{"id":"W4394988439","doi":"10.1007/s11548-024-03133-y","title":"From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Breast Cancer Treatment Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Contouring; Margin (machine learning); Artificial intelligence; Deep learning; Ranking (information retrieval); Segmentation; Machine learning; Computer science; Medicine; Medical physics; Surgical margin; Radiology; Surgery; Resection","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006838218,0.0008283368,0.0006555055,0.002681904,0.0002843336,0.0017818,0.0007616621,0.0016193,0.001413295],"category_scores_gemma":[0.05028594,0.0002443966,0.0004762886,0.00136633,0.001170405,0.002030881,0.001283102,0.000974403,0.0005413742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008186478,"about_ca_system_score_gemma":0.0006776077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001718036,"about_ca_topic_score_gemma":0.002246141,"domain_scores_codex":[0.996479,0.001461702,0.0003838236,0.0004752837,0.0009982156,0.0002020445],"domain_scores_gemma":[0.959628,0.03011389,0.004553405,0.001494168,0.002990087,0.00122042],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004455859,0.0004294555,0.7108157,0.0003955908,0.0008993795,0.00016751,0.0006050876,0.04460111,0.00372922,0.001517023,0.004348984,0.2280351],"study_design_scores_gemma":[0.0002017787,0.004565001,0.4351183,0.0002304376,0.0005417555,0.001153201,0.001221976,0.5341549,0.008759895,0.01035733,0.003514813,0.0001805696],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651076,0.00270109,0.02517664,0.001053131,0.000132748,0.0001031858,0.001615173,0.0003970279,0.003713476],"genre_scores_gemma":[0.9959596,0.0001534846,0.003057889,0.00005701125,0.00003199121,0.00003337732,0.0003869865,0.00004205422,0.0002777141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9931618,"threshold_uncertainty_score":0.0361644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04167093970059457,"score_gpt":0.3753714439555198,"score_spread":0.3337005042549253,"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."}}