{"id":"W4414301659","doi":"10.1016/j.rineng.2025.107174","title":"TransfusionNet: Framework for cervical cancer detection using deep learning with multi-level fusion","year":2025,"lang":"en","type":"article","venue":"Results in Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep learning; Pattern recognition (psychology); Robustness (evolution); Overfitting; Preprocessor; Feature (linguistics); Concatenation (mathematics); Thresholding; Histogram; Image fusion","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002533314,0.0001613398,0.0001628867,0.0002883365,0.0001396732,0.00006212707,0.0002558629,0.0001586075,0.000001307091],"category_scores_gemma":[0.0001492564,0.0001589664,0.0000432436,0.0009340416,0.00001138385,0.0002397996,0.00006180693,0.000412258,5.065689e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004103553,"about_ca_system_score_gemma":0.00004877716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002053646,"about_ca_topic_score_gemma":0.0005423166,"domain_scores_codex":[0.9988109,0.00002457294,0.0002657755,0.0004310271,0.000158879,0.0003088846],"domain_scores_gemma":[0.9993724,0.0002244873,0.00005651033,0.0002375258,0.00006590938,0.00004320173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001003951,0.00001589342,0.0001736918,0.00009206889,0.00001238551,0.000002153029,0.0005688866,0.8329369,0.007888007,0.0003401247,3.315338e-7,0.1578691],"study_design_scores_gemma":[0.001087591,0.00006216227,0.00527481,0.0005529688,0.000008609968,0.00000417159,0.00004078361,0.9765996,0.0157219,0.0001154135,0.0003484541,0.0001835229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04769356,0.0002202194,0.9506174,0.0001208566,0.0008131051,0.0002921713,0.000002621676,0.0002197184,0.00002038776],"genre_scores_gemma":[0.6955287,0.00004641883,0.3042216,0.00001975798,0.00007659323,0.00007161413,7.067164e-7,0.00001554365,0.00001906898],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6478351,"threshold_uncertainty_score":0.6482463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02336389411432279,"score_gpt":0.2780332151394058,"score_spread":0.254669321025083,"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."}}