{"id":"W6902024928","doi":"10.6084/m9.figshare.14752279.v1","title":"Additional file 3 of Implementation of deep learning-based auto-segmentation for radiotherapy planning structures: a workflow study at two cancer centers","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saskatchewan Cancer Agency","funders":"","keywords":"Workflow; Cancer; Radiation therapy; Volume (thermodynamics); File management","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001417952,0.001446352,0.0008488674,0.001489081,0.0006262936,0.001922059,0.002163534,0.001178197,0.8097537],"category_scores_gemma":[0.01560974,0.0008584854,0.001025638,0.00143107,0.0002606326,0.001167018,0.001434065,0.0009845082,0.2457183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001064422,"about_ca_system_score_gemma":0.001332307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005898801,"about_ca_topic_score_gemma":0.01007945,"domain_scores_codex":[0.9994494,0.00008265048,0.00009499902,0.0001282808,0.0001795752,0.0000651403],"domain_scores_gemma":[0.9919938,0.005245522,0.0003318154,0.0007421177,0.001428055,0.000258747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0005463741,0.00005925073,0.001538936,0.0008929588,0.00004187401,0.0001281957,0.00006189162,0.001847233,0.0003403439,0.0004282674,0.9720805,0.02203425],"study_design_scores_gemma":[0.003294906,0.0002888545,0.01365212,0.00135134,0.0001795729,0.00127754,0.0002629764,0.02043029,0.008525138,0.0118539,0.9386664,0.0002170566],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.001246524,0.00009004944,0.009890036,0.0003983664,0.0001323925,0.0003215853,0.9523445,0.02835462,0.007221999],"genre_scores_gemma":[0.02701435,0.0001849283,0.03444232,0.0007709161,0.0001671537,0.002062563,0.8769803,0.03527701,0.0231005],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8097537,"threshold_uncertainty_score":0.2713633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02008202783399754,"score_gpt":0.3469453588253156,"score_spread":0.326863330991318,"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."}}