{"id":"W4327899673","doi":"10.1002/mp.16374","title":"Prostate cancer segmentation from MRI by a multistream fusion encoder","year":2023,"lang":"en","type":"article","venue":"Medical Physics","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Innovation and Technology Commission; Research Grants Council, University Grants Committee; City University of Hong Kong","keywords":"Computer science; Segmentation; Artificial intelligence; Pattern recognition (psychology); Encoder; Feature (linguistics); Modality (human–computer interaction); Convolution (computer science); Weighting; Image segmentation; Computer vision; Artificial neural network; Medicine; Radiology","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":[0.00005863869,0.00009975473,0.00009848071,0.0000131918,0.0001149407,0.00003050574,0.000414708,0.0000451657,0.00004014378],"category_scores_gemma":[0.00001867538,0.00008857251,0.0000287708,0.0005919449,0.00005377976,0.0002267239,0.0002130832,0.0001475157,0.0002321373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004136812,"about_ca_system_score_gemma":0.00004847684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001170277,"about_ca_topic_score_gemma":0.00002304866,"domain_scores_codex":[0.9987409,0.00002555399,0.0001495829,0.0003467752,0.0005156871,0.0002215681],"domain_scores_gemma":[0.9993191,0.0001434083,0.00006383897,0.0002933942,0.00003272949,0.0001475722],"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":[0.000004209988,0.00009316877,0.0009894294,0.000005903963,0.00001193019,0.00001071297,0.0008221556,0.001151644,0.007205992,0.0005187189,0.06739907,0.9217871],"study_design_scores_gemma":[0.001762845,0.00006101423,0.002981723,0.0001272602,0.00001743006,0.000001538448,0.00004600485,0.8078756,0.08140846,0.07586208,0.02930108,0.0005549611],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03435997,0.0001228647,0.9584455,0.005919138,0.0002976638,0.0002576196,0.00004049891,0.0004502839,0.000106491],"genre_scores_gemma":[0.9678452,0.002519497,0.02100748,0.004017458,0.001131408,0.000938792,0.0006591083,0.00005435237,0.001826694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.937438,"threshold_uncertainty_score":0.3611882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01488737271069286,"score_gpt":0.2992948942534812,"score_spread":0.2844075215427884,"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."}}