{"id":"W4363650308","doi":"10.1117/12.2656072","title":"Attention-based CT scan interpolation for lesion segmentation of colorectal liver metastases","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Institutes of Health","keywords":"Segmentation; Artificial intelligence; Interpolation (computer graphics); Computer science; Leverage (statistics); Computer vision; Radiation treatment planning; Convolutional neural network; Pattern recognition (psychology); Sørensen–Dice coefficient; Image segmentation; Radiology; Medicine; Radiation therapy; Image (mathematics)","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":[0.0001254399,0.000167028,0.0002045377,0.0001757648,0.00003608198,0.0000218127,0.00008621982,0.00004676208,0.00004975605],"category_scores_gemma":[0.00002751454,0.0001738682,0.0001464105,0.00008411109,0.00002015101,0.0001024657,0.00004971984,0.0001208001,0.000009895773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008798818,"about_ca_system_score_gemma":0.0000249959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006072723,"about_ca_topic_score_gemma":0.00006655143,"domain_scores_codex":[0.9992492,0.00001868402,0.000290844,0.000190971,0.000121188,0.0001291342],"domain_scores_gemma":[0.9995411,0.0001358933,0.00009544542,0.0001276587,0.00007278174,0.00002711227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007692668,0.00004903556,0.001366821,0.001919736,0.0001935916,0.000003316359,0.0001546849,0.8898564,0.08072603,0.0002485965,0.00103985,0.02436499],"study_design_scores_gemma":[0.0003896868,0.00003602307,0.00190921,0.0002805441,0.0001008087,6.555574e-7,0.0002363423,0.9034436,0.09273759,0.0005791986,0.00006854697,0.0002178092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1642431,0.0001005579,0.8336995,0.00002053721,0.0006085004,0.0005765471,0.0001905559,0.0003711409,0.0001895436],"genre_scores_gemma":[0.9472474,0.00004242454,0.05120111,0.000009189102,0.00004281794,0.0001588962,0.001131735,0.00004837271,0.0001179932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7830043,"threshold_uncertainty_score":0.7090142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03668162893622066,"score_gpt":0.2926418482741166,"score_spread":0.2559602193378959,"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."}}