{"id":"W4413800665","doi":"10.1101/2025.08.26.25334483","title":"The African Breast Imaging Dataset for Equitable Cancer Care: Protocol for an Open Mammogram and Ultrasound Breast Cancer Detection Dataset","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Breast cancer; Mammography; Outreach; Breast examination; Cancer; Incidence (geometry); Breast ultrasound; Family medicine; Radiology; Medical physics; Internal medicine","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008120011,0.001402759,0.001531572,0.001866222,0.001411722,0.002151261,0.003973113,0.002808308,0.050499],"category_scores_gemma":[0.02931239,0.0007137712,0.001250377,0.002678234,0.0008311508,0.001038155,0.002657349,0.00179317,0.02649724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001872766,"about_ca_system_score_gemma":0.003610403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007650491,"about_ca_topic_score_gemma":0.01430816,"domain_scores_codex":[0.9962626,0.001535525,0.0006507006,0.0007350137,0.0004877163,0.0003283685],"domain_scores_gemma":[0.990979,0.001958126,0.0008995286,0.003164557,0.002205192,0.0007936874],"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":[0.002435308,0.0003297058,0.00667581,0.002659103,0.0002504175,0.0001486947,0.0001265553,0.00101603,0.0006713059,0.00145288,0.9691282,0.01510596],"study_design_scores_gemma":[0.005778223,0.0003544601,0.03306841,0.001707838,0.0002911189,0.0006116969,0.000289167,0.003358553,0.001784235,0.004612115,0.9479955,0.0001485175],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"protocol","genre_scores_codex":[0.002435017,0.0002182975,0.002175561,0.0006109106,0.0001165926,0.006246857,0.9860917,0.0007161746,0.001389002],"genre_scores_gemma":[0.005838136,0.0001331058,0.007429638,0.0005276448,0.00007186356,0.03942912,0.94491,0.0001609776,0.00149948],"genre_candidate":"protocol","genre_consensus":null,"teacher_disagreement_score":0.9960269,"threshold_uncertainty_score":0.168936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04130322339861259,"score_gpt":0.3791196600181018,"score_spread":0.3378164366194892,"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."}}