{"id":"W4410198781","doi":"10.1016/j.bea.2025.100174","title":"Advanced biomedical imaging for identifying blood cell type: Integrating segmentation, feature extraction, and GraphSAGE model","year":2025,"lang":"en","type":"article","venue":"Biomedical Engineering Advances","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Segmentation; Feature extraction; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Extraction (chemistry); Computer vision; Chemistry; Chromatography","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":[0.0001735596,0.0002327117,0.0002105234,0.0003662427,0.0001511401,0.000292626,0.000426412,0.00005884697,0.000001175548],"category_scores_gemma":[0.0003924694,0.0002193442,0.00007303269,0.0008242328,0.0001223641,0.001434426,0.0001598611,0.0001687925,0.000001205543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000342456,"about_ca_system_score_gemma":0.00009921563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002022073,"about_ca_topic_score_gemma":4.499919e-7,"domain_scores_codex":[0.9984838,0.00001047612,0.0002967882,0.0005216522,0.0003096314,0.0003776021],"domain_scores_gemma":[0.9991464,0.0001971699,0.0000836118,0.0002479041,0.0001106459,0.0002142429],"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":[0.00005160928,0.0009641302,0.0006806337,0.002679531,0.0001964343,0.00007910449,0.0006359695,0.007308834,0.3344582,0.02401096,0.007143067,0.6217915],"study_design_scores_gemma":[0.001881839,0.00008036419,0.0002460828,0.0005870468,0.00009965855,0.00003550102,0.0002330693,0.9449785,0.01817724,0.006013932,0.02711255,0.0005541977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0054067,0.008170241,0.9835855,0.0008538843,0.001103904,0.0002387912,0.00002220389,0.0004751473,0.0001436596],"genre_scores_gemma":[0.28354,0.0002301648,0.7152692,0.0002725067,0.00008715891,0.0001010301,0.00006390371,0.00002857362,0.0004074453],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9376697,"threshold_uncertainty_score":0.8944598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005780231304421612,"score_gpt":0.2731571475930953,"score_spread":0.2673769162886737,"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."}}