{"id":"W4414902551","doi":"10.48550/arxiv.2503.15008","title":"A Novel Channel Boosted Residual CNN-Transformer with Regional-Boundary Learning for Breast Cancer Detection","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Residual; Pattern recognition (psychology); Redundancy (engineering); Convolutional neural network; Block (permutation group theory); Pixel; Deep learning; Feature extraction; Digital mammography","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":[0.0004093159,0.000985394,0.0006732217,0.0006708966,0.000210324,0.0005174791,0.001575196,0.0005522923,0.002644365],"category_scores_gemma":[0.0008872033,0.0002931545,0.0006953729,0.0004876203,0.0002875501,0.001001512,0.0009273487,0.0006610524,0.001042097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006172548,"about_ca_system_score_gemma":0.001083097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006720264,"about_ca_topic_score_gemma":0.01097956,"domain_scores_codex":[0.9997365,0.00002391718,0.00001016325,0.00008734953,0.00008832171,0.00005374924],"domain_scores_gemma":[0.9998332,0.00002904961,0.00001754175,0.00003502585,0.00006612369,0.00001902016],"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":[0.0003993201,0.0001898087,0.004201905,0.0001843048,0.0001930967,0.0001959343,0.00006443298,0.1106683,0.07680139,0.004333482,0.01172148,0.7910466],"study_design_scores_gemma":[0.00002400431,0.0001451555,0.0009889761,0.00001032801,0.00006160024,0.0001629555,0.00001757523,0.9651991,0.02798218,0.001705805,0.0036839,0.00001838558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0883159,0.001286131,0.8924022,0.0003346672,0.0001941423,0.0002037571,0.0009395548,0.01017344,0.006150042],"genre_scores_gemma":[0.6641889,0.0005436316,0.3180735,0.0005124444,0.00009677779,0.0001748835,0.003925653,0.00042852,0.01205562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006720264,"threshold_uncertainty_score":0.01336229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04226370881019845,"score_gpt":0.2801283594251154,"score_spread":0.237864650614917,"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."}}