{"id":"W4415218161","doi":"10.1016/j.fraope.2025.100385","title":"A combined UNet++ and LSTM approach for breast ultrasound image segmentation","year":2025,"lang":"en","type":"article","venue":"Franklin Open","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Zoo","funders":"","keywords":"Segmentation; Pipeline (software); Pattern recognition (psychology); Ground truth; Feature (linguistics); Breast ultrasound; Feature extraction; Deep learning; Artificial neural network","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":[0.000373241,0.001195438,0.0005501584,0.000523228,0.0003135534,0.0006657502,0.001496569,0.001388566,0.002507637],"category_scores_gemma":[0.001092316,0.0004456449,0.0008643072,0.0006105723,0.0002819507,0.001134266,0.0009982121,0.001148638,0.001085957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007370865,"about_ca_system_score_gemma":0.0009915932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008915385,"about_ca_topic_score_gemma":0.01232705,"domain_scores_codex":[0.9997701,0.00002732653,0.00001388103,0.00009433513,0.00004879232,0.00004565648],"domain_scores_gemma":[0.9998189,0.00004844241,0.00001738966,0.00002591252,0.00007337809,0.00001601386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002981336,0.0001605572,0.001565458,0.0002388546,0.0001505527,0.0004091407,0.0001472438,0.3262364,0.05311169,0.003336319,0.009726605,0.604619],"study_design_scores_gemma":[0.000007776265,0.00006867902,0.0003156503,0.0000143876,0.00002859865,0.00007969953,0.00001435924,0.9860784,0.009877216,0.001745522,0.001757465,0.00001227418],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0582171,0.001914372,0.921033,0.0008411153,0.0003248343,0.0001770556,0.001044309,0.01094101,0.005507215],"genre_scores_gemma":[0.5904465,0.001289106,0.3915576,0.001043177,0.0001750035,0.0003385381,0.002881495,0.0004290217,0.01183957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008915385,"threshold_uncertainty_score":0.01772702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01174547518244128,"score_gpt":0.283422305787283,"score_spread":0.2716768306048417,"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."}}