.004288164,0.003089748],"genre_scores_gemma":[0.5931315,0.000976659,0.3999689,0.000271298,0.00003640309,0.00008911892,0.001770847,0.0001707701,0.003584377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008613174,"threshold_uncertainty_score":0.01712608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04139582083193932,"score_gpt":0.1868613522911583,"score_spread":0.145465531459219,"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."}}