{"id":"W4408570713","doi":"10.3390/bioengineering12030311","title":"Improved A-Line and B-Line Detection in Lung Ultrasound Using Deep Learning with Boundary-Aware Dice Loss","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Innovates","keywords":"Dice; Segmentation; Artificial intelligence; Computer science; Computer vision; Encoder; Sørensen–Dice coefficient; Pattern recognition (psychology); Hausdorff distance; Boundary (topology); Image segmentation; Preprocessor; Deep learning; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002034519,0.0001798227,0.0002733906,0.0001929351,0.0001160186,0.00004643983,0.00005939241,0.0001241741,0.000009530504],"category_scores_gemma":[0.0003475661,0.0001649477,0.00003714834,0.0006120877,0.00008765545,0.0001012006,0.00003334359,0.0004849677,0.000001369724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001777182,"about_ca_system_score_gemma":0.00005400804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001162582,"about_ca_topic_score_gemma":0.000139034,"domain_scores_codex":[0.9989421,0.00001538651,0.0003356623,0.0003318987,0.000111098,0.0002638664],"domain_scores_gemma":[0.9991975,0.0003661792,0.00005917405,0.0002069598,0.00007610585,0.00009409146],"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":[0.0005111335,0.0003218011,0.1710335,0.001288628,0.0002976663,0.0000330383,0.0004243848,0.02789299,0.7738894,0.000168303,0.000004044115,0.02413512],"study_design_scores_gemma":[0.003752844,0.0004520711,0.08924932,0.0008079654,0.0003122276,0.0002402377,0.0003647931,0.8693954,0.0326189,0.00007184367,0.002248867,0.0004855546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6796952,0.0005298788,0.319087,0.0001218804,0.00007111773,0.0002836257,0.000002458745,0.0001706611,0.00003813925],"genre_scores_gemma":[0.9926862,0.0001277572,0.006804793,0.00007433802,0.0001136029,0.00003701342,0.00001886336,0.00004034985,0.00009713347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8415024,"threshold_uncertainty_score":0.6726371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01275065276905529,"score_gpt":0.2932581660303193,"score_spread":0.280507513261264,"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."}}