{"id":"W6958864747","doi":"10.6084/m9.figshare.c.6991530.v1","title":"Combining generative modelling and semi-supervised domain adaptation for whole heart cardiovascular magnetic resonance angiography segmentation","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Agricultural pest management studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Segmentation; Pattern recognition (psychology); Generative grammar; Generative model; Magnetic resonance imaging; Domain (mathematical analysis); Noise (video)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00005233422,0.0002450294,0.0002731932,0.00003356656,0.0001393027,0.0001216922,0.00009515358,0.0001274804,0.003311236],"category_scores_gemma":[0.00001379291,0.0001054139,0.0003151369,0.0002658507,0.00001102426,0.0000691259,0.00008745331,0.00007989376,0.0001980203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001659302,"about_ca_system_score_gemma":0.000002165665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008204285,"about_ca_topic_score_gemma":0.0001166996,"domain_scores_codex":[0.9989324,0.000044843,0.0001405698,0.000476942,0.0002045344,0.0002007223],"domain_scores_gemma":[0.9997472,0.00005526103,0.00005617081,0.00005281263,0.00004804008,0.00004053198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003932353,0.000008627898,0.000008940911,0.0002093595,0.0001426662,0.000002343444,0.0002047961,0.0002314457,0.0001597182,0.00000863168,0.9923214,0.006698144],"study_design_scores_gemma":[0.0001396904,0.0001103452,0.0004145381,0.001316499,0.00009778629,0.000001036637,0.0006763294,0.001927621,0.00001356079,0.0001640307,0.9948361,0.0003024798],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"dataset","genre_scores_codex":[0.0009112306,0.6313745,0.0001458896,0.00138797,0.0003671802,0.006744491,0.3234351,0.00109777,0.03453583],"genre_scores_gemma":[0.0091151,0.00262049,0.01919539,0.001232129,0.00446122,0.008181173,0.5919752,0.000189162,0.3630302],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.628754,"threshold_uncertainty_score":0.9975999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04430138999099202,"score_gpt":0.2193546285474492,"score_spread":0.1750532385564572,"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."}}