{"id":"W4401209463","doi":"10.1007/978-3-031-67751-9_9","title":"SnapSeg: Training-Free Few-Shot Medical Image Segmentation with Segment Anything Model","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Shot (pellet); Artificial intelligence; Computer vision; Segmentation; Image segmentation; Training (meteorology); Image (mathematics); Computer graphics (images)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007504853,0.0006518564,0.0005125966,0.0005959609,0.000343923,0.0006924939,0.004588323,0.0003031869,0.00002787813],"category_scores_gemma":[0.00006049091,0.0005429809,0.0001136895,0.0009230844,0.0008482432,0.0009866018,0.002120433,0.001386609,0.0000485479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004739796,"about_ca_system_score_gemma":0.0009366722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005530833,"about_ca_topic_score_gemma":0.000101046,"domain_scores_codex":[0.9942378,0.00002321601,0.0006118989,0.002125349,0.002197177,0.0008045346],"domain_scores_gemma":[0.9968618,0.0004110024,0.0002665946,0.001907198,0.0001920384,0.0003614161],"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":[0.00001080967,0.00004036579,0.000002836358,0.00008431781,0.00002930064,0.0003366354,0.003143279,0.4313622,0.0007142335,0.104536,0.0001563744,0.4595836],"study_design_scores_gemma":[0.000233231,0.00009979601,0.000002197373,0.000461855,0.00001195495,0.0001661578,6.361933e-7,0.7343612,0.0007361147,0.2632068,0.0002358866,0.0004842326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004464967,0.0003199177,0.9883343,0.00496617,0.0006462572,0.0006349385,0.00001126641,0.0004239237,0.004618568],"genre_scores_gemma":[0.0204596,0.00007806042,0.9751101,0.003021037,0.0005035883,0.00007333508,0.00001820083,0.00007764828,0.0006584496],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4590994,"threshold_uncertainty_score":0.9997022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02892619621889873,"score_gpt":0.2819824265583252,"score_spread":0.2530562303394265,"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."}}