{"id":"W4225004743","doi":"10.1109/isbi52829.2022.9761663","title":"Lightseg: Efficient Yet Effective Medical Image Segmentation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Robustness (evolution); Computer science; Segmentation; Image segmentation; Artificial intelligence; Market segmentation; Deep learning; Scale-space segmentation; Segmentation-based object categorization; Separable space; Computer vision; Image (mathematics); Pattern recognition (psychology); Machine learning; Mathematics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001487071,0.0004008841,0.0004668553,0.0006773522,0.0004618381,0.0001099315,0.0007091481,0.000110383,0.00816198],"category_scores_gemma":[0.0007429944,0.0003760701,0.000312907,0.0007803322,0.000437722,0.0001233348,0.0004719372,0.001174111,0.0004416034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002218429,"about_ca_system_score_gemma":0.0003836337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001973679,"about_ca_topic_score_gemma":0.000003012933,"domain_scores_codex":[0.9926247,0.0003455918,0.0007605444,0.001022344,0.004657286,0.0005895055],"domain_scores_gemma":[0.9973809,0.0009928236,0.0002731905,0.0004714765,0.0002203531,0.0006612723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00152499,0.008216759,0.003985432,0.0002366666,0.000819302,0.003962618,0.001951682,0.001140832,0.2924142,0.0009553763,0.6480023,0.0367898],"study_design_scores_gemma":[0.01175482,0.001762213,0.005114273,0.000751208,0.0003599708,0.001392827,0.0005229168,0.1856644,0.04463207,0.0002153429,0.746707,0.001122967],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2923062,0.0002755788,0.007782604,0.666238,0.02300574,0.00271777,0.0006042802,0.0009737841,0.006095981],"genre_scores_gemma":[0.9118149,0.00007820805,0.0008641573,0.08098156,0.001930201,0.001184527,0.00120873,0.0001473141,0.001790372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6195087,"threshold_uncertainty_score":0.9998691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008831438168704917,"score_gpt":0.315245715190075,"score_spread":0.3064142770213701,"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."}}