{"id":"W3186077304","doi":"10.1016/j.compmedimag.2021.101957","title":"MSDS-UNet: A multi-scale deeply supervised 3D U-Net for automatic segmentation of lung tumor in CT","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Beijing Science and Technology Planning Project; National University's Basic Research Foundation of China; National Natural Science Foundation of China","keywords":"Computer science; Scale (ratio); Artificial intelligence; Segmentation; Computer vision; Nuclear medicine; Pattern recognition (psychology); Medicine; Cartography; Geography","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":[0.0007740987,0.0001901828,0.0005879545,0.0002213141,0.00007678226,0.00003784754,0.0001139918,0.00004898199,0.00004300222],"category_scores_gemma":[0.0007053333,0.0001725504,0.0001273669,0.0003651688,0.000278351,0.00007507542,0.00009151875,0.0004372571,5.517446e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002745324,"about_ca_system_score_gemma":0.0002310571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007276982,"about_ca_topic_score_gemma":0.00001156836,"domain_scores_codex":[0.9981353,0.0001260417,0.0005862341,0.0003832882,0.000435177,0.0003339504],"domain_scores_gemma":[0.9988047,0.0003883272,0.0001157491,0.0002188889,0.0001255462,0.0003467385],"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":[0.0001919686,0.001350229,0.2972062,0.00479791,0.0002630813,0.001680919,0.002543247,0.00003901083,0.02619139,0.0003750933,0.002073417,0.6632875],"study_design_scores_gemma":[0.008718239,0.00004948711,0.0203303,0.001078581,0.0001051246,0.000515281,0.0001466759,0.9670242,0.0004590765,0.0001402213,0.001268432,0.0001643774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6907326,0.001630342,0.3009577,0.005687019,0.0004018873,0.0004448789,0.000008827002,0.00009068026,0.00004599073],"genre_scores_gemma":[0.6574047,0.0006282979,0.3331157,0.008151289,0.0002433982,0.00007226193,0.000246945,0.00006760266,0.0000698503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9669852,"threshold_uncertainty_score":0.7036402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01100650193009569,"score_gpt":0.3016983485890285,"score_spread":0.2906918466589328,"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."}}