{"id":"W3193532867","doi":"10.1016/j.compmedimag.2021.101974","title":"An unsupervised method for histological image segmentation based on tissue cluster level graph cut","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Jaccard index; Artificial intelligence; Computer science; Pattern recognition (psychology); Segmentation; Voronoi diagram; Cut; Cluster analysis; Image segmentation; Adjacency list; Graph partition; Graph; Computer vision; 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":[],"consensus_categories":[],"category_scores_codex":[0.0008944192,0.0002330343,0.0003164871,0.0002055897,0.000280282,0.0002549915,0.0004965821,0.0001424152,0.00002074168],"category_scores_gemma":[0.0001686522,0.0002148059,0.0001086138,0.000495353,0.0001856976,0.0003572134,0.000143743,0.0003192364,0.000001909785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004754063,"about_ca_system_score_gemma":0.0001835307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001792518,"about_ca_topic_score_gemma":0.000008758407,"domain_scores_codex":[0.9974975,0.0004346397,0.0003431952,0.0008111197,0.0005653416,0.0003482041],"domain_scores_gemma":[0.9981321,0.0006532734,0.00009762534,0.0005346847,0.0002270061,0.0003553731],"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":[0.000136711,0.0003979317,0.0002174483,0.0001774283,0.00004196477,0.0001799282,0.0004384415,0.0001704233,0.02035703,0.007278151,0.00413762,0.9664669],"study_design_scores_gemma":[0.002526509,0.0002101826,0.0006077121,0.00007408397,0.0000235723,0.0001162602,0.00001999973,0.978437,0.006815195,0.006715902,0.004177607,0.0002759714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001585009,0.0001607814,0.9852048,0.01137837,0.001081964,0.0002579302,0.00001183613,0.0002720598,0.00004726186],"genre_scores_gemma":[0.04228956,0.00006687134,0.9421262,0.01509722,0.0002357912,0.00007766536,0.00006606937,0.00002376141,0.00001688943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9782666,"threshold_uncertainty_score":0.875953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03159187053559112,"score_gpt":0.3381906320323873,"score_spread":0.3065987614967961,"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."}}