{"id":"W4388101099","doi":"10.18280/ts.400522","title":"Multi-Modal Medical Image Matching Based on Multi-Task Learning and Semantic-Enhanced Cross-Modal Retrieval","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Matching (statistics); Modal; Modality (human–computer interaction); Image retrieval; Task (project management); Artificial intelligence; Information retrieval; Image (mathematics); Feature (linguistics); Template matching; Feature extraction; Pattern recognition (psychology); Computer vision; Medicine; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002967372,0.0007575492,0.001507173,0.002084054,0.0006320755,0.001280137,0.001854815,0.001961773,0.001893212],"category_scores_gemma":[0.005486654,0.0003372228,0.001690939,0.001663583,0.0008200528,0.001918118,0.002083894,0.001388092,0.0007737438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006297004,"about_ca_system_score_gemma":0.0009120439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00194482,"about_ca_topic_score_gemma":0.001757628,"domain_scores_codex":[0.9985086,0.0003505647,0.0001222333,0.0004412768,0.0004082406,0.0001690276],"domain_scores_gemma":[0.9985372,0.0005076657,0.000176039,0.0002448592,0.0004369378,0.00009730701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005572352,0.0007281558,0.002152163,0.0002856014,0.0003028969,0.0002918983,0.000374833,0.1362586,0.04550764,0.01184988,0.005229598,0.7964614],"study_design_scores_gemma":[0.00001819293,0.0001407939,0.0007405453,0.00001139224,0.00004845286,0.000220695,0.00004207297,0.9832149,0.007667734,0.006715462,0.001154098,0.00002573297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01301236,0.0003641228,0.9852862,0.0001643874,0.00004829548,0.00008299132,0.00003330604,0.0003641566,0.0006440387],"genre_scores_gemma":[0.4061905,0.0005638091,0.5877498,0.0006144302,0.0002671452,0.0003264926,0.0004542326,0.0001876445,0.003645979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002967372,"threshold_uncertainty_score":0.01569313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02106303875143166,"score_gpt":0.3102289237663226,"score_spread":0.2891658850148909,"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."}}