{"id":"W4387844354","doi":"10.1016/j.heliyon.2023.e21369","title":"Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model","year":2023,"lang":"en","type":"article","venue":"Heliyon","topic":"AI in cancer detection","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Charles Darwin University","keywords":"Ultrasound; Artificial intelligence; Segmentation; Computer science; Image segmentation; Pattern recognition (psychology); Ultrasound imaging; Breast ultrasound; Breast tumor; Computer vision; Breast cancer; Medicine; Radiology; Mammography; 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":[0.0001714386,0.0001327502,0.0001063867,0.0001543156,0.0001740285,0.0002017773,0.0001637301,0.00002779189,0.000004403351],"category_scores_gemma":[0.00001172626,0.0001259755,0.00001726289,0.0006142879,0.00005074008,0.000763391,0.00005498655,0.00008331813,0.00005064713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001527213,"about_ca_system_score_gemma":0.00008246605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002298461,"about_ca_topic_score_gemma":0.00001754934,"domain_scores_codex":[0.9988981,0.00004645514,0.0001751576,0.0003985978,0.0002632058,0.0002184102],"domain_scores_gemma":[0.9993725,0.00004834776,0.0001245345,0.0002997007,0.0000933281,0.00006161469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005782276,0.00003618584,0.001291922,0.000211127,0.00002463724,0.00002513008,0.0008713938,0.01891862,0.9697722,0.0002861467,0.0007191642,0.007785617],"study_design_scores_gemma":[0.0003655351,0.00004572417,0.01291571,0.00008257632,0.00001126584,0.0002383862,0.00004668831,0.957218,0.0287057,0.0001956218,0.00001721872,0.0001576015],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6187156,0.00003221805,0.3795953,0.0002306723,0.000115363,0.0001885231,0.00001511025,0.001021338,0.0000859084],"genre_scores_gemma":[0.9525776,0.00005048129,0.04705851,0.00008369168,0.00004972342,0.00003265026,0.00003232458,0.00002267693,0.00009233705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9410666,"threshold_uncertainty_score":0.513713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02564810022028016,"score_gpt":0.2730403870078402,"score_spread":0.24739228678756,"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."}}