{"id":"W2604440528","doi":"10.1016/j.patcog.2018.09.007","title":"Sparse autoencoder for unsupervised nucleus detection and representation in histopathology images","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"AI in cancer detection","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Concordia University","funders":"U.S. National Library of Medicine; National Cancer Institute","keywords":"Autoencoder; Artificial intelligence; Pattern recognition (psychology); Computer science; Feature extraction; Convolutional neural network; Feature (linguistics); Feature vector; ENCODE; Feature learning; Unsupervised learning; Computer vision; Deep learning; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002518918,0.00009890122,0.0001077637,0.0001976318,0.00010485,0.00006522847,0.0001146663,0.00008083006,0.00001950168],"category_scores_gemma":[0.00006211191,0.0001115487,0.00002810936,0.0002081157,0.00006215533,0.0004582055,0.00005183121,0.00007884713,0.00004455091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001159585,"about_ca_system_score_gemma":0.00001395901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001809809,"about_ca_topic_score_gemma":0.0004582291,"domain_scores_codex":[0.9989859,0.00009509477,0.0002055043,0.0004325677,0.00009690898,0.0001840242],"domain_scores_gemma":[0.9994656,0.00007501071,0.00009288796,0.000200057,0.0001313596,0.00003504654],"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":[0.00003108454,0.0000202431,0.002207746,0.00002042942,0.000002389952,0.000003283557,0.000623686,0.00000568527,0.02063835,0.000005179363,0.00005324329,0.9763887],"study_design_scores_gemma":[0.003247376,0.001263857,0.2986681,0.000116512,0.00003440393,0.000214433,0.0001876517,0.4172896,0.2398794,0.03754489,0.0009141982,0.0006394912],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.308931,0.00001873625,0.6896266,0.0002568672,0.0006103736,0.0002696268,0.000006782571,0.0001014851,0.0001785132],"genre_scores_gemma":[0.9815507,0.00002552576,0.01770852,0.0002826952,0.0002224633,0.0001707277,0.000009784018,0.00001267629,0.00001688529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9757492,"threshold_uncertainty_score":0.4548824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04444275579844309,"score_gpt":0.2841243134265597,"score_spread":0.2396815576281167,"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."}}