{"id":"W4316673537","doi":"10.1049/cit2.12175","title":"Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features","year":2023,"lang":"en","type":"article","venue":"CAAI Transactions on Intelligence Technology","topic":"Sarcoma Diagnosis and Treatment","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Zhejiang Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Osteosarcoma; Classifier (UML); Artificial intelligence; Feature extraction; Medicine; Pathology; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0005759617,0.0003313298,0.0003422801,0.001256827,0.0001175461,0.0004705101,0.0002156815,0.0003109074,0.0005125924],"category_scores_gemma":[0.0013571,0.0001272745,0.0002808379,0.0004295177,0.0001684233,0.0002782086,0.0002179996,0.0001876496,0.000221218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000247523,"about_ca_system_score_gemma":0.0002478529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001601698,"about_ca_topic_score_gemma":0.001891863,"domain_scores_codex":[0.9997718,0.0000359347,0.0000247327,0.00004920858,0.00009155217,0.00002673544],"domain_scores_gemma":[0.9994223,0.000166185,0.0001399203,0.00003876949,0.0002008652,0.00003206376],"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":[0.0008393746,0.0004210903,0.3489067,0.0002324363,0.0001932818,0.0004483768,0.0001353426,0.04706096,0.225102,0.0007797415,0.002270411,0.3736103],"study_design_scores_gemma":[0.00003650672,0.0006351139,0.152394,0.00003188111,0.0002236344,0.0008268561,0.0001365433,0.7809723,0.06258608,0.0006556421,0.00145016,0.00005129977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8810927,0.0005237577,0.1158328,0.0001038898,0.00003842452,0.00008429297,0.0004074954,0.0005898954,0.001326722],"genre_scores_gemma":[0.9768116,0.00009022637,0.02224711,0.00002061607,0.00001463372,0.00003275155,0.0003099916,0.00001206169,0.0004609387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001601698,"threshold_uncertainty_score":0.003184736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04853993164704506,"score_gpt":0.3198876288026712,"score_spread":0.2713476971556262,"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."}}