{"id":"W3159603107","doi":"10.1007/s11548-021-02381-6","title":"Domain adaptation and self-supervised learning for surgical margin detection","year":2021,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Classifier (UML); Transfer of learning; Breast cancer; Breast-conserving surgery; Margin (machine learning); Modality (human–computer interaction); Surgical margin; Machine learning; Medicine; Pattern recognition (psychology); Surgery; Cancer; Mastectomy; Resection; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001842875,0.0006944921,0.0009847024,0.001028602,0.0003722173,0.0006252388,0.001436728,0.001291678,0.001114947],"category_scores_gemma":[0.003607003,0.0003104492,0.001066466,0.0008826207,0.0004396026,0.0007980767,0.001022053,0.001295803,0.0009344723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003977104,"about_ca_system_score_gemma":0.0007804738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002532508,"about_ca_topic_score_gemma":0.002753302,"domain_scores_codex":[0.9991745,0.0002719106,0.00004846015,0.0002497123,0.0001426314,0.0001127949],"domain_scores_gemma":[0.9979532,0.0008989847,0.0001441128,0.0003563102,0.0005720873,0.00007539053],"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":[0.0003935341,0.0004873135,0.004230806,0.0001346117,0.0001894481,0.0001088577,0.0001163482,0.2113986,0.02130532,0.001542765,0.007918657,0.7521738],"study_design_scores_gemma":[0.000009381462,0.00005640469,0.001068393,0.000006164159,0.00001823926,0.00005756963,0.00001752701,0.9927383,0.004086082,0.001374371,0.0005585755,0.00000898701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07514687,0.001088954,0.9185666,0.0002346214,0.0001578858,0.00009809237,0.0002389924,0.003099672,0.001368355],"genre_scores_gemma":[0.7686968,0.0004074701,0.2237051,0.0002954504,0.0001785718,0.00016058,0.001359151,0.0002473707,0.004949403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002532508,"threshold_uncertainty_score":0.009746134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01967210501897412,"score_gpt":0.2494062698770753,"score_spread":0.2297341648581012,"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."}}