{"id":"W3091878842","doi":"10.1016/j.media.2020.101838","title":"ELNet:Automatic classification and segmentation for esophageal lesions using convolutional neural network","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Esophageal Cancer Research and Treatment","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Jiangsu Provincial Key Research and Development Program; China Scholarship Council; National Natural Science Foundation of China","keywords":"Convolutional neural network; Artificial intelligence; Segmentation; Computer science; Lesion; Pattern recognition (psychology); Esophageal cancer; Deep learning; Image segmentation; Medicine; Pathology; Cancer","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005783248,0.001410929,0.0007208652,0.001617819,0.0004570991,0.0009488766,0.001338796,0.001249506,0.007185516],"category_scores_gemma":[0.0007157152,0.0006423603,0.0007880369,0.0007794626,0.000207489,0.0007736396,0.001057551,0.0008473785,0.003566303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009599975,"about_ca_system_score_gemma":0.001326979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01464575,"about_ca_topic_score_gemma":0.0254715,"domain_scores_codex":[0.999778,0.00001946608,0.00001229897,0.00007554993,0.00005950518,0.00005523351],"domain_scores_gemma":[0.9998198,0.00004428374,0.00001861574,0.00002690945,0.00006982003,0.0000205379],"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":[0.0009212474,0.0004127403,0.006397749,0.0003939423,0.0003509231,0.0004410155,0.00008232613,0.03579186,0.05343848,0.002409905,0.07936431,0.8199956],"study_design_scores_gemma":[0.0001048054,0.0001758403,0.005429472,0.00006533211,0.0001045325,0.0004916938,0.00004103848,0.8986244,0.07468562,0.002533507,0.01769034,0.00005341749],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1246999,0.003175477,0.7490204,0.0009450528,0.0006246042,0.0006171661,0.01361934,0.09921308,0.008085092],"genre_scores_gemma":[0.3083095,0.001251972,0.6291503,0.0009535069,0.0002105528,0.0006451553,0.02561997,0.002615948,0.0312431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01464575,"threshold_uncertainty_score":0.02912104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06490156277561017,"score_gpt":0.3793603688123824,"score_spread":0.3144588060367723,"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."}}