{"id":"W4414372291","doi":"10.1007/s00521-025-11631-6","title":"MammoSegNet: a convolutional network analysis for segmenting tumor tissue masses in digital mammograms of breast cancer patients","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Lakehead University","funders":"University of Southern Queensland","keywords":"Preprocessor; Convolutional neural network; Pattern recognition (psychology); Segmentation; Normalization (sociology); Feature extraction; Breast cancer; Robustness (evolution); Mammography; Pixel","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":[0.00009082588,0.00009100654,0.0001656503,0.0001340228,0.0001729259,0.00009430308,0.0002197226,0.00002639666,0.000001361305],"category_scores_gemma":[0.000007067569,0.00009534547,0.00005095848,0.001396274,0.00004336624,0.0001359389,0.0001456464,0.00006974088,3.015956e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005114737,"about_ca_system_score_gemma":0.00003427391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008068754,"about_ca_topic_score_gemma":0.00004134993,"domain_scores_codex":[0.9991025,0.00001332537,0.0002739929,0.000315808,0.0001023135,0.0001920886],"domain_scores_gemma":[0.9993738,0.0001580181,0.0001462037,0.0001629223,0.0001292208,0.00002985576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001127252,0.0001025218,0.6392525,0.00006985152,0.00009163688,1.540662e-7,0.00005798562,0.04223494,0.0001043995,0.006247383,0.0001459319,0.3116814],"study_design_scores_gemma":[0.0004213282,0.00003334582,0.4654672,0.00005221811,0.00005818873,0.000001795294,0.00001765785,0.5305787,0.0001320137,0.002030626,0.001067325,0.0001396293],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.251938,0.0001501676,0.746939,0.0002533839,0.00009598258,0.0004115838,0.00005162377,0.00005952454,0.0001007338],"genre_scores_gemma":[0.9931155,0.000003407479,0.006547171,0.00008155854,0.00007225785,0.0001297436,0.00001932271,0.000004060328,0.00002693424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7411776,"threshold_uncertainty_score":0.3888075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007587469216668794,"score_gpt":0.2684202071225921,"score_spread":0.2608327379059233,"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."}}