{"id":"W4412979322","doi":"10.1016/j.media.2025.103749","title":"MedCLIP-SAMv2: Towards universal text-driven medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Computer vision; Segmentation; Image segmentation; Image (mathematics); Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00198899,0.003362915,0.001963152,0.004512262,0.0008478492,0.003239482,0.004933177,0.004285308,0.03174692],"category_scores_gemma":[0.00817128,0.001574761,0.002742519,0.002901386,0.0007195278,0.001681313,0.004368287,0.002160323,0.02232664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001158797,"about_ca_system_score_gemma":0.00174117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006311275,"about_ca_topic_score_gemma":0.009761026,"domain_scores_codex":[0.9985433,0.0002436058,0.0001439329,0.0004376348,0.0004917749,0.0001399077],"domain_scores_gemma":[0.9981013,0.0008128016,0.0001040382,0.0003318502,0.0004885027,0.000161532],"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":[0.001534904,0.0002897677,0.0014355,0.002067349,0.0006631679,0.0004927168,0.0002813526,0.01370104,0.04361923,0.006701505,0.36531,0.5639035],"study_design_scores_gemma":[0.0004438859,0.0003148499,0.002191449,0.0004222465,0.000208297,0.001386866,0.00018867,0.6698992,0.1136762,0.03314532,0.1779092,0.0002139049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004964629,0.001321688,0.5895422,0.0008624965,0.0005092924,0.0005984911,0.02363351,0.3742303,0.004337399],"genre_scores_gemma":[0.05615639,0.0009517209,0.8355512,0.002213074,0.0003239706,0.001109126,0.06643624,0.02912341,0.008134855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03174692,"threshold_uncertainty_score":0.106204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01201337465348444,"score_gpt":0.3527614810408809,"score_spread":0.3407481063873964,"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."}}