{"id":"W4220748891","doi":"10.1038/s41598-022-08355-1","title":"Cell segmentation for immunofluorescence multiplexed images using two-stage domain adaptation and weakly labeled data for pre-training","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Ontario Institute for Cancer Research; Kela","keywords":"Domain adaptation; Stage (stratigraphy); Segmentation; Immunofluorescence; Computer science; Domain (mathematical analysis); Artificial intelligence; Training set; Pattern recognition (psychology); Computational biology; Adaptation (eye); Biology; Mathematics; Genetics; Neuroscience; Antibody","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001196514,0.0001037641,0.0001055029,0.00009208771,0.0008302074,0.0002713987,0.0001760237,0.00001888691,0.00000828865],"category_scores_gemma":[0.0000426874,0.0001180525,0.00002556302,0.0002163115,0.00006182321,0.000363263,0.000127773,0.00006774136,1.248785e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006729435,"about_ca_system_score_gemma":0.00007017217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000216353,"about_ca_topic_score_gemma":0.000004198941,"domain_scores_codex":[0.9988186,0.00001479437,0.0003145021,0.0004658443,0.0001770833,0.0002091365],"domain_scores_gemma":[0.9991349,0.00004728969,0.0001626888,0.0005413948,0.00008043685,0.00003331388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007524904,0.00001795309,0.00002964691,0.0001147344,0.000005633075,0.000002311345,0.0009113482,0.01206954,0.9816467,0.0000319913,0.001433692,0.003728919],"study_design_scores_gemma":[0.0003283638,0.00001958512,0.00002710517,0.00002216268,0.00002883835,0.00002880113,0.001270984,0.7889858,0.1945272,0.003671235,0.01088066,0.0002092584],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1931343,0.0003939682,0.8037643,0.00003133407,0.0007527004,0.001350492,0.0002451079,0.0002867464,0.00004100046],"genre_scores_gemma":[0.5286877,0.000002534577,0.4697194,0.000005631617,0.00002192583,0.0004379238,0.0008206521,0.00002444645,0.0002798667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7871195,"threshold_uncertainty_score":0.6385368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0551160905547091,"score_gpt":0.3166209594390914,"score_spread":0.2615048688843822,"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."}}