{"id":"W4416052529","doi":"10.1016/j.bspc.2025.109089","title":"A self-supervised framework for improved generalisability in ultrasound B-mode image segmentation","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Providence Health Care","funders":"Engineering and Physical Sciences Research Council; UK Research and Innovation","keywords":"Segmentation; Metric (unit); Pattern recognition (psychology); Breast ultrasound; Similarity (geometry); Representation (politics); Feature learning; Supervised learning; Deep learning","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":[0.004394754,0.001692307,0.001819331,0.001826713,0.000712984,0.00148817,0.003258125,0.002606213,0.001473153],"category_scores_gemma":[0.009742561,0.0006927995,0.001683064,0.001325353,0.001404901,0.001856289,0.002227079,0.002827314,0.001144057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173066,"about_ca_system_score_gemma":0.001634999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006976321,"about_ca_topic_score_gemma":0.00975563,"domain_scores_codex":[0.9972932,0.0008574199,0.0001340544,0.001059066,0.000466757,0.0001895192],"domain_scores_gemma":[0.9958106,0.001859707,0.0004232333,0.0008561375,0.0008808885,0.0001694212],"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":[0.0006297755,0.0004872156,0.004593608,0.0002933415,0.0003163708,0.0002893487,0.0003529659,0.4227924,0.02091477,0.006916862,0.01647629,0.525937],"study_design_scores_gemma":[0.00001890901,0.00004833737,0.0003632458,0.00001267397,0.00001544974,0.00005263179,0.00001272907,0.9928558,0.001903582,0.003799058,0.0009071199,0.00001054187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04099278,0.00124567,0.9485453,0.0006363562,0.0001155455,0.0001545727,0.000481165,0.00589083,0.00193792],"genre_scores_gemma":[0.5076563,0.0008485914,0.4753311,0.001607101,0.0005126589,0.000458332,0.004976525,0.001613557,0.006995974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006976321,"threshold_uncertainty_score":0.02324194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009560800702488017,"score_gpt":0.2845185971131794,"score_spread":0.2749577964106914,"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."}}