{"id":"W4415357126","doi":"10.3390/make7040124","title":"SemiSeg-CAW: Semi-Supervised Segmentation of Ultrasound Images by Leveraging Class-Level Information and an Adaptive Multi-Loss Function","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Weighting; Scale-space segmentation; Feature (linguistics); Pattern recognition (psychology); Image segmentation; Segmentation-based object categorization; Dependency (UML)","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":[0.0006168592,0.0001708846,0.0001731905,0.0002670544,0.000279287,0.0001901754,0.0001153747,0.0001018422,0.00001954022],"category_scores_gemma":[0.000186731,0.000171794,0.00002890309,0.0002866495,0.00007867195,0.00269217,0.00007177938,0.0003524623,0.000004320611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000715786,"about_ca_system_score_gemma":0.00005025491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000205135,"about_ca_topic_score_gemma":0.00001681962,"domain_scores_codex":[0.9987249,0.0002705771,0.0003749878,0.000294003,0.0001809107,0.0001545954],"domain_scores_gemma":[0.9991354,0.0002326489,0.0002252011,0.0001344915,0.0001884203,0.00008385019],"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":[0.00007629956,0.0001755443,0.0114869,0.0001664887,0.000044832,6.651111e-7,0.002368879,0.00006893636,0.2784661,0.0002599065,0.00098861,0.7058969],"study_design_scores_gemma":[0.003707819,0.0006676327,0.0404157,0.0003039682,0.0001131563,0.00004384186,0.002948726,0.6423062,0.3049218,0.0006293533,0.003322059,0.0006197544],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02794263,0.0006636325,0.9700331,0.0001368131,0.000184047,0.0002259214,0.00001044754,0.0002340112,0.0005693604],"genre_scores_gemma":[0.936148,0.0004214355,0.06216871,0.0001174557,0.00003336536,0.00003526432,0.0001971898,0.000009898691,0.0008686263],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9082054,"threshold_uncertainty_score":0.7005558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01765701309575109,"score_gpt":0.310877910444076,"score_spread":0.293220897348325,"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."}}