{"id":"W4407463850","doi":"10.1016/j.ibmed.2025.100224","title":"Hybrid deep learning and active contour approach for enhanced breast lesion segmentation and classification in mammograms","year":2025,"lang":"en","type":"article","venue":"Intelligence-Based Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Segmentation; Active contour model; Deep learning; Computer science; Pattern recognition (psychology); Lesion; Mammography; Computer vision; Medicine; Image segmentation; Breast cancer; Pathology; Internal medicine; Cancer","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":[0.0004582502,0.0001373357,0.000190203,0.0002800003,0.0001136254,0.00003852904,0.0001465975,0.00006000976,0.000003437456],"category_scores_gemma":[0.0001224771,0.0001234152,0.00001896341,0.0003686068,0.0001387238,0.0002163934,0.00003549142,0.0001737115,6.297608e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001919374,"about_ca_system_score_gemma":0.00005977087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009353808,"about_ca_topic_score_gemma":0.00003502129,"domain_scores_codex":[0.9988096,0.0000867507,0.0002852035,0.0004638034,0.0001725603,0.0001820656],"domain_scores_gemma":[0.9992046,0.0003222905,0.0001349539,0.0001506282,0.0001298568,0.000057647],"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":[0.0001549113,0.00003256317,0.0005120064,0.00009422564,0.000008765516,6.918316e-7,0.0006014585,0.0005565468,0.01948016,0.001523936,0.0000135223,0.9770212],"study_design_scores_gemma":[0.001223963,0.0005023379,0.005728754,0.0003590506,0.00002666997,0.00001288434,0.001826799,0.8004925,0.1839922,0.005359803,0.0002803144,0.0001947186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01762627,0.0003218501,0.979368,0.001029384,0.0001939134,0.0006331149,0.000001259583,0.00007004696,0.0007561919],"genre_scores_gemma":[0.9778349,0.000228271,0.02138782,0.0001775383,0.00005832336,0.000206492,0.00002223792,0.000007016928,0.0000774002],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9768265,"threshold_uncertainty_score":0.5032725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02897732523378391,"score_gpt":0.3115068216683414,"score_spread":0.2825294964345575,"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."}}